Search results for: back propagation neural network model

Authors: Chanh Nghia Nguyen, Yu Kurokawa, Hirotsugu Inoue

Abstract:

The surface roughness is an important parameter for evaluating the quality of material surfaces since it affects functions and performance of industrial components. Although stylus and optical techniques are commonly used for measuring the surface roughness, they are applicable only to accessible surfaces. In practice, surface roughness measurement from the back side is sometimes demanded, for example, in inspection of safety-critical parts such as inner surface of pipes. However, little attention has been paid to the measurement of back surface roughness so far. Since back surface is usually inaccessible by stylus or optical techniques, ultrasonic technique is one of the most effective among others. In this research, an ultrasonic pulse-echo technique is considered for evaluating the pitch and the height of back surface having periodic triangular profile as a very first step. The pitch of the surface profile is measured by applying the diffraction grating theory for oblique incidence; then the height is evaluated by numerical analysis based on the Kirchhoff theory for normal incidence. The validity of the proposed method was verified by both numerical simulation and experiment. It was confirmed that the pitch is accurately measured in most cases. The height was also evaluated with good accuracy when it is smaller than a half of the pitch because of the approximation in the Kirchhoff theory.

Keywords: back side, inaccessible surface, periodic roughness, pulse-echo technique, ultrasonic NDE

Procedia PDF Downloads 275

Authors: Neziha Jaouedi, Noureddine Boujnah, Mohamed Salim Bouhlel

Abstract:

In the framework of human machine interaction systems enhancement, we focus throw this paper on human behavior analysis and action recognition. Human behavior is characterized by actions and reactions duality (movements, psychological modification, verbal and emotional expression). It’s worth noting that many information is hidden behind gesture, sudden motion points trajectories and speeds, many research works reconstructed an information retrieval issues. In our work we will focus on motion extraction, tracking and action recognition using wavelet network approaches. Our contribution uses an analysis of human subtraction by Gaussian Mixture Model (GMM) and body movement through trajectory models of motion constructed from kalman filter. These models allow to remove the noise using the extraction of the main motion features and constitute a stable base to identify the evolutions of human activity. Each modality is used to recognize a human action using wavelets of derived beta distributions approach. The proposed approach has been validated successfully on a subset of KTH and UCF sports database.

Keywords: feautures extraction, human action classifier, wavelet neural network, beta wavelet

Procedia PDF Downloads 411

Authors: Philipp Ruf, Massiwa Chabbi, Christoph Reich, Djaffar Ould-Abdeslam

Abstract:

In recent years, convolutional neural networks (CNN) have demonstrated high performance in image analysis, but oftentimes, there is only structured data available regarding a specific problem. By interpreting structured data as images, CNNs can effectively learn and extract valuable insights from tabular data, leading to improved predictive accuracy and uncovering hidden patterns that may not be apparent in traditional structured data analysis. In applying a single neural network for analyzing multimodal data, e.g., both structured and unstructured information, significant advantages in terms of time complexity and energy efficiency can be achieved. Converting structured data into images and merging them with existing visual material offers a promising solution for applying CNN in multimodal datasets, as they often occur in a medical context. By employing suitable preprocessing techniques, structured data is transformed into image representations, where the respective features are expressed as different formations of colors and shapes. In an additional step, these representations are fused with existing images to incorporate both types of information. This final image is finally analyzed using a CNN.

Keywords: CNN, image processing, tabular data, mixed dataset, data transformation, multimodal fusion

Procedia PDF Downloads 123

Authors: Sinarwati Mohamad Suhaili, Naomie Salim, Mohamad Nazim Jambli

Abstract:

Sequence-to-sequence (seq2seq) models augmented with attention mechanisms are playing an increasingly important role in automated customer service. These models, which are able to recognize complex relationships between input and output sequences, are crucial for optimizing chatbot responses. Central to these mechanisms are neural attention weights that determine the focus of the model during sequence generation. Despite their widespread use, there remains a gap in the comparative analysis of different attention weighting functions within seq2seq models, particularly in the domain of chatbots using the Customer Support Twitter (CST) dataset. This study addresses this gap by evaluating four distinct attention-scoring functions—dot, multiplicative/general, additive, and an extended multiplicative function with a tanh activation parameter — in neural generative seq2seq models. Utilizing the CST dataset, these models were trained and evaluated over 10 epochs with the AdamW optimizer. Evaluation criteria included validation loss and BLEU scores implemented under both greedy and beam search strategies with a beam size of k=3. Results indicate that the model with the tanh-augmented multiplicative function significantly outperforms its counterparts, achieving the lowest validation loss (1.136484) and the highest BLEU scores (0.438926 under greedy search, 0.443000 under beam search, k=3). These results emphasize the crucial influence of selecting an appropriate attention-scoring function in improving the performance of seq2seq models for chatbots. Particularly, the model that integrates tanh activation proves to be a promising approach to improve the quality of chatbots in the customer support context.

Keywords: attention weight, chatbot, encoder-decoder, neural generative attention, score function, sequence-to-sequence

Procedia PDF Downloads 78

Authors: Sai Sankalp Vemavarapu

Abstract:

This paper discusses the application of machine learning in the field of transportation engineering for predicting engineering properties of pavement more accurately and efficiently. Predicting the elastic properties aid us in assessing the current road conditions and taking appropriate measures to avoid any inconvenience to commuters. This improves the longevity and sustainability of the pavement layer while reducing its overall life-cycle cost. As an example, we have implemented differential evolution (DE) in the back-calculation of the elastic modulus of multi-layered pavement. The proposed DE global optimization back-calculation approach is integrated with a forward response model. This approach treats back-calculation as a global optimization problem where the cost function to be minimized is defined as the root mean square error in measured and computed deflections. The optimal solution which is elastic modulus, in this case, is searched for in the solution space by the DE algorithm. The best DE parameter combinations and the most optimum value is predicted so that the results are reproducible whenever the need arises. The algorithm’s performance in varied scenarios was analyzed by changing the input parameters. The prediction was well within the permissible error, establishing the supremacy of DE.

Keywords: cost function, differential evolution, falling weight deflectometer, genetic algorithm, global optimization, metaheuristic algorithm, multilayered pavement, pavement condition assessment, pavement layer moduli back calculation

Procedia PDF Downloads 164

Authors: Abhishek Agarwal, Manoj Sarda, Juhi Kaushik, Vatsal Sanjay, Arup Kumar Das

Abstract:

Propagation of fire through a non-air conditioned railway compartment is studied by virtue of numerical simulations. Simultaneous computational fire dynamics equations, such as Navier-Stokes, lumped species continuity, overall mass and energy conservation, and heat transfer are solved using finite volume based (for radiation) and finite difference based (for all other equations) solver, Fire Dynamics Simulator (FDS). A single coupe with an eight berth occupancy is used to establish the numerical model, followed by the selection of a three coupe system as the fundamental unit of the locomotive compartment. Heat Release Rate Per Unit Area (HRRPUA) of the initial fire is varied to consider a wide range of compartmental fires. Parameters, such as air inlet velocity relative to the locomotive at the windows, the level of interaction with the ambiance and closure of middle berth are studied through a wide range of numerical simulations. Almost all the loss of lives and properties due to fire breakout can be attributed to the direct or indirect exposure to flames or to the inhalation of toxic gases and resultant suffocation due to smoke and soot. Therefore, the temporal stature of fire and smoke are reported for each of the considered cases which can be used in the present or extended form to develop guidelines to be followed in case of a fire breakout.

Keywords: fire dynamics, flame propagation, locomotive fire, soot flow pattern, non-air-conditioned coaches

Procedia PDF Downloads 293

Authors: Sangmo Jon, Ganghyok Kim, Kwanghyok Jong, Ilnam Jo, Hyangsun Kim, Kukhyon Pae, GyeChol Sin

Abstract:

The back contact dye solar cells (BCDSCs), in which the transparent conductive oxide (TCO) is omitted, have the potential to use intact low-cost general substrates such as glass, metal foil, and papers. Herein, we introduce a facile manufacturing method of a Ti back contact electrode for the BCDSCs. We found that the polylinkers such as poly(butyl titanate) have a strong binding property to make Ti particles connect with one another. A porous Ti film, which consists of Ti particles of ≤10㎛ size connected by a small amount of polylinkers, has an excellent low sheet resistance of 10 ohm sq⁻¹ for an efficient electron collection for DSCs. This Ti back contact electrode can be prepared by using a facile printing method under normal ambient conditions. Conjugating the new back contact electrode technology with the traditional monolithic structure using the carbon counter electrode, we fabricated all TCO-less DSCs. These four-layer structured DSCs consist of a dye-adsorbed nanocrystalline TiO₂ film on a glass substrate, a porous Ti back contact layer, a ZrO₂ spacer layer, and a carbon counter electrode in a layered structure. Under AM 1.5G and 100mWcm⁻² simulated sunlight illumination, the four-layer structured DSCs with N719 dyes and I⁻/I₃⁻ redox electrolytes achieved PCEs up to 5.21%.

Keywords: dye solar cells, TCO-less, back contact, printing, porous Ti film

Procedia PDF Downloads 66

Authors: Tatsuya Otoshi, Masayuki Murata

Abstract:

With the development and diversification of applications on the Internet, applications that require high responsiveness, such as video streaming, are becoming mainstream. Application responsiveness is not only a matter of communication delay but also a matter of time required to grasp changes in network conditions. The tradeoff between accuracy and measurement time is a challenge in network control. We people make countless decisions all the time, and our decisions seem to resolve tradeoffs between time and accuracy. When making decisions, people are known to make appropriate choices based on relatively small samples. Although there have been various studies on models of human decision-making, a model that integrates various cognitive biases, called ”quantum decision-making,” has recently attracted much attention. However, the modeling of small samples has not been examined much so far. In this paper, we extend the model of quantum decision-making to model decision-making with a small sample. In the proposed model, the state is updated by value-based probability amplitude amplification. By analytically obtaining a lower bound on the number of samples required for decision-making, we show that decision-making with a small number of samples is feasible.

Keywords: quantum decision making, small sample, MPEG-DASH, Grover's algorithm

Procedia PDF Downloads 79

Authors: Aref Aasi, Sahar Ebrahimi Bajgani, Erfan Aasi

Abstract:

Breast cancer (BC) continues to be the most frequent cancer in females and causes the highest number of cancer-related deaths in women worldwide. Inspired by recent advances in studying the relationship between different patient attributes and features and the disease, in this paper, we have tried to investigate the different classification methods for better diagnosis of BC in the early stages. In this regard, datasets from the University Hospital Centre of Coimbra were chosen, and different machine learning (ML)-based and neural network (NN) classifiers have been studied. For this purpose, we have selected favorable features among the nine provided attributes from the clinical dataset by using a random forest algorithm. This dataset consists of both healthy controls and BC patients, and it was noted that glucose, BMI, resistin, and age have the most importance, respectively. Moreover, we have analyzed these features with various ML-based classifier methods, including Decision Tree (DT), K-Nearest Neighbors (KNN), eXtreme Gradient Boosting (XGBoost), Logistic Regression (LR), Naive Bayes (NB), and Support Vector Machine (SVM) along with NN-based Multi-Layer Perceptron (MLP) classifier. The results revealed that among different techniques, the SVM and MLP classifiers have the most accuracy, with amounts of 96% and 92%, respectively. These results divulged that the adopted procedure could be used effectively for the classification of cancer cells, and also it encourages further experimental investigations with more collected data for other types of cancers.

Keywords: breast cancer, diagnosis, machine learning, biomarker classification, neural network

Procedia PDF Downloads 135

Authors: Thomas Abraham, Garcia de la Vega Felipe, Lubna Nishath, Nzekwe Nduka, Powell Anne-Marie

Abstract:

Introduction: The purpose of this paper is to discuss the effectiveness of a peer support network created to provide medical education, pastoral support, and reliable resources to registrars to help them pass the MRCGP exams. This paper will include a description of the network and its purpose, discuss how it has been used by trainees since its creation, and explain how this methodology can be applied to other areas of medical education and primary care. Background: The peer support network was created in February 2021, using Facebook, Telegram, and WhatsApp platforms to facilitate discussion of cases and answer queries about the exams, share resources, and offer peer support from qualified GPs and specialists. The network was created and is maintained by the authors of this paper and is open to anyone who is registered with the General Medical Council (GMC) and is studying for the MRCGP exams. Purpose: The purpose of the network is to provide medical education, pastoral support, and reliable resources to registrars to help them pass the exams. The network is free to use and is designed to take the onus away from a single medical educator and collate a vast amount of information from multiple medical educators/trainers; thereby creating a digital library of information for all trainees - exam related or otherwise. Methodology The network is managed by a team of moderators who respond to queries and facilitate discussion. Smaller study groups are created from the main group and provide a platform for trainees to work together, share resources, and provide peer support. The network has had thousands of trainees using it since February 2021, with positive feedback from all trainees. Results: The feedback from trainees has been overwhelmingly positive. Word of mouth has spread rapidly, growing the groups exponentially. Trainees add colleagues to the groups and often stay after they pass their exams to 'give back' to their fellow trainees. To date, thousands of trainees have passed the MRCGP exams using the resources and support provided by the network. Conclusion The success of this peer support network demonstrates the effectiveness of creating a network of thousands of doctors to provide medical education and support.

Keywords: peer support, medical education, pastoral support, MRCGP exams

Procedia PDF Downloads 135

Authors: Juan Huang, Hugo Ninanya

Abstract:

Oil has been used as a source of energy and supply to make materials, such as asphalt or rubber for many years. This is the reason why new technologies have been implemented through time. However, research still needs to continue increasing due to new challenges engineers face every day, just like unconventional reservoirs. Various numerical methodologies have been applied in petroleum engineering as tools in order to optimize the production of reservoirs before drilling a wellbore, although not all of these have the same efficiency when talking about studying fracture propagation. Analytical methods like those based on linear elastic fractures mechanics fail to give a reasonable prediction when simulating fracture propagation in ductile materials whereas numerical methods based on the cohesive zone method (CZM) allow to represent the elastoplastic behavior in a reservoir based on a constitutive model; therefore, predictions in terms of displacements and pressure will be more reliable. In this work, a hydro-geomechanical coupled model of horizontal wells in fractured rock was developed using ABAQUS; both extended element method and cohesive elements were used to represent predefined fractures in a model (2-D). A power law for representing the rheological behavior of fluid (shear-thinning, power index <1) through fractures and leak-off rate permeating to the matrix was considered. Results have been showed in terms of aperture and length of the fracture, pressure within fracture and fluid loss. It was showed a high infiltration rate to the matrix as power index decreases. A sensitivity analysis is conclusively performed to identify the most influential factor of fluid loss.

Keywords: fracture, hydro-geomechanical model, non-Newtonian fluid, numerical analysis, sensitivity analysis

Procedia PDF Downloads 205

Authors: Alexander Vandesompele, Joni Dambre

Abstract:

The diversity in dendritic arborization, as first illustrated by Santiago Ramon y Cajal, has always suggested a role for dendrites in the functionality of neurons. In the past decades, thanks to new recording techniques and optical stimulation methods, it has become clear that dendrites are not merely passive electrical components. They are observed to integrate inputs in a non-linear fashion and actively participate in computations. Regardless, in simulations of neural networks dendritic structure and functionality are often overlooked. Especially in a machine learning context, when designing artificial neural networks, point neuron models such as the leaky-integrate-and-fire (LIF) model are dominant. These models mimic the integration of inputs at the neuron soma, and ignore the existence of dendrites. In this work, the LIF point neuron model is extended with a simple form of dendritic computation. This gives the LIF neuron increased capacity to discriminate spatiotemporal input sequences, a dendritic functionality as observed in another study. Simulations of the spiking neurons are performed using the Bindsnet framework. In the common LIF model, incoming synapses are independent. Here, we introduce a dependency between incoming synapses such that the post-synaptic impact of a spike is not only determined by the weight of the synapse, but also by the activity of other synapses. This is a form of short term plasticity where synapses are potentiated or depressed by the preceding activity of neighbouring synapses. This is a straightforward way to prevent inputs from simply summing linearly at the soma. To implement this, each pair of synapses on a neuron is assigned a variable,representing the synaptic relation. This variable determines the magnitude ofthe short term plasticity. These variables can be chosen randomly or, more interestingly, can be learned using a form of Hebbian learning. We use Spike-Time-Dependent-Plasticity (STDP), commonly used to learn synaptic strength magnitudes. If all neurons in a layer receive the same input, they tend to learn the same through STDP. Adding inhibitory connections between the neurons creates a winner-take-all (WTA) network. This causes the different neurons to learn different input sequences. To illustrate the impact of the proposed dendritic mechanism, even without learning, we attach five input neurons to two output neurons. One output neuron isa regular LIF neuron, the other output neuron is a LIF neuron with dendritic relationships. Then, the five input neurons are allowed to fire in a particular order. The membrane potentials are reset and subsequently the five input neurons are fired in the reversed order. As the regular LIF neuron linearly integrates its inputs at the soma, the membrane potential response to both sequences is similar in magnitude. In the other output neuron, due to the dendritic mechanism, the membrane potential response is different for both sequences. Hence, the dendritic mechanism improves the neuron’s capacity for discriminating spa-tiotemporal sequences. Dendritic computations improve LIF neurons even if the relationships between synapses are established randomly. Ideally however, a learning rule is used to improve the dendritic relationships based on input data. It is possible to learn synaptic strength with STDP, to make a neuron more sensitive to its input. Similarly, it is possible to learn dendritic relationships with STDP, to make the neuron more sensitive to spatiotemporal input sequences. Feeding structured data to a WTA network with dendritic computation leads to a significantly higher number of discriminated input patterns. Without the dendritic computation, output neurons are less specific and may, for instance, be activated by a sequence in reverse order.

Keywords: dendritic computation, spiking neural networks, point neuron model

Procedia PDF Downloads 133

Authors: Belkacem Selma, Boumediene Selma, Tourkia Guerzou, Abbes Labdelli

Abstract:

Natural disasters have occurred and will continue to cause human and material damage. Therefore, the idea of "preventing" natural disasters will never be possible. However, their prediction is possible with the advancement of technology. Even if natural disasters are effectively inevitable, their consequences may be partly controlled. The rapid growth and progress of artificial intelligence (AI) had a major impact on the prediction of natural disasters and risk assessment which are necessary for effective disaster reduction. The Earthquakes prediction to prevent the loss of human lives and even property damage is an important factor; that is why it is crucial to develop techniques for predicting this natural disaster. This present study aims to analyze the ability of artificial neural networks (ANNs) to predict earthquakes that occur in a given area. The used data describe the problem of high energy (higher than 10^4J) seismic bumps forecasting in a coal mine using two long walls as an example. For this purpose, seismic bumps data obtained from mines has been analyzed. The results obtained show that the ANN with high accuracy was able to predict earthquake parameters; the classification accuracy through neural networks is more than 94%, and that the models developed are efficient and robust and depend only weakly on the initial database.

Keywords: earthquake prediction, ANN, seismic bumps

Procedia PDF Downloads 126

Authors: Iqra Yaseen

Abstract:

One of the well-known areas of computer science and engineering, image processing in the context of computer vision has been essential to automation. In remote sensing, medical science, and many other fields, it has made it easier to uncover previously undiscovered facts. Grading of diverse items is now possible because of neural network algorithms, categorization, and digital image processing. Its use in the classification of agricultural products, particularly in the grading of seeds or grains and their cultivars, is widely recognized. A grading and sorting system enables the preservation of time, consistency, and uniformity. Global population growth has led to an increase in demand for food staples, biofuel, and other agricultural products. To meet this demand, available resources must be used and managed more effectively. Image processing is rapidly growing in the field of agriculture. Many applications have been developed using this approach for crop identification and classification, land and disease detection and for measuring other parameters of crop. Vegetation localization is the base of performing these task. Vegetation helps to identify the area where the crop is present. The productivity of the agriculture industry can be increased via image processing that is based upon Unmanned Aerial Vehicle photography and satellite. In this paper we use the machine learning techniques like Convolutional Neural Network, deep learning, image processing, classification, You Only Live Once to UAV imaging dataset to divide the crop into distinct groups and choose the best way to use it.

Keywords: image processing, UAV, YOLO, CNN, deep learning, classification

Procedia PDF Downloads 107

Authors: Shin Je Lee, Go Bong Choi, Jeong Cheol Seo, Jong Min Lee, Gibaek Lee

Abstract:

Water pipe network is installed underground and once equipped; it is difficult to recognize the state of pipes when the leak or burst happens. Accordingly, post management is often delayed after the fault occurs. Therefore, the systematic fault management system of water pipe network is required to prevent the accident and minimize the loss. In this work, we develop online fault detection system of water pipe network using data of pipes such as flow rate or pressure. The transient model describing water flow in pipelines is presented and simulated using Matlab. The fault situations such as the leak or burst can be also simulated and flow rate or pressure data when the fault happens are collected. Faults are detected using statistical methods of fast Fourier transform and discrete wavelet transform, and they are compared to find which method shows the better fault detection performance.

Keywords: fault detection, water pipeline model, fast Fourier transform, discrete wavelet transform

Procedia PDF Downloads 512

Authors: Rupu Yang, Cong Toan Tran, Assaad Zoughaib

Abstract:

The work provides an iterative nonlinear programming method to synthesize a heat exchanger network by manipulating the trade-offs between the heat load of process heat exchangers (HEs) and utilities. We consider for the synthesis problem two cases, the first one without fixed cost for HEs, and the second one with fixed cost. For the no fixed cost problem, the nonlinear programming (NLP) model with all the potential HEs is optimized to obtain the global optimum. For the case with fixed cost, the NLP model is iterated through adding/removing HEs. The method was applied in five case studies and illustrated quite well effectiveness. Among which, the approach reaches the lowest TAC (2,904,026$/year) compared with the best record for the famous Aromatic plants problem. It also locates a slightly better design than records in literature for a 10 streams case without fixed cost with only 1/9 computational time. Moreover, compared to the traditional mixed-integer nonlinear programming approach, the iterative NLP method opens a possibility to consider constraints (such as controllability or dynamic performances) that require knowing the structure of the network to be calculated.

Keywords: heat exchanger network, synthesis, NLP, optimization

Procedia PDF Downloads 162

Authors: Andrew Hwang

Abstract:

The average American worker sits for thirteen hours a day, often with poor posture and infrequent breaks, which can lead to health issues and back problems. The Smart Cushion was created to alert individuals of their poor postures, and may potentially alleviate back problems and correct poor posture. The Smart Cushion is a portable, rectangular, foam cushion, with five strategically placed pressure sensors, that utilizes an Arduino Uno circuit board and specifically designed software, allowing it to collect data from the five pressure sensors and store the data on an SD card. The data is then compiled into graphs and compared to controlled postures. Before volunteers sat on the cushion, their levels of back pain were recorded on a scale from 1-10. Data was recorded for an hour during sitting, and then a new, corrected posture was suggested. After using the suggested posture for an hour, the volunteers described their level of discomfort on a scale from 1-10. Different patterns of sitting postures were generated that were able to serve as early warnings of potential back problems. By using the Smart Cushion, the areas where different volunteers were applying the most pressure while sitting could be identified, and the sitting postures could be corrected. Further studies regarding the relationships between posture and specific regions of the body are necessary to better understand the origins of back pain; however, the Smart Cushion is sufficient for correcting sitting posture and preventing the development of additional back pain.

Keywords: Arduino Sketch Algorithm, biomedical technology, pressure sensors, Smart Cushion

Procedia PDF Downloads 134

Authors: Christina Adly, Meena Abdelmeseeh, Tamer Basha

Abstract:

This paper proposes a system for hand movement recognition using multichannel surface EMG(sEMG) signals obtained from 40 subjects using 40 different exercises, which are available on the Ninapro(Non-Invasive Adaptive Prosthetics) database. First, we applied processing methods to the raw sEMG signals to convert them to their amplitudes. Second, we used deep learning methods to solve our problem by passing the preprocessed signals to Fully connected neural networks(FCNN) and recurrent neural networks(RNN) with Long Short Term Memory(LSTM). Using intrasubject evaluation, The accuracy using the FCNN is 72%, with a processing time for training around 76 minutes, and for RNN's accuracy is 79.9%, with 8 minutes and 22 seconds processing time. Third, we applied some postprocessing methods to improve the accuracy, like majority voting(MV) and Movement Error Rate(MER). The accuracy after applying MV is 75% and 86% for FCNN and RNN, respectively. The MER value has an inverse relationship with the prediction delay while varying the window length for measuring the MV. The different part uses the RNN with the intersubject evaluation. The experimental results showed that to get a good accuracy for testing with reasonable processing time, we should use around 20 subjects.

Keywords: hand movement recognition, recurrent neural network, movement error rate, intrasubject evaluation, intersubject evaluation

Procedia PDF Downloads 142

Authors: Naveed Ghani

Abstract:

With the arrival of higher speed communication links and mature application running over the internet, the requirement for reliable, efficient and robust network designs rising day by day. Multi-Protocol Label Switching technology (MPLS) Virtual Private Networks (VPNs) have committed to provide optimal network services. They are gaining popularity in industry day by day. Enterprise customers are moving to service providers that offer MPLS VPNs. The main reason for this shifting is the capability of MPLS VPN to provide built in security features and any-to-any connectivity. MPLS VPNs improved the network performance due to fast label switching as compare to traditional IP Forwarding but traffic classification and policing was still required on per hop basis to enhance the performance of real time traffic which is delay sensitive (particularly voice and video). QoS (Quality of service) is the most important factor to prioritize enterprise networks’ real time traffic such as voice and video. This thesis is focused on the study of QoS parameters (e.g. delay, jitter and MOS (Mean Opinion Score)) for the real time traffic over MPLS VPNs. DiffServ (Differentiated Services) QoS model will be used over MPLS VPN network to get end-to-end service quality.

Keywords: network, MPLS, VPN, DiffServ, MPLS VPN, DiffServ QoS, QoS Model, GNS2

Procedia PDF Downloads 426

Authors: Tahir Nawaz Cheema, Dumitru Baleanu, Ali Raza

Abstract:

In this research work, we design intelligent computing through Bayesian Regularization artificial neural networks (BRANNs) introduced to solve the mathematical modeling of infectious diseases (Covid-19). The dynamical transmission is due to the interaction of people and its mathematical representation based on the system's nonlinear differential equations. The generation of the dataset of the Covid-19 model is exploited by the power of the explicit Runge Kutta method for different countries of the world like India, Pakistan, Italy, and many more. The generated dataset is approximately used for training, testing, and validation processes for every frequent update in Bayesian Regularization backpropagation for numerical behavior of the dynamics of the Covid-19 model. The performance and effectiveness of designed methodology BRANNs are checked through mean squared error, error histograms, numerical solutions, absolute error, and regression analysis.

Keywords: mathematical models, beysian regularization, bayesian-regularization backpropagation networks, regression analysis, numerical computing

Procedia PDF Downloads 147

Authors: Goutam Kumar Ghorai, Sandip Sadhukhan, Arpita Sarkar, Debprasad Sinha, G. Sarkar, Ashis K. Dhara

Abstract:

Diabetes mellitus is one of the most common chronic diseases in all countries and continues to increase in numbers significantly. Diabetic retinopathy (DR) is damage to the retina that occurs with long-term diabetes. DR is a major cause of blindness in the Indian population. Therefore, its early diagnosis is of utmost importance towards preventing progression towards imminent irreversible loss of vision, particularly in the huge population across rural India. The barriers to eye examination of all diabetic patients are socioeconomic factors, lack of referrals, poor access to the healthcare system, lack of knowledge, insufficient number of ophthalmologists, and lack of networking between physicians, diabetologists and ophthalmologists. A few diabetic patients often visit a healthcare facility for their general checkup, but their eye condition remains largely undetected until the patient is symptomatic. This work aims to focus on the design and development of a fully automated intelligent decision system for screening retinal fundus images towards detection of the pathophysiology caused by microaneurysm in the early stage of the diseases. Automated detection of microaneurysm is a challenging problem due to the variation in color and the variation introduced by the field of view, inhomogeneous illumination, and pathological abnormalities. We have developed aconvolutional neural network for efficient detection of microaneurysm. A loss function is also developed to handle severe class imbalance due to very small size of microaneurysms compared to background. The network is able to locate the salient region containing microaneurysms in case of noisy images captured by non-mydriatic cameras. The ground truth of microaneurysms is created by expert ophthalmologists for MESSIDOR database as well as private database, collected from Indian patients. The network is trained from scratch using the fundus images of MESSIDOR database. The proposed method is evaluated on DIARETDB1 and the private database. The method is successful in detection of microaneurysms for dilated and non-dilated types of fundus images acquired from different medical centres. The proposed algorithm could be used for development of AI based affordable and accessible system, to provide service at grass root-level primary healthcare units spread across the country to cater to the need of the rural people unaware of the severe impact of DR.

Keywords: retinal fundus image, deep convolutional neural network, early detection of microaneurysms, screening of diabetic retinopathy

Procedia PDF Downloads 141

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator

Procedia PDF Downloads 250

Authors: Hossein Aghababaei, Sergio Vitale, Giampaolo Ferraioli

Abstract:

In the context of Synthetic Aperture Radar (SAR) data, polarization is an important source of information for Earth's surface monitoring. SAR Systems are often considered to transmit only one polarization. This constraint leads to either single or dual polarimetric SAR imaging modalities. Single polarimetric systems operate with a fixed single polarization of both transmitted and received electromagnetic (EM) waves, resulting in a single acquisition channel. Dual polarimetric systems, on the other hand, transmit in one fixed polarization and receive in two orthogonal polarizations, resulting in two acquisition channels. Dual polarimetric systems are obviously more informative than single polarimetric systems and are increasingly being used for a variety of remote sensing applications. In dual polarimetric systems, the choice of polarizations for the transmitter and the receiver is open. The choice of circular transmit polarization and coherent dual linear receive polarizations forms a special dual polarimetric system called hybrid polarimetry, which brings the properties of rotational invariance to geometrical orientations of features in the scene and optimizes the design of the radar in terms of reliability, mass, and power constraints. The complete characterization of target scattering, however, requires fully polarimetric data, which can be acquired with systems that transmit two orthogonal polarizations. This adds further complexity to data acquisition and shortens the coverage area or swath of fully polarimetric images compared to the swath of dual or hybrid polarimetric images. The search for solutions to augment dual polarimetric data to full polarimetric data will therefore take advantage of full characterization and exploitation of the backscattered field over a wider coverage with less system complexity. Several methods for reconstructing fully polarimetric images using hybrid polarimetric data can be found in the literature. Although the improvements achieved by the newly investigated and experimented reconstruction techniques are undeniable, the existing methods are, however, mostly based upon model assumptions (especially the assumption of reflectance symmetry), which may limit their reliability and applicability to vegetation and forest scenarios. To overcome the problems of these techniques, this paper proposes a new framework for reconstructing fully polarimetric information from hybrid polarimetric data. The framework uses Deep Learning solutions to augment hybrid polarimetric data without relying on model assumptions. A convolutional neural network (CNN) with a specific architecture and loss function is defined for this augmentation problem by focusing on different scattering properties of the polarimetric data. In particular, the method controls the CNN training process with respect to several characteristic features of polarimetric images defined by the combination of different terms in the cost or loss function. The proposed method is experimentally validated with real data sets and compared with a well-known and standard approach from the literature. From the experiments, the reconstruction performance of the proposed framework is superior to conventional reconstruction methods. The pseudo fully polarimetric data reconstructed by the proposed method also agree well with the actual fully polarimetric images acquired by radar systems, confirming the reliability and efficiency of the proposed method.

Keywords: SAR image, polarimetric SAR image, convolutional neural network, deep learnig, deep neural network

Procedia PDF Downloads 67

Authors: Zohreh Moghaddas, Morteza Yazdani, Farhad Hosseinzadeh

Abstract:

Nowadays, data envelopment analysis (DEA) models featuring network structures have gained widespread usage for evaluating the performance of production systems and activities (Decision-Making Units (DMUs)) across diverse fields. By examining the relationships between the internal stages of the network, these models offer valuable insights to managers and decision-makers regarding the performance of each stage and its impact on the overall network. To further empower system decision-makers, the inverse data envelopment analysis (IDEA) model has been introduced. This model allows the estimation of crucial information for estimating parameters while keeping the efficiency score unchanged or improved, enabling analysis of the sensitivity of system inputs or outputs according to managers' preferences. This empowers managers to apply their preferences and policies on resources, such as inputs and outputs, and analyze various aspects like production, resource allocation processes, and resource efficiency enhancement within the system. The results obtained can be instrumental in making informed decisions in the future. The top result of this study is an analysis of infeasibility and incorrect estimation that may arise in the theory and application of the inverse model of data envelopment analysis with network structures. By addressing these pitfalls, novel protocols are proposed to circumvent these shortcomings effectively. Subsequently, several theoretical and applied problems are examined and resolved through insightful case studies.

Keywords: inverse models of data envelopment analysis, series network, estimation of inputs and outputs, efficiency, resource allocation, sensitivity analysis, infeasibility

Procedia PDF Downloads 51

Authors: Tammam A. Benmusa, Mohamed A. Shlibek, Rawad M. Swesi

Abstract:

The investigation of Buildings Penetration Loss (BPL) of radio signal is getting more and more important. It plays an important role in calculating the indoor coverage for wireless communication networks. In this paper, the theory behind BPL and its mechanisms have been reviewed. The operating frequency, coverage area type, climate condition, time of measurement, and other factors affecting the values of BPL have been discussed. The practical part of this work was conducting 4000 measurements of BPL in different areas in the Libyan capital, Tripoli, to get empirical model for this loss. The measurements were taken for 2 different types of wireless communication networks; mobile telephone network (for Almadar company), which operates at 900 MHz and WiMAX network (LTT company) which operates at 2500 MHz. The results for each network were summarized and presented in several graphs. The graphs are showing how the BPL affected by: time of measurement, morphology (type of area), and climatic environment.

Keywords: building penetration loss, wireless network, mobile network, link budget, indoor network performance

Procedia PDF Downloads 384

Authors: Ghoul Rachid Brahim

Abstract:

Introduction: Degenerative disc disease is a process of premature and accelerated deterioration of the intervertebral disc; it is of multifactorial origin and is responsible for chronic low back pain. Objectives: Determine an epidemiological profile of patients with painful lumbar degenerative disc disease. Patients and methods: We performed a prospective study of 104 patients operated on for degenerative painful lumbar disc disease over a period of 25 months. The parameters analyzed were: age, sex, Body Mass Index (BMI), comorbidities, family history of low back pain, and difficulty with professional activity. Results: The average age was 43.3 years, with a clear predominance of men: 72 men for 32 women, the average BMI was 26.80Kg / m2, and 63.5% of the patients were overweight. The occurrence of disc degeneration in pathological conditions was noted in 14.4% of cases. The notion of familial low back pain was found in 49% of cases. The majority of patients perform more or less arduous work (51%) in the cases. Conclusion: In our series, degenerative painful lumbar disc disease predominates in the male subject, active obese who performs more or less painful work, in whom we find a family history of low back pain.

Keywords: degenerative disc disease, low back pain, body mass index, disque intervertebrale

Procedia PDF Downloads 92

Authors: Masoud Ghaemi, MohammadJafar Hedayati, Faezeh Yousefzadeh, Hoseinali Heydarzadeh

Abstract:

According to the statistics of the International Committee on Large Dams, internal erosion and piping (scour) are major causes of the destruction of earth-fill dams. If such dams are constructed in narrow valleys, the valley walls will increase the arching of the dam body due to the transfer of vertical and horizontal stresses, so the occurrence of hydraulic fracturing in these embankments is more likely. Roudbar Dam in Lorestan is a clay-core pebble earth-fill dam constructed in a relatively narrow valley in western Iran. Three years after the onset of impoundment, there has been a fall in dam behavior. Evaluation of the dam behavior based on the data recorded on the instruments installed inside the dam body and foundation confirms the occurrence of internal erosion in the lower and adjacent parts of the core on the left support (abutment). The phenomenon of hydraulic fracturing is one of the main causes of the onset of internal erosion in this dam. Accordingly, the main objective of this paper is to evaluate the validity of this hypothesis. To evaluate the validity of this hypothesis, the dam behavior during construction and impoundment has been first simulated with a three-dimensional numerical model. Then, using validated empirical equations, the safety factor of the occurrence of hydraulic fracturing phenomenon upstream of the dam score was calculated. Then, using the artificial neural network, the failure time of the given section was predicted based on the maximum stress trend created. The study results show that steep slopes of valley walls, sudden changes in coefficient, and differences in compressibility properties of dam body materials have caused considerable stress transfer from core to adjacent valley walls, especially at its lower levels. This has resulted in the coefficient of confidence of the occurrence of hydraulic fracturing in each of these areas being close to one in each of the empirical equations used.

Keywords: arching, artificial neural network, FLAC3D, hydraulic fracturing, internal erosion, pore water pressure

Procedia PDF Downloads 177

Authors: Anna Rinaldi, Pierfrancesco Dellino

Abstract:

COVID-19 vaccine hesitancy can be observed at different rates in different countries. In June 2021, 1,068 people were surveyed in France and Italy to inquire about individual potential acceptance, focusing on time preferences in a risk-return framework: having the vaccination today, in a month, and in 3 months; perceived risks of vaccination and COVID-19; and expected benefit of the vaccine. A randomized controlled trial was conducted to understand how everyday stimuli like fact-based news about vaccines impact an audience's acceptance of vaccination. The main experiment involved two groups of participants and two different articles about vaccine-related thrombosis taken from two Italian newspapers. One article used a more abstract description and language, and the other used a more anecdotal description and concrete language; each group read only one of these articles. Two other groups were assigned categorization tasks; one was asked to complete a concrete categorization task, and the other an abstract categorization task. Individual preferences for vaccination were found to be variable and unstable over time, and individual choices of accepting, refusing, or delaying could be affected by the way news is written. In order to understand these dynamic preferences, the present work proposes a new model based on seven categories of human behaviors that were validated by a neural network. A treatment effect was observed: participants who read the articles shifted to vaccine hesitancy categories more than participants assigned to other treatments and control. Furthermore, there was a significant gender effect, showing that the type of language leading to a lower hesitancy rate for men is correlated with a higher hesitancy rate for women and vice versa. This outcome should be taken into consideration for an appropriate gender-based communication campaign aimed at achieving herd immunity. The trial was registered at ClinicalTrials.gov NCT05582564 (17/10/2022).

Keywords: vaccine hesitancy, risk elicitation, neural network, covid19

Procedia PDF Downloads 83

Authors: Liang Wang, Beste F. Yuksel, David Guy Brizan

Abstract:

A computational model of affect that can distinguish between spontaneous and posed smiles with no errors on a large, popular data set using deep learning techniques is presented in this paper. A Long Short-Term Memory (LSTM) classifier, a type of Recurrent Neural Network, is utilized and compared to human classification. Results showed that while human classification (mean of 0.7133) was above chance, the LSTM model was more accurate than human classification and other comparable state-of-the-art systems. Additionally, a high accuracy rate was maintained with small amounts of training videos (70 instances). The derivation of important features to further understand the success of our computational model were analyzed, and it was inferred that thousands of pairs of points within the eyes and mouth are important throughout all time segments in a smile. This suggests that distinguishing between a posed and spontaneous smile is a complex task, one which may account for the difficulty and lower accuracy of human classification compared to machine learning models.

Keywords: affective computing, affect detection, computer vision, deep learning, human-computer interaction, machine learning, posed smile detection, spontaneous smile detection

Procedia PDF Downloads 125

Authors: Stephen L. Green, Alexander N. Gorban, Ivan Y. Tyukin

Abstract:

Within the past decade, using Convolutional Neural Networks (CNN)’s to create Deep Learning systems capable of translating Sign Language into text has been a breakthrough in breaking the communication barrier for deaf-mute people. Conventional research on this subject has been concerned with training the network to recognize the fingerspelling gestures of a given language and produce their corresponding alphanumerics. One of the problems with the current developing technology is that images are scarce, with little variations in the gestures being presented to the recognition program, often skewed towards single skin tones and hand sizes that makes a percentage of the population’s fingerspelling harder to detect. Along with this, current gesture detection programs are only trained on one finger spelling language despite there being one hundred and forty-two known variants so far. All of this presents a limitation for traditional exploitation for the state of current technologies such as CNN’s, due to their large number of required parameters. This work aims to present a technology that aims to resolve this issue by combining a pretrained legacy AI system for a generic object recognition task with a corrector method to uptrain the legacy network. This is a computationally efficient procedure that does not require large volumes of data even when covering a broad range of sign languages such as American Sign Language, British Sign Language and Chinese Sign Language (Pinyin). Implementing recent results on method concentration, namely the stochastic separation theorem, an AI system is supposed as an operate mapping an input present in the set of images u ∈ U to an output that exists in a set of predicted class labels q ∈ Q of the alphanumeric that q represents and the language it comes from. These inputs and outputs, along with the interval variables z ∈ Z represent the system’s current state which implies a mapping that assigns an element x ∈ ℝⁿ to the triple (u, z, q). As all xi are i.i.d vectors drawn from a product mean distribution, over a period of time the AI generates a large set of measurements xi called S that are grouped into two categories: the correct predictions M and the incorrect predictions Y. Once the network has made its predictions, a corrector can then be applied through centering S and Y by subtracting their means. The data is then regularized by applying the Kaiser rule to the resulting eigenmatrix and then whitened before being split into pairwise, positively correlated clusters. Each of these clusters produces a unique hyperplane and if any element x falls outside the region bounded by these lines then it is reported as an error. As a result of this methodology, a self-correcting recognition process is created that can identify fingerspelling from a variety of sign language and successfully identify the corresponding alphanumeric and what language the gesture originates from which no other neural network has been able to replicate.

Keywords: convolutional neural networks, deep learning, shallow correctors, sign language

Procedia PDF Downloads 100