Search results for: Deep mixed column

Authors: Yeong-Gyeong Choi, Kyoung-Seok Kim

Abstract:

This study, literature review research, intends to deal with the problem of conceptual ambiguity among research on emotional labor, and to look into the evolutionary trends and changing aspects of defining the concept of emotional labor. In addition, in existing studies, deep acting and surface acting are highly related to a positive outcome variable and a negative outcome variable, respectively. It was confirmed that for employees performing emotional labor, deep acting and surface acting are highly related to OCB and CWB, respectively. While positive emotion that employees come to experience during job performance process can easily trigger a positive non-task behavior such as OCB, negative emotion that employees experience through excessive workload or unfair treatment can easily induce a negative behavior like CWB. The two management behaviors of emotional labor, surface acting and deep acting, can have either a positive or negative effect on non-task behavior of employees, depending on which one they would choose. Thus, the purpose of this review paper is to clarify the relationship between emotional labor and non-task behavior more specifically.

Keywords: emotion labor, non-task behavior, OCB, CWB

Procedia PDF Downloads 351

Authors: Asim Laeeq Khan, Mazhar Amjad Gilani, Tayub Raza

Abstract:

The use of fossil fuels for energy generation leads to the emission of greenhouse gases particularly CO2 into the atmosphere. To date, several techniques have been proposed for the efficient removal of CO2 from flue gas mixtures. Membrane technology is a promising choice due to its several inherent advantages such as low capital cost, high energy efficiency, and low ecological footprint. One of the goals in the development of membranes is to achieve high permeability and selectivity. Mixed matrix membranes comprising of inorganic fillers embedded in polymer matrix are a class of membranes that have showed improved separation properties. One of the biggest challenges in the commercialization if mixed matrix membranes are the removal of non-selective voids existing at the polymer-filler interface. In this work, mixed matrix membranes were prepared using polysulfone as polymer matrix and ordered mesoporous MCM-41 as filler materials. A new approach to removing the interfacial voids was developed by introducing room temperature ionic (RTIL) at the polymer-filler interface. The results showed that the imidazolium based RTIL not only provided wettability characteristics but also helped in further improving the separation properties. The removal of interfacial voids and good contact between polymer and filler was verified by SEM measurement. The synthesized membranes were tested in a custom built gas permeation set-up for the measurement of gas permeability and ideal gas selectivity. The results showed that the mixed matrix membranes showed significantly higher CO2 permeability in comparison to the pristine membrane. In order to have further insight into the role of fillers, diffusion and solubility measurements were carried out. The results showed that the presence of highly porous fillers resulted in increasing the diffusion coefficient while the solubility showed a slight drop. The RTIL filled membranes showed higher CO2/CH4 and CO2/N2 selectivity than unfilled membranes while the permeability dropped slightly. The increase in selectivity was due to the highly selective RTIL used in this work. The study revealed that RTIL filled mixed matrix membranes are an interesting candidate for gas separation membranes.

Keywords: ionic liquids, CO2 separation, membranes, mixed matrix membranes

Procedia PDF Downloads 479

Authors: K. R. Sreenivas, Shaurya Kaushal

Abstract:

After sunset, under calm & clear-sky nocturnal conditions, the air layer near the surface containing aerosols cools through radiative processes to the upper atmosphere. Due to this cooling, surface air-layer temperature can fall 2-6 degrees C lower than the ground-surface temperature. This unstable convection layer, on the top, is capped by a stable inversion-boundary layer. Radiative divergence, along with the convection within the surface layer, governs the vertical transport of heat and moisture. Micro-physics in this layer have implications for the occurrence and growth of the fog layer. This particular configuration, featuring a convective mixed layer beneath a stably stratified inversion layer, exemplifies a classic case of penetrative convection. In this study, we conduct numerical simulations of the penetrative convection phenomenon within the nocturnal atmospheric surface layer and elucidate its relevance to the dynamics of fog layers. We employ field and laboratory measurements of aerosol number density to model the strength of the radiative cooling. Our analysis encompasses horizontally averaged, vertical profiles of temperature, density, and heat flux. The energetic incursion of the air from the mixed layer into the stable inversion layer across the interface results in entrainment and the growth of the mixed layer, modeling of which is the key focus of our investigation. In our research, we ascertain the appropriate length scale to employ in the Richardson number correlation, which allows us to estimate the entrainment rate and model the growth of the mixed layer. Our analysis of the mixed layer and the entrainment zone reveals a close alignment with previously reported laboratory experiments on penetrative convection. Additionally, we demonstrate how aerosol number density influences the growth or decay of the mixed layer. Furthermore, our study suggests that the presence of fog near the ground surface can induce extensive vertical mixing, a phenomenon observed in field experiments.

Keywords: inversion layer, penetrative convection, radiative cooling, fog occurrence

Procedia PDF Downloads 71

Authors: Nurhak Altın, Ayhan Kucukmanisa, Oguzhan Urhan

Abstract:

It is important that highways are in good condition for traffic safety. Road crashes (road cracks, erosion of lane markings, etc.) can cause accidents by affecting driving. Image processing based methods for detecting road cracks are available in the literature. In this paper, a deep learning based road crack detection approach is proposed. YOLO (You Look Only Once) is adopted as core component of the road crack detection approach presented. The YOLO network structure, which is developed for object detection, is trained with road crack images as a new class that is not previously used in YOLO. The performance of the proposed method is compared using different training methods: using randomly generated weights and training their own pre-trained weights (transfer learning). A similar training approach is applied to the simplified version of the YOLO network model (tiny yolo) and the results of the performance are examined. The developed system is able to process 8 fps on NVIDIA Jetson TX1 development kit.

Keywords: deep learning, embedded platform, real-time processing, road crack detection

Procedia PDF Downloads 338

Authors: Kazuaki Shiraishi, Narumitsu Asai, Tsukasa Kitahara, Sosuke Mieno, Takaharu Kameoka

Abstract:

The purpose of this research is to facilitate productivity advances in agriculture. To accomplish this, we developed an automatic three-dimensional (3D) recording system for growth of field crops that consists of a number of inexpensive modules: a very low-cost stereo camera, a couple of ZigBee wireless modules, a Raspberry Pi single-board computer, and a third generation (3G) wireless communication module. Our system uses an inexpensive Web stereo camera in order to keep total costs low. However, inexpensive video cameras record low-resolution images that are very noisy. Accordingly, in order to resolve these problems, we adopted a deep learning method. Based on the results of extended period of time operation test conducted without the use of an external power supply, we found that by using Super-Resolution Convolutional Neural Network method, our system could achieve a balance between the competing goals of low-cost and superior performance. Our experimental results showed the effectiveness of our system.

Keywords: 3D plant data, automatic recording, stereo camera, deep learning, image processing

Procedia PDF Downloads 273

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: visual search, deep learning, convolutional neural network, machine learning

Procedia PDF Downloads 215

Authors: Jikhil Joseph, Satish Kumar S R.

Abstract:

Cold-formed steel frames are preferable for framed constructions due to its low seismic weights and results into low seismic forces, but on the contrary, significant lateral deflections are expected under seismic/wind loading. The various factors affecting the lateral stiffness of steel frames are the stiffness of connections, beams and columns. So, by increasing the stiffness of beam, column and making the connections rigid will enhance the lateral stiffness. The present study focused on Structural elements made of rectangular hollow sections and fastened with screwed in-plane moment connections for the building frames. The self-drilling screws can be easily drilled on either side of the connection area with the help of gusset plates. The strength of screwed connections can be made 1.2 times the connecting elements. However, achieving high stiffness in connections is also a challenging job. Hence in addition to beam and column stiffness’s the connection stiffness are also going to be a governing parameter in the lateral deflections of the frames. SAP 2000 Non-linear static analysis has been planned to study the seismic behavior of steel frames. The SAP model will be consisting of nonlinear spring model for the connection to account the semi-rigid connections and the nonlinear hinges will be assigned for beam and column sections according to FEMA 273 guidelines. The reliable spring and hinge parameters will be assigned based on an experimental and analytical database. The non-linear static analysis is mainly focused on the identification of various hinge formations and the estimation of lateral deflection and these will contribute as an inputs for the direct displacement-based Seismic design. The research output from this study are the modelling techniques and suitable design guidelines for the performance-based seismic design of cold-formed steel frames.

Keywords: buckling, cold formed steel, nonlinear static analysis, screwed connections

Procedia PDF Downloads 177

Authors: Muthana A. M. Jameel Al-Jaboori

Abstract:

In this paper, we will present a mathematical model to design a system able to generate electricity from ocean-sea waves. We will use the basic principles of the transfer of the energy potential of waves in a chamber to force the air inside a vertical or inclined cylindrical column, which is topped by a wind turbine to rotate the electric generator. The present mathematical model included a high number of variables such as the wave, height, width, length, velocity, and frequency, as well as others for the energy cylindrical column, like varying diameters and heights, and the wave chamber shape diameter and height. While for the wells wind turbine the variables included the number of blades, length, width, and clearance, as well as the rotor and tip radius. Additionally, the turbine rotor and blades must be made from the light and strong material for a smooth blade surface. The variables were too vast and high in number. Then the program was run successfully within the MATLAB and presented very good modeling results.

Keywords: water wave, models, Wells turbine, MATLAB program

Procedia PDF Downloads 363

Authors: Seong-Ho Ha, Young-Ok Yoon, Shae K. Kim

Abstract:

Oxide layer of normal Al-Mg alloy can be characterized by upper MgO and lower MgAl2O4 spinel. The formation of the MgO outmost layer occurs by the surface segregation of Mg in the initial oxidation. After then, the oxidation is proceeded with the formation of MgA12O4 spinel beneath the MgO. Growth of the oxide layer is accelerated by constant formation of MgA12O4 spinel. On the other hand, the oxidation resistance of Al-Mg alloys can be significantly improved simply by Mg+Al2Ca master alloy use as the Mg alloying element and such an improvement is attributed to the CaO/MgO mixed layer. Al-Mg alloy containing Al2Ca shows CaO as the upper layer and MgO as the lower one without MgA12O4 spinel. Such a dense oxide film acts as a protective layer. However, the CaO/MgO scale has the outmost MgO, partly, after a long time exposure to a harsh oxidation condition. The aim of this study is to investigate the inter-filling behaviour of CaO and MgO mixed layer in oxidation resistance mechanism of Al-Mg alloys containing Al2Ca. The process of outmost MgO layer formation will be clarified.

Keywords: Al-Mg alloy, Al2Ca, oxidation, MgO

Procedia PDF Downloads 282

Authors: Nan Xu

Abstract:

In airlines, the crew scheduling problem is usually decomposed into two stages: crew pairing and crew rostering. In the crew pairing stage, pairings are generated such that each flight is covered by exactly one pairing and the overall cost is minimized. In the crew rostering stage, the pairings generated in the crew pairing stage are combined with off days, training and other breaks to create individual work schedules. The paper focuses on cabin crew rostering problem, which is challenging due to the extremely large size and the complex working rules involved. In our approach, the objective of rostering consists of two major components. The first is to minimize the number of unassigned pairings and the second is to ensure the fairness to crew members. There are two measures of fairness to crew members, the number of overnight duties and the total fly-hour over a given period. Pairings should be assigned to each crew member so that their actual overnight duties and fly hours are as close to the expected average as possible. Deviations from the expected average are penalized in the objective function. Since several small deviations are preferred than a large deviation, the penalization is quadratic. Our model of the airline crew rostering problem is based on column generation. The problem is decomposed into a master problem and subproblems. The mater problem is modeled as a set partition problem and exactly one roster for each crew is picked up such that the pairings are covered. The restricted linear master problem (RLMP) is considered. The current subproblem tries to find columns with negative reduced costs and add them to the RLMP for the next iteration. When no column with negative reduced cost can be found or a stop criteria is met, the procedure ends. The subproblem is to generate feasible crew rosters for each crew member. A separate acyclic weighted graph is constructed for each crew member and the subproblem is modeled as resource constrained shortest path problems in the graph. Labeling algorithm is used to solve it. Since the penalization is quadratic, a method to deal with non-additive shortest path problem using labeling algorithm is proposed and corresponding domination condition is defined. The major contribution of our model is: 1) We propose a method to deal with non-additive shortest path problem; 2) Operation to allow relaxing some soft rules is allowed in our algorithm, which can improve the coverage rate; 3) Multi-thread techniques are used to improve the efficiency of the algorithm when generating Line-of-Work for crew members. Here a column generation based algorithm for the airline cabin crew rostering problem is proposed. The objective is to assign a personalized roster to crew member which minimize the number of unassigned pairings and ensure the fairness to crew members. The algorithm we propose in this paper has been put into production in a major airline in China and numerical experiments show that it has a good performance.

Keywords: aircrew rostering, aircrew scheduling, column generation, SPPRC

Procedia PDF Downloads 146

Authors: Mario Isaza-Ruget, Claudia C. Colmenares-Mejia, Nancy Yomayusa, Camilo A. González, Andres Cely, Jossie Murcia

Abstract:

Quantification of risks associated with complications development from chronic kidney disease (CKD) through accurate survival models can help with patient management. A retrospective cohort that included patients diagnosed with CKD from a primary care program and followed up between 2013 and 2018 was carried out. Time-dependent and static covariates associated with demographic, clinical, and laboratory factors were included. Deep Learning (DL) survival analyzes were developed for three CKD outcomes: CKD stage progression, >25% decrease in Estimated Glomerular Filtration Rate (eGFR), and Renal Replacement Therapy (RRT). Models were evaluated and compared with Random Survival Forest (RSF) based on concordance index (C-index) metric. 2.143 patients were included. Two models were developed for each outcome, Deep Neural Network (DNN) model reported C-index=0.9867 for CKD stage progression; C-index=0.9905 for reduction in eGFR; C-index=0.9867 for RRT. Regarding the RSF model, C-index=0.6650 was reached for CKD stage progression; decreased eGFR C-index=0.6759; RRT C-index=0.8926. DNN models applied in survival analysis context with considerations of longitudinal covariates at the start of follow-up can predict renal stage progression, a significant decrease in eGFR and RRT. The success of these survival models lies in the appropriate definition of survival times and the analysis of covariates, especially those that vary over time.

Keywords: artificial intelligence, chronic kidney disease, deep neural networks, survival analysis

Procedia PDF Downloads 134

Authors: Arya Prakash Padhi, Anupam Chakrabarti, Rajib Chowdhury

Abstract:

Topology or layout optimization often gives better performing economic structures and is very helpful in the conceptual design phase. But traditionally it is being done in finite element-based optimization schemes which, although gives a good result, is very time-consuming especially in 3D structures. Among other alternatives machine learning, especially deep learning-based methods, have a very good potential in resolving this computational issue. Here convolutional neural network (3D-CNN) based variational auto encoder (VAE) is trained using a dataset generated from commercially available topology optimization code ABAQUS Tosca using solid isotropic material with penalization (SIMP) method for compliance minimization. The encoded data in latent space is then fed to a 3D generative adversarial network (3D-GAN) to generate the outcome in 64x64x64 size. Here the network consists of 3D volumetric CNN with rectified linear unit (ReLU) activation in between and sigmoid activation in the end. The proposed network is seen to provide almost optimal results with significantly reduced computational time, as there is no iteration involved.

Keywords: 3D generative adversarial network, deep learning, structural topology optimization, variational auto encoder

Procedia PDF Downloads 174

Authors: Ksenia Meshkova

Abstract:

With increasing amount of multimedia data, it is very important to automate and speed up the process of obtaining meta. This process means not just recognition of some object or its movement, but recognition of the entire scene versus separate frames and having timeline segmentation as a final result. Labeling datasets is time consuming, besides, attributing characteristics to particular scenes is clearly difficult due to their nature. In this article, we will consider autoencoders application to unsupervised scene recognition and clusterization based on interpretable features. Further, we will focus on particular types of auto encoders that relevant to our study. We will take a look at the specificity of deep learning related to information theory and rate-distortion theory and describe the solutions empowering poor interpretability of deep learning in media content processing. As a conclusion, we will present the results of the work of custom framework, based on autoencoders, capable of scene recognition as was deeply studied above, with highlights generation resulted out of this recognition. We will not describe in detail the mathematical description of neural networks work but will clarify the necessary concepts and pay attention to important nuances.

Keywords: neural networks, computer vision, representation learning, autoencoders

Procedia PDF Downloads 127

Authors: William Li

Abstract:

Lane-change path planning is a crucial and yet complex task in autonomous driving. The traditional path planning approach based on a system of carefully-crafted rules to cover various driving scenarios becomes unwieldy as more and more rules are added to deal with exceptions and corner cases. This paper proposes to divide the entire path planning to two stages. In the first stage the ego vehicle travels longitudinally in the source lane to reach a safe state. In the second stage the ego vehicle makes lateral lane-change maneuver to the target lane. The paper derives the safe state conditions based on lateral lane-change maneuver calculation to ensure collision free in the second stage. To determine the acceleration sequence that minimizes the time to reach a safe state in the first stage, the paper proposes three schemes, namely, kinetic model based optimization, deep reinforcement learning, and 5G vehicle-to-vehicle (V2V) communications. The paper investigates these schemes via simulation. The model-based optimization is sensitive to the model assumptions. The deep reinforcement learning is more flexible in handling scenarios beyond the model assumed by the optimization. The 5G V2V eliminates uncertainty in predicting future behaviors of surrounding vehicles by sharing driving intents and enabling cooperative driving.

Keywords: lane change, path planning, autonomous driving, deep reinforcement learning, 5G, V2V communications, connected vehicles

Procedia PDF Downloads 252

Authors: Snowie Jane Galgo, Victor Asio

Abstract:

Geochemical composition of soils provides vital information about their origin and development. Highly weathered soils are widespread in the islands of Leyte and Samar but limited data have been published in terms of their nature, characteristics and nutrient status. This study evaluated the total elemental composition, properties and nutrient status of eight (8) deep and highly weathered soils in various parts of Leyte and Samar. Sampling was done down to 3 to 4 meters deep. Total amounts of Al₂O₃, As₂O₃, CaO, CdO, Cr₂O₃, CuO, Fe₂O₃, K₂O, MgO, MnO, Na₂O, NiO, P₂O₅, PbO, SO₃, SiO₂, TiO₂, ZnO and ZrO₂ were analyzed using an X-ray analytical microscope for eight soil profiles. Most of the deep and highly weathered soils have probably developed from homogenous parent materials based on the regular distribution with depth of TiO₂ and ZrO₂. Two of the soils indicated high variability with depth of TiO₂ and ZrO₂ suggesting that these soils developed from heterogeneous parent material. Most soils have K₂O and CaO values below those of MgO and Na₂O. This suggests more losses of K₂O and CaO have occurred since they are more mobile in the weathering environment. Most of the soils contain low amounts of other elements such as CuO, ZnO, PbO, NiO, CrO and SO₂. Basic elements such as K₂O and CaO are more mobile in the weathering environment than MgO and Na₂O resulting in higher losses of the former than the latter. Other elements also show small amounts in all soil profile. Thus, this study is very useful for sustainable crop production and environmental conservation in the study area specifically for highly weathered soils which are widespread in the Philippines.

Keywords: depth function, geochemical composition, highly weathered soils, total elemental composition

Procedia PDF Downloads 263

Authors: Youji Miyake

Abstract:

In aircraft assembly, a large number of preparatory holes are required for screw and rivet joints. Currently, many holes are drilled manually because it is difficult to machine the holes using conventional computerized numerical control(CNC) machines. The application of industrial robots to drill the hole has been considered as an alternative to the CNC machines. However, the rigidity of robot arms is so low that vibration is likely to occur during drilling. In this study, it is proposed constant-load feed machining as a method to perform high-precision drilling while minimizing the thrust force, which is considered to be the cause of vibration. In this method, the drill feed is realized by a constant load applied onto the tool so that the thrust force is theoretically kept below the applied load. The performance of the proposed method was experimentally examined through the deep hole drilling of plastic and simultaneous drilling of metal/plastic stack plates. It was confirmed that the deep hole drilling and simultaneous drilling could be performed without generating vibration by controlling the tool feed rate in the appropriate range.

Keywords: constant load feed machining, robotic drilling, deep hole, simultaneous drilling

Procedia PDF Downloads 194

Authors: Atakan Aral Ormancı, Tuğçe Arslantaş, Murat Özcü

Abstract:

This study presents the design and implementation of an experimental chassis-level system for various control applications. Specifically, the height level of the chassis is controlled using proportional integrated derivative, fuzzy logic, and deep learning control methods. Real-time data obtained from height and pressure sensors installed in a 6x2 truck chassis, in combination with pulse-width modulation signal values, are utilized during the tests. A prototype pneumatic system of a 6x2 truck is added to the setup, which enables the Smart Pneumatic Actuators to function as if they were in a real-world setting. To obtain real-time signal data from height sensors, an Arduino Nano is utilized, while a Raspberry Pi processes the data using Matlab/Simulink and provides the correct output signals to control the Smart Pneumatic Actuator in the truck chassis. The objective of this research is to optimize the time it takes for the chassis to level down and up under various loads. To achieve this, proportional integrated derivative control, fuzzy logic control, and deep learning techniques are applied to the system. The results show that the deep learning method is superior in optimizing time for a non-linear system. Fuzzy logic control with a triangular membership function as the rule base achieves better outcomes than proportional integrated derivative control. Traditional proportional integrated derivative control improves the time it takes to level the chassis down and up compared to an uncontrolled system. The findings highlight the superiority of deep learning techniques in optimizing the time for a non-linear system, and the potential of fuzzy logic control. The proposed approach and the experimental results provide a valuable contribution to the field of control, automation, and systems engineering.

Keywords: automotive, chassis level control, control systems, pneumatic system control

Procedia PDF Downloads 81

Authors: D. A. S. Gamage, B. F. A. Basnayake, W. A. J. M. De Costa

Abstract:

Agriculture plays an important and strategic role in the performance of Sri Lankan national economy. Rice is the staple food of Sri Lankans thus; rice cultivation is the major agricultural activity of the country. In Sri Lanka, out of the total rice production, a considerable amount of rice straw and rice husk goes wasted. Hence, there is a great potential of production of quality compost and rice husk charcoal. The concept of making rice straw compost and rice husk charcoal is practicable in Sri Lanka, where more than 40% of the farmers are engaged in rice cultivation. The application of inorganic nitrogen fertilizer has become a burden to the country. Rice husk charcoal as a coating material to retain N fertilizer is a suitable solution to gradually release nitrogenous compounds. Objective of this study was to produce rice husk charcoal coated urea as a slow releasing fertilizer with rice straw compost and to compare the leaching losses of nitrogen, phosphorus and potassium using leaching columns. Leaching column studies were prepared using 1.2 m tall PVC pipes with a diameter of 15 cm and a sampling port was attached to the bottom end of the column-cap. Leachates (100 ml/leaching column) were obtained from two sets of (each set has four leaching columns) leaching columns. The sampling was done once a week for 3 month period. Rice husk charcoal coated urea can potentially be used as a slow releasing nitrogen fertilizer which reduces leaching losses of urea. It also helps reduce the phosphate and potassium leaching. The cyclic effect of phosphate release is an important finding which could be the central issue in defining microbial behavior in soils. The fluctuations of phosphate may have cyclic effects of 28 days. In addition, rice straw compost and rice husk charcoal coating is less costly and contribute to mitigate pollution of water bodies by inorganic fertilizers.

Keywords: leaching, mitigate, rice husk charcoal, slow releasing fertilizer

Procedia PDF Downloads 326

Authors: John Pomerat, Aviv Segev

Abstract:

Recently, deep learning has had many theoretical breakthroughs. For deep learning to be successful in the industry, however, there need to be practical algorithms capable of handling many real-world hiccups preventing the immediate application of a learning algorithm. Although AI promises to revolutionize the healthcare industry, getting access to patient data in order to train learning algorithms has not been easy. One proposed solution to this is data- sharing. In this paper, we propose an alternative protocol, based on multi-party computation, to train deep learning models while maintaining both the privacy and security of training data. We examine three methods of training neural networks in this way: Transfer learning, average ensemble learning, and series network learning. We compare these methods to the equivalent model obtained through data-sharing across two different experiments. Additionally, we address the security concerns of this protocol. While the motivating example is healthcare, our findings regarding multi-party computation of neural network training are purely theoretical and have use-cases outside the domain of healthcare.

Keywords: neural network aggregation, multi-party computation, transfer learning, average ensemble learning

Procedia PDF Downloads 162

Authors: Carlos Riascos, Peter Thomson

Abstract:

Real-time hybrid simulation (RTHS) is a modern cyber-physical technique used for the experimental evaluation of complex systems, that treats the system components with predictable behavior as a numerical substructure and the components that are difficult to model as an experimental substructure. Therefore it is an attractive method for evaluation of the response of civil structures under earthquake, wind and anthropic loads. Another practical application of RTHS is the evaluation of control systems, as these devices are often nonlinear and their characterization is an important step in the design of controllers with the desired performance. In this paper, the response of three-story shear frame controlled by a tuned liquid column damper (TLCD) and subject to base excitation is considered. Both passive and semi-active control strategies were implemented and are compared. While the passive TLCD achieved a reduction of 50% in the acceleration response of the main structure in comparison with the structure without control, the semi-active TLCD achieved a reduction of 70%, and was robust to variations in the dynamic properties of the main structure. In addition, a RTHS was implemented with the main structure modeled as a linear, time-invariant (LTI) system through a state space representation and the TLCD, with both control strategies, was evaluated on a shake table that reproduced the displacement of the virtual structure. Current assessment measures for RTHS were used to quantify the performance with parameters such as generalized amplitude, equivalent time delay between the target and measured displacement of the shake table, and energy error using the measured force, and prove that the RTHS described in this paper is an accurate method for the experimental evaluation of structural control systems.

Keywords: structural control, hybrid simulation, tuned liquid column damper, semi-active sontrol strategy

Procedia PDF Downloads 297

Authors: Devarakonda Ramadevi, Dasari Rambabu, K. Suresh Babu, Battu Ganga Rao, Lakshmi Sirisha Kotikalapudi

Abstract:

The phytochemical and biological evaluation of the whole plant of Derris scandens is belonging to the family fabaceae. The dried plant of D.scandens was procured from the tirumala. The completely dried powder of the whole plant was taken and ground to a coarse powder which was then subjected to Soxhlet extraction with hexane and chloroform successively for 36 hrs. Chloroform extract was filtered and concentrated by using rotary evaporator an about 100g extract was obtained. The chloroform extract was subjected to column chromatographed over silicagel. From the column chromatography seven compounds were isolated named as osajin, scandinone, scandenone, 4,5,7-tri hydroxy biprenyl isoflavone, derris isoflavone-A, scandenin and isoscandinone. D.scandens resulting in the isolation of seven compounds in the plant was confirmed by spectral data (1H NMR, 13C NMR, ESI-MS and FTIR). The isolated compounds were screened for antioxidant activity, antidiabetic activity, α-glucosidase (inhibitory activity) and anti-bacterial activity. The isolated seven compounds were tested for α-glucosidase inhibitory activity and antioxidant activity. All the seven compounds showed good α-glucosidase inhibitory activity and moderate antioxidant activity.

Keywords: Derris scandens, phytochemical, antioxident, antidiabetic, antibacterial activity

Procedia PDF Downloads 316

Authors: Huy Hieu Pham, Houssam Salmane, Louahdi Khoudour, Alain Crouzil, Pablo Zegers, Sergio Velastin

Abstract:

We present a deep learning-based multitask framework for joint 3D human pose estimation and action recognition from color video sequences. Our approach proceeds along two stages. In the first, we run a real-time 2D pose detector to determine the precise pixel location of important key points of the body. A two-stream neural network is then designed and trained to map detected 2D keypoints into 3D poses. In the second, we deploy the Efficient Neural Architecture Search (ENAS) algorithm to find an optimal network architecture that is used for modeling the Spatio-temporal evolution of the estimated 3D poses via an image-based intermediate representation and performing action recognition. Experiments on Human3.6M, Microsoft Research Redmond (MSR) Action3D, and Stony Brook University (SBU) Kinect Interaction datasets verify the effectiveness of the proposed method on the targeted tasks. Moreover, we show that our method requires a low computational budget for training and inference.

Keywords: human action recognition, pose estimation, D-CNN, deep learning

Procedia PDF Downloads 145

Authors: B. Mohebi, N. Asadi, F. Kazemi

Abstract:

Inelastic deformation of the brace in Special Concentrically Braced Frame (SCBF) creates inelastic damages on gusset plate connections such as buckling at edges. In this study, to improve the seismic performance of SCBFs connections, an analytical study was undertaken. To improve the gusset plate connection, this study proposes using ‎edge’s stiffeners in both sides of gusset plate.‎ For this purpose, in order to examine edge’s stiffeners effect on gusset plate connections, two groups of modeling with and without considering edge’s stiffener and different types of braces were modeled using ABAQUS software. The results show that considering the edge’s stiffener reduces the equivalent plastic strain values at a connection region of gusset plate with beam and column, which can improve the seismic performance of gusset plate. Furthermore, considering the edge’s stiffeners significantly decreases the strain concentration at regions where gusset plates have been connected to beam and column. Moreover, considering 2t_pl distance causes reduction in the plastic strain.

Keywords: special concentrically braced frame, gusset plate, edge's stiffener, seismic performance

Procedia PDF Downloads 126

Authors: Zhenjie Liu

Abstract:

This paper investigates the existence and uniqueness of solutions for singular higher order boundary value problems on time scales by using mixed monotone method. The theorems obtained are very general. For the different time scale, the problem may be the corresponding continuous or discrete boundary value problem.

Keywords: mixed monotone operator, boundary value problem, time scale, green's function, positive solution, singularity

Procedia PDF Downloads 256

Authors: Abdallah Sofiane Berrouk, Dara Satyadileep

Abstract:

This paper investigates the feasibility of retrofitting a middle-east based commercial amine sweetening unit with a split-flow scheme which involves withdrawing a portion of partially stripped semi-lean solvent from the stripping column and re-injecting it in the absorption column to reduce the overall energy consumption of the unit. This method is comprehensively explored by performing parametric analysis of the split fraction of the semi-lean solvent using a kinetics based process simulator ProMax V 3.2. Re-boiler duty, condenser duty, solvent cooling and pumping loads are analysed as functions of a split fraction of the semi-lean solvent from the stripper. It is shown that the proposed method significantly reduces the overall energy consumption of the unit resulting in an annual savings of 325,000 USD. The thorough economic analysis is performed using Aspen Economic Evaluation V 8.4 to reveal that the retrofit scheme pays back the capital cost in less than eight years and is highly recommended for any commercial plant having suitable provisions for solvent inlet/withdrawal on the columns.

Keywords: split flow, Amine, gas processing, optimization

Procedia PDF Downloads 329

Authors: Payam Rasoulnia, Seyyed Mohammad Mousavi

Abstract:

Heavy fuel oil firing power plants produce huge amounts of ashes as solid wastes, which seriously need to be managed and processed. Recycling precious metals of V and Ni from these oil-fired ashes which are considered as secondary sources of metals recovery, not only has a great economic importance for use in industry, but also it is noteworthy from the environmental point of view. Vanadium is an important metal that is mainly used in the steel industry because of its physical properties of hardness, tensile strength, and fatigue resistance. It is also utilized in oxidation catalysts, titanium–aluminum alloys and vanadium redox batteries. In the present study bioleaching of vanadium and nickel from an oil-fired ash sample was conducted using Aspergillus niger fungus. The experiments were carried out using spent-medium bioleaching method in both Erlenmeyer flasks and also bubble column bioreactor, in order to compare them together. In spent-medium bioleaching the solid waste is not in direct contact with the fungus and consequently the fungal growth is not retarded and maximum organic acids are produced. In this method the metals are leached through biogenic produced organic acids present in the medium. In shake flask experiments the fungus was cultured for 15 days, where the maximum production of organic acids was observed, while in bubble column bioreactor experiments a 7 days fermentation period was applied. The amount of produced organic acids were measured using high performance liquid chromatography (HPLC) and the results showed that depending on the fermentation period and the scale of experiments, the fungus has different major lixiviants. In flask tests, citric acid was the main produced organic acid by the fungus and the other organic acids including gluconic, oxalic, and malic were excreted in much lower concentrations, while in the bioreactor oxalic acid was the main lixiviant and it was produced considerably. In Erlenmeyer flasks during 15 days fermentation of Aspergillus niger, 8080 ppm citric acid and 1170 ppm oxalic acid was produced, while in bubble column bioreactor over 7 days of fungal growth, 17185 ppm oxalic acid and 1040 ppm citric acid was secreted. The leaching tests using the spent-media obtained from both of fermentation experiments, were performed at the same conditions of leaching duration of 7 days, leaching temperature of 60 °C and pulp density up to 3% (w/v). The results revealed that in Erlenmeyer flask experiments 97% of V and 50% of Ni were extracted while using spent medium produced in bubble column bioreactor, V and Ni recoveries were achieved to 100% and 33%, respectively. These recovery yields indicate that in both scales almost total vanadium can be recovered, while nickel recovery was lower. With help of the bioreactor spent-medium nickel recovery yield was lower than that of obtained from the flask experiments, which it could be due to precipitation of some values of Ni in presence of high levels of oxalic acid existing in its spent medium.

Keywords: Aspergillus niger, bubble column bioreactor, oil-fired ash, spent-medium bioleaching

Procedia PDF Downloads 229

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 266

Authors: My Hachem Aouragh, Hind Ragragui, Abdellah El-Hmaidi, Ali Essahlaoui, Abdelhadi El Ouali

Abstract:

This study investigates soil erosion susceptibility in the Oued Mikkes watershed, located in the Meknes-Fez region of northern Morocco, utilizing advanced techniques such as deep learning algorithms and remote sensing integrated within Geographic Information Systems (GIS). Spanning approximately 1,920 km², the watershed is characterized by a semi-arid Mediterranean climate with irregular rainfall and limited water resources. The waterways within the watershed, especially the Oued Mikkes, are vital for agricultural irrigation and potable water supply. The research assesses the extent of erosion risk upstream of the Sidi Chahed dam while developing a spatial model of soil loss. Several important factors, including topography, land use/land cover, and climate, were analyzed, with data on slope, NDVI, and rainfall erosivity processed using deep learning models (DLNN, CNN, RNN). The results demonstrated excellent predictive performance, with AUC values of 0.92, 0.90, and 0.88 for DLNN, CNN, and RNN, respectively. The resulting susceptibility maps provide critical insights for soil management and conservation strategies, identifying regions at high risk for erosion across 24% of the study area. The most high-risk areas are concentrated on steep slopes, particularly near the Ifrane district and the surrounding mountains, while low-risk areas are located in flatter regions with less rugged topography. The combined use of remote sensing and deep learning offers a powerful tool for accurate erosion risk assessment and resource management in the Mikkes watershed, highlighting the implications of soil erosion on dam siltation and operational efficiency.

Keywords: soil erosion, GIS, remote sensing, deep learning, Mikkes Watershed, Morocco

Procedia PDF Downloads 17

Authors: John Gibbs, Benjamin Flanders, Dylan Pozorski, Weixuan Liu

Abstract:

Weight Painting–adjusting the influence a skeletal joint has on a given vertex in a character mesh–is an arduous and time con- suming part of the 3D animation pipeline. This process generally requires a trained technical animator and many hours of work to complete. Our skiNNer plug-in, which works within Autodesk’s Maya 3D animation software, uses Machine Learning and data pro- cessing techniques to create a deep neural network model that can accomplish the weight painting task in seconds rather than hours for bipedal quasi-humanoid character meshes. In order to create a properly trained network, a number of challenges were overcome, including curating an appropriately large data library, managing an arbitrary 3D mesh size, handling arbitrary skeletal architectures, accounting for extreme numeric values (most data points are near 0 or 1 for weight maps), and constructing an appropriate neural network model that can properly capture the high frequency alter- ation between high weight values (near 1.0) and low weight values (near 0.0). The arrived at neural network model is a cross between a traditional CNN, deep residual network, and fully dense network. The resultant network captures the unusually hard-edged features of a weight map matrix, and produces excellent results on many bipedal models.

Keywords: 3d animation, animation, character, rigging, skinning, weight painting, machine learning, artificial intelligence, neural network, deep neural network

Procedia PDF Downloads 271

Authors: Masood Varshosaz, Kamyar Hasanpour

Abstract:

In recent years, we have seen growing interest in recognizing humans in drone images for post-disaster search and rescue operations. Deep learning algorithms have shown great promise in this area, but they often require large amounts of labeled data to train the models. To keep the data acquisition cost low, augmentation techniques can be used to create additional data from existing images. There are many techniques of such that can help generate variations of an original image to improve the performance of deep learning algorithms. While data augmentation is potentially assumed to improve the accuracy and robustness of the models, it is important to ensure that the performance gains are not outweighed by the additional computational cost or complexity of implementing the techniques. To this end, it is important to evaluate the impact of data augmentation on the performance of the deep learning models. In this paper, we evaluated the most currently available 2D data augmentation techniques on a standard convolutional network which was trained for recognizing humans in drone images. The techniques include rotation, scaling, random cropping, flipping, shifting, and their combination. The results showed that the augmented models perform 1-3% better compared to a base network. However, as the augmented images only contain the human parts already visible in the original images, a new data augmentation approach is needed to include the invisible parts of the human body. Thus, we suggest a new method that employs simulated 3D human models to generate new data for training the network.

Keywords: human recognition, deep learning, drones, disaster mitigation

Procedia PDF Downloads 93