Search results for: Whale Optimization Algorithm

Authors: Ja-Keoung Koo, Kensuke Nakamura, Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Byung-Woo Hong

Abstract:

The machine learning techniques based on a convolutional neural network (CNN) have been actively developed and successfully applied to a variety of image analysis tasks including reconstruction, noise reduction, resolution enhancement, segmentation, motion estimation, object recognition. The classical visual information processing that ranges from low level tasks to high level ones has been widely developed in the deep learning framework. It is generally considered as a challenging problem to derive visual interpretation from high dimensional imagery data. A CNN is a class of feed-forward artificial neural network that usually consists of deep layers the connections of which are established by a series of non-linear operations. The CNN architecture is known to be shift invariant due to its shared weights and translation invariance characteristics. However, it is often computationally intractable to optimize the network in particular with a large number of convolution layers due to a large number of unknowns to be optimized with respect to the training set that is generally required to be large enough to effectively generalize the model under consideration. It is also necessary to limit the size of convolution kernels due to the computational expense despite of the recent development of effective parallel processing machinery, which leads to the use of the constantly small size of the convolution kernels throughout the deep CNN architecture. However, it is often desired to consider different scales in the analysis of visual features at different layers in the network. Thus, we propose a CNN model where different sizes of the convolution kernels are applied at each layer based on the random projection. We apply random filters with varying sizes and associate the filter responses with scalar weights that correspond to the standard deviation of the random filters. We are allowed to use large number of random filters with the cost of one scalar unknown for each filter. The computational cost in the back-propagation procedure does not increase with the larger size of the filters even though the additional computational cost is required in the computation of convolution in the feed-forward procedure. The use of random kernels with varying sizes allows to effectively analyze image features at multiple scales leading to a better generalization. The robustness and effectiveness of the proposed CNN based on random kernels are demonstrated by numerical experiments where the quantitative comparison of the well-known CNN architectures and our models that simply replace the convolution kernels with the random filters is performed. The experimental results indicate that our model achieves better performance with less number of unknown weights. The proposed algorithm has a high potential in the application of a variety of visual tasks based on the CNN framework. Acknowledgement—This work was supported by the MISP (Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by IITP, and NRF-2014R1A2A1A11051941, NRF2017R1A2B4006023.

Keywords: deep learning, convolutional neural network, random kernel, random projection, dimensionality reduction, object recognition

Procedia PDF Downloads 286

Authors: Hongmei Wang, Ziyun Xiang, Ying liu, Li Yu, Dongsheng Yue

Abstract:

Intro: The COVID-19 (Corona Virus Disease 2019) has greatly changed the global economic, political and financial ecology. The mutation of the coronavirus in the UK in December 2020 has brought new panic to the world. Deep learning was performed on Chest Computed tomography (CT) of COVID-19 and Influenza and describes their characteristics. The predominant features of COVID-19 pneumonia was ground-glass opacification, followed by consolidation. Lesion density: most lesions appear as ground-glass shadows, and some lesions coexist with solid lesions. Lesion distribution: the focus is mainly on the dorsal side of the periphery of the lung, with the lower lobe of the lungs as the focus, and it is often close to the pleura. Other features it has are grid-like shadows in ground glass lesions, thickening signs of diseased vessels, air bronchi signs and halo signs. The severe disease involves whole bilateral lungs, showing white lung signs, air bronchograms can be seen, and there can be a small amount of pleural effusion in the bilateral chest cavity. At the same time, this year's flu season could be near its peak after surging throughout the United States for months. Chest CT for Influenza infection is characterized by focal ground glass shadows in the lungs, with or without patchy consolidation, and bronchiole air bronchograms are visible in the concentration. There are patchy ground-glass shadows, consolidation, air bronchus signs, mosaic lung perfusion, etc. The lesions are mostly fused, which is prominent near the hilar and two lungs. Grid-like shadows and small patchy ground-glass shadows are visible. Deep neural networks have great potential in image analysis and diagnosis that traditional machine learning algorithms do not. Method: Aiming at the two major infectious diseases COVID-19 and influenza, which are currently circulating in the world, the chest CT of patients with two infectious diseases is classified and diagnosed using deep learning algorithms. The residual network is proposed to solve the problem of network degradation when there are too many hidden layers in a deep neural network (DNN). The proposed deep residual system (ResNet) is a milestone in the history of the Convolutional neural network (CNN) images, which solves the problem of difficult training of deep CNN models. Many visual tasks can get excellent results through fine-tuning ResNet. The pre-trained convolutional neural network ResNet is introduced as a feature extractor, eliminating the need to design complex models and time-consuming training. Fastai is based on Pytorch, packaging best practices for in-depth learning strategies, and finding the best way to handle diagnoses issues. Based on the one-cycle approach of the Fastai algorithm, the classification diagnosis of lung CT for two infectious diseases is realized, and a higher recognition rate is obtained. Results: A deep learning model was developed to efficiently identify the differences between COVID-19 and influenza using chest CT.

Keywords: COVID-19, Fastai, influenza, transfer network

Procedia PDF Downloads 142

Authors: Jaden Lu, Olivia Lu

Abstract:

Despite the remarkable advancement of solar cell technology, the challenge of optimizing total solar energy harvest efficiency persists, primarily due to significant heat loss. This excess heat not only diminishes solar panel output efficiency but also curtails its operational lifespan. A promising approach to address this issue is the conversion of surplus heat into electricity. In recent years, there is growing interest in the use of thermoelectric generators (TEG) as a potential solution. The integration of efficient TEG devices holds the promise of augmenting overall energy harvest efficiency while prolonging the longevity of solar panels. While certain research groups have proposed the integration of solar cells and TEG devices, a substantial gap between conceptualization and practical implementation remains, largely attributed to low thermal energy conversion efficiency of TEG devices. To bridge this gap and meet the requisites of practical application, a feasible strategy involves the incorporation of a substantial number of p-n junctions within a confined unit volume. However, the manufacturing of high-density TEG p-n junctions presents a formidable challenge. The prevalent solution often leads to large device sizes to accommodate enough p-n junctions, consequently complicating integration with solar cells. Recently, the adoption of 3D printing technology has emerged as a promising solution to address this challenge by fabricating high-density p-n arrays. Despite this, further developmental efforts are necessary. Presently, the primary focus is on the 3D printing of vertically layered TEG devices, wherein p-n junction density remains constrained by spatial limitations and the constraints of 3D printing techniques. This study proposes a novel device configuration featuring horizontally arrayed p-n junctions of Bi2Te3. The structural design of the device is subjected to simulation through the Finite Element Method (FEM) within COMSOL Multiphysics software. Various device configurations are simulated to identify optimal device structure. Based on the simulation results, a new TEG device is fabricated utilizing 3D Selective laser melting (SLM) printing technology. Fusion 360 facilitates the translation of the COMSOL device structure into a 3D print file. The horizontal design offers a unique advantage, enabling the fabrication of densely packed, three-dimensional p-n junction arrays. The fabrication process entails printing a singular row of horizontal p-n junctions using the 3D SLM printing technique in a single layer. Subsequently, successive rows of p-n junction arrays are printed within the same layer, interconnected by thermally conductive copper. This sequence is replicated across multiple layers, separated by thermal insulating glass. This integration created in a highly compact three-dimensional TEG device with high density p-n junctions. The fabricated TEG device is then attached to the bottom of the solar cell using thermal glue. The whole device is characterized, with output data closely matching with COMSOL simulation results. Future research endeavors will encompass the refinement of thermoelectric materials. This includes the advancement of high-resolution 3D printing techniques tailored to diverse thermoelectric materials, along with the optimization of material microstructures such as porosity and doping. The objective is to achieve an optimal and highly integrated PV-TEG device that can substantially increase the solar energy harvest efficiency.

Keywords: thermoelectric, finite element method, 3d print, energy conversion

Procedia PDF Downloads 62

Authors: Annika J. Meyer, Tom Piechotta

Abstract:

Unmanned Aerial Vehicles (UAVs) have increasingly become vital tools in various applications, including surveillance, search and rescue, and environmental monitoring. One common approach to ensure redundant communication systems when flying beyond visual line of sight is for UAVs to employ multiple mobile data modems by different providers. Although widely adopted, this approach suffers from several drawbacks, such as high costs, added weight and potential increases in signal interference. In light of these challenges, this paper proposes a communication framework intermeshing mobile networks and LoRa (Long Range) technology—a low-power, long-range communication protocol. LoRaWAN (Long Range Wide Area Network) is commonly used in Internet of Things applications, relying on stationary gateways and Internet connectivity. This paper, however, utilizes the underlying LoRa protocol, taking advantage of the protocol’s low power and long-range capabilities while ensuring efficiency and reliability. Conducted in collaboration with the Potsdam Fire Department, the implementation of mobile network technology in combination with the LoRa protocol in small UAVs (take-off weight < 0.4 kg), specifically designed for search and rescue and area monitoring missions, is explored. This research aims to test the viability of LoRa as an additional redundant communication system during UAV flights as well as its intermeshing with the primary, mobile network-based controller. The methodology focuses on direct UAV-to-UAV and UAV-to-ground communications, employing different spreading factors optimized for specific operational scenarios—short-range for UAV-to-UAV interactions and long-range for UAV-to-ground commands. This explored use case also dramatically reduces one of the major drawbacks of LoRa communication systems, as a line of sight between the modules is necessary for reliable data transfer. Something that UAVs are uniquely suited to provide, especially when deployed as a swarm. Additionally, swarm deployment may enable UAVs that have lost contact with their primary network to reestablish their connection through another, better-situated UAV. The experimental setup involves multiple phases of testing, starting with controlled environments to assess basic communication capabilities and gradually advancing to complex scenarios involving multiple UAVs. Such a staged approach allows for meticulous adjustment of parameters and optimization of the communication protocols to ensure reliability and effectiveness. Furthermore, due to the close partnership with the Fire Department, the real-world applicability of the communication system is assured. The expected outcomes of this paper include a detailed analysis of LoRa's performance as a communication tool for UAVs, focusing on aspects such as signal integrity, range, and reliability under different environmental conditions. Additionally, the paper seeks to demonstrate the cost-effectiveness and operational efficiency of using a single type of communication technology that reduces UAV payload and power consumption. By shifting from traditional cellular network communications to a more robust and versatile cellular and LoRa-based system, this research has the potential to significantly enhance UAV capabilities, especially in critical applications where reliability is paramount. The success of this paper could pave the way for broader adoption of LoRa in UAV communications, setting a new standard for UAV operational communication frameworks.

Keywords: LoRa communication protocol, mobile network communication, UAV communication systems, search and rescue operations

Procedia PDF Downloads 42

Authors: Jaden Lu, Olivia Lu

Abstract:

Despite the remarkable advancement of solar cell technology, the challenge of optimizing total solar energy harvest efficiency persists, primarily due to significant heat loss. This excess heat not only diminishes solar panel output efficiency but also curtails its operational lifespan. A promising approach to address this issue is the conversion of surplus heat into electricity. In recent years, there is growing interest in the use of thermoelectric generators (TEG) as a potential solution. The integration of efficient TEG devices holds the promise of augmenting overall energy harvest efficiency while prolonging the longevity of solar panels. While certain research groups have proposed the integration of solar cells and TEG devices, a substantial gap between conceptualization and practical implementation remains, largely attributed to low thermal energy conversion efficiency of TEG devices. To bridge this gap and meet the requisites of practical application, a feasible strategy involves the incorporation of a substantial number of p-n junctions within a confined unit volume. However, the manufacturing of high-density TEG p-n junctions presents a formidable challenge. The prevalent solution often leads to large device sizes to accommodate enough p-n junctions, consequently complicating integration with solar cells. Recently, the adoption of 3D printing technology has emerged as a promising solution to address this challenge by fabricating high-density p-n arrays. Despite this, further developmental efforts are necessary. Presently, the primary focus is on the 3D printing of vertically layered TEG devices, wherein p-n junction density remains constrained by spatial limitations and the constraints of 3D printing techniques. This study proposes a novel device configuration featuring horizontally arrayed p-n junctions of Bi2Te3. The structural design of the device is subjected to simulation through the Finite Element Method (FEM) within COMSOL Multiphysics software. Various device configurations are simulated to identify optimal device structure. Based on the simulation results, a new TEG device is fabricated utilizing 3D Selective laser melting (SLM) printing technology. Fusion 360 facilitates the translation of the COMSOL device structure into a 3D print file. The horizontal design offers a unique advantage, enabling the fabrication of densely packed, three-dimensional p-n junction arrays. The fabrication process entails printing a singular row of horizontal p-n junctions using the 3D SLM printing technique in a single layer. Subsequently, successive rows of p-n junction arrays are printed within the same layer, interconnected by thermally conductive copper. This sequence is replicated across multiple layers, separated by thermal insulating glass. This integration created in a highly compact three-dimensional TEG device with high density p-n junctions. The fabricated TEG device is then attached to the bottom of the solar cell using thermal glue. The whole device is characterized, with output data closely matching with COMSOL simulation results. Future research endeavors will encompass the refinement of thermoelectric materials. This includes the advancement of high-resolution 3D printing techniques tailored to diverse thermoelectric materials, along with the optimization of material microstructures such as porosity and doping. The objective is to achieve an optimal and highly integrated PV-TEG device that can substantially increase the solar energy harvest efficiency.

Keywords: thermoelectric, finite element method, 3d print, energy conversion

Procedia PDF Downloads 67

Authors: Shuai Yuan, Minxia Shi, Xu Zhang, Jianzhi Yang, Kangqi Tian, Yuzheng Ma

Abstract:

The precise measurement of muscle activities is essential for understanding the function of various body movements. This work aims to develop a muscle magnetic field signal detection system based on mathematical analysis. Medical research has underscored that early detection of muscle atrophy, coupled with lifestyle adjustments such as dietary control and increased exercise, can significantly enhance muscle-related diseases. Currently, surface electromyography (sEMG) is widely employed in research as an early predictor of muscle atrophy. Nonetheless, the primary limitation of using sEMG to forecast muscle strength is its inability to directly measure the signals generated by muscles. Challenges arise from potential skin-electrode contact issues due to perspiration, leading to inaccurate signals or even signal loss. Additionally, resistance and phase are significantly impacted by adipose layers. The recent emergence of optically pumped magnetometers introduces a fresh avenue for bio-magnetic field measurement techniques. These magnetometers possess high sensitivity and obviate the need for a cryogenic environment unlike superconducting quantum interference devices (SQUIDs). They detect muscle magnetic field signals in the range of tens to thousands of femtoteslas (fT). The utilization of magnetometers for capturing muscle magnetic field signals remains unaffected by issues of perspiration and adipose layers. Since their introduction, optically pumped atomic magnetometers have found extensive application in exploring the magnetic fields of organs such as cardiac and brain magnetism. The optimal operation of these magnetometers necessitates an environment with an ultra-weak magnetic field. To achieve such an environment, researchers usually utilize a combination of active magnetic compensation technology with passive magnetic shielding technology. Passive magnetic shielding technology uses a magnetic shielding device built with high permeability materials to attenuate the external magnetic field to a few nT. Compared with more layers, the coils that can generate a reverse magnetic field to precisely compensate for the residual magnetic fields are cheaper and more flexible. To attain even lower magnetic fields, compensation coils designed by Biot-Savart law are involved to generate a counteractive magnetic field to eliminate residual magnetic fields. By solving the magnetic field expression of discrete points in the target region, the parameters that determine the current density distribution on the plane can be obtained through the conventional target field method. The current density is obtained from the partial derivative of the stream function, which can be represented by the combination of trigonometric functions. Optimization algorithms in mathematics are introduced into coil design to obtain the optimal current density distribution. A one-dimensional linear regression analysis was performed on the collected data, obtaining a coefficient of determination R2 of 0.9349 with a p-value of 0. This statistical result indicates a stable relationship between the peak-to-peak value (PPV) of the muscle magnetic field signal and the magnitude of grip strength. This system is expected to be a widely used tool for healthcare professionals to gain deeper insights into the muscle health of their patients.

Keywords: muscle magnetic signal, magnetic shielding, compensation coils, trigonometric functions.

Procedia PDF Downloads 56

Authors: Laurence Weinberg, Dominic Walpole, Dong-Kyu Lee, Michael D’Silva, Jian W. Chan, Lachlan F. Miles, Bradley Carp, Adam Wells, Tuck S. Ngun, Siven Seevanayagam, George Matalanis, Ziauddin Ansari, Rinaldo Bellomo, Michael Yii

Abstract:

Background: There have been multiple recent advancements in the selection, optimization and management of cardiac surgical patients. However, there is limited data regarding the outcomes of nonagenarians undergoing cardiac surgery, despite this vulnerable cohort increasingly receiving these interventions. This study describes the patient characteristics, management and outcomes of a group of nonagenarians undergoing cardiac surgery in the context of contemporary peri-operative care. Methods: A retrospective observational study was conducted of patients 90 to 99 years of age (i.e., nonagenarians) who had undergone cardiac surgery requiring a classic median sternotomy (i.e., open-heart surgery). All operative indications were included. Patients who underwent minimally invasive surgery, transcatheter aortic valve implantation and thoracic aorta surgery were excluded. Data were collected from four hospitals in Victoria, Australia, over an 8-year period (January 2012 – December 2019). The primary objective was to assess six-month mortality in nonagenarians undergoing open-heart surgery and to evaluate the incidence and severity of postoperative complications using the Clavien-Dindo classification system. The secondary objective was to provide a detailed description of the characteristics and peri-operative management of this group. Results: A total of 12,358 adult patients underwent cardiac surgery at the study centers during the observation period, of whom 18 nonagenarians (0.15%) fulfilled the inclusion criteria. The median (IQR) [min-max] age was 91 years (90.0:91.8) [90-94] and 14 patients (78%) were men. Cardiovascular comorbidities, polypharmacy and frailty, were common. The median (IQR) predicted in-hospital mortality by EuroSCORE II was 6.1% (4.1-14.5). All patients were optimized preoperatively by a multidisciplinary team of surgeons, cardiologists, geriatricians and anesthetists. All index surgeries were performed on cardiopulmonary bypass. Isolated coronary artery bypass grafting (CABG) and CABG with aortic valve replacement were the most common surgeries being performed in four and five patients, respectively. Half the study group underwent surgery involving two or more major procedures (e.g. CABG and valve replacement). Surgery was undertaken emergently in 44% of patients. All patients except one experienced at least one postoperative complication. The most common complications were acute kidney injury (72%), new atrial fibrillation (44%) and delirium (39%). The highest Clavien-Dindo complication grade was IIIb occurring once each in three patients. Clavien-Dindo grade IIIa complications occurred in only one patient. The median (IQR) postoperative length of stay was 11.6 days (9.8:17.6). One patient was discharged home and all others to an inpatient rehabilitation facility. Three patients had an unplanned readmission within 30 days of discharge. All patients had follow-up to at least six months after surgery and mortality over this period was zero. The median (IQR) duration of follow-up was 11.3 months (6.0:26.4) and there were no cases of mortality observed within the available follow-up records. Conclusion: In this group of nonagenarians undergoing cardiac surgery, postoperative six-month mortality was zero. Complications were common but generally of low severity. These findings support carefully selected nonagenarian patients being offered cardiac surgery in the context of contemporary, multidisciplinary perioperative care. Further, studies are needed to assess longer-term mortality and functional and quality of life outcomes in this vulnerable surgical cohort.

Keywords: cardiac surgery, mortality, nonagenarians, postoperative complications

Procedia PDF Downloads 118

Authors: Michael Brave, Mark Kroll, Steven Karch, Charles Wetli, Michael Graham, Sebastian Kunz, Dorin Panescu

Abstract:

Background: Conducted electrical weapons (CEW) are now used in 107 countries and are a common law enforcement less-lethal force practice in the United Kingdom (UK), United States of America (USA), Canada, Australia, New Zealand, and others. Use of these devices is rarely temporally associated with the occurrence of sudden arrest-related deaths (ARD). Because such deaths are uncommon, few Medical Examiners (MEs) ever encounter one, and even fewer offices have established comprehensive investigative protocols. Without sufficient scientific data, the role, if any, played by a CEW in a given case is largely supplanted by conjecture often defaulting to a CEW-induced fatal cardiac arrhythmia. In addition to the difficulty in investigating individual deaths, the lack of information also detrimentally affects being able to define and evaluate the ARD cohort generally. More comprehensive, better information leads to better interpretation in individual cases and also to better research. The purpose of this presentation is to provide MEs with a comprehensive evidence-based checklist to assist in the assessment of CEW-ARD cases. Methods: PUBMED and Sociology/Criminology data bases were queried to find all medical, scientific, electrical, modeling, engineering, and sociology/criminology peer-reviewed literature for mentions of CEW or synonymous terms. Each paper was then individually reviewed to identify those that discussed possible bioelectrical mechanisms relating CEW to ARD. A Naranjo-type pharmacovigilance algorithm was also employed, when relevant, to identify and quantify possible direct CEW electrical myocardial stimulation. Additionally, CEW operational manuals and training materials were reviewed to allow incorporation of CEW-specific technical parameters. Results: Total relevant PUBMED citations of CEWs were less than 250, and reports of death extremely rare. Much relevant information was available from Sociology/Criminology data bases. Once the relevant published papers were identified, and reviewed, we compiled an annotated checklist of data that we consider critical to a thorough CEW-involved ARD investigation. Conclusion: We have developed an evidenced-based checklist that can be used by MEs and their staffs to assist them in identifying, collecting, documenting, maintaining, and objectively analyzing the role, if any, played by a CEW in any specific case of sudden death temporally associated with the use of a CEW. Even in cases where the collected information is deemed by the ME as insufficient for formulating an opinion or diagnosis to a reasonable degree of medical certainty, information collected as per the checklist will often be adequate for other stakeholders to use as a basis for informed decisions. Having reviewed the appropriate materials in a significant number of cases careful examination of the heart and brain is likely adequate. Channelopathy testing should be considered in some cases, however it may be considered cost prohibitive (aprox $3000). Law enforcement agencies may want to consider establishing a reserve fund to help manage such rare cases. The expense may stay the enormous costs associated with incident-precipitated litigation.

Keywords: ARD, CEW, police, TASER

Procedia PDF Downloads 345

Authors: Sherif Keddis, Rafik Mitry, Norbert Schwesinger

Abstract:

Intelligent networking of devices has rapidly been gaining importance over the past years and with recent advances in the fields of microcontrollers, integrated circuits and wireless communication, low power applications have emerged, enabling this trend even more. Connected devices provide a much larger database thus enabling highly intelligent and accurate systems. Ensuring safe drinking water is one of the fields that require constant monitoring and can benefit from an increased accuracy. Monitoring is mainly achieved either through complex measures, such as collecting samples from the points of use, or through metering systems typically distant to the points of use which deliver less accurate assessments of the quality of water. Constant metering near the points of use is complicated due to their inaccessibility; e.g. buried water pipes, locked spaces, which makes system maintenance extremely difficult and often unviable. The research presented here attempts to overcome this challenge by providing these systems with enough energy through a flow harvester inside the pipe thus eliminating the maintenance requirements in terms of battery replacements or containment of leakage resulting from wiring such systems. The proposed flow harvester exploits the piezoelectric properties of polyvinylidene difluoride (PVDF) films to convert turbulence induced oscillations into electrical energy. It is intended to be used in standard water pipes with diameters between 0.5 and 1 inch. The working principle of the harvester uses a ring shaped bluff body inside the pipe to induce pressure fluctuations. Additionally the bluff body houses electronic components such as storage, circuitry and RF-unit. Placing the piezoelectric films downstream of that bluff body causes their oscillation which generates electrical charge. The PVDF-film is placed as a multilayered wrap fixed to the pipe wall leaving the top part to oscillate freely inside the flow. The warp, which allows for a larger active, consists of two layers of 30µm thick and 12mm wide PVDF layered alternately with two centered 6µm thick and 8mm wide aluminum foil electrodes. The length of the layers depends on the number of windings and is part of the investigation. Sealing the harvester against liquid penetration is achieved by wrapping it in a ring-shaped LDPE-film and welding the open ends. The fabrication of the PVDF-wraps is done by hand. After validating the working principle using a wind tunnel, experiments have been conducted in water, placing the harvester inside a 1 inch pipe at water velocities of 0.74m/s. To find a suitable placement of the wrap inside the pipe, two forms of fixation were compared regarding their power output. Further investigations regarding the number of windings required for efficient transduction were made. Best results were achieved using a wrap with 3 windings of the active layers which delivers a constant power output of 0.53µW at a 2.3MΩ load and an effective voltage of 1.1V. Considering the extremely low power requirements of sensor applications, these initial results are promising. For further investigations and optimization, machine designs are currently being developed to automate the fabrication and decrease tolerance of the prototypes.

Keywords: maintenance-free sensors, measurements at point of use, piezoelectric flow harvesting, universal micro generator, wireless metering systems

Procedia PDF Downloads 193

Authors: Armin Nabaei, M. Omair Ahmad, M. N. S. Swamy

Abstract:

Many facial expression and emotion recognition methods in the traditional approaches of using LDA, PCA, and EBGM have been proposed. In recent years deep learning models have provided a unique platform addressing by automatically extracting the features for the detection of facial expression and emotions. However, deep networks require large training datasets to extract automatic features effectively. In this work, we propose an efficient emotion detection algorithm using face images when only small datasets are available for training. We design a deep network whose feature extraction capability is enhanced by utilizing several parallel modules between the input and output of the network, each focusing on the extraction of different types of coarse features with fined grained details to break the symmetry of produced information. In fact, we leverage long range dependencies, which is one of the main drawback of CNNs. We develop this work by introducing a Dynamic Soft-Margin SoftMax.The conventional SoftMax suffers from reaching to gold labels very soon, which take the model to over-fitting. Because it’s not able to determine adequately discriminant feature vectors for some variant class labels. We reduced the risk of over-fitting by using a dynamic shape of input tensor instead of static in SoftMax layer with specifying a desired Soft- Margin. In fact, it acts as a controller to how hard the model should work to push dissimilar embedding vectors apart. For the proposed Categorical Loss, by the objective of compacting the same class labels and separating different class labels in the normalized log domain.We select penalty for those predictions with high divergence from ground-truth labels.So, we shorten correct feature vectors and enlarge false prediction tensors, it means we assign more weights for those classes with conjunction to each other (namely, “hard labels to learn”). By doing this work, we constrain the model to generate more discriminate feature vectors for variant class labels. Finally, for the proposed optimizer, our focus is on solving weak convergence of Adam optimizer for a non-convex problem. Our noteworthy optimizer is working by an alternative updating gradient procedure with an exponential weighted moving average function for faster convergence and exploiting a weight decay method to help drastically reducing the learning rate near optima to reach the dominant local minimum. We demonstrate the superiority of our proposed work by surpassing the first rank of three widely used Facial Expression Recognition datasets with 93.30% on FER-2013, and 16% improvement compare to the first rank after 10 years, reaching to 90.73% on RAF-DB, and 100% k-fold average accuracy for CK+ dataset, and shown to provide a top performance to that provided by other networks, which require much larger training datasets.

Keywords: computer vision, facial expression recognition, machine learning, algorithms, depp learning, neural networks

Procedia PDF Downloads 74

Authors: Kaushikk Iyer, Richard M Hall, David Keeling

Abstract:

Hardware-in-the-loop (HIL) simulation is an advanced technique for developing and testing complex real-time control systems. This paper presents the benefits of HIL simulation and how it can be implemented and used effectively to develop, test, and validate advanced control algorithms used in a spinal joint Wear simulator for the Tribological testing of spinal disc prostheses. spinal wear simulator is technologically the most advanced machine currently employed For the in-vitro testing of newly developed spinal Discimplants. However, the existing control techniques, such as a simple position control Does not allow the simulator to test non-sinusoidal waveforms. Thus, there is a need for better and advanced control methods that can be developed and tested Rigorouslybut safely before deploying it into the real simulator. A benchtop HILsetupis was created for experimentation, controller verification, and validation purposes, allowing different control strategies to be tested rapidly in a safe environment. The HIL simulation aspect in this setup attempts to replicate similar spinal motion and loading conditions. The spinal joint wear simulator containsa four-Barlinkpowered by electromechanical actuators. LabVIEW software is used to design a kinematic model of the spinal wear Simulator to Validatehow each link contributes towards the final motion of the implant under test. As a result, the implant articulates with an angular motion specified in the international standards, ISO-18192-1, that define fixed, simplified, and sinusoid motion and load profiles for wear testing of cervical disc implants. Using a PID controller, a velocity-based position control algorithm was developed to interface with the benchtop setup that performs HIL simulation. In addition to PID, a fuzzy logic controller (FLC) was also developed that acts as a supervisory controller. FLC provides intelligence to the PID controller by By automatically tuning the controller for profiles that vary in amplitude, shape, and frequency. This combination of the fuzzy-PID controller is novel to the wear testing application for spinal simulators and demonstrated superior performance against PIDwhen tested for a spectrum of frequency. Kaushikk Iyer is a Ph.D. Student at the University of Leeds and an employee at Key Engineering Solutions, Leeds, United Kingdom, (e-mail: [email protected], phone: +44 740 541 5502). Richard M Hall is with the University of Leeds, the United Kingdom as a professor in the Mechanical Engineering Department (e-mail: [email protected]). David Keeling is the managing director of Key Engineering Solutions, Leeds, United Kingdom (e-mail: [email protected]). Results obtained are successfully validated against the load and motion tolerances specified by the ISO18192-1 standard and fall within limits, that is, ±0.5° at the maxima and minima of the motion and ±2 % of the complete cycle for phasing. The simulation results prove the efficacy of the test setup using HIL simulation to verify and validate the accuracy and robustness of the prospective controller before its deployment into the spinal wear simulator. This method of testing controllers enables a wide range of possibilities to test advanced control algorithms that can potentially test even profiles of patients performing various dailyliving activities.

Keywords: Fuzzy-PID controller, hardware-in-the-loop (HIL), real-time simulation, spinal wear simulator

Procedia PDF Downloads 170

Authors: David F. Nettleton, Elodie Bugnicourt, Christian Wasiak, Alejandro Rosales

Abstract:

In this presentation, preliminary results are given for the modeling and calibration of two different industrial winding MIMO (Multiple Input Multiple Output) processes using machine learning techniques. In contrast to previous approaches which have typically used ‘black-box’ linear statistical methods together with a definition of the mechanical behavior of the process, we use non-linear machine learning algorithms together with a ‘white-box’ rule induction technique to create a supervised model of the fitting error between the expected and real force measures. The final objective is to build a precise model of the winding process in order to control de-tension of the material being wound in the first case, and the friction of the material passing through the die, in the second case. Case 1, Tension Control of a Winding Process. A plastic web is unwound from a first reel, goes over a traction reel and is rewound on a third reel. The objectives are: (i) to train a model to predict the web tension and (ii) calibration to find the input values which result in a given tension. Case 2, Friction Force Control of a Micro-Pullwinding Process. A core+resin passes through a first die, then two winding units wind an outer layer around the core, and a final pass through a second die. The objectives are: (i) to train a model to predict the friction on die2; (ii) calibration to find the input values which result in a given friction on die2. Different machine learning approaches are tested to build models, Kernel Ridge Regression, Support Vector Regression (with a Radial Basis Function Kernel) and MPART (Rule Induction with continuous value as output). As a previous step, the MPART rule induction algorithm was used to build an explicative model of the error (the difference between expected and real friction on die2). The modeling of the error behavior using explicative rules is used to help improve the overall process model. Once the models are built, the inputs are calibrated by generating Gaussian random numbers for each input (taking into account its mean and standard deviation) and comparing the output to a target (desired) output until a closest fit is found. The results of empirical testing show that a high precision is obtained for the trained models and for the calibration process. The learning step is the slowest part of the process (max. 5 minutes for this data), but this can be done offline just once. The calibration step is much faster and in under one minute obtained a precision error of less than 1x10-3 for both outputs. To summarize, in the present work two processes have been modeled and calibrated. A fast processing time and high precision has been achieved, which can be further improved by using heuristics to guide the Gaussian calibration. Error behavior has been modeled to help improve the overall process understanding. This has relevance for the quick optimal set up of many different industrial processes which use a pull-winding type process to manufacture fibre reinforced plastic parts. Acknowledgements to the Openmind project which is funded by Horizon 2020 European Union funding for Research & Innovation, Grant Agreement number 680820

Keywords: data model, machine learning, industrial winding, calibration

Procedia PDF Downloads 240

Authors: Luminiţa Duţică, Gheorghe Duţică

Abstract:

One of the most powerful language innovation in the twentieth century music was the heterophony–hypostasis of the vertical syntax entered into the sphere of interest of many composers, such as George Enescu, Pierre Boulez, Mauricio Kagel, György Ligeti and others. The heterophonic syntax has a history of its growth, which means a succession of different concepts and writing techniques. The trajectory of settling this phenomenon does not necessarily take into account the chronology: there are highly complex primary stages and advanced stages of returning to the simple forms of writing. In folklore, the plurimelodic simultaneities are free or random and originate from the (unintentional) differences/‘deviations’ from the state of unison, through a variety of ornaments, melismas, imitations, elongations and abbreviations, all in a flexible rhythmic and non-periodic/immeasurable framework, proper to the parlando-rubato rhythmics. Within the general framework of the multivocal organization, the heterophonic syntax in elaborate (academic) version has imposed itself relatively late compared with polyphony and homophony. Of course, the explanation is simple, if we consider the causal relationship between the sound vocabulary elements – in this case, the modalism – and the typologies of vertical organization appropriate for it. Therefore, adding up the ‘classic’ pathway of the writing typologies (monody – polyphony – homophony), heterophony - applied equally to the structures of modal, serial or synthesis vocabulary – reclaims necessarily an own macrotemporal form, in the sense of the analogies enshrined by the evolution of the musical styles and languages: polyphony→fugue, homophony→sonata. Concerned about the prospect of edifying a new musical ontology, the composer Ştefan Niculescu experienced – along with the mathematical organization of heterophony according to his own original methods – the possibility of extrapolation of this phenomenon in macrostructural plan, reaching this way to the unique form of ‘synchrony’. Founded on coincidentia oppositorum principle (involving the ‘one-multiple’ binom), the sound architecture imagined by Ştefan Niculescu consists in one (temporal) model / algorithm of articulation of two sound states: 1. monovocality state (principle of identity) and 2. multivocality state (principle of difference). In this context, the heterophony becomes an (auto)generative mechanism, with macrotemporal amplitude, strategy that will be grown by the composer, practically throughout his creation (see the works: Ison I, Ison II, Unisonos I, Unisonos II, Duplum, Triplum, Psalmus, Héterophonies pour Montreux (Homages to Enescu and Bartók etc.). For the present demonstration, we selected one of the most edifying works of Ştefan Niculescu – Simphony II, Opus dacicum – where the form of (heterophony-)synchrony acquires monumental-symphonic features, representing an emblematic case for the complexity level achieved by this type of vertical syntax in the twentieth century music.

Keywords: heterophony, modalism, serialism, synchrony, syntax

Procedia PDF Downloads 341

Authors: Aleksandra Bylinska, Samantha Slight-Webb, Kevin Thomas, Miles Smith, Susan Macwana, Nicolas Dominguez, Eliza Chakravarty, Joan T. Merrill, Judith A. James, Joel M. Guthridge

Abstract:

Background: Systemic Lupus Erythematosus (SLE) is an interferon-related autoimmune disease characterized by B cell dysfunction. One of the main hallmarks is a loss of tolerance to self-antigens leading to increased levels of autoantibodies against nuclear components (ANAs). However, up to 20% of healthy ANA+ individuals will not develop clinical illness. SLE is more prevalent among women and minority populations (African, Asian American and Hispanics). Moreover, African Americans have a stronger interferon (IFN) signature and develop more severe symptoms. The exact mechanisms involved in ethnicity-dependent B cell dysregulation and the progression of autoimmune disease from ANA+ healthy individuals to clinical disease remains unclear. Methods: Peripheral blood mononuclear cells (PBMCs) from African (AA) and European American (EA) ANA- (n=12), ANA+ (n=12) and SLE (n=12) individuals were assessed by multimodal scRNA-Seq/CITE-Seq methods to examine differential gene signatures in specific B cell subsets. Library preparation was done with a 10X Genomics Chromium according to established protocols and sequenced on Illumina NextSeq. The data were further analyzed for distinct cluster identification and differential gene signatures in the Seurat package in R and pathways analysis was performed using Ingenuity Pathways Analysis (IPA). Results: Comparing all subjects, 14 distinct B cell clusters were identified using a community detection algorithm and visualized with Uniform Manifold Approximation Projection (UMAP). The proportion of each of those clusters varied by disease status and ethnicity. Transitional B cells trended higher in ANA+ healthy individuals, especially in AA. Ribonucleoprotein high population (HNRNPH1 elevated, heterogeneous nuclear ribonucleoprotein, RNP-Hi) of proliferating Naïve B cells were more prevalent in SLE patients, specifically in EA. Interferon-induced protein high population (IFIT-Hi) of Naive B cells are increased in EA ANA- individuals. The proportion of memory B cells and plasma cells clusters tend to be expanded in SLE patients. As anticipated, we observed a higher signature of cytokine-related pathways, especially interferon, in SLE individuals. Pathway analysis among AA individuals revealed an NRF2-mediated Oxidative Stress response signature in the transitional B cell cluster, not seen in EA individuals. TNFR1/2 and Sirtuin Signaling pathway genes were higher in AA IFIT-Hi Naive B cells, whereas they were not detected in EA individuals. Interferon signaling was observed in B cells in both ethnicities. Oxidative phosphorylation was found in age-related B cells (ABCs) for both ethnicities, whereas Death Receptor Signaling was found only in EA patients in these cells. Interferon-related transcription factors were elevated in ABCs and IFIT-Hi Naive B cells in SLE subjects of both ethnicities. Conclusions: ANA+ healthy individuals have altered gene expression pathways in B cells that might drive apoptosis and subsequent clinical autoimmune pathogenesis. Increases in certain regulatory pathways may delay progression to SLE. Further, AA individuals have more elevated activation pathways that may make them more susceptible to SLE.

Keywords:

Procedia PDF Downloads 174

Authors: P. J. Sweeney, T. Ahtoniemi, J. Puoliväli, T. Laitinen, K. Lehtimäki, A. Nurmi, D. Wells

Abstract:

Duchenne muscular dystrophy (DMD) is caused by an X linked mutation in the dystrophin gene; lack of dystrophin causes a progressive muscle necrosis which leads to a progressive decrease in mobility in those suffering from the disease. The MDX mouse, a mutant mouse model which displays a frank dystrophinopathy, is currently widely employed in pre clinical efficacy models for treatments and therapies aimed at DMD. In general the end-points examined within this model have been based on invasive histopathology of muscles and serum biochemical measures like measurement of serum creatine kinase (sCK). It is established that a “critical period” between 4 and 6 weeks exists in the MDX mouse when there is extensive muscle damage that is largely sub clinical but evident with sCK measurements and histopathological staining. However, a full characterization of the MDX model remains largely incomplete especially with respect to the ability to aggravate of the muscle damage beyond the critical period. The purpose of this study was to attempt to aggravate the muscle damage in the MDX mouse and to create a wider, more readily translatable and discernible, therapeutic window for the testing of potential therapies for DMD. The study consisted of subjecting 15 male mutant MDX mice and 15 male wild-type mice to an intense chronic exercise regime that consisted of bi-weekly (two times per week) treadmill sessions over a 12 month period. Each session was 30 minutes in duration and the treadmill speed was gradually built up to 14m/min for the entire session. Baseline plasma creatine kinase (pCK), treadmill training performance and locomotor activity were measured after the “critical period” at around 10 weeks of age and again at 14 weeks of age, 6 months, 9 months and 12 months of age. In addition, kinematic gait analysis was employed using a novel analysis algorithm in order to compare changes in gait and fine motor skills in diseased exercised MDX mice compared to exercised wild type mice and non exercised MDX mice. In addition, a morphological and metabolic profile (including lipid profile), from the muscles most severely affected, the gastrocnemius muscle and the tibialis anterior muscle, was also measured at the same time intervals. Results indicate that by aggravating or exacerbating the underlying muscle damage in the MDX mouse by exercise a more pronounced and severe phenotype in comes to light and this can be picked up earlier by kinematic gait analysis. A reduction in mobility as measured by open field is not apparent at younger ages nor during the critical period, but changes in gait are apparent in the mutant MDX mice. These gait changes coincide with pronounced morphological and metabolic changes by non-invasive anatomical MRI and proton spectroscopy (1H-MRS) we have reported elsewhere. Evidence of a progressive asymmetric pathology in imaging parameters as well as in the kinematic gait analysis was found. Taken together, the data show that chronic exercise regime exacerbates the muscle damage beyond the critical period and the ability to measure through non-invasive means are important factors to consider when performing preclinical efficacy studies in the MDX mouse.

Keywords: Gait, muscular dystrophy, Kinematic analysis, neuromuscular disease

Procedia PDF Downloads 276

Authors: Kumar Satyam Das, Murali Raghunathan

Abstract:

This note discusses the feasibility of field development of a challenging shallow offshore field in South East Asia and how its learnings can be applied to marginal field development across the world especially developing marginal fields in this low oil price world. The field was found to be economically challenging even during high oil prices and the project was put on hold. Shell started development study with the aim to significantly reduce cost through competitively scoping and revive stranded projects. The proposed strategy to achieve this involved Improve Per platform recovery and Reduction in CAPEX. Methodology: Based on various Benchmarking Tool such as Woodmac for similar projects in the region and economic affordability, a challenging target of 50% reduction in unit development cost (UDC) was set for the project. Technical scope was defined to the minimum as to be a wellhead platform with minimum functionality to ensure production. The evaluation of key project decisions like Well location and number, well design, Artificial lift methods and wellhead platform type under different development concept was carried out through integrated multi-discipline approach. Key elements influencing per platform recovery were Wellhead Platform (WHP) location, Well count, well reach and well productivity. Major Findings: Reservoir being shallow posed challenges in well design (dog-leg severity, casing size and the achievable step-out), choice of artificial lift and sand-control method. Integrated approach amongst relevant disciplines with challenging mind-set enabled to achieve optimized set of development decisions. This led to significant improvement in per platform recovery. It was concluded that platform recovery largely depended on the reach of the well. Choice of slim well design enabled designing of high inclination and better productivity wells. However, there is trade-off between high inclination Gas Lift (GL) wells and low inclination wells in terms of long term value, operational complexity, well reach, recovery and uptime. Well design element like casing size, well completion, artificial lift and sand control were added successively over the minimum technical scope design leading to a value and risk staircase. Logical combinations of options (slim well, GL) were competitively screened to achieve 25% reduction in well cost. Facility cost reduction was achieved through sourcing standardized Low Cost Facilities platform in combination with portfolio execution to maximizing execution efficiency; this approach is expected to reduce facilities cost by ~23% with respect to the development costs. Further cost reductions were achieved by maximizing use of existing facilities nearby; changing reliance on existing water injection wells and utilizing existing water injector (W.I.) platform for new injectors. Conclusion: The study provides a spectrum of technically feasible options. It also made clear that different drivers lead to different development concepts and the cost value trade off staircase made this very visible. Scoping of the project through competitive way has proven to be valuable for decision makers by creating a transparent view of value and associated risks/uncertainty/trade-offs for difficult choices: elements of the projects can be competitive, whilst other parts will struggle, even though contributing to significant volumes. Reduction in UDC through proper scoping of present projects and its benchmarking paves as a learning for the development of marginal fields across the world, especially in this low oil price scenario. This way of developing a field has on average a reduction of 40% of cost for the Shell projects.

Keywords: benchmarking, full field development, CAPEX, feasibility

Procedia PDF Downloads 157

Authors: Adela Diepoltova, Klara Konecna, Ondrej Jandourek, Petr Nachtigal

Abstract:

A loss of control over antibiotic-resistant pathogens has become a global issue due to severe and often untreatable infections. This state is reflected in complicated treatment, health costs, and higher mortality. All these factors emphasize the urgent need for the discovery and development of new anti-infectives. One of the most common pathogens mentioned in the phenomenon of antibiotic resistance are bacteria of the genus Staphylococcus. These bacterial agents have developed several mechanisms against the effect of antibiotics. One of them is biofilm formation. In staphylococci, biofilms are associated with infections such as endocarditis, osteomyelitis, catheter-related bloodstream infections, etc. To author's best knowledge, no validated and standardized methodology evaluating candidate compound activity against staphylococcal biofilms exists. However, a variety of protocols for in vitro drug activity testing has been suggested, yet there are often fundamental differences. Based on our experience, a key methodological step that leads to credible results is to form a robust biofilm with appropriate attributes such as firm adherence to the substrate, a complex arrangement in layers, and the presence of extracellular polysaccharide matrix. At first, for the purpose of drug antibiofilm activity evaluation, the focus was put on various conditions (supplementation of cultivation media by human plasma/fetal bovine serum, shaking mode, the density of initial inoculum) that should lead to reproducible and robust in vitro staphylococcal biofilm formation in microtiter plate model. Three model staphylococcal reference strains were included in the study: Staphylococcus aureus (ATCC 29213), methicillin-resistant Staphylococcus aureus (ATCC 43300), and Staphylococcus epidermidis (ATCC 35983). The total biofilm biomass was quantified using the Christensen method with crystal violet, and results obtained from at least three independent experiments were statistically processed. Attention was also paid to the viability of the biofilm-forming staphylococcal cells and the presence of extracellular polysaccharide matrix. The conditions that led to robust biofilm biomass formation with attributes for biofilms mentioned above were then applied by introducing an alternative method analogous to the commercially available test system, the Calgary Biofilm Device. In this test system, biofilms are formed on pegs that are incorporated into the lid of the microtiter plate. This system provides several advantages (in situ detection and quantification of biofilm microbial cells that have retained their viability after drug exposure). Based on our preliminary studies, it was found that the attention to the peg surface and substrate on which the bacterial biofilms are formed should also be paid to. Therefore, further steps leading to the optimization were introduced. The surface of pegs was coated by human plasma, fetal bovine serum, and L-polylysine. Subsequently, the willingness of bacteria to adhere and form biofilm was monitored. In conclusion, suitable conditions were revealed, leading to the formation of reproducible, robust staphylococcal biofilms in vitro for the microtiter model and the system analogous to the Calgary biofilm device, as well. The robustness and typical slime texture could be detected visually. Likewise, an analysis by confocal laser scanning microscopy revealed a complex three-dimensional arrangement of biofilm forming organisms surrounded by an extracellular polysaccharide matrix.

Keywords: anti-biofilm drug activity screening, in vitro biofilm formation, microtiter plate model, the Calgary biofilm device, staphylococcal infections, substrate modification, surface coating

Procedia PDF Downloads 154

Authors: Vijaya Dixit Aasheesh Dixit

Abstract:

Shipbuilding industry operates in Engineer Procure Construct (EPC) context. Product mix of a shipyard comprises of various types of ships like bulk carriers, tankers, barges, coast guard vessels, sub-marines etc. Each order is unique based on the type of ship and customized requirements, which are engineered into the product right from design stage. Thus, to execute every new project, a shipyard needs to upgrade its production expertise. As a result, over the long run, holistic learning occurs across different types of projects which contributes to the knowledge base of the shipyard. Simultaneously, in the short term, during execution of a project comprising of multiple sister ships, repetition of similar tasks leads to learning at activity level. This research aims to capture above learnings of a shipyard and incorporate learning curve effect in project scheduling and materials procurement to improve project performance. Extant literature provides support for the existence of such learnings in an organization. In shipbuilding, there are sequences of similar activities which are expected to exhibit learning curve behavior. For example, the nearly identical structural sub-blocks which are successively fabricated, erected, and outfitted with piping and electrical systems. Learning curve representation can model not only a decrease in mean completion time of an activity, but also a decrease in uncertainty of activity duration. Sister ships have similar material requirements. The same supplier base supplies materials for all the sister ships within a project. On one hand, this provides an opportunity to reduce transportation cost by batching the order quantities of multiple ships. On the other hand, it increases the inventory holding cost at shipyard and the risk of obsolescence. Further, due to learning curve effect the production scheduled of each consequent ship gets compressed. Thus, the material requirement schedule of every next ship differs from its previous ship. As more and more ships get constructed, compressed production schedules increase the possibility of batching the orders of sister ships. This work aims at integrating materials management with project scheduling of long duration projects for manufacturing of multiple sister ships. It incorporates the learning curve effect on progressively compressing material requirement schedules and addresses the above trade-off of transportation cost and inventory holding and shortage costs while satisfying budget constraints of various stages of the project. The activity durations and lead time of items are not crisp and are available in the form of probabilistic distribution. A Stochastic Mixed Integer Programming (SMIP) model is formulated which is solved using evolutionary algorithm. Its output provides ordering dates of items and degree of order batching for all types of items. Sensitivity analysis determines the threshold number of sister ships required in a project to leverage the advantage of learning curve effect in materials management decisions. This analysis will help materials managers to gain insights about the scenarios: when and to what degree is it beneficial to treat a multiple ship project as an integrated one by batching the order quantities and when and to what degree to practice distinctive procurement for individual ship.

Keywords: learning curve, materials management, shipbuilding, sister ships

Procedia PDF Downloads 502

Authors: Thilini M. Yatanwala

Abstract:

CCTV (Closed-Circuit-Television) Surveillance System is being used in public places over decades and a large variety of data is being produced every moment. However, most of the CCTV data is stored in isolation without having integrity. As a result, identification of the behavior of suspicious people along with their location has become strenuous. This research was conducted to acquire more accurate and reliable timely information from the CCTV video records. The implemented system can identify human objects in public places based on outfit colors. Inter-process communication technologies were used to implement the CCTV camera network to track people in the premises. The research was conducted in three stages and in the first stage human objects were filtered from other movable objects available in public places. In the second stage people were uniquely identified based on their outfit colors and in the third stage an individual was continuously tracked in the CCTV network. A face detection algorithm was implemented using cascade classifier based on the training model to detect human objects. HAAR feature based two-dimensional convolution operator was introduced to identify features of the human face such as region of eyes, region of nose and bridge of the nose based on darkness and lightness of facial area. In the second stage outfit colors of human objects were analyzed by dividing the area into upper left, upper right, lower left, lower right of the body. Mean color, mod color and standard deviation of each area were extracted as crucial factors to uniquely identify human object using histogram based approach. Color based measurements were written in to XML files and separate directories were maintained to store XML files related to each camera according to time stamp. As the third stage of the approach, inter-process communication techniques were used to implement an acknowledgement based CCTV camera network to continuously track individuals in a network of cameras. Real time analysis of XML files generated in each camera can determine the path of individual to monitor full activity sequence. Higher efficiency was achieved by sending and receiving acknowledgments only among adjacent cameras. Suspicious incidents such as a person staying in a sensitive area for a longer period or a person disappeared from the camera coverage can be detected in this approach. The system was tested for 150 people with the accuracy level of 82%. However, this approach was unable to produce expected results in the presence of group of people wearing similar type of outfits. This approach can be applied to any existing camera network without changing the physical arrangement of CCTV cameras. The study of human identification and suspicious incident detection using outfit color analysis can achieve higher level of accuracy and the project will be continued by integrating motion and gait feature analysis techniques to derive more information from CCTV videos.

Keywords: CCTV surveillance, human detection and identification, image processing, inter-process communication, security, suspicious detection

Procedia PDF Downloads 181

Authors: Wei Ji

Abstract:

This study was conducted in the Kansas City metropolitan area of the United States, which has experienced significant urban sprawling in recent decades. The remote sensing of land cover changes in this area spanned over four decades from 1972 through 2010. The project was implemented in two stages: the first stage focused on detection of long-term trends of urban land cover change, while the second one examined how to detect the coupled effects of human impact and climate change on urban landscapes. For the first-stage study, six Landsat images were used with a time interval of about five years for the period from 1972 through 2001. Four major land cover types, built-up land, forestland, non-forest vegetation land, and surface water, were mapped using supervised image classification techniques. The study found that over the three decades the built-up lands in the study area were more than doubled, which was mainly at the expense of non-forest vegetation lands. Surprisingly and interestingly, the area also saw a significant gain in surface water coverage. This observation raised questions: How have human activities and precipitation variation jointly impacted surface water cover during recent decades? How can we detect such coupled impacts through remote sensing analysis? These questions led to the second stage of the study, in which we designed and developed approaches to detecting fine-scale surface waters and analyzing coupled effects of human impact and precipitation variation on the waters. To effectively detect urban landscape changes that might be jointly shaped by precipitation variation, our study proposed “urban wetscapes” (loosely-defined urban wetlands) as a new indicator for remote sensing detection. The study examined whether urban wetscape dynamics was a sensitive indicator of the coupled effects of the two driving forces. To better detect this indicator, a rule-based classification algorithm was developed to identify fine-scale, hidden wetlands that could not be appropriately detected based on their spectral differentiability by a traditional image classification. Three SPOT images for years 1992, 2008, and 2010, respectively were classified with this technique to generate the four types of land cover as described above. The spatial analyses of remotely-sensed wetscape changes were implemented at the scales of metropolitan, watershed, and sub-watershed, as well as based on the size of surface water bodies in order to accurately reveal urban wetscape change trends in relation to the driving forces. The study identified that urban wetscape dynamics varied in trend and magnitude from the metropolitan, watersheds, to sub-watersheds in response to human impacts at different scales. The study also found that increased precipitation in the region in the past decades swelled larger wetlands in particular while generally smaller wetlands decreased mainly due to human development activities. These results confirm that wetscape dynamics can effectively reveal the coupled effects of human impact and climate change on urban landscapes. As such, remote sensing of this indicator provides new insights into the relationships between urban land cover changes and driving forces.

Keywords: urban land cover, human impact, climate change, rule-based classification, across-scale analysis

Procedia PDF Downloads 307

Authors: Giuseppina Anna Giorgio, Angela Lorusso, Maria Ragosta, Vito Telesca

Abstract:

Climate change is a major public health threat due to the effects of extreme weather events on human health and on quality of life in general. In this context, mean temperatures are increasing, in particular, extreme temperatures, with heat waves becoming more frequent, more intense, and longer lasting. In many cities, extreme heat waves have drastically increased, giving rise to so-called Urban Heat Island (UHI) phenomenon. In an urban centre, maximum temperatures may be up to 10° C warmer, due to different local atmospheric conditions. UHI occurs in the metropolitan areas as function of the population size and density of a city. It consists of a significant difference in temperature compared to the rural/suburban areas. Increasing industrialization and urbanization have increased this phenomenon and it has recently also been detected in small cities. Weather conditions and land use are one of the key parameters in the formation of UHI. In particular surface urban heat island is directly related to temperatures, to land surface types and surface modifications. The present study concern a UHI analysis of Matera city (Italy) based on the analysis of temperature, change in land use and land cover, using Corine Land Cover maps and satellite Landsat images. Matera, located in Southern Italy, has a typical Mediterranean climate with mild winters and hot and humid summers. Moreover, Matera has been awarded the international title of the 2019 European Capital of Culture. Matera represents a significant example of vernacular architecture. The structure of the city is articulated by a vertical succession of dug layers sometimes excavated or partly excavated and partly built, according to the original shape and height of the calcarenitic slope. In this study, two meteorological stations were selected: MTA (MaTera Alsia, in industrial zone) and MTCP (MaTera Civil Protection, suburban area located in a green zone). In order to evaluate the increase in temperatures (in terms of UHI occurrences) over time, and evaluating the effect of land use on weather conditions, the climate variability of temperatures for both stations was explored. Results show that UHI phenomena is growing in Matera city, with an increase of maximum temperature values at a local scale. Subsequently, spatial analysis was conducted by Landsat satellite images. Four years was selected in the summer period (27/08/2000, 27/07/2006, 11/07/2012, 02/08/2017). In Particular, Landsat 7 ETM+ for 2000, 2006 and 2012 years; Landsat 8 OLI/TIRS for 2017. In order to estimate the LST, Mono Window Algorithm was applied. Therefore, the increase of LST values spatial scale trend has been verified, in according to results obtained at local scale. Finally, the analysis of land use maps over the years by the LST and/or the maximum temperatures measured, show that the development of industrialized area produces a corresponding increase in temperatures and consequently a growth in UHI.

Keywords: climate variability, land surface temperature, LANDSAT images, urban heat island

Procedia PDF Downloads 124

Authors: Evelyn Castle, Adam Thompson

Abstract:

Background: In 2013, the Kano State Primary Health Care Management Board redesigned its Routine immunization supply chain from diffused pull to direct delivery push. It addressed issues around stockouts and reduced time spent by health facility staff collecting, and reporting on vaccine usage. The health care board sought the help of a 3PL for twice-monthly deliveries from its cold store to 484 facilities across 44 local governments. eHA’s Health Delivery Systems group formed a 3PL to serve 326 of these new facilities in partnership with the State. We focused on designing and implementing a technology system throughout. Basic methodologies: GIS Mapping: - Planning the delivery of vaccines to hundreds of health facilities requires detailed route planning for delivery vehicles. Mapping the road networks across Kano and Bauchi with a custom routing tool provided information for the optimization of deliveries. Reducing the number of kilometers driven each round by 20%, - reducing cost and delivery time. Direct Delivery Information System: - Vaccine Direct Deliveries are facilitated through pre-round planning (driven by health facility database, extensive GIS, and inventory workflow rules), manager and driver control panel customizing delivery routines and reporting, progress dashboard, schedules/routes, packing lists, delivery reports, and driver data collection applications. Move: Last Mile Logistics Management System: - MOVE has improved vaccine supply information management to be timely, accurate and actionable. Provides stock management workflow support, alerts management for cold chain exceptions/stock outs, and on-device analytics for health and supply chain staff. Software was built to be offline-first with user-validated interface and experience. Deployed to hundreds of vaccine storage site the improved information tools helps facilitate the process of system redesign and change management. Findings: - Stock-outs reduced from 90% to 33% - Redesigned current health systems and managing vaccine supply for 68% of Kano’s wards. - Near real time reporting and data availability to track stock. - Paperwork burdens of health staff have been dramatically reduced. - Medicine available when the community needs it. - Consistent vaccination dates for children under one to prevent polio, yellow fever, tetanus. - Higher immunization rates = Lower infection rates. - Hundreds of millions of Naira worth of vaccines successfully transported. - Fortnightly service to 326 facilities in 326 wards across 30 Local Government areas. - 6,031 cumulative deliveries. - Over 3.44 million doses transported. - Minimum travel distance covered in a round of delivery is 2000 kms & maximum of 6297 kms. - 153,409 kms travelled by 6 drivers. - 500 facilities in 326 wards. - Data captured and synchronized for the first time. - Data driven decision making now possible. Conclusion: eHA’s Vaccine Direct delivery has met challenges in Kano and Bauchi State and provided a reliable delivery service of vaccinations that ensure t health facilities can run vaccination clinics for children under one. eHA uses innovative technology that delivers vaccines from Northern Nigerian zonal stores straight to healthcare facilities. Helped healthcare workers spend less time managing supplies and more time delivering care, and will be rolled out nationally across Nigeria.

Keywords: direct delivery information system, health delivery system, GIS mapping, Northern Nigeria, vaccines

Procedia PDF Downloads 373

Authors: Nurkhairul Bariyah Baharun, Afzan Adam, Reena Rahayu Md Zin

Abstract:

Tumor microenvironment (TME) in breast cancer is mainly composed of cancer cells, immune cells, and stromal cells. The interaction between cancer cells and their microenvironment plays an important role in tumor development, progression, and treatment response. The TME in breast cancer includes tumor-infiltrating lymphocytes (TILs) that are implicated in killing tumor cells. TILs can be found in tumor stroma (sTILs) and within the tumor (iTILs). TILs in triple negative breast cancer (TNBC) have been demonstrated to have prognostic and potentially predictive value. The international Immune-Oncology Biomarker Working Group (TIL-WG) had developed a guideline focus on the assessment of sTILs using hematoxylin and eosin (H&E)-stained slides. According to the guideline, the pathologists use “eye balling” method on the H&E stained- slide for sTILs assessment. This method has low precision, poor interobserver reproducibility, and is time-consuming for a comprehensive evaluation, besides only counted sTILs in their assessment. The TIL-WG has therefore recommended that any algorithm for computational assessment of TILs utilizing the guidelines provided to overcome the limitations of manual assessment, thus providing highly accurate and reliable TILs detection and classification for reproducible and quantitative measurement. This study is carried out to develop a TNBC digital whole slide image (WSI) dataset from H&E-stained slides and IHC (CD4+ and CD8+) stained slides. TNBC cases were retrieved from the database of the Department of Pathology, Hospital Canselor Tuanku Muhriz (HCTM). TNBC cases diagnosed between the year 2010 and 2021 with no history of other cancer and available block tissue were included in the study (n=58). Tissue blocks were sectioned approximately 4 µm for H&E and IHC stain. The H&E staining was performed according to a well-established protocol. Indirect IHC stain was also performed on the tissue sections using protocol from Diagnostic BioSystems PolyVue™ Plus Kit, USA. The slides were stained with rabbit monoclonal, CD8 antibody (SP16) and Rabbit monoclonal, CD4 antibody (EP204). The selected and quality-checked slides were then scanned using a high-resolution whole slide scanner (Pannoramic DESK II DW- slide scanner) to digitalize the tissue image with a pixel resolution of 20x magnification. A manual TILs (sTILs and iTILs) assessment was then carried out by the appointed pathologist (2 pathologists) for manual TILs scoring from the digital WSIs following the guideline developed by TIL-WG 2014, and the result displayed as the percentage of sTILs and iTILs per mm² stromal and tumour area on the tissue. Following this, we aimed to develop an automated digital image scoring framework that incorporates key elements of manual guidelines (including both sTILs and iTILs) using manually annotated data for robust and objective quantification of TILs in TNBC. From the study, we have developed a digital dataset of TNBC H&E and IHC (CD4+ and CD8+) stained slides. We hope that an automated based scoring method can provide quantitative and interpretable TILs scoring, which correlates with the manual pathologist-derived sTILs and iTILs scoring and thus has potential prognostic implications.

Keywords: automated quantification, digital pathology, triple negative breast cancer, tumour infiltrating lymphocytes

Procedia PDF Downloads 114

Authors: Michael Josef Schwerer

Abstract:

Background: The identification of unknown victims from mass disasters, violent crimes, or terrorist attacks is frequently facilitated through information from missing persons lists, portrait photos, old or recent pictures showing unique characteristics of a person such as scars or tattoos, or simply reference samples from blood relatives for DNA analysis. In contrast, the identification or at least the characterization of an unknown perpetrator from criminal or terrorist actions remains challenging, particularly in the absence of material or data for comparison, such as fingerprints, which had been previously stored in criminal records. In scenarios that result in high levels of destruction of the perpetrator’s corpse, for instance, blast or fire events, the chance for a positive identification using standard techniques is further impaired. Objectives: This study shows the forensic genetic procedures in the Legal Medicine Service of the German Air Force for the identification of unknown individuals, including such cases in which reference samples are not available. Scenarios requiring such efforts predominantly involve aircraft crash investigations, which are routinely carried out by the German Air Force Centre of Aerospace Medicine as one of the Institution’s essential missions. Further, casework by military police or military intelligence is supported based on administrative cooperation. In the talk, data from study projects, as well as examples from real casework, will be demonstrated and discussed with the audience. Methods: Forensic genetic identification in our laboratories involves the analysis of Short Tandem Repeats and Single Nucleotide Polymorphisms in nuclear DNA along with mitochondrial DNA haplotyping. Extended DNA analysis involves phenotypic markers for skin, hair, and eye color together with the investigation of a person’s biogeographic ancestry. Assessment of the biological age of an individual employs CpG-island methylation analysis using bisulfite-converted DNA. Forensic Investigative Genealogy assessment allows the detection of an unknown person’s blood relatives in reference databases. Technically, end-point-PCR, real-time PCR, capillary electrophoresis, pyrosequencing as well as next generation sequencing using flow-cell-based and chip-based systems are used. Results and Discussion: Optimization of DNA extraction from various sources, including difficult matrixes like formalin-fixed, paraffin-embedded tissues, degraded specimens from decomposed bodies or from decedents exposed to blast or fire events, provides soil for successful PCR amplification and subsequent genetic profiling. For cases with extremely low yields of extracted DNA, whole genome preamplification protocols are successfully used, particularly regarding genetic phenotyping. Improved primer design for CpG-methylation analysis, together with validated sampling strategies for the analyzed substrates from, e.g., lymphocyte-rich organs, allows successful biological age estimation even in bodies with highly degraded tissue material. Conclusions: Successful identification of unknown individuals or at least their phenotypic characterization using pigmentation markers together with age-informative methylation profiles, possibly supplemented by family tree search employing Forensic Investigative Genealogy, can be provided in specialized laboratories. However, standard laboratory procedures must be adapted to work with difficult and highly degraded sample materials.

Keywords: identification, forensic genetics, phenotypic markers, CPG methylation, biological age estimation, forensic investigative genealogy

Procedia PDF Downloads 50

Authors: Mingxin Li, Liya Ni

Abstract:

Autonomous parking is a valuable feature applicable to many robotics applications such as tour guide robots, UV sanitizing robots, food delivery robots, and warehouse robots. With auto-parking, the robot will be able to park at the charging zone and charge itself without human intervention. As compared to self-driving vehicles, auto-parking is more challenging for a small-scale mobile robot only equipped with a front camera due to the camera view limited by the robot’s height and the narrow Field of View (FOV) of the inexpensive camera. In this research, auto-parking of a small-scale mobile robot with a front camera only was achieved in a four-step process: Firstly, transfer learning was performed on the AlexNet, a popular pre-trained convolutional neural network (CNN). It was trained with 150 pictures of empty parking slots and 150 pictures of occupied parking slots from the view angle of a small-scale robot. The dataset of images was divided into a group of 70% images for training and the remaining 30% images for validation. An average success rate of 95% was achieved. Secondly, the image of detected empty parking space was processed with edge detection followed by the computation of parametric representations of the boundary lines using the Hough Transform algorithm. Thirdly, the positions of the entrance point and center of available parking space were predicted based on the robot kinematic model as the robot was driving closer to the parking space because the boundary lines disappeared partially or completely from its camera view due to the height and FOV limitations. The robot used its wheel speeds to compute the positions of the parking space with respect to its changing local frame as it moved along, based on its kinematic model. Lastly, the predicted entrance point of the parking space was used as the reference for the motion control of the robot until it was replaced by the actual center when it became visible again by the robot. The linear and angular velocities of the robot chassis center were computed based on the error between the current chassis center and the reference point. Then the left and right wheel speeds were obtained using inverse kinematics and sent to the motor driver. The above-mentioned four subtasks were all successfully accomplished, with the transformed learning, image processing, and target prediction performed in MATLAB, while the motion control and image capture conducted on a self-built small scale differential drive mobile robot. The small-scale robot employs a Raspberry Pi board, a Pi camera, an L298N dual H-bridge motor driver, a USB power module, a power bank, four wheels, and a chassis. Future research includes three areas: the integration of all four subsystems into one hardware/software platform with the upgrade to an Nvidia Jetson Nano board that provides superior performance for deep learning and image processing; more testing and validation on the identification of available parking space and its boundary lines; improvement of performance after the hardware/software integration is completed.

Keywords: autonomous parking, convolutional neural network, image processing, kinematics-based prediction, transfer learning

Procedia PDF Downloads 131

Authors: Maria Lazari, Lorenzo Sanavia

Abstract:

Mechanics of unsaturated soils has been an active field of research in the last decades. Efficient constitutive models that take into account the partial saturation of soil are necessary to solve a number of engineering problems e.g. instability of slopes and cuts due to heavy rainfalls. A large number of constitutive models can now be found in the literature that considers fundamental issues associated with the unsaturated soil behaviour, like the volume change and shear strength behaviour with suction or saturation changes. Partially saturated soils may either expand or collapse upon wetting depending on the stress level, and it is also possible that a soil might experience a reversal in the volumetric behaviour during wetting. Shear strength of soils also changes dramatically with changes in the degree of saturation, and a related engineering problem is slope failures caused by rainfall. There are several states of the art reviews over the last years for studying the topic, usually providing a thorough discussion of the stress state, the advantages, and disadvantages of specific constitutive models as well as the latest developments in the area of unsaturated soil modelling. However, only a few studies focused on the coupling between partial saturation states and time effects on the behaviour of geomaterials. Rate dependency is experimentally observed in the mechanical response of granular materials, and a viscoplastic constitutive model is capable of reproducing creep and relaxation processes. Therefore, in this work an elasto-viscoplastic constitutive model for unsaturated soils is proposed and validated on the basis of experimental data. The model constitutes an extension of an existing elastoplastic strain-hardening constitutive model capable of capturing the behaviour of variably saturated soils, based on energy conjugated stress variables in the framework of superposed continua. The purpose was to develop a model able to deal with possible mechanical instabilities within a consistent energy framework. The model shares the same conceptual structure of the elastoplastic laws proposed to deal with bonded geomaterials subject to weathering or diagenesis and is capable of modelling several kinds of instabilities induced by the loss of hydraulic bonding contributions. The novelty of the proposed formulation is enhanced with the incorporation of density dependent stiffness and hardening coefficients in order to allow the modeling of the pycnotropy behaviour of granular materials with a single set of material constants. The model has been implemented in the commercial FE platform PLAXIS, widely used in Europe for advanced geotechnical design. The algorithmic strategies adopted for the stress-point algorithm had to be revised to take into account the different approach adopted by PLAXIS developers in the solution of the discrete non-linear equilibrium equations. An extensive comparison between models with a series of experimental data reported by different authors is presented to validate the model and illustrate the capability of the newly developed model. After the validation, the effectiveness of the viscoplastic model is displayed by numerical simulations of a partially saturated slope failure of the laboratory scale and the effect of viscosity and degree of saturation on slope’s stability is discussed.

Keywords: PLAXIS software, slope, unsaturated soils, Viscoplasticity

Procedia PDF Downloads 223

Authors: Irina Mizeva, Elena Potapova, Viktor Dremin, Mikhail Mezentsev, Valeri Shupletsov

Abstract:

The local tissue perfusion is regulated by the microvascular tone which is under the control of a number of physiological mechanisms. Laser Doppler flowmetry (LDF) together with wavelet analyses is the most commonly used technique to study the regulatory mechanisms of cutaneous microcirculation. External factors such as temperature, local pressure of the probe on the skin, etc. influence on the blood flow characteristics and are used as physiological tests to evaluate microvascular regulatory mechanisms. Local probe pressure influences on the microcirculation parameters measured by optical methods: diffuse reflectance spectroscopy, fluorescence spectroscopy, and LDF. Therefore, further study of probe pressure effects can be useful to improve the reliability of optical measurement. During pressure tests variation of the mean perfusion measured by means of LDF usually is estimated. An additional information concerning the physiological mechanisms of the vascular tone regulation system in response to local pressure can be obtained using spectral analyses of LDF samples. The aim of the present work was to develop protocol and algorithm of data processing appropriate for study physiological response to the local pressure test. Involving 6 subjects (20±2 years) and providing 5 measurements for every subject we estimated intersubject and-inter group variability of response of both averaged and oscillating parts of the LDF sample on external surface pressure. The final purpose of the work was to find special features which further can be used in wider clinic studies. The cutaneous perfusion measurements were carried out by LAKK-02 (SPE LAZMA Ltd., Russia), the skin loading was provided by the originally designed device which allows one to distribute the pressure around the LDF probe. The probe was installed on the dorsal part of the distal finger of the index figure. We collected measurements continuously for one hour and varied loading from 0 to 180mmHg stepwise with a step duration of 10 minutes. Further, we post-processed the samples using the wavelet transform and traced the energy of oscillations in five frequency bands over time. Weak loading leads to pressure-induced vasodilation, so one should take into account that the perfusion measured under pressure conditions will be overestimated. On the other hand, we revealed a decrease in endothelial associated fluctuations. Further loading (88 mmHg) induces amplification of pulsations in all frequency bands. We assume that such loading leads to a higher number of closed capillaries, higher input of arterioles in the LDF signal and as a consequence more vivid oscillations which mainly are formed in arterioles. External pressure higher than 144 mmHg leads to the decrease of oscillating components, after removing the loading very rapid restore of the tissue perfusion takes place. In this work, we have demonstrated that local skin loading influence on the microcirculation parameters measured by optic technique; this should be taken into account while developing portable electronic devices. The proposed protocol of local loading allows one to evaluate PIV as far as to trace dynamic of blood flow oscillations. This study was supported by the Russian Science Foundation under project N 18-15-00201.

Keywords: blood microcirculation, laser Doppler flowmetry, pressure-induced vasodilation, wavelet analyses blood

Procedia PDF Downloads 150

Authors: Lucille Alonso, Florent Renard

Abstract:

The characterizations of urban heat island (UHI) and their interactions with climate change and urban climates are the main research and public health issue, due to the increasing urbanization of the population. These solutions require a better knowledge of the UHI and micro-climate in urban areas, by combining measurements and modelling. This study is part of this topic by evaluating microclimatic conditions in dense urban areas in the Lyon Metropolitan Area (France) using a combination of data traditionally used such as topography, but also from LiDAR (Light Detection And Ranging) data, Landsat 8 satellite observation and Sentinel and ground measurements by bike. These bicycle-dependent weather data collections are used to build the database of the variable to be modelled, the air temperature, over Lyon’s hyper-center. This study aims to model the air temperature, measured during 6 mobile campaigns in Lyon in clear weather, using multiple linear regressions based on 33 explanatory variables. They are of various categories such as meteorological parameters from remote sensing, topographic variables, vegetation indices, the presence of water, humidity, bare soil, buildings, radiation, urban morphology or proximity and density to various land uses (water surfaces, vegetation, bare soil, etc.). The acquisition sources are multiple and come from the Landsat 8 and Sentinel satellites, LiDAR points, and cartographic products downloaded from an open data platform in Greater Lyon. Regarding the presence of low, medium, and high vegetation, the presence of buildings and ground, several buffers close to these factors were tested (5, 10, 20, 25, 50, 100, 200 and 500m). The buffers with the best linear correlations with air temperature for ground are 5m around the measurement points, for low and medium vegetation, and for building 50m and for high vegetation is 100m. The explanatory model of the dependent variable is obtained by multiple linear regression of the remaining explanatory variables (Pearson correlation matrix with a |r| < 0.7 and VIF with < 5) by integrating a stepwise sorting algorithm. Moreover, holdout cross-validation is performed, due to its ability to detect over-fitting of multiple regression, although multiple regression provides internal validation and randomization (80% training, 20% testing). Multiple linear regression explained, on average, 72% of the variance for the study days, with an average RMSE of only 0.20°C. The impact on the model of surface temperature in the estimation of air temperature is the most important variable. Other variables are recurrent such as distance to subway stations, distance to water areas, NDVI, digital elevation model, sky view factor, average vegetation density, or building density. Changing urban morphology influences the city's thermal patterns. The thermal atmosphere in dense urban areas can only be analysed on a microscale to be able to consider the local impact of trees, streets, and buildings. There is currently no network of fixed weather stations sufficiently deployed in central Lyon and most major urban areas. Therefore, it is necessary to use mobile measurements, followed by modelling to characterize the city's multiple thermal environments.

Keywords: air temperature, LIDAR, multiple linear regression, surface temperature, urban heat island

Procedia PDF Downloads 137

Authors: Philipp Sommer, Amgad Agoub

Abstract:

The construction sector significantly impacts global CO₂ emissions, particularly through the energy usage of residential buildings. To address this, various governments, including Germany's, are focusing on reducing emissions via sustainable refurbishment initiatives. This study examines the application of machine learning (ML) to estimate energy demands dynamically in residential buildings and enhance the potential for large-scale sustainable refurbishment. A major challenge in Germany is the lack of extensive publicly labeled datasets for energy performance, as energy performance certificates, which provide critical data on building-specific energy requirements and consumption, are not available for all buildings or require on-site inspections. Conversely, England and other countries in the European Union (EU) have rich public datasets, providing a viable alternative for analysis. This research adapts insights from these English datasets to the German context by developing a comprehensive data schema and calibration dataset capable of predicting building energy demand effectively. The study proposes a minimal feature set, determined through feature importance analysis, to optimize the ML model. Findings indicate that ML significantly improves the scalability and accuracy of energy demand forecasts, supporting more effective emissions reduction strategies in the construction industry. Integrating energy performance certificates into municipal heat planning in Germany highlights the transformative impact of data-driven approaches on environmental sustainability. The goal is to identify and utilize key features from open data sources that significantly influence energy demand, creating an efficient forecasting model. Using Extreme Gradient Boosting (XGB) and data from energy performance certificates, effective features such as building type, year of construction, living space, insulation level, and building materials were incorporated. These were supplemented by data derived from descriptions of roofs, walls, windows, and floors, integrated into three datasets. The emphasis was on features accessible via remote sensing, which, along with other correlated characteristics, greatly improved the model's accuracy. The model was further validated using SHapley Additive exPlanations (SHAP) values and aggregated feature importance, which quantified the effects of individual features on the predictions. The refined model using remote sensing data showed a coefficient of determination (R²) of 0.64 and a mean absolute error (MAE) of 4.12, indicating predictions based on efficiency class 1-100 (G-A) may deviate by 4.12 points. This R² increased to 0.84 with the inclusion of more samples, with wall type emerging as the most predictive feature. After optimizing and incorporating related features like estimated primary energy consumption, the R² score for the training and test set reached 0.94, demonstrating good generalization. The study concludes that ML models significantly improve prediction accuracy over traditional methods, illustrating the potential of ML in enhancing energy efficiency analysis and planning. This supports better decision-making for energy optimization and highlights the benefits of developing and refining data schemas using open data to bolster sustainability in the building sector. The study underscores the importance of supporting open data initiatives to collect similar features and support the creation of comparable models in Germany, enhancing the outlook for environmental sustainability.

Keywords: machine learning, remote sensing, residential building, energy performance certificates, data-driven, heat planning

Procedia PDF Downloads 56

Authors: Zuhal Kurt, Meral Kurt, Bilge T. Bal, Kemal Ozkan

Abstract:

Shade matching and reproduction is the most important element of success in prosthetic dentistry. Until recently, shade matching procedure was implemented by dentists visual perception with the help of shade guides. Since many factors influence visual perception; tooth shade matching using visual devices (shade guides) is highly subjective and inconsistent. Subjective nature of this process has lead to the development of instrumental devices. Nowadays, colorimeters, spectrophotometers, spectroradiometers and digital image analysing systems are used for instrumental shade selection. Instrumental devices have advantages that readings are quantifiable, can obtain more rapidly and simply, objectively and precisely. However, these devices have noticeable drawbacks. For example, translucent structure and irregular surfaces of teeth lead to defects on measurement with these devices. Also between the results acquired by devices with different measurement principles may make inconsistencies. So, its obligatory to search for new methods for dental shade matching process. A computer-aided system device; digital camera has developed rapidly upon today. Currently, advances in image processing and computing have resulted in the extensive use of digital cameras for color imaging. This procedure has a much cheaper process than the use of traditional contact-type color measurement devices. Digital cameras can be taken by the place of contact-type instruments for shade selection and overcome their disadvantages. Images taken from teeth show morphology and color texture of teeth. In last decades, a new method was recommended to compare the color of shade tabs taken by a digital camera using color features. This method showed that visual and computer-aided shade matching systems should be used as concatenated. Recently using methods of feature extraction techniques are based on shape description and not used color information. However, color is mostly experienced as an essential property in depicting and extracting features from objects in the world around us. When local feature descriptors with color information are extended by concatenating color descriptor with the shape descriptor, that descriptor will be effective on visual object recognition and classification task. Therefore, the color descriptor is to be used in combination with a shape descriptor it does not need to contain any spatial information, which leads us to use local histograms. This local color histogram method is remain reliable under variation of photometric changes, geometrical changes and variation of image quality. So, coloring local feature extraction methods are used to extract features, and also the Scale Invariant Feature Transform (SIFT) descriptor used to for shape description in the proposed method. After the combination of these descriptors, the state-of-art descriptor named by Color-SIFT will be used in this study. Finally, the image feature vectors obtained from quantization algorithm are fed to classifiers such as Nearest Neighbor (KNN), Naive Bayes or Support Vector Machines (SVM) to determine label(s) of the visual object category or matching. In this study, SVM are used as classifiers for color determination and shade matching. Finally, experimental results of this method will be compared with other recent studies. It is concluded from the study that the proposed method is remarkable development on computer aided tooth shade determination system.

Keywords: classifiers, color determination, computer-aided system, tooth shade matching, feature extraction

Procedia PDF Downloads 443