Search results for: residual network 50

Authors: Markus Remm, Sebastian Dienert

Abstract:

Vehicle interiors are not only changing in terms of design and functionality but also due to new driving situations in which, for example, autonomous operating modes are possible. Flexible seating positions are changing the requirements for passive safety system behavior and location in the interior of a vehicle. With fully autonomous driving, the driver can, for example, leave the position behind the steering wheel and take a seated position facing backward. Since autonomous and non-autonomous vehicles will share the same road network for the foreseeable future, accidents cannot be avoided, which makes the use of passive safety systems indispensable. With JENOPTIK-VOTAN® A technology, the trend towards flexible predetermined airbag weakening lines is enabled. With the help of laser beams, the predetermined weakening lines are introduced from the backside of the components so that they are absolutely invisible. This machining process is sensor-controlled and guarantees that a small residual wall thickness remains for the best quality and reliability for airbag weakening lines. Due to the wide processing range of the laser, the processing of almost all materials is possible. A CO₂ laser is used for many plastics, natural fiber materials, foams, foils and material composites. A femtosecond laser is used for natural materials and textiles that are very heat-sensitive. This laser type has extremely short laser pulses with very high energy densities. Supported by a high-precision and fast movement of the laser beam by a laser scanner system, the so-called cold ablation is enabled to predetermine weakening lines layer by layer until the desired residual wall thickness remains. In that way, for example, genuine leather can be processed in a material-friendly and process-reliable manner without design implications to the components A-Side. Passive safety in the vehicle is increased through the interaction of modern airbag technology and high-precision laser airbag weakening. The JENOPTIK-VOTAN® A product family has been representing this for more than 25 years and is pointing the way to the future with new and innovative technologies.

Keywords: design freedom, interior material processing, laser technology, passive safety

Procedia PDF Downloads 121

Authors: Himanshu Payal, Sachin Maheshwari, Pushpendra S. Bharti

Abstract:

Electrical discharge machining (EDM), a non-conventional machining process, finds wide applications for shaping difficult-to-cut alloys. Process modeling of EDM is required to exploit the process to the fullest. Process modeling of EDM is a challenging task owing to involvement of so many electrical and non-electrical parameters. This work is an attempt to model the EDM process using artificial neural network (ANN). Experiments were carried out on die-sinking EDM taking Inconel 825 as work material. ANN modeling has been performed using experimental data. The prediction ability of trained network has been verified experimentally. Results indicate that ANN can predict the values of performance measures of EDM satisfactorily.

Keywords: artificial neural network, EDM, metal removal rate, modeling, surface roughness

Procedia PDF Downloads 413

Authors: Ehsan Khademi, Mahdi Jalili

Abstract:

Despite the special features of bipartite networks, they are common in many systems. Real-world bipartite networks may show community structure, similar to what one can find in one-mode networks. However, the interpretation of the community structure in bipartite networks is different as compared to one-mode networks. In this manuscript, we compare a number of available methods that are frequently used to discover community structure of bipartite networks. These networks are categorized into two broad classes. One class is the methods that, first, transfer the network into a one-mode network, and then apply community detection algorithms. The other class is the algorithms that have been developed specifically for bipartite networks. These algorithms are applied on a model network with prescribed community structure.

Keywords: community detection, bipartite networks, co-clustering, modularity, network projection, complex networks

Procedia PDF Downloads 627

Authors: Francesco Buccafurri, Celeste Romolo

Abstract:

Nowadays phishing is the most frequent starting point of cyber-attack vectors. Phishing is implemented both via email and social network messages. While a wide scientific literature exists which addresses the problem of contrasting email spam-phishing, no specific countermeasure has been so far proposed for phishing included into private messages of social network platforms. Unfortunately, the problem is severe. This paper proposes an approach against social network phishing, based on a non invasive collaborative information-sharing approach which leverages blockchain. The detection method works by filtering candidate messages, by distilling them by means of a distance-preserving hash function, and by publishing hashes over a public blockchain through a trusted smart contract (thus avoiding denial of service attacks). Phishing detection exploits social information embedded into social network profiles to identify similar messages belonging to disjoint contexts. The main contribution of the paper is to introduce a new approach to contrasting the problem of social network phishing, which, despite its severity, received little attention by both research and industry.

Keywords: phishing, social networks, information sharing, blockchain

Procedia PDF Downloads 330

Authors: Jose L. Oliver, Taras Agryzkov, Leandro Tortosa, Jose F. Vicent, Javier Santacruz

Abstract:

This paper aims to demonstrate how a topological study of an urban street network can be used as a tool to be applied to some heritage conservation areas in a city. In the last decades, we find different kinds of approaches in the discipline of Architecture and Urbanism based in the so-called Sciences of Complexity. In this context, this paper uses mathematics from the Network Theory. Hence, it proposes a methodology based in obtaining information from a graph, which is created from a network of urban streets. Then, it is used an algorithm that establishes a ranking of importance of the nodes of that network, from its topological point of view. The results are applied to a heritage area in a particular city, confronting the data obtained from the mathematical model, with the ones from the field work in the case study. As a result of this process, we may conclude the necessity of implementing some actions in the area, and where those actions would be more effective for the whole heritage site.

Keywords: graphs, heritage cities, spatial analysis, urban networks

Procedia PDF Downloads 398

Authors: Ravi Raj, Louis Chiu, Deepak Marla, Aijun Huang

Abstract:

Hybridization of the directed laser deposition (DLD) process using an in-situ micro-roller to impart a vertical compressive load on the deposited bead at elevated temperatures can relieve tensile residual stresses incurred in the process. To investigate this stress relief mechanism and its relationship with the in-situ rolling parameters, a fully coupled dynamic thermo-mechanical model is presented in this study. A single bead deposition of Ti-6Al-4V alloy with an in-situ roller made of mild steel moving at a constant speed with a fixed nominal bead reduction is simulated using the explicit solver of the finite element software, Abaqus. The thermal model includes laser heating during the deposition process and the heat transfer between the roller and the deposited bead. The laser heating is modeled using a moving heat source with a Gaussian distribution, applied along the pre-formed bead’s surface using the VDFLUX Fortran subroutine. The bead’s cross-section is assumed to be semi-elliptical. The interfacial heat transfer between the roller and the bead is considered in the model. Besides, the roller is cooled internally using axial water flow, considered in the model using convective heat transfer. The mechanical model for the bead and substrate includes the effects of rolling along with the deposition process, and their elastoplastic material behavior is captured using the J2 plasticity theory. The model accounts for strain, strain rate, and temperature effects on the yield stress based on Johnson-Cook’s theory. Various aspects of this material behavior are captured in the FE software using the subroutines -VUMAT for elastoplastic behavior, VUHARD for yield stress, and VUEXPAN for thermal strain. The roller is assumed to be elastic and does not undergo any plastic deformation. Also, contact friction at the roller-bead interface is considered in the model. Based on the thermal results of the bead, the distance between the roller and the deposition nozzle (roller o set) can be determined to ensure rolling occurs around the beta-transus temperature for the Ti-6Al-4V alloy. It is identified that roller offset and the nominal bead height reduction are crucial parameters that influence the residual stresses in the hybrid process. The results obtained from a simulation at roller offset of 20 mm and nominal bead height reduction of 7% reveal that the tensile residual stresses decrease to about 52% due to in-situ rolling throughout the deposited bead. This model can be used to optimize the rolling parameters to minimize the residual stresses in the hybrid DLD process with in-situ micro-rolling.

Keywords: directed laser deposition, finite element analysis, hybrid in-situ rolling, thermo-mechanical model

Procedia PDF Downloads 111

Authors: Jae Hee Choi, Seung Il Ahn, Sae Kyul Kim, Byung Wook Yang, Bong Sun Park, Hwan Sup Kim, Young Tae Hahm

Abstract:

The root of Panax ginseng C. A. MEYER, commonly known as Korean ginseng, has several physiologic effects as a cure-all or a panacea. Among the ginseng, ginseng berry can be obtained from 3 or 4-year-old ginseng plant. Ginseng berry contains the high amount of ginsenoside Re, compared with other ginsenosides. Ginseng berry wine was manufactured with berry extract. The concentration of ginsenoside in ginseng berry extract obtained from Anseong Ginseng Nonghyup was 3.6 mg/g. Ethanol content of ginseng berry wine was 15.00±1.00%. Total polyphenol content was 1.62±0.12 mg/ml. In analysis of organic acids, acetic acid was high in ginseng berry extract whereas malic acid in ginseng berry wine was high.Ginseng berry rice wine was manufactured with berry extract with traditional nuruk (yeast). When the ginseng berry rice wine was manufactured, ginseng berry extract was diluted into 5% of total volume of wine. pH values and total acidity were 3.30±0.03 and 1.28±0.0 %, respectively. Residual sugar content was 8.8 ± 0.0 °Brix and ethanol content was 14.00 %. Any residual pesticides were not detected over acceptable range. Overall, the ginseng berry extract were valuable food stuffs for the manufacture of new ginseng product.

Keywords: ginseng berry, ginseng berry wine, ginsenoside, panax ginseng

Procedia PDF Downloads 298

Authors: Zhaofeng Li, Jun Kang Chow, Yu-Hsing Wang

Abstract:

This paper attempts to bridge the soil properties and the mechanical response of soil in the discrete element method (DEM) simulation. The artificial neural network (ANN) was therefore adopted, aiming to reproduce the stress-strain-volumetric response when soil properties are given. 31 biaxial shearing tests with varying soil parameters (e.g., initial void ratio and interparticle friction coefficient) were generated using the DEM simulations. Based on these 45 sets of training data, a three-layer neural network was established which can output the entire stress-strain-volumetric curve during the shearing process from the input soil parameters. Beyond the training data, 2 additional sets of data were generated to examine the validity of the network, and the stress-strain-volumetric curves for both cases were well reproduced using this network. Overall, the ANN was found promising in predicting the soil behavior and reducing repetitive simulation work.

Keywords: artificial neural network, discrete element method, soil properties, stress-strain-volumetric response

Procedia PDF Downloads 395

Authors: Vrince Vimal, Madhav J. Nigam

Abstract:

Wireless sensor networks have enticed much of the spotlight from researchers all around the world, owing to its extensive applicability in agricultural, industrial and military fields. Energy conservation node deployment stratagems play a notable role for active implementation of Wireless Sensor Networks. Clustering is the approach in wireless sensor networks which improves energy efficiency in the network. The clustering algorithm needs to have an optimum size and number of clusters, as clustering, if not implemented properly, cannot effectively increase the life of the network. In this paper, an algorithm has been proposed to address connectivity issues with the aim of ensuring the uniform energy consumption of nodes in every part of the network. The results obtained after simulation showed that the proposed algorithm has an edge over existing algorithms in terms of throughput and networks lifetime.

Keywords: Wireless Sensor network (WSN), Random Deployment, Clustering, Isolated Nodes, Networks Lifetime

Procedia PDF Downloads 337

Authors: Kevin D. Manalo, Jumelyn L. Torres, Noel B. Linsangan

Abstract:

This paper focuses on a wireless myoelectric prosthesis of the upper-limb that uses a Multilayer Perceptron Neural network with back propagation. The algorithm is widely used in pattern recognition. The network can be used to train signals and be able to use it in performing a function on their own based on sample inputs. The paper makes use of the Neural Network in classifying the electromyography signal that is produced by the muscle in the amputee’s skin surface. The gathered data will be passed on through the Classification Stage wirelessly through Zigbee Technology. The signal will be classified and trained to be used in performing the arm positions in the prosthesis. Through programming using Verilog and using a Field Programmable Gate Array (FPGA) with Zigbee, the EMG signals will be acquired and will be used for classification. The classified signal is used to produce the corresponding Hand Movements (Open, Pick, Hold, and Grip) through the Zigbee controller. The data will then be processed through the MLP Neural Network using MATLAB which then be used for the surface myoelectric prosthesis. Z-test will be used to display the output acquired from using the neural network.

Keywords: field programmable gate array, multilayer perceptron neural network, verilog, zigbee

Procedia PDF Downloads 389

Authors: Earleen Jane Fuentes, Regeene Melarese Lim, Franklin Benjamin Tapia, Alexis Pantola

Abstract:

Mobile Ad-hoc Network (MANET) is an infrastructure-less network of mobile devices, also known as nodes. These nodes heavily rely on each other’s resources such as memory, computing power, and energy. Thus, some nodes may become selective in forwarding packets so as to conserve their resources. These nodes are called misleading nodes. Several reputation-based techniques (e.g. CORE, CONFIDANT, LARS, SORI, OCEAN) and acknowledgment-based techniques (e.g. TWOACK, S-TWOACK, EAACK) have been proposed to detect such nodes. These techniques do not appropriately punish misleading nodes. Hence, this paper addresses the limitations of these techniques using a system called MINDRA.

Keywords: acknowledgment-based techniques, mobile ad-hoc network, selfish nodes, reputation-based techniques

Procedia PDF Downloads 386

Authors: D. Jagath Kumari, K. Srinivasa Rao

Abstract:

Reinforced concrete column is an important structural element in a building. Concrete usually performs well in building fires. However, when it is subjected to prolonged fire exposure or unusually high temperatures, and then it will suffer significant distress. Because concrete pre-fire compressive strength generally exceeds design requirements, therefore an average strength reduction can be tolerated. However high temperature reduces the compressive strength of concrete so much that the concrete retains no useful structural strength. Therefore the residual strength and its performance of structure can be assed by NDT testing. In this paper, rebound hammer test and the ultrasonic pulse velocity (UPV) are used to evaluate the residual compressive strength and material integrity of post-fire-curing concrete subjected to elevated temperatures. Also considering the large availability of fly ash in most of the countries, an attempt was made to study the effect of high volume fly ash concrete exposed to elevated temperatures. 32 RC column specimens were made with a M20 grade concrete mix. Out of 32 column specimens 16 column specimens were made with OPC concrete and other 16 column specimens were made with HVFA concrete. All specimens having similar cross-section details. Columns were exposed to fire for temperatures from 100oC to 800o C with increments of 100o C for duration of 3 hours. Then the specimens allowed cooling to room temperature by two methods natural air cooling method and immediate water quenching method. All the specimens were tested identically, for the compressive strengths and material integrity by rebound hammer and ultrasonic pulse velocity meter respectively for study. These two tests were carried out on preheating and post heating of the column specimens. The percentage variation of compressive strengths of RCC columns with the increase in temperature has been studied and compared the results for both OPC and HVFA concretes. Physical observations of the heated columns were observed.

Keywords: HVFA concrete, NDT testing, residual strength

Procedia PDF Downloads 387

Authors: Yang Xiong, Hua Cheng

Abstract:

In this paper, for the basic problem of wireless sensor network topology control and deployment, the Roesser model in rectangular grid sensor networks is presented. In addition, a general constructive realization procedure will be proposed. The procedure enables a distributed implementation of linear systems on a sensor network. A non-trivial example is illustrated.

Keywords: grid sensor networks, Roesser model, state-space realization, multidimensional systems

Procedia PDF Downloads 657

Authors: Frederic Jumelle, Kelvin So, Didan Deng

Abstract:

In this paper, we are introducing a model of artificial general intelligence (AGI), the functional neural network (FNN), for modeling human decision-making processes. The FNN is composed of multiple artificial mirror neurons (AMN) racing in the network. Each AMN has a similar structure programmed independently by the users and composed of an intention wheel, a motor core, and a sensory core racing at a specific velocity. The mathematics of the node’s formulation and the racing mechanism of multiple nodes in the network will be discussed, and the group decision process with fuzzy logic and the transformation of these conceptual methods into practical methods of simulation and in operations will be developed. Eventually, we will describe some possible future research directions in the fields of finance, education, and medicine, including the opportunity to design an intelligent learning agent with application in AGI. We believe that FNN has a promising potential to transform the way we can compute decision-making and lead to a new generation of AI chips for seamless human-machine interactions (HMI).

Keywords: neural computing, human machine interation, artificial general intelligence, decision processing

Procedia PDF Downloads 125

Authors: Han Bing, Yin Zhenjie

Abstract:

In order to analyze the status of a diesel engine, as well as conduct fault prediction, a new prediction model based on a gray system is proposed in this paper, which takes advantage of the neural network and the genetic algorithm. The proposed GBPGA prediction model builds on the GM (1.5) model and uses a neural network, which is optimized by a genetic algorithm to construct the error compensator. We verify our proposed model on the diesel faulty simulation data and the experimental results show that GBPGA has the potential to employ fault prediction on diesel.

Keywords: fault prediction, neural network, GM(1, 5) genetic algorithm, GBPGA

Procedia PDF Downloads 306

Authors: Abhisek Dash

Abstract:

This study had three neural networks, one for number segmentation, one for number detection and one for number recognition all of which are coupled to one another. All networks were trained on the MNIST dataset and were convolutional. It was assumed that the images had lighter background and darker foreground. The segmentation network took 28x28 images as input and had sixteen outputs. Segmentation training starts when a dark pixel is encountered. Taking a window(7x7) over that pixel as focus, the eight neighborhood of the focus was checked for further dark pixels. The segmentation network was then trained to move in those directions which had dark pixels. To this end the segmentation network had 16 outputs. They were arranged as “go east”, ”don’t go east ”, “go south east”, “don’t go south east”, “go south”, “don’t go south” and so on w.r.t focus window. The focus window was resized into a 28x28 image and the network was trained to consider those neighborhoods which had dark pixels. The neighborhoods which had dark pixels were pushed into a queue in a particular order. The neighborhoods were then popped one at a time stitched to the existing partial image of the number one at a time and trained on which neighborhoods to consider when the new partial image was presented. The above process was repeated until the image was fully covered by the 7x7 neighborhoods and there were no more uncovered black pixels. During testing the network scans and looks for the first dark pixel. From here on the network predicts which neighborhoods to consider and segments the image. After this step the group of neighborhoods are passed into the detection network. The detection network took 28x28 images as input and had two outputs denoting whether a number was detected or not. Since the ground truth of the bounds of a number was known during training the detection network outputted in favor of number not found until the bounds were not met and vice versa. The recognition network was a standard CNN that also took 28x28 images and had 10 outputs for recognition of numbers from 0 to 9. This network was activated only when the detection network votes in favor of number detected. The above methodology could segment connected and overlapping numbers. Additionally the recognition unit was only invoked when a number was detected which minimized false positives. It also eliminated the need for rules of thumb as segmentation is learned. The strategy can also be extended to other characters as well.

Keywords: convolutional neural networks, OCR, text detection, text segmentation

Procedia PDF Downloads 163

Authors: Muhammad Azam, Micheal Olaolu Arowolo, Fei He, Mihail Popescu, Dong Xu

Abstract:

The number of biological papers is growing quickly, which means that the number of biological pathway figures in those papers is also increasing quickly. Each pathway figure shows extensive biological information, like the names of genes and how the genes are related. However, manually annotating pathway figures takes a lot of time and work. Even though using advanced image understanding models could speed up the process of curation, these models still need to be made more accurate. To improve gene name recognition from pathway figures, we applied a Siamese network to map image segments to a library of pictures containing known genes in a similar way to person recognition from photos in many photo applications. We used a triple loss function and a triplet spatial pyramid pooling network by combining the triplet convolution neural network and the spatial pyramid pooling (TSPP-Net). We compared VGG19 and VGG16 as the Siamese network model. VGG16 achieved better performance with an accuracy of 93%, which is much higher than OCR results.

Keywords: biological pathway, image understanding, gene name recognition, object detection, Siamese network, VGG

Procedia PDF Downloads 292

Authors: Henok Mezemr Besfat, Haftom Gebreslassie Gebregwergs

Abstract:

wireless network is one of the most important mediums of transmission of information from one device to another devices. Wireless communication has a broad range of applications, including mobile communications through cell phones and satellites, Internet of Things (IoT) connecting several devices, wireless sensor networks for traffic management and environmental monitoring, satellite communication for weather forecasting and TV without requiring any cable or wire or other electronic conductors, by using electromagnetic waves like IR, RF, satellite, etc. This paper summarizes different wireless network technologies, applications of different wireless technologies and different types of wireless networks. Generally, wireless technology will further enhance operations and experiences across sectors with continued innovation. This paper suggests different strategies that can improve wireless networks and technologies.

Keywords: wireless senser, wireless technology, wireless network, internet of things

Procedia PDF Downloads 58

Authors: Oluwaponmile David Alao

Abstract:

Misdiagnosis has been the major problem in health sector. Heart attack has been one of diseases that have high level of misdiagnosis recorded on the part of physicians. In this paper, an intelligent system has been developed for diagnosis of heart attack in the health sector. Dataset of heart attack obtained from UCI repository has been used. This dataset is made up of thirteen attributes which are very vital in diagnosis of heart disease. The system is developed on the multilayer perceptron trained with back propagation neural network then simulated with feed forward neural network and a recognition rate of 87% was obtained which is a good result for diagnosis of heart attack in medical field.

Keywords: heart attack, artificial neural network, diagnosis, intelligent system

Procedia PDF Downloads 655

Authors: İkbal Eski

Abstract:

This investigation is researched on design of robust neural network predictors for analyzing vibration effects on moving parts of a drilling machine. Moreover, the research is divided two parts; first part is experimental investigation, second part is simulation analysis with neural networks. Therefore, a real time the drilling machine is used to vibrations during working conditions. The measured real vibration parameters are analyzed with proposed neural network. As results: Simulation approaches show that Radial Basis Neural Network has good performance to adapt real time parameters of the drilling machine.

Keywords: artificial neural network, vibration analyses, drilling machine, robust

Procedia PDF Downloads 395

Authors: Safak Baykal

Abstract:

The purpose of this study is analyzing the relationship between self leadership and social capital of people with using Social Network Analysis. In this study, two aspects of social capital will be focused: bonding, homophilous social capital (BoSC) which implies better, strong, dense or closed network ties, and bridging, heterophilous social capital (BrSC) which implies weak ties, bridging the structural holes. The other concept of the study is Trust (Tr), namely interpersonal trust, willingness to ascribe good intentions to and have confidence in the words and actions of other people. In this study, the sample group, 61 people, was selected from a private firm from the defense industry. The relation between BoSC/BrSC and Tr is shown by using Social Network Analysis (SNA) and statistical analysis with Likert type-questionnaire. The results of the analysis show the Cronbach’s alpha value is 0.73 and social capital values (BoSC/BrSC) is highly correlated with Tr values of the people.

Keywords: bonding social capital, bridging social capital, trust, social network analysis (SNA)

Procedia PDF Downloads 529

Authors: Hyohun Kim, Dongwha Shin, Yeonseok Kim, Ji-Su Ahn, Kensuke Nakamura, Dongeun Choi, Byung-Woo Hong

Abstract:

Artefacts are commonly encountered in the imaging process of clinical computed tomography (CT) where the artefact refers to any systematic discrepancy between the reconstructed observation and the true attenuation coefficient of the object. It is known that CT images are inherently more prone to artefacts due to its image formation process where a large number of independent detectors are involved, and they are assumed to yield consistent measurements. There are a number of different artefact types including noise, beam hardening, scatter, pseudo-enhancement, motion, helical, ring, and metal artefacts, which cause serious difficulties in reading images. Thus, it is desired to remove nuisance factors from the degraded image leaving the fundamental intrinsic information that can provide better interpretation of the anatomical and pathological characteristics. However, it is considered as a difficult task due to the high dimensionality and variability of data to be recovered, which naturally motivates the use of machine learning techniques. We propose an image restoration algorithm based on the deep neural network framework where the denoising auto-encoders are stacked building multiple layers. The denoising auto-encoder is a variant of a classical auto-encoder that takes an input data and maps it to a hidden representation through a deterministic mapping using a non-linear activation function. The latent representation is then mapped back into a reconstruction the size of which is the same as the size of the input data. The reconstruction error can be measured by the traditional squared error assuming the residual follows a normal distribution. In addition to the designed loss function, an effective regularization scheme using residual-driven dropout determined based on the gradient at each layer. The optimal weights are computed by the classical stochastic gradient descent algorithm combined with the back-propagation algorithm. In our algorithm, we initially decompose an input image into its intrinsic representation and the nuisance factors including artefacts based on the classical Total Variation problem that can be efficiently optimized by the convex optimization algorithm such as primal-dual method. The intrinsic forms of the input images are provided to the deep denosing auto-encoders with their original forms in the training phase. In the testing phase, a given image is first decomposed into the intrinsic form and then provided to the trained network to obtain its reconstruction. We apply our algorithm to the restoration of the corrupted CT images by the artefacts. It is shown that our algorithm improves the readability and enhances the anatomical and pathological properties of the object. The quantitative evaluation is performed in terms of the PSNR, and the qualitative evaluation provides significant improvement in reading images despite degrading artefacts. The experimental results indicate the potential of our algorithm as a prior solution to the image interpretation tasks in a variety of medical imaging applications. This work was supported by the MISP(Ministry of Science and ICT), Korea, under the National Program for Excellence in SW (20170001000011001) supervised by the IITP(Institute for Information and Communications Technology Promotion).

Keywords: auto-encoder neural network, CT image artefact, deep learning, intrinsic image representation, noise reduction, total variation

Procedia PDF Downloads 190

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 45

Authors: Mary Anne Roa

Abstract:

Congestion in network occurs due to exceed in aggregate demand as compared to the accessible capacity of the resources. Network congestion will increase as network speed increases and new effective congestion control methods are needed, especially for today’s very high speed networks. To address this undeniably global issue, the study focuses on the development of a fuzzy-based congestion control model concerned with allocating the resources of a computer network such that the system can operate at an adequate performance level when the demand exceeds or is near the capacity of the resources. Fuzzy logic based models have proven capable of accurately representing a wide variety of processes. The model built is based on bandwidth, the aggregate incoming traffic and the waiting time. The theoretical analysis and simulation results show that the proposed algorithm provides not only good utilization but also low packet loss.

Keywords: congestion control, queue management, computer networks, fuzzy logic

Procedia PDF Downloads 399

Authors: Alexander Hempfing

Abstract:

The desire to understand business cycle fluctuations, trade interdependencies and co-movement has a long tradition in economic thinking. From input-output economics to business cycle theory, researchers aimed to find appropriate answers from an empirical as well as a theoretical perspective. This paper empirically analyses how the production structure of the global economy and several states developed over time, what their distributional properties are and if there are network specific metrics that allow identifying structurally important nodes, on a global, national and sectoral scale. For this, the World Input-Output Database was used, and different statistical methods were applied. Empirical evidence is provided that the importance of the Eastern hemisphere in the global production network has increased significantly between 2000 and 2014. Moreover, it was possible to show that the sectoral eigenvector centrality indices on a global level are power-law distributed, providing evidence that specific national sectors exist which are more critical to the world economy than others while serving as a hub within the global production network. However, further findings suggest, that global production cannot be characterized as a scale-free network.

Keywords: economic integration, industrial organization, input-output economics, network economics, production networks

Procedia PDF Downloads 278

Authors: M. R. Martinez-Torres, S. L. Toral, M. Olmedilla

Abstract:

Typically, virtual communities exhibit the well-known phenomenon of participation inequality, which means that only a small percentage of users is responsible of the majority of contributions. However, the sustainability of the community requires that the group of active users must be continuously nurtured with new users that gain expertise through a participation process. This paper analyzes the time evolution of Open Source Software (OSS) communities, considering users that join/abandon the community over time and several topological properties of the network when modeled as a social network. More specifically, the paper analyzes the role of those users rejoining the community and their influence in the global characteristics of the network.

Keywords: open source communities, social network Analysis, time series, virtual communities

Procedia PDF Downloads 525

Authors: Younghyun Jeon, Seungjoo Maeng

Abstract:

In the Ad-hoc network, the great interests regarding MIMO scheme leads to their combination, which is also utilized into its applicable network. We manage the field of the problem into Reverse-link MIMO Ad-hoc Network (RMAN) and propose the methodology to maximize the data rate with its power consumption using Node-Cooperative beamforming technique. Based on the result of mathematical optimization formulation, we design the algorithm to construct optimal orthogonal weight vector according to channel feedback and control its transmission power according to QoS-pricing value level. In simulation results, we show the validity of the proposed mathematical optimization result and algorithm which mean that the sum-rate of each link is converged into some point.

Keywords: ad-hoc network, MIMO, cooperative beamforming, transmit power

Procedia PDF Downloads 399

Authors: Sultan Noman Qasem

Abstract:

This paper presents an evolutionary algorithm for solving multi-objective optimization problems-based artificial neural network (ANN). The multi-objective evolutionary algorithm used in this study is genetic algorithm while ANN used is radial basis function network (RBFN). The proposed algorithm named memetic elitist Pareto non-dominated sorting genetic algorithm-based RBFNN (MEPGAN). The proposed algorithm is implemented on medical diseases problems. The experimental results indicate that the proposed algorithm is viable, and provides an effective means to design multi-objective RBFNs with good generalization capability and compact network structure. This study shows that MEPGAN generates RBFNs coming with an appropriate balance between accuracy and simplicity, comparing to the other algorithms found in literature.

Keywords: radial basis function network, hybrid learning, multi-objective optimization, genetic algorithm

Procedia PDF Downloads 564

Authors: Widyani Fatwa Dewi, Subroto Athor

Abstract:

In a telecommunication service provider, quantity and interval of customer demand often difficult to predict due to high dependency on customer expansion strategy and technological development. Demand arrives when a customer needs to add capacity to an existing site or build a network in a new site. Because demand is uncertain for each period, and sometimes there is a null demand for several equipments, it is categorized as intermittent. This research aims to improve demand forecast quality in Indonesia's telecommunication service providers by using Artificial Neural Network. In Artificial Neural Network, the pattern or relationship within data will be analyzed using the training process, followed by the learning process as validation stage. Historical demand data for 36 periods is used to support this research. It is found that demand forecast by using Artificial Neural Network outperforms the existing method if it is reviewed on two criteria: the forecast accuracy, using Mean Absolute Deviation (MAD), Mean of the sum of the Squares of the Forecasting Error (MSE), Mean Error (ME) and service level which is shown through inventory cost. This research is expected to increase the reference for a telecommunication demand forecast, which is currently still limited.

Keywords: artificial neural network, demand forecast, forecast accuracy, intermittent, service level, telecommunication

Procedia PDF Downloads 165

Authors: Donya Ashtiani Haghighi, Amirali Baniasadi

Abstract:

Coronavirus (COVID-19) disease has spread abruptly all over the world since the end of 2019. Computed tomography (CT) scans and X-ray images are used to detect this disease. Different Deep Neural Network (DNN)-based diagnosis solutions have been developed, mainly based on Convolutional Neural Networks (CNNs), to accelerate the identification of COVID-19 cases. However, CNNs lose important information in intermediate layers and require large datasets. In this paper, Capsule Network (CapsNet) is used. Capsule Network performs better than CNNs for small datasets. Accuracy of 0.9885, f1-score of 0.9883, precision of 0.9859, recall of 0.9908, and Area Under the Curve (AUC) of 0.9948 are achieved on the Capsule-based framework with hyperparameter tuning. Moreover, different dropout rates are investigated to decrease overfitting. Accordingly, a dropout rate of 0.1 shows the best results. Finally, we remove one convolution layer and decrease the number of trainable parameters to 146,752, which is a promising result.

Keywords: capsule network, dropout, hyperparameter tuning, classification

Procedia PDF Downloads 79