Search results for: Generative Adversarial Networks

Authors: Ahmad M. Shafiee, Mehrdad Montazeri, Mahdi Nikdast

Abstract:

Every day human life experiences new equipments more automatic and with more abilities. So the need for faster processors doesn-t seem to finish. Despite new architectures and higher frequencies, a single processor is not adequate for many applications. Parallel processing and networks are previous solutions for this problem. The new solution to put a network of resources on a chip is called NOC (network on a chip). The more usual topology for NOC is mesh topology. There are several routing algorithms suitable for this topology such as XY, fully adaptive, etc. In this paper we have suggested a new algorithm named Intermittent X, Y (IX/Y). We have developed the new algorithm in simulation environment to compare delay and power consumption with elders' algorithms.

Keywords: Computer architecture, parallel computing, NOC, routing algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1683

Authors: Prof. Chokri SLIM

Abstract:

A Novel fuzzy neural network combining with support vector learning mechanism called support-vector-based fuzzy neural networks (SVBFNN) is proposed. The SVBFNN combine the capability of minimizing the empirical risk (training error) and expected risk (testing error) of support vector learning in high dimensional data spaces and the efficient human-like reasoning of FNN.

Keywords: Neural network, fuzzy inference, machine learning, fuzzy modeling and rule extraction, support vector regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16691

Authors: Hazem M. El-Bakry, Ahmed A. Mohammed

Abstract:

In this paper, an intelligent algorithm for optimal document archiving is presented. It is kown that electronic archives are very important for information system management. Minimizing the size of the stored data in electronic archive is a main issue to reduce the physical storage area. Here, the effect of different types of Arabic fonts on electronic archives size is discussed. Simulation results show that PDF is the best file format for storage of the Arabic documents in electronic archive. Furthermore, fast information detection in a given PDF file is introduced. Such approach uses fast neural networks (FNNs) implemented in the frequency domain. The operation of these networks relies on performing cross correlation in the frequency domain rather than spatial one. It is proved mathematically and practically that the number of computation steps required for the presented FNNs is less than that needed by conventional neural networks (CNNs). Simulation results using MATLAB confirm the theoretical computations.

Keywords: Information Storage and Retrieval, Electronic Archiving, Fast Information Detection, Cross Correlation, Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1592

Authors: Hidehiko Okada

Abstract:

The author proposes an extension of genetic algorithm (GA) for solving fuzzy-valued optimization problems. In the proposed GA, values in the genotypes are not real numbers but fuzzy numbers. Evolutionary processes in GA are extended so that GA can handle genotype instances with fuzzy numbers. The proposed method is applied to evolving neural networks with fuzzy weights and biases. Experimental results showed that fuzzy neural networks evolved by the fuzzy GA could model hidden target fuzzy functions well despite the fact that no training data was explicitly provided.

Keywords: Evolutionary algorithm, genetic algorithm, fuzzy number, neural network, neuroevolution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2313

Authors: Tadatsugu Kitamoto

Abstract:

Recently, a quality of motors is inspected by human ears. In this paper, I propose two systems using a method of speech recognition for automation of the inspection. The first system is based on a method of linear processing which uses K-means and Nearest Neighbor method, and the second is based on a method of non-linear processing which uses neural networks. I used motor sounds in these systems, and I successfully recognize 86.67% of motor sounds in the linear processing system and 97.78% in the non-linear processing system.

Keywords: Acoustical diagnosis, Neural networks, K-means, Short-time Fourier transformation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1704

Authors: Julien Romieux, Fabio Verdicchio

Abstract:

Wireless Sensor Networks (WSNs), which sense environmental data with battery-powered nodes, require multi-hop communication. This power-demanding task adds an extra workload that is unfairly distributed across the network. As a result, nodes run out of battery at different times: this requires an impractical individual node maintenance scheme. Therefore we investigate a new Cooperative Sensing approach that extends the WSN operational life and allows a more practical network maintenance scheme (where all nodes deplete their batteries almost at the same time). We propose a novel cooperative algorithm that derives a piecewise representation of the sensed signal while controlling approximation accuracy. Simulations show that our algorithm increases WSN operational life and spreads communication workload evenly. Results convey a counterintuitive conclusion: distributing workload fairly amongst nodes may not decrease the network power consumption and yet extend the WSN operational life. This is achieved as our cooperative approach decreases the workload of the most burdened cluster in the network.

Keywords: Cooperative signal processing, power management, signal representation, signal approximation, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1788

Authors: Umair Shafique, Hafiz Usman Zia, Fiaz Majeed, Samina Naz, Javeria Ahmed, Maleeha Zainab

Abstract:

The Internet of Things (IoT) has become a hot topic for the last couple of years. This innovative technology has shown promising progress in various areas and the world has witnessed exponential growth in multiple application domains. Researchers are working to investigate its aptitudes to get the best from it by harnessing its true potential. But at the same time, IoT networks open up a new aspect of vulnerability and physical threats to data integrity, privacy, and confidentiality. It is due to centralized control, data silos approach for handling information, and a lack of standardization in the IoT networks. As we know, blockchain is a new technology that involves creating secure distributed ledgers to store and communicate data. Some of the benefits include resiliency, integrity, anonymity, decentralization, and autonomous control. The potential for blockchain technology to provide the key to managing and controlling IoT has created a new wave of excitement around the idea of putting that data back into the hands of the end-users. In this manuscript, we have proposed a model that combines blockchain and IoT networks to address potential security and privacy issues in the healthcare domain and how various stakeholders will interact with the system.

Keywords: Internet of Things, IoT, blockchain, data integrity, authentication, data privacy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 425

Authors: Farshad Zeinali, Sajedeh Norouzi, Nader Mokari, Eduard A. Jorswieck

Abstract:

The capacity of fifth-generation (5G)vehicle-to-everything (V2X) networks poses significant challenges.To address this challenge, this paper utilizes New Radio (NR) and New Radio Unlicensed (NR-U) networks to develop a vehicular heterogeneous network (HetNet). We propose a framework, named joint BS assignment and resource allocation (JBSRA) for mobile V2X users and also consider coexistence schemes based on flexible duty cycle (DC) mechanism for unlicensed bands. Our objective is to maximize the average throughput of vehicles, while guarantying the WiFi users throughput. In simulations based on deep reinforcement learning (DRL) algorithms such as deep deterministic policy gradient (DDPG) and deep Q network (DQN), our proposed framework outperforms existing solutions that rely on fixed DC or schemes without consideration of unlicensed bands.

Keywords: Vehicle-to-everything, resource allocation, BS assignment, new radio, new radio unlicensed, coexistence NR-U and WiFi, deep deterministic policy gradient, Deep Q-network, Duty cycle mechanism.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 340

Authors: Akram M. Othman, May H. Riadh

Abstract:

This research work is aimed at speech recognition using scaly neural networks. A small vocabulary of 11 words were established first, these words are “word, file, open, print, exit, edit, cut, copy, paste, doc1, doc2". These chosen words involved with executing some computer functions such as opening a file, print certain text document, cutting, copying, pasting, editing and exit. It introduced to the computer then subjected to feature extraction process using LPC (linear prediction coefficients). These features are used as input to an artificial neural network in speaker dependent mode. Half of the words are used for training the artificial neural network and the other half are used for testing the system; those are used for information retrieval. The system components are consist of three parts, speech processing and feature extraction, training and testing by using neural networks and information retrieval. The retrieve process proved to be 79.5-88% successful, which is quite acceptable, considering the variation to surrounding, state of the person, and the microphone type.

Keywords: Feature extraction, Liner prediction coefficients, neural network, Speech Recognition, Scaly ANN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1741

Authors: F. Smach, M. Atri, J. Mitéran, M. Abid

Abstract:

Face detection and recognition has many applications in a variety of fields such as security system, videoconferencing and identification. Face classification is currently implemented in software. A hardware implementation allows real-time processing, but has higher cost and time to-market. The objective of this work is to implement a classifier based on neural networks MLP (Multi-layer Perceptron) for face detection. The MLP is used to classify face and non-face patterns. The systm is described using C language on a P4 (2.4 Ghz) to extract weight values. Then a Hardware implementation is achieved using VHDL based Methodology. We target Xilinx FPGA as the implementation support.

Keywords: Classification, Face Detection, FPGA Hardware description, MLP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2286

Authors: Amin Sedighfar, M. R. Moniri

Abstract:

Determination of state of charge (SOC) in today’s world becomes an increasingly important issue in all the applications that include a battery. In fact, estimation of the SOC is a fundamental need for the battery, which is the most important energy storage in Hybrid Electric Vehicles (HEVs), smart grid systems, drones, UPS and so on. Regarding those applications, the SOC estimation algorithm is expected to be precise and easy to implement. This paper presents an online method for the estimation of the SOC of Valve-Regulated Lead Acid (VRLA) batteries. The proposed method uses the well-known Kalman Filter (KF), and Neural Networks (NNs) and all of the simulations have been done with MATLAB software. The NN is trained offline using the data collected from the battery discharging process. A generic cell model is used, and the underlying dynamic behavior of the model has used two capacitors (bulk and surface) and three resistors (terminal, surface, and end), where the SOC determined from the voltage represents the bulk capacitor. The aim of this work is to compare the performance of conventional integration-based SOC estimation methods with a mixed algorithm. Moreover, by containing the effect of temperature, the final result becomes more accurate. 

Keywords: Kalman filter, neural networks, state-of-charge, VRLA battery.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1409

Authors: Y. Harold Robinson, M. Rajaram, E. Golden Julie, S. Balaji

Abstract:

A mobile ad hoc network (MANET) is a wireless communication network where nodes that are not within direct transmission range establish their communication via the help of other nodes to forward data. Routing protocols in MANETs are usually categorized as proactive. Tree Based Opportunistic Routing (TBOR) finds a multipath link based on maximum probability of the throughput. The simulation results show that the presented method is performed very well compared to the existing methods in terms of throughput, delay and routing overhead.

Keywords: Mobile ad hoc networks, opportunistic data forwarding, proactive Source routing, BFS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1229

Authors: Eun-Jun Yoon, Kee-Young Yoo

Abstract:

In order to guarantee secure communication for wireless sensor networks (WSNs), many user authentication schemes have successfully drawn researchers- attention and been studied widely. In 2012, He et al. proposed a robust biometric-based user authentication scheme for WSNs. However, this paper demonstrates that He et al.-s scheme has some drawbacks: poor reparability problem, user impersonation attack, and sensor node impersonate attack.

Keywords: Security, authentication, biometrics, poor reparability, impersonation attack, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1874

Authors: Stefan Rass

Abstract:

Quantum cryptography offers a way of key agreement, which is unbreakable by any external adversary. Authentication is of crucial importance, as perfect secrecy is worthless if the identity of the addressee cannot be ensured before sending important information. Message authentication has been studied thoroughly, but no approach seems to be able to explicitly counter meet-in-the-middle impersonation attacks. The goal of this paper is the development of an authentication scheme being resistant against active adversaries controlling the communication channel. The scheme is built on top of a key-establishment protocol and is unconditionally secure if built upon quantum cryptographic key exchange. In general, the security is the same as for the key-agreement protocol lying underneath.

Keywords: Meet-in-the-middle attack, quantum key distribution, quantum networks, unconditionally secure authentication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1913

Authors: Mahanijah Md Kamal., Dingli Yu

Abstract:

This paper presents a new method of fault detection and isolation (FDI) for polymer electrolyte membrane (PEM) fuel cell (FC) dynamic systems under an open-loop scheme. This method uses a radial basis function (RBF) neural network to perform fault identification, classification and isolation. The novelty is that the RBF model of independent mode is used to predict the future outputs of the FC stack. One actuator fault, one component fault and three sensor faults have been introduced to the PEMFC systems experience faults between -7% to +10% of fault size in real-time operation. To validate the results, a benchmark model developed by Michigan University is used in the simulation to investigate the effect of these five faults. The developed independent RBF model is tested on MATLAB R2009a/Simulink environment. The simulation results confirm the effectiveness of the proposed method for FDI under an open-loop condition. By using this method, the RBF networks able to detect and isolate all five faults accordingly and accurately.

Keywords: Polymer electrolyte membrane fuel cell, radial basis function neural networks, fault detection, fault isolation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1820

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Electricity prices have sophisticated features such as high volatility, nonlinearity and high frequency that make forecasting quite difficult. Electricity price has a volatile and non-random character so that, it is possible to identify the patterns based on the historical data. Intelligent decision-making requires accurate price forecasting for market traders, retailers, and generation companies. So far, many shallow-ANN (artificial neural networks) models have been published in the literature and showed adequate forecasting results. During the last years, neural networks with many hidden layers, which are referred to as DNN (deep neural networks) have been using in the machine learning community. The goal of this study is to investigate electricity price forecasting performance of the shallow-ANN and DNN models for the Turkish day-ahead electricity market. The forecasting accuracy of the models has been evaluated with publicly available data from the Turkish day-ahead electricity market. Both shallow-ANN and DNN approach would give successful result in forecasting problems. Historical load, price and weather temperature data are used as the input variables for the models. The data set includes power consumption measurements gathered between January 2016 and December 2017 with one-hour resolution. In this regard, forecasting studies have been carried out comparatively with shallow-ANN and DNN models for Turkish electricity markets in the related time period. The main contribution of this study is the investigation of different shallow-ANN and DNN models in the field of electricity price forecast. All models are compared regarding their MAE (Mean Absolute Error) and MSE (Mean Square) results. DNN models give better forecasting performance compare to shallow-ANN. Best five MAE results for DNN models are 0.346, 0.372, 0.392, 0,402 and 0.409.

Keywords: Deep learning, artificial neural networks, energy price forecasting, Turkey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1105

Authors: Kemal Bicakci, Yusuf Uzunay

Abstract:

It is well-known that in wireless local area networks, authenticating nodes by their MAC addresses is not secure since it is very easy for an attacker to learn one of the authorized addresses and change his MAC address accordingly. In this paper, in order to prevent MAC address spoofing attacks, we propose to use dynamically changing MAC addresses and make each address usable for only one session. The scheme we propose does not require any change in 802.11 protocols and incurs only a small performance overhead. One of the nice features of our new scheme is that no third party can link different communication sessions of the same user by monitoring MAC addresses therefore our scheme is preferable also with respect to user privacy.

Keywords: Authentication, MAC address spoofing, security, wireless networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2585

Authors: Mojca Ciglaric, Andrej Krevl, Matjaž Pancur, Tone Vidmar

Abstract:

P2P Networks are highly dynamic structures since their nodes – peer users keep joining and leaving continuously. In the paper, we study the effects of network change rates on query routing efficiency. First we describe some background and an abstract system model. The chosen routing technique makes use of cached metadata from previous answer messages and also employs a mechanism for broken path detection and metadata maintenance. Several metrics are used to show that the protocol behaves quite well even with high rate of node departures, but above a certain threshold it literally breaks down and exhibits considerable efficiency degradation.

Keywords: Network dynamics, overlay network, P2P system, routing efficiency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1367

Authors: Sami Baraketi, Jean-Marie Garcia, Olivier Brun

Abstract:

Wavelength Division Multiplexing (WDM) is the dominant transport technology used in numerous high capacity backbone networks, based on optical infrastructures. Given the importance of costs (CapEx and OpEx) associated to these networks, resource management is becoming increasingly important, especially how the optical circuits, called “lightpaths”, are routed throughout the network. This requires the use of efficient algorithms which provide routing strategies with the lowest cost. We focus on the lightpath routing and wavelength assignment problem, known as the RWA problem, while optimizing wavelength fragmentation over the network. Wavelength fragmentation poses a serious challenge for network operators since it leads to the misuse of the wavelength spectrum, and then to the refusal of new lightpath requests. In this paper, we first establish a new Integer Linear Program (ILP) for the problem based on a node-link formulation. This formulation is based on a multilayer approach where the original network is decomposed into several network layers, each corresponding to a wavelength. Furthermore, we propose an efficient heuristic for the problem based on a greedy algorithm followed by a post-treatment procedure. The obtained results show that the optimal solution is often reached. We also compare our results with those of other RWA heuristic methods

Keywords: WDM, lightpath, RWA, wavelength fragmentation, optimization, linear programming, heuristic

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1873

Authors: Viktor R. Stoynov, Zlatka V. Valkova-Jarvis

Abstract:

The intelligent management and optimisation of radio resource technologies will lead to a considerable improvement in the overall performance in Next Generation Networks (NGNs). Carrier Aggregation (CA) technology, also known as Spectrum Aggregation, enables more efficient use of the available spectrum by combining multiple Component Carriers (CCs) in a virtual wideband channel. LTE-A (Long Term Evolution–Advanced) CA technology can combine multiple adjacent or separate CCs in the same band or in different bands. In this way, increased data rates and dynamic load balancing can be achieved, resulting in a more reliable and efficient operation of mobile networks and the enabling of high bandwidth mobile services. In this paper, several distinct CA deployment strategies for the utilisation of spectrum bands are compared in indoor-outdoor scenarios, simulated via the recently-developed Realistic Indoor Environment Generator (RIEG). We analyse the performance of the User Equipment (UE) by integrating the average throughput, the level of fairness of radio resource allocation, and other parameters, into one summative assessment termed a Comparative Factor (CF). In addition, comparison of non-CA and CA indoor mobile networks is carried out under different load conditions: varying numbers and positions of UEs. The experimental results demonstrate that the CA technology can improve network performance, especially in the case of indoor scenarios. Additionally, we show that an increase of carrier frequency does not necessarily lead to improved CF values, due to high wall-penetration losses. The performance of users under bad-channel conditions, often located in the periphery of the cells, can be improved by intelligent CA location. Furthermore, a combination of such a deployment and effective radio resource allocation management with respect to user-fairness plays a crucial role in improving the performance of LTE-A networks.

Keywords: Comparative factor, carrier aggregation, indoor mobile network, resource allocation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 719

Authors: A. Safari, R. Jahani, H. A. Shayanfar, J. Olamaei

Abstract:

This paper shows the results obtained in the analysis of the impact of distributed generation (DG) on distribution losses and presents a new algorithm to the optimal allocation of distributed generation resources in distribution networks. The optimization is based on a Hybrid Genetic Algorithm and Particle Swarm Optimization (HGAPSO) aiming to optimal DG allocation in distribution network. Through this algorithm a significant improvement in the optimization goal is achieved. With a numerical example the superiority of the proposed algorithm is demonstrated in comparison with the simple genetic algorithm.

Keywords: Distributed Generation, Distribution Networks, Genetic Algorithm, Particle Swarm Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2710

Authors: Qingqing Wang, Shouming Zhong

Abstract:

This paper is concerned with the stability problem with two additive time-varying delay components. By choosing one augmented Lyapunov-Krasovskii functional, using some new zero equalities, and combining linear matrix inequalities (LMI) techniques, two new sufficient criteria ensuring the global stability asymptotic stability of DNNs is obtained. These stability criteria are present in terms of linear matrix inequalities and can be easily checked. Finally, some examples are showed to demonstrate the effectiveness and less conservatism of the proposed method.

Keywords: Neural networks, Globally asymptotic stability, LMI approach, Additive time-varying delays.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1573

Authors: Mario Gonzalez, David Dominguez, Francisco B. Rodriguez

Abstract:

The model of neural networks on the small-world topology, with metric (local and random connectivity) is investigated. The synaptic weights are random, driving the network towards a chaotic state for the neural activity. An ordered macroscopic neuron state is induced by a bias in the network connections. When the connections are mainly local, the network emulates a block-like structure. It is found that the topology and the bias compete to influence the network to evolve into a global or a block activity ordering, according to the initial conditions.

Keywords: Block attractor, random interaction, small world, spin glass.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1342

Authors: S. M. Kamruzzaman, Md. Monirul Islam

Abstract:

Although backpropagation ANNs generally predict better than decision trees do for pattern classification problems, they are often regarded as black boxes, i.e., their predictions cannot be explained as those of decision trees. In many applications, it is desirable to extract knowledge from trained ANNs for the users to gain a better understanding of how the networks solve the problems. A new rule extraction algorithm, called rule extraction from artificial neural networks (REANN) is proposed and implemented to extract symbolic rules from ANNs. A standard three-layer feedforward ANN is the basis of the algorithm. A four-phase training algorithm is proposed for backpropagation learning. Explicitness of the extracted rules is supported by comparing them to the symbolic rules generated by other methods. Extracted rules are comparable with other methods in terms of number of rules, average number of conditions for a rule, and predictive accuracy. Extensive experimental studies on several benchmarks classification problems, such as breast cancer, iris, diabetes, and season classification problems, demonstrate the effectiveness of the proposed approach with good generalization ability.

Keywords: Backpropagation, clustering algorithm, constructivealgorithm, continuous activation function, pruning algorithm, ruleextraction algorithm, symbolic rules.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1621

Authors: Gergely Treplan, Long Tran-Thanh, Janos Levendovszky

Abstract:

In this paper, a reliable cooperative multipath routing algorithm is proposed for data forwarding in wireless sensor networks (WSNs). In this algorithm, data packets are forwarded towards the base station (BS) through a number of paths, using a set of relay nodes. In addition, the Rayleigh fading model is used to calculate the evaluation metric of links. Here, the quality of reliability is guaranteed by selecting optimal relay set with which the probability of correct packet reception at the BS will exceed a predefined threshold. Therefore, the proposed scheme ensures reliable packet transmission to the BS. Furthermore, in the proposed algorithm, energy efficiency is achieved by energy balancing (i.e. minimizing the energy consumption of the bottleneck node of the routing path) at the same time. This work also demonstrates that the proposed algorithm outperforms existing algorithms in extending longevity of the network, with respect to the quality of reliability. Given this, the obtained results make possible reliable path selection with minimum energy consumption in real time.

Keywords: wireless sensor networks, reliability, cooperativerouting, Rayleigh fading model, energy balancing

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1615

Authors: Wei Zhang

Abstract:

With the rapid development of deep learning, neural network and deep learning algorithms play a significant role in various practical applications. Due to the high accuracy and good performance, Convolutional Neural Networks (CNNs) especially have become a research hot spot in the past few years. However, the size of the networks becomes increasingly large scale due to the demands of the practical applications, which poses a significant challenge to construct a high-performance implementation of deep learning neural networks. Meanwhile, many of these application scenarios also have strict requirements on the performance and low-power consumption of hardware devices. Therefore, it is particularly critical to choose a moderate computing platform for hardware acceleration of CNNs. This article aimed to survey the recent advance in Field Programmable Gate Array (FPGA)-based acceleration of CNNs. Various designs and implementations of the accelerator based on FPGA under different devices and network models are overviewed, and the versions of Graphic Processing Units (GPUs), Application Specific Integrated Circuits (ASICs) and Digital Signal Processors (DSPs) are compared to present our own critical analysis and comments. Finally, we give a discussion on different perspectives of these acceleration and optimization methods on FPGA platforms to further explore the opportunities and challenges for future research. More helpfully, we give a prospect for future development of the FPGA-based accelerator.

Keywords: Deep learning, field programmable gate array, FPGA, hardware acceleration, convolutional neural networks, CNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 913

Authors: M. R. Mustafa, M. H. Isa, R. B. Rezaur

Abstract:

The use of artificial neural network (ANN) modeling for prediction and forecasting variables in water resources engineering are being increasing rapidly. Infrastructural applications of ANN in terms of selection of inputs, architecture of networks, training algorithms, and selection of training parameters in different types of neural networks used in water resources engineering have been reported. ANN modeling conducted for water resources engineering variables (river sediment and discharge) published in high impact journals since 2002 to 2011 have been examined and presented in this review. ANN is a vigorous technique to develop immense relationship between the input and output variables, and able to extract complex behavior between the water resources variables such as river sediment and discharge. It can produce robust prediction results for many of the water resources engineering problems by appropriate learning from a set of examples. It is important to have a good understanding of the input and output variables from a statistical analysis of the data before network modeling, which can facilitate to design an efficient network. An appropriate training based ANN model is able to adopt the physical understanding between the variables and may generate more effective results than conventional prediction techniques.

Keywords: ANN, discharge, modeling, prediction, sediment,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5696

Authors: Yi Yu, Vu Xuan Nguyen, Gaoxi Xiao

Abstract:

Opinion formation in complex social networks may exhibit complex system dynamics even when based on some simplest system evolution models. An interesting and important issue is the effects of the initial state on the final steady-state opinion distribution. By carrying out extensive simulations and providing necessary discussions, we show that, while different initial opinion distributions certainly make differences to opinion evolution in social systems without noises, in systems with noises, given enough time, different initial states basically do not contribute to making any significant differences in the final steady state. Instead, it is the basal distribution of the preferred opinions that contributes to deciding the final state of the systems. We briefly explain the reasons leading to the observed conclusions. Such an observation contradicts with a long-term belief on the roles of system initial state in opinion formation, demonstrating the dominating role that opinion mutation can play in opinion formation given enough time. The observation may help to better understand certain observations of opinion evolution dynamics in real-life social networks.

Keywords: Opinion formation, Deffuant model, opinion mutation, consensus making.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 680

Authors: P.S.Prakash, S.Selvan

Abstract:

Over the past several years, there has been a considerable amount of research within the field of Quality of Service (QoS) support for distributed multimedia systems. One of the key issues in providing end-to-end QoS guarantees in packet networks is determining a feasible path that satisfies a number of QoS constraints. The problem of finding a feasible path is NPComplete if number of constraints is more than two and cannot be exactly solved in polynomial time. We proposed Feasible Path Selection Algorithm (FPSA) that addresses issues with pertain to finding a feasible path subject to delay and cost constraints and it offers higher success rate in finding feasible paths.

Keywords: feasible path, multiple constraints, path selection, QoS routing

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1758

Authors: Taiwo. M. Akinmuyisitan, John Cosmas

Abstract:

This paper practically demonstrates the theories and concepts of an Advanced Convolutional Neural Network in the design and development of a scalable artificial intelligence model for the detection of criminal masterminds. The technique uses machine vision algorithms to compute the facial characteristics of suspects and classify actors as criminal or non-criminal faces. The paper proceeds further to compare the results of the error accuracy of two popular custom convolutional pre-trained networks, VGG16 and Resnet50. The result shows that VGG16 is probably more efficient than ResNet50 for the dataset we used.

Keywords: Artificial intelligence, convolutional neural networks, Resnet50, VGG16.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 321