Search results for: structured P2P networks
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2249

Search results for: structured P2P networks

2189 Training Radial Basis Function Networks with Differential Evolution

Authors: Bing Yu , Xingshi He

Abstract:

In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.

Keywords: differential evolution, neural network, Rbf function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2050
2188 Neuro-Fuzzy Networks for Identification of Mathematical Model Parameters of Geofield

Authors: A. Pashayev, R. Sadiqov, C. Ardil, F. Ildiz , H. Karabork

Abstract:

The new technology of fuzzy neural networks for identification of parameters for mathematical models of geofields is proposed and checked. The effectiveness of that soft computing technology is demonstrated, especially in the early stage of modeling, when the information is uncertain and limited.

Keywords: Identification, interpolation methods, neuro-fuzzy networks, geofield.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1331
2187 Investigation on Bio-Inspired Population Based Metaheuristic Algorithms for Optimization Problems in Ad Hoc Networks

Authors: C. Rajan, K. Geetha, C. Rasi Priya, R. Sasikala

Abstract:

Nature is a great source of inspiration for solving complex problems in networks. It helps to find the optimal solution. Metaheuristic algorithm is one of the nature-inspired algorithm which helps in solving routing problem in networks. The dynamic features, changing of topology frequently and limited bandwidth make the routing, challenging in MANET. Implementation of appropriate routing algorithms leads to the efficient transmission of data in mobile ad hoc networks. The algorithms that are inspired by the principles of naturally-distributed/collective behavior of social colonies have shown excellence in dealing with complex optimization problems. Thus some of the bio-inspired metaheuristic algorithms help to increase the efficiency of routing in ad hoc networks. This survey work presents the overview of bio-inspired metaheuristic algorithms which support the efficiency of routing in mobile ad hoc networks.

Keywords: Ant colony optimization algorithm, Genetic algorithm, naturally inspired algorithms and particle swarm optimization algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3610
2186 A Novel Approach of Route Choice in Stochastic Time-varying Networks

Authors: Siliang Wang, Minghui Wang

Abstract:

Many exist studies always use Markov decision processes (MDPs) in modeling optimal route choice in stochastic, time-varying networks. However, taking many variable traffic data and transforming them into optimal route decision is a computational challenge by employing MDPs in real transportation networks. In this paper we model finite horizon MDPs using directed hypergraphs. It is shown that the problem of route choice in stochastic, time-varying networks can be formulated as a minimum cost hyperpath problem, and it also can be solved in linear time. We finally demonstrate the significant computational advantages of the introduced methods.

Keywords: Markov decision processes (MDPs), stochastictime-varying networks, hypergraphs, route choice.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1554
2185 Hybrid MAC Protocols Characteristics in Multi-hops Wireless Sensor Networks

Authors: M. Miladi, T. Ezzedine, R. Bouallegue

Abstract:

In the current decade, wireless sensor networks are emerging as a peculiar multi-disciplinary research area. By this way, energy efficiency is one of the fundamental research themes in the design of Medium Access Control (MAC) protocols for wireless sensor networks. Thus, in order to optimize the energy consumption in these networks, a variety of MAC protocols are available in the literature. These schemes were commonly evaluated under simple network density and a few results are published on their robustness in realistic network-s size. We, in this paper, provide an analytical study aiming to highlight the energy waste sources in wireless sensor networks. Then, we experiment three energy efficient hybrid CSMA/CA based MAC protocols optimized for wireless sensor networks: Sensor-MAC (SMAC), Time-out MAC (TMAC) and Traffic aware Energy Efficient MAC (TEEM). We investigate these protocols with different network densities in order to discuss the end-to-end performances of these schemes (i.e. in terms of energy efficiency, delay and throughput). Through Network Simulator (NS- 2) implementations, we explore the behaviors of these protocols with respect to the network density. In fact, this study may help the multihops sensor networks designers to design or select the MAC layer which matches better their applications aims.

Keywords: Energy efficiency, medium access control, network density, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1626
2184 A Combined Neural Network Approach to Soccer Player Prediction

Authors: Wenbin Zhang, Hantian Wu, Jian Tang

Abstract:

An artificial neural network is a mathematical model inspired by biological neural networks. There are several kinds of neural networks and they are widely used in many areas, such as: prediction, detection, and classification. Meanwhile, in day to day life, people always have to make many difficult decisions. For example, the coach of a soccer club has to decide which offensive player to be selected to play in a certain game. This work describes a novel Neural Network using a combination of the General Regression Neural Network and the Probabilistic Neural Networks to help a soccer coach make an informed decision.

Keywords: General Regression Neural Network, Probabilistic Neural Networks, Neural function.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3763
2183 Routing in Mobile Wireless Networks for Realtime Multimedia Applications- Reuse of Virtual Circuits

Authors: A.Khaja Kamaluddin, B.Muhammed Yousoof

Abstract:

Routing places an important role in determining the quality of service in wireless networks. The routing methods adopted in wireless networks have many drawbacks. This paper aims to review the current routing methods used in wireless networks. This paper proposes an innovative solution to overcome the problems in routing. This solution is aimed at improving the Quality of Service. This solution is different from others as it involves the resuage of the part of the virtual circuits. This improvement in quality of service is important especially in propagation of multimedia applications like video, animations etc. So it is the dire need to propose a new solution to improve the quality of service in ATM wireless networks for multimedia applications especially during this era of multimedia based applications.

Keywords: Packet buffering, Routing Table, Virtual Circuits (VC)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1641
2182 2D Structured Non-Cyclic Fuzzy Graphs

Authors: T. Pathinathan, M. Peter

Abstract:

Fuzzy graphs incorporate concepts from graph theory with fuzzy principles. In this paper, we make a study on the properties of fuzzy graphs which are non-cyclic and are of two-dimensional in structure. In particular, this paper presents 2D structure or the structure of double layer for a non-cyclic fuzzy graph whose underlying crisp graph is non-cyclic. In any graph structure, introducing 2D structure may lead to an inherent cycle. We propose relevant conditions for 2D structured non-cyclic fuzzy graphs. These conditions are extended even to fuzzy graphs of the 3D structure. General theoretical properties that are studied for any fuzzy graph are verified to 2D structured or double layered fuzzy graphs. Concepts like Order, Degree, Strong and Size for a fuzzy graph are studied for 2D structured or double layered non-cyclic fuzzy graphs. Using different types of fuzzy graphs, the proposed concepts relating to 2D structured fuzzy graphs are verified.

Keywords: Double layered fuzzy graph, double layered non-cyclic fuzzy graph, strong, order, degree and size.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 835
2181 A Novel QoS Optimization Architecture for 4G Networks

Authors: Aaqif Afzaal Abbasi, Javaid Iqbal, Akhtar Nawaz Malik

Abstract:

4G Communication Networks provide heterogeneous wireless technologies to mobile subscribers through IP based networks and users can avail high speed access while roaming across multiple wireless channels; possible by an organized way to manage the Quality of Service (QoS) functionalities in these networks. This paper proposes the idea of developing a novel QoS optimization architecture that will judge the user requirements and knowing peak times of services utilization can save the bandwidth/cost factors. The proposed architecture can be customized according to the network usage priorities so as to considerably improve a network-s QoS performance.

Keywords: QoS, Network Coverage Boundary, ServicesArchives Units (SAU), Cumulative Services Archives Units (CSAU).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2020
2180 Agent-based Framework for Energy Efficiency in Wireless Sensor Networks

Authors: Hongjoong Sin, Jangsoo Lee, Sungju Lee, Seunghwan Yoo, Sanghyuck Lee, Jaesik Lee, Yongjun Lee, Sungchun Kim

Abstract:

Wireless sensor networks are consisted of hundreds or thousands of small sensors that have limited resources. Energy-efficient techniques are the main issue of wireless sensor networks. This paper proposes an energy efficient agent-based framework in wireless sensor networks. We adopt biologically inspired approaches for wireless sensor networks. Agent operates automatically with their behavior policies as a gene. Agent aggregates other agents to reduce communication and gives high priority to nodes that have enough energy to communicate. Agent behavior policies are optimized by genetic operation at the base station. Simulation results show that our proposed framework increases the lifetime of each node. Each agent selects a next-hop node with neighbor information and behavior policies. Our proposed framework provides self-healing, self-configuration, self-optimization properties to sensor nodes.

Keywords: Agent, Energy Efficiency, Genetic algorithm, Wireless Sensor Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1662
2179 Coverage Strategies for Wireless Sensor Networks

Authors: Nor Azlina Ab. Aziz, Kamarulzaman Ab. Aziz, Wan Zakiah Wan Ismail

Abstract:

Coverage is one of the main research interests in wireless sensor networks (WSN), it is used to determine the quality of service (QoS) of the networks. Therefore this paper aims to review the common strategies use in solving coverage problem in WSN. The strategies studied are used during deployment phase where the coverage is calculated based on the placement of the sensors on the region of interest (ROI). The strategies reviewed are categorized into three groups based on the approaches used, namely; force based, grid based or computational geometry based approach.

Keywords: Computational geometry, coverage, Delaunay triangulation, force, grid, Voronoi diagram, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3347
2178 Towards Security in Virtualization of SDN

Authors: Wanqing You, Kai Qian, Xi He, Ying Qian

Abstract:

In this paper, the potential security issues brought by the virtualization of a Software Defined Networks (SDN) would be analyzed. The virtualization of SDN is achieved by FlowVisor (FV). With FV, a physical network is divided into multiple isolated logical networks while the underlying resources are still shared by different slices (isolated logical networks). However, along with the benefits brought by network virtualization, it also presents some issues regarding security. By examining security issues existing in an OpenFlow network, which uses FlowVisor to slice it into multiple virtual networks, we hope we can get some significant results and also can get furtherdiscussions among the security of SDN virtualization.

Keywords: FlowVisor, Network virtualization, Potential threats, Possible solutions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2162
2177 Security Threat and Countermeasure on 3G Network

Authors: Dongwan Kang, Joohyung Oh, Chaetae Im

Abstract:

Recent communications environment significantly expands the mobile environment. The popularization of smartphones with various mobile services has emerged, and smartphone users are rapidly increasing. Because of these symptoms, existing wired environment in a variety of mobile traffic entering to mobile network has threatened the stability of the mobile network. Unlike traditional wired infrastructure, mobile networks has limited radio resources and signaling procedures for complex radio resource management. So these traffic is not a problem in wired networks but mobile networks, it can be a threat. In this paper, we analyze the security threats in mobile networks and provide direction to solve it.

Keywords: 3G, Core Network Security, GTP, Mobile NetworkSecurity

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2138
2176 A Model-following Adaptive Controller for Linear/Nonlinear Plantsusing Radial Basis Function Neural Networks

Authors: Yuichi Masukake, Yoshihisa Ishida

Abstract:

In this paper, we proposed a method to design a model-following adaptive controller for linear/nonlinear plants. Radial basis function neural networks (RBF-NNs), which are known for their stable learning capability and fast training, are used to identify linear/nonlinear plants. Simulation results show that the proposed method is effective in controlling both linear and nonlinear plants with disturbance in the plant input.

Keywords: Linear/nonlinear plants, neural networks, radial basisfunction networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1481
2175 Application of Artificial Neural Networks for Temperature Forecasting

Authors: Mohsen Hayati, Zahra Mohebi

Abstract:

In this paper, the application of neural networks to study the design of short-term temperature forecasting (STTF) Systems for Kermanshah city, west of Iran was explored. One important architecture of neural networks named Multi-Layer Perceptron (MLP) to model STTF systems is used. Our study based on MLP was trained and tested using ten years (1996-2006) meteorological data. The results show that MLP network has the minimum forecasting error and can be considered as a good method to model the STTF systems.

Keywords: Artificial neural networks, Forecasting, Weather, Multi-layer perceptron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4356
2174 Exponential Stability Analysis for Switched Cellular Neural Networks with Time-varying Delays and Impulsive Effects

Authors: Zixin Liu, Fangwei Chen

Abstract:

In this Letter, a class of impulsive switched cellular neural networks with time-varying delays is investigated. At the same time, parametric uncertainties assumed to be norm bounded are considered. By dividing the network state variables into subgroups according to the characters of the neural networks, some sufficient conditions guaranteeing exponential stability for all admissible parametric uncertainties are derived via constructing appropriate Lyapunov functional. One numerical example is provided to illustrate the validity of the main results obtained in this paper.

Keywords: Switched systems, exponential stability, cellular neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1416
2173 Review of Trust Models in Wireless Sensor Networks

Authors: V. Uma Rani, K. Soma Sundaram

Abstract:

The major challenge faced by wireless sensor networks is security. Because of dynamic and collaborative nature of sensor networks the connected sensor devices makes the network unusable. To solve this issue, a trust model is required to find malicious, selfish and compromised insiders by evaluating trust worthiness sensors from the network. It supports the decision making processes in wireless sensor networks such as pre key-distribution, cluster head selection, data aggregation, routing and self reconfiguration of sensor nodes. This paper discussed the kinds of trust model, trust metrics used to address attacks by monitoring certain behavior of network. It describes the major design issues and their countermeasures of building trust model. It also discusses existing trust models used in various decision making process of wireless sensor networks.

Keywords: Attacks, Security, Trust, Trust model, Wireless sensor network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4566
2172 Energy-Aware Routing in Mobile Wireless Sensor Networks

Authors: R. Geetha, G. Umarani Srikanth, S. Prabhu

Abstract:

Wireless sensor networks are resource constrained networks, where energy is the major resource in such networks. Therefore, energy conservation is major aspect in the deployment of Wireless Sensor Network. This work makes use of an extended Greedy Perimeter Stateless Routing (eGPSR) protocol that mainly focuses on energy efficient data transmission. This data transmission is based on the fact that the message that is sent to a distant node consumes more energy than the message that is sent to a short range transmission. Every cluster contains a head set that consists of many virtual cluster heads. Routing is decided by head set members. The energy level of the received signal is the major constraint to choose head set from its members. The experimental result shows that the use of eGPSR in routing has improved throughput with comparatively less delay.

Keywords: eGPSR, energy efficiency, routing, wireless sensor networks, WSN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 925
2171 Cognitive Radio Networks (CRN): Resource Allocation Techniques Based On DNA-inspired Computing

Authors: Santosh Kumar Singh, Krishna Chandra Roy, Vibhakar Pathak

Abstract:

Spectrum is a scarce commodity, and considering the spectrum scarcity faced by the wireless-based service providers led to high congestion levels. Technical inefficiencies from pooled, since all networks share a common pool of channels, exhausting the available channels will force networks to block the services. Researchers found that cognitive radio (CR) technology may resolve the spectrum scarcity. A CR is a self-configuring entity in a wireless networking that senses its environment, tracks changes, and frequently exchanges information with their networks. However, CRN facing challenges and condition become worst while tracks changes i.e. reallocation of another under-utilized channels while primary network user arrives. In this paper, channels or resource reallocation technique based on DNA-inspired computing algorithm for CRN has been proposed.

Keywords: Ad hoc networks, channels reallocation, cognitive radio, DNA local sequence alignment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1786
2170 Capacity Optimization in Cooperative Cognitive Radio Networks

Authors: Mahdi Pirmoradian, Olayinka Adigun, Christos Politis

Abstract:

Cooperative spectrum sensing is a crucial challenge in cognitive radio networks. Cooperative sensing can increase the reliability of spectrum hole detection, optimize sensing time and reduce delay in cooperative networks. In this paper, an efficient central capacity optimization algorithm is proposed to minimize cooperative sensing time in a homogenous sensor network using OR decision rule subject to the detection and false alarm probabilities constraints. The evaluation results reveal significant improvement in the sensing time and normalized capacity of the cognitive sensors.

Keywords: Cooperative networks, normalized capacity, sensing time.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1879
2169 Improving Quality of Business Networks for Information Systems

Authors: Hazem M. El-Bakry, Ahmed Atwan

Abstract:

Computer networks are essential part in computerbased information systems. The performance of these networks has a great influence on the whole information system. Measuring the usability criteria and customers satisfaction on small computer network is very important. In this article, an effective approach for measuring the usability of business network in an information system is introduced. The usability process for networking provides us with a flexible and a cost-effective way to assess the usability of a network and its products. In addition, the proposed approach can be used to certify network product usability late in the development cycle. Furthermore, it can be used to help in developing usable interfaces very early in the cycle and to give a way to measure, track, and improve usability. Moreover, a new approach for fast information processing over computer networks is presented. The entire data are collected together in a long vector and then tested as a one input pattern. Proposed fast time delay neural networks (FTDNNs) use cross correlation in the frequency domain between the tested data and the input weights of neural networks. It is proved mathematically and practically that the number of computation steps required for the presented time delay neural networks is less than that needed by conventional time delay neural networks (CTDNNs). Simulation results using MATLAB confirm the theoretical computations.

Keywords: Usability Criteria, Computer Networks, Fast Information Processing, Cross Correlation, Frequency Domain.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2033
2168 Novel Approach for Promoting the Generalization Ability of Neural Networks

Authors: Naiqin Feng, Fang Wang, Yuhui Qiu

Abstract:

A new approach to promote the generalization ability of neural networks is presented. It is based on the point of view of fuzzy theory. This approach is implemented through shrinking or magnifying the input vector, thereby reducing the difference between training set and testing set. It is called “shrinking-magnifying approach" (SMA). At the same time, a new algorithm; α-algorithm is presented to find out the appropriate shrinking-magnifying-factor (SMF) α and obtain better generalization ability of neural networks. Quite a few simulation experiments serve to study the effect of SMA and α-algorithm. The experiment results are discussed in detail, and the function principle of SMA is analyzed in theory. The results of experiments and analyses show that the new approach is not only simpler and easier, but also is very effective to many neural networks and many classification problems. In our experiments, the proportions promoting the generalization ability of neural networks have even reached 90%.

Keywords: Fuzzy theory, generalization, misclassification rate, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1534
2167 Investigation of Some Technical Indexes inStock Forecasting Using Neural Networks

Authors: Myungsook Klassen

Abstract:

Training neural networks to capture an intrinsic property of a large volume of high dimensional data is a difficult task, as the training process is computationally expensive. Input attributes should be carefully selected to keep the dimensionality of input vectors relatively small. Technical indexes commonly used for stock market prediction using neural networks are investigated to determine its effectiveness as inputs. The feed forward neural network of Levenberg-Marquardt algorithm is applied to perform one step ahead forecasting of NASDAQ and Dow stock prices.

Keywords: Stock Market Prediction, Neural Networks, Levenberg-Marquadt Algorithm, Technical Indexes

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1946
2166 Dynamic Admission Control for Quality of Service in IP Networks

Authors: J. Kasigwa, V. Baryamureeba, D. Williams

Abstract:

The goal of admission control is to support the Quality of Service demands of real-time applications via resource reservation in IP networks. In this paper we introduce a novel Dynamic Admission Control (DAC) mechanism for IP networks. The DAC dynamically allocates network resources using the previous network pattern for each path and uses the dynamic admission algorithm to improve bandwidth utilization using bandwidth brokers. We evaluate the performance of the proposed mechanism through trace-driven simulation experiments in view point of blocking probability, throughput and normalized utilization.

Keywords: Bandwidth broker, dynamic admission control(DAC), IP networks, quality of service, real-time flows.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1292
2165 Cooperative Energy Efficient Routing for Wireless Sensor Networks in Smart Grid Communications

Authors: Ghazi AL-Sukkar, Iyad Jafar, Khalid Darabkh, Raed Al-Zubi, Mohammed Hawa

Abstract:

Smart Grids employ wireless sensor networks for their control and monitoring. Sensors are characterized by limitations in the processing power, energy supply and memory spaces, which require a particular attention on the design of routing and data management algorithms. Since most routing algorithms for sensor networks, focus on finding energy efficient paths to prolong the lifetime of sensor networks, the power of sensors on efficient paths depletes quickly, and consequently sensor networks become incapable of monitoring events from some parts of their target areas. In consequence, the design of routing protocols should consider not only energy efficiency paths, but also energy efficient algorithms in general. In this paper we propose an energy efficient routing protocol for wireless sensor networks without the support of any location information system. The reliability and the efficiency of this protocol have been demonstrated by simulation studies where we compare them to the legacy protocols. Our simulation results show that these algorithms scale well with network size and density.

Keywords: Data-centric storage, Dynamic Address Allocation, Sensor networks, Smart Grid Communications.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1852
2164 Modeling and Prediction of Zinc Extraction Efficiency from Concentrate by Operating Condition and Using Artificial Neural Networks

Authors: S. Mousavian, D. Ashouri, F. Mousavian, V. Nikkhah Rashidabad, N. Ghazinia

Abstract:

PH, temperature and time of extraction of each stage,  agitation speed and delay time between stages effect on efficiency of  zinc extraction from concentrate. In this research, efficiency of zinc  extraction was predicted as a function of mentioned variable by  artificial neural networks (ANN). ANN with different layer was  employed and the result show that the networks with 8 neurons in  hidden layer has good agreement with experimental data.

 

Keywords: Zinc extraction, Efficiency, Neural networks, Operating condition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1589
2163 Improvement of Ground Truth Data for Eye Location on Infrared Driver Recordings

Authors: Sorin Valcan, Mihail Găianu

Abstract:

Labeling is a very costly and time consuming process which aims to generate datasets for training neural networks in several functionalities and projects. For driver monitoring system projects, the need of labeled images has a significant impact on the budget and distribution of effort. This paper presents the modifications done to a ground truth data generation algorithm for 2D eyes location on infrared images with drivers in order to improve the quality of the data and performance of the trained neural networks. The algorithm restrictions become tougher which makes it more accurate but also less constant. The resulting dataset becomes smaller and shall not be altered by any kind of manual labels adjustment before being used in the neural networks training process. These changes resulted in a much better performance of the trained neural networks.

Keywords: Labeling automation, infrared camera, driver monitoring, eye detection, Convolutional Neural Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 420
2162 Prediction of Vapor Liquid Equilibrium for Dilute Solutions of Components in Ionic Liquid by Neural Networks

Authors: S. Mousavian, A. Abedianpour, A. Khanmohammadi, S. Hematian, Gh. Eidi Veisi

Abstract:

Ionic liquids are finding a wide range of applications from reaction media to separations and materials processing. In these applications, Vapor–Liquid equilibrium (VLE) is the most important one. VLE for six systems at 353 K and activity coefficients at infinite dilution [(γ)_i^∞] for various solutes (alkanes, alkenes, cycloalkanes, cycloalkenes, aromatics, alcohols, ketones, esters, ethers, and water) in the ionic liquids (1-ethyl-3-methylimidazolium bis (trifluoromethylsulfonyl)imide [EMIM][BTI], 1-hexyl-3-methyl imidazolium bis (trifluoromethylsulfonyl) imide [HMIM][BTI], 1-octyl-3-methylimidazolium bis(trifluoromethylsulfonyl) imide [OMIM][BTI], and 1-butyl-1-methylpyrrolidinium bis (trifluoromethylsulfonyl) imide [BMPYR][BTI]) have been used to train neural networks in the temperature range from (303 to 333) K. Densities of the ionic liquids, Hildebrant constant of substances, and temperature were selected as input of neural networks. The networks with different hidden layers were examined. Networks with seven neurons in one hidden layer have minimum error and good agreement with experimental data.

Keywords: Ionic liquid, Neural networks, VLE, Dilute solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1366
2161 3G WCDMA Mobile Network DoS Attack and Detection Technology

Authors: JooHyung Oh, Dongwan Kang, Sekwon Kim, ChaeTae Im

Abstract:

Currently, there has been a 3G mobile networks data traffic explosion due to the large increase in the number of smartphone users. Unlike a traditional wired infrastructure, 3G mobile networks have limited wireless resources and signaling procedures for complex wireless resource management. And mobile network security for various abnormal and malicious traffic technologies was not ready. So Malicious or potentially malicious traffic originating from mobile malware infected smart devices can cause serious problems to the 3G mobile networks, such as DoS and scanning attack in wired networks. This paper describes the DoS security threat in the 3G mobile network and proposes a detection technology.

Keywords: 3G, WCDMA, DoS, Security Threat

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3266
2160 Proximal Parallel Alternating Direction Method for Monotone Structured Variational Inequalities

Authors: Min Sun, Jing Liu

Abstract:

In this paper, we focus on the alternating direction method, which is one of the most effective methods for solving structured variational inequalities(VI). In fact, we propose a proximal parallel alternating direction method which only needs to solve two strongly monotone sub-VI problems at each iteration. Convergence of the new method is proved under mild assumptions. We also present some preliminary numerical results, which indicate that the new method is quite efficient.

Keywords: structured variational inequalities, proximal point method, global convergence

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1318