Search results for: network pattern models.

Authors: Gunasekaran Raja, Ramkumar Jayaraman, Rajakumar Arul, Kottilingam Kottursamy

Abstract:

Broadband Wireless Network (BWN) is the promising technology nowadays due to the increased number of smartphones. Buffering scheme using network coding considers the reliability and proper degree distribution in Worldwide interoperability for Microwave Access (WiMAX) multi-hop network. Using network coding, a secure way of transmission is performed which helps in improving throughput and reduces the packet loss in the multicast network. At the outset, improved network coding is proposed in multicast wireless mesh network. Considering the problem of performance overhead, degree distribution makes a decision while performing buffer in the encoding / decoding process. Consequently, BuS (Buffer Scheme) based on network coding is proposed in the multi-hop network. Here the encoding process introduces buffer for temporary storage to transmit packets with proper degree distribution. The simulation results depend on the number of packets received in the encoding/decoding with proper degree distribution using buffering scheme.

Keywords: Encoding and decoding, buffer, network coding, degree distribution, broadband wireless networks, multicast.

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

Authors: Luciano Nieddu, Giuseppe Manfredi, Salvatore D'Acunto, Katia La Regina

Abstract:

In this paper a non-parametric statistical pattern recognition algorithm for the problem of credit scoring will be presented. The proposed algorithm is based on a clustering k- means algorithm and allows for the determination of subclasses of homogenous elements in the data. The algorithm will be tested on two benchmark datasets and its performance compared with other well known pattern recognition algorithm for credit scoring.

Keywords: Constrained clustering, Credit scoring, Statistical pattern recognition, Supervised classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2051

Authors: Vidhu Mitha Goutham, Ruma Mukherjee

Abstract:

The low availability of well-trained, unlimited, dynamic-access models for specific languages makes it hard for corporate users to adopt quick translation techniques and incorporate them into product solutions. As translation tasks increasingly require a dynamic sequence learning curve; stable, cost-free opensource models are scarce. We survey and compare current translation techniques and propose a modified sequence to sequence model repurposed with attention techniques. Sequence learning using an encoder-decoder model is now paving the path for higher precision levels in translation. Using a Convolutional Neural Network (CNN) encoder and a Recurrent Neural Network (RNN) decoder background, we use Fairseq tools to produce an end-to-end bilingually trained Spanish-English machine translation model including source language detection. We acquire competitive results using a duo-lingo-corpus trained model to provide for prospective, ready-made plug-in use for compound sentences and document translations. Our model serves a decent system for large, organizational data translation needs. While acknowledging its shortcomings and future scope, it also identifies itself as a well-optimized deep neural network model and solution.

Keywords: Attention, encoder-decoder, Fairseq, Seq2Seq, Spanish, translation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 477

Authors: M. Padmavathi, R. M. Suresh

Abstract:

Every machine plays roles of client and server simultaneously in a peer-to-peer (P2P) network. Though a P2P network has many advantages over traditional client-server models regarding efficiency and fault-tolerance, it also faces additional security threats. Users/IT administrators should be aware of risks from malicious code propagation, downloaded content legality, and P2P software’s vulnerabilities. Security and preventative measures are a must to protect networks from potential sensitive information leakage and security breaches. Bit Torrent is a popular and scalable P2P file distribution mechanism which successfully distributes large files quickly and efficiently without problems for origin server. Bit Torrent achieved excellent upload utilization according to measurement studies, but it also raised many questions as regards utilization in settings, than those measuring, fairness, and Bit Torrent’s mechanisms choice. This work proposed a block selection technique using Fuzzy ACO with optimal rules selected using ACO.

Keywords: Ant Colony Optimization (ACO), Bit Torrent, Download time, Peer-to-Peer (P2P) network, Performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2590

Authors: Keny Ordaz-Hernandez, Xavier Fischer, Fouad Bennis

Abstract:

In a particular case of behavioural model reduction by ANNs, a validity domain shortening has been found. In mechanics, as in other domains, the notion of validity domain allows the engineer to choose a valid model for a particular analysis or simulation. In the study of mechanical behaviour for a cantilever beam (using linear and non-linear models), Multi-Layer Perceptron (MLP) Backpropagation (BP) networks have been applied as model reduction technique. This reduced model is constructed to be more efficient than the non-reduced model. Within a less extended domain, the ANN reduced model estimates correctly the non-linear response, with a lower computational cost. It has been found that the neural network model is not able to approximate the linear behaviour while it does approximate the non-linear behaviour very well. The details of the case are provided with an example of the cantilever beam behaviour modelling.

Keywords: artificial neural network, validity domain, cantileverbeam, non-linear behaviour, model reduction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1429

Authors: Penghui Zhang, Hua Zhang, Jun-Bo Wang, Cheng Zeng, Zijian Cao

Abstract:

With the development of software-defined networks and programmable data planes, in-band network telemetry (INT) has become an emerging technology in communications because it can get accurate and real-time network information. However, due to the expansion of the network scale, existing telemetry systems, to the best of the authors’ knowledge, have difficulty in meeting the common requirements of low overhead, low latency and full coverage for traffic measurement. This paper proposes a network-wide telemetry system with a low-latency low-overhead path planning (INT-LLPP). This paper builds a mathematical model to analyze the telemetry overhead and latency of INT systems. Then, we adopt a greedy-based path planning algorithm to reduce the overhead and latency of the network telemetry with the full network coverage. The simulation results show that network-wide telemetry is achieved and the telemetry overhead can be reduced significantly compared with existing INT systems. INT-LLPP can control the system latency to get real-time network information.

Keywords: Network telemetry, network monitoring, path planning, low latency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 259

Authors: K. K. Aggarwal, Yogesh Singh, Arvinder Kaur, Ruchika Malhotra

Abstract:

Importance of software quality is increasing leading to development of new sophisticated techniques, which can be used in constructing models for predicting quality attributes. One such technique is Artificial Neural Network (ANN). This paper examined the application of ANN for software quality prediction using Object- Oriented (OO) metrics. Quality estimation includes estimating maintainability of software. The dependent variable in our study was maintenance effort. The independent variables were principal components of eight OO metrics. The results showed that the Mean Absolute Relative Error (MARE) was 0.265 of ANN model. Thus we found that ANN method was useful in constructing software quality model.

Keywords: Software quality, Measurement, Metrics, Artificial neural network, Coupling, Cohesion, Inheritance, Principal component analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2575

Authors: Do-Woo Kim, Geon Woo Kim, Jun-Ho Lee, Jong-Wook Han

Abstract:

The home in these days has not one computer connected to the Internet but rather a network of many devices within the home, and that network might be connected to the Internet. In such an environment, the potential for attacks is greatly increased. The general security technology can not apply because of the use of various wired and wireless network, middleware and protocol in digital home environment and a restricted system resource of home information appliances. To offer secure home services home network environments have need of access control for various home devices and information when users want to access. Therefore home network access control for user authorization is a very important issue. In this paper we propose access control model using RBAC in home network environments to provide home users with secure home services.

Keywords: Home network, access control, RBAC, security.

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

Authors: B. S. Yew, B. L. Ong, R. B. Ahmad

Abstract:

A study on the performance of TCP Vegas versus different TCP variants in homogeneous and heterogeneous wired networks are performed via simulation experiment using network simulator (ns-2). This performance evaluation prepared a comparison medium for the performance evaluation of enhanced-TCP Vegas in wired network and for wireless network. In homogeneous network, the performance of TCP Tahoe, TCP Reno, TCP NewReno, TCP Vegas and TCP SACK are analyzed. In heterogeneous network, the performances of TCP Vegas against TCP variants are analyzed. TCP Vegas outperforms other TCP variants in homogeneous wired network. However, TCP Vegas achieves unfair throughput in heterogeneous wired network.

Keywords: TCP Vegas, Homogeneous, Heterogeneous, WiredNetwork.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1718

Authors: Saulius Minkevicius, Genadijus Kulvietis

Abstract:

The modern queueing theory is one of the powerful tools for a quantitative and qualitative analysis of communication systems, computer networks, transportation systems, and many other technical systems. The paper is designated to the analysis of queueing systems, arising in the networks theory and communications theory (called open queueing network). The authors of this research in the sphere of queueing theory present the theorem about the law of the iterated logarithm (LIL) for the queue length of a customers in open queueing network and its application to the mathematical model of the open message switching system.

Keywords: Models of information systems, open message switching system, open queueing network, queue length of a customers, heavy traffic, a law of the iterated logarithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1358

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: Distillation, machine learning, neural networks, quantization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 732

Authors: Isaac K. E. Ampomah, Seong-Bae Park, Sang-Jo Lee

Abstract:

Over the past decade, there have been promising developments in Natural Language Processing (NLP) with several investigations of approaches focusing on Recognizing Textual Entailment (RTE). These models include models based on lexical similarities, models based on formal reasoning, and most recently deep neural models. In this paper, we present a sentence encoding model that exploits the sentence-to-sentence relation information for RTE. In terms of sentence modeling, Convolutional neural network (CNN) and recurrent neural networks (RNNs) adopt different approaches. RNNs are known to be well suited for sequence modeling, whilst CNN is suited for the extraction of n-gram features through the filters and can learn ranges of relations via the pooling mechanism. We combine the strength of RNN and CNN as stated above to present a unified model for the RTE task. Our model basically combines relation vectors computed from the phrasal representation of each sentence and final encoded sentence representations. Firstly, we pass each sentence through a convolutional layer to extract a sequence of higher-level phrase representation for each sentence from which the first relation vector is computed. Secondly, the phrasal representation of each sentence from the convolutional layer is fed into a Bidirectional Long Short Term Memory (Bi-LSTM) to obtain the final sentence representations from which a second relation vector is computed. The relations vectors are combined and then used in then used in the same fashion as attention mechanism over the Bi-LSTM outputs to yield the final sentence representations for the classification. Experiment on the Stanford Natural Language Inference (SNLI) corpus suggests that this is a promising technique for RTE.

Keywords: Deep neural models, natural language inference, recognizing textual entailment, sentence-to-sentence relation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1454

Authors: H. Khorashadi-Zadeh, M. R. Aghaebrahimi

Abstract:

A novel application of neural network approach to fault classification and fault location of Medium voltage cables is demonstrated in this paper. Different faults on a protected cable should be classified and located correctly. This paper presents the use of neural networks as a pattern classifier algorithm to perform these tasks. The proposed scheme is insensitive to variation of different parameters such as fault type, fault resistance, and fault inception angle. Studies show that the proposed technique is able to offer high accuracy in both of the fault classification and fault location tasks.

Keywords: Artificial neural networks, cable, fault location andfault classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1851

Authors: Seongchan Kang, Hongsik Yun, Hyukgil Kim, Minwoo Park

Abstract:

For this study, this researcher conducted a precision network adjustment with QOCA, the precision network adjustment software developed by Jet Propulsion Laboratory, to perform an integrated network adjustment on the Unified Control Points managed by the National Geographic Information Institute. Towards this end, 275 Unified Control Points observed in 2008 were selected before a network adjustment is performed on those 275 Unified Control Points. The RMSE on the discrepancies of coordinates as compared to the results of GLOBK was ±6.07mm along the N axis, ±2.68mm along the E axis and ±6.49mm along the U axis.

Keywords: Network adjustment, QOCA, unified control point.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1850

Authors: Huan Xiong, Ming Chen

Abstract:

In order to research Internet quantificationally and better model the performance of network, this paper proposes a novel AS level network performance model (MNPM), it takes autonomous system (AS) as basic modeling unit, measures E2E performance between any two outdegrees of an AS and organizes measurement results into matrix form which called performance matrix (PM). Inter-AS performance calculation is defined according to performance information stored in PM. Simulation has been implemented to verify the correctness of MNPM and a practical application of MNPM (network congestion detection) is given.

Keywords: AS, network performance, model, metric, congestion.

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

Authors: M. Javadzadeh, H. Khoshsima

Abstract:

In this article, we present a layout printing way for producing Fresnel zone on 1294-1b doped liquid crystal with Methyl-Red azo dye. We made a Fresnel zone mask with 25 zones and radius of 5 mm using lithography technique. With layout printing way, we recorded mask’s pattern on cell with λ=532 nm solid-state diode pump laser. By recording Fresnel zone pattern on cell and making Fresnel pattern on the surface of cell, odd and even zones, will form. The printed pattern, because of Azo dye’s photoisomerization, was permanent. Experimentally, we saw focal length tunability from 32 cm to 43 cm.

Keywords: Liquid crystal, lens, Fresnel zone, diffraction, Fresnel lens.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1259

Authors: M. Mahdavi, E. Mahdavi

Abstract:

In this research, STNEP is being studied considering network adequacy and limitation of investment cost by decimal codification genetic algorithm (DCGA). The goal is obtaining the maximum of network adequacy with lowest expansion cost for a specific investment. Finally, the proposed idea is applied to the Garvers 6-bus network. The results show that considering the network adequacy for solution of STNEP problem is caused that among of expansion plans for a determined investment, configuration which has relatively lower expansion cost and higher adequacy is proposed by GA based method. Finally, with respect to the curve of adequacy versus expansion cost it can be said that more optimal configurations for expansion of network are obtained with lower investment costs.

Keywords: TNEP, Network Adequacy, Investment Cost, GA

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1516

Authors: Hidehiko Okada

Abstract:

The author previously proposed an extension of differential evolution. The proposed method extends the processes of DE to handle interval numbers as genotype values so that DE can be applied to interval-valued optimization problems. The interval DE can employ either of two interval models, the lower and upper model or the center and width model, for specifying genotype values. Ability of the interval DE in searching for solutions may depend on the model. In this paper, the author compares the two models to investigate which model contributes better for the interval DE to find better solutions. Application of the interval DE is evolutionary training of interval-valued neural networks. A result of preliminary study indicates that the CW model is better than the LU model: the interval DE with the CW model could evolve better neural networks. 

Keywords: Evolutionary algorithms, differential evolution, neural network, neuroevolution, interval arithmetic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1667

Authors: B. Q. Huang, Tarik Rashid, M-T. Kechadi

Abstract:

this paper presents a multi-context recurrent network for time series analysis. While simple recurrent network (SRN) are very popular among recurrent neural networks, they still have some shortcomings in terms of learning speed and accuracy that need to be addressed. To solve these problems, we proposed a multi-context recurrent network (MCRN) with three different learning algorithms. The performance of this network is evaluated on some real-world application such as handwriting recognition and energy load forecasting. We study the performance of this network and we compared it to a very well established SRN. The experimental results showed that MCRN is very efficient and very well suited to time series analysis and its applications.

Keywords: Gradient descent method, recurrent neural network, learning algorithms, time series, BP

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3048

Authors: N. F. F. Ebecken, G. C. Pereira

Abstract:

Ecological systems are exposed and are influenced by various natural and anthropogenic disturbances. They produce various effects and states seeking response symmetry to a state of global phase coherence or stability and balance of their food webs. This research project addresses the development of a computational methodology for modeling plankton food webs. The use of algorithms to establish connections, the generation of representative fuzzy multigraphs and application of technical analysis of complex networks provide a set of tools for defining, analyzing and evaluating community structure of coastal aquatic ecosystems, beyond the estimate of possible external impacts to the networks. Thus, this study aims to develop computational systems and data models to assess how these ecological networks are structurally and functionally organized, to analyze the types and degree of compartmentalization and synchronization between oscillatory and interconnected elements network and the influence of disturbances on the overall pattern of rhythmicity of the system.

Keywords: Ecological networks, plankton food webs, fuzzy multigraphs, dynamic of networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1995

Authors: Sidhartha Panda, N.P.Padhy

Abstract:

Wind power is among the most actively developing distributed generation (DG) technology. Majority of the wind power based DG technologies employ wind turbine induction generators (WTIG) instead of synchronous generators, for the technical advantages like: reduced size, increased robustness, lower cost, and increased electromechanical damping. However, dynamic changes of wind speed make the amount of active/reactive power injected/drawn to a WTIG embedded distribution network highly variable. This paper analyzes the effect of wind speed changes on the active and reactive power penetration to the wind energy embedded distribution network. Four types of wind speed changes namely; constant, linear change, gust change and random change of wind speed are considered in the analysis. The study is carried out by three-phase, non-linear, dynamic simulation of distribution system component models. Results obtained from the investigation are presented and discussed.

Keywords: Wind turbine induction generator, distribution network, active and reactive power, wind speed.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2450

Authors: S. Wechmongkhonkon, N.Poomtong, S. Areerachakul

Abstract:

Water quality is a subject of ongoing concern. Deterioration of water quality has initiated serious management efforts in many countries. This study endeavors to automatically classify water quality. The water quality classes are evaluated using 6 factor indices. These factors are pH value (pH), Dissolved Oxygen (DO), Biochemical Oxygen Demand (BOD), Nitrate Nitrogen (NO3N), Ammonia Nitrogen (NH3N) and Total Coliform (TColiform). The methodology involves applying data mining techniques using multilayer perceptron (MLP) neural network models. The data consisted of 11 sites of canals in Dusit district in Bangkok, Thailand. The data is obtained from the Department of Drainage and Sewerage Bangkok Metropolitan Administration during 2007-2011. The results of multilayer perceptron neural network exhibit a high accuracy multilayer perception rate at 96.52% in classifying the water quality of Dusit district canal in Bangkok Subsequently, this encouraging result could be applied with plan and management source of water quality.

Keywords: artificial neural network, classification, surface water quality

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3210

Authors: A. Nasiri Pour, B. Rostami Tabar, A.Rahimzadeh

Abstract:

Accurate demand forecasting is one of the most key issues in inventory management of spare parts. The problem of modeling future consumption becomes especially difficult for lumpy patterns, which characterized by intervals in which there is no demand and, periods with actual demand occurrences with large variation in demand levels. However, many of the forecasting methods may perform poorly when demand for an item is lumpy. In this study based on the characteristic of lumpy demand patterns of spare parts a hybrid forecasting approach has been developed, which use a multi-layered perceptron neural network and a traditional recursive method for forecasting future demands. In the described approach the multi-layered perceptron are adapted to forecast occurrences of non-zero demands, and then a conventional recursive method is used to estimate the quantity of non-zero demands. In order to evaluate the performance of the proposed approach, their forecasts were compared to those obtained by using Syntetos & Boylan approximation, recently employed multi-layered perceptron neural network, generalized regression neural network and elman recurrent neural network in this area. The models were applied to forecast future demand of spare parts of Arak Petrochemical Company in Iran, using 30 types of real data sets. The results indicate that the forecasts obtained by using our proposed mode are superior to those obtained by using other methods.

Keywords: Lumpy Demand, Neural Network, Forecasting, Hybrid Approach.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2682

Authors: Ivo Jánský, Milan Rippel

Abstract:

The paper evaluates several hundred one-day-ahead VaR forecasting models in the time period between the years 2004 and 2009 on data from six world stock indices - DJI, GSPC, IXIC, FTSE, GDAXI and N225. The models model mean using the ARMA processes with up to two lags and variance with one of GARCH, EGARCH or TARCH processes with up to two lags. The models are estimated on the data from the in-sample period and their forecasting accuracy is evaluated on the out-of-sample data, which are more volatile. The main aim of the paper is to test whether a model estimated on data with lower volatility can be used in periods with higher volatility. The evaluation is based on the conditional coverage test and is performed on each stock index separately. The primary result of the paper is that the volatility is best modelled using a GARCH process and that an ARMA process pattern cannot be found in analyzed time series.

Keywords: VaR, risk analysis, conditional volatility, garch, egarch, tarch, moving average process, autoregressive process

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1430

Authors: A. M. El-Zonkoly

Abstract:

In this paper, based on steady-state models of Flexible AC Transmission System (FACTS) devices, the sizing of static synchronous series compensator (SSSC) controllers in transmission network is formed as an optimization problem. The objective of this problem is to reduce the transmission losses in the network. The optimization problem is solved using particle swarm optimization (PSO) technique. The Newton-Raphson load flow algorithm is modified to consider the insertion of the SSSC devices in the network. A numerical example, illustrating the effectiveness of the proposed algorithm, is introduced. In addition, a novel model of a 3- phase voltage source converter (VSC) that is suitable for series connected FACTS a controller is introduced. The model is verified by simulation using Power System Blockset (PSB) and Simulink software.

Keywords: FACTS, Modeling, PSO, SSSC, Transmission lossreduction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2278

Authors: Hamid R. S. Mojaveri, Seyed S. Mousavi, Mojtaba Heydar, Ahmad Aminian

Abstract:

The aim of this paper is to present a methodology in three steps to forecast supply chain demand. In first step, various data mining techniques are applied in order to prepare data for entering into forecasting models. In second step, the modeling step, an artificial neural network and support vector machine is presented after defining Mean Absolute Percentage Error index for measuring error. The structure of artificial neural network is selected based on previous researchers' results and in this article the accuracy of network is increased by using sensitivity analysis. The best forecast for classical forecasting methods (Moving Average, Exponential Smoothing, and Exponential Smoothing with Trend) is resulted based on prepared data and this forecast is compared with result of support vector machine and proposed artificial neural network. The results show that artificial neural network can forecast more precisely in comparison with other methods. Finally, forecasting methods' stability is analyzed by using raw data and even the effectiveness of clustering analysis is measured.

Keywords: Artificial Neural Networks (ANN), bullwhip effect, demand forecasting, Support Vector Machine (SVM).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2011

Authors: J. K. Alhassan, B. Attah, S. Misra

Abstract:

Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. Medical dataset is a vital ingredient used in predicting patient’s health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. WEKA software was used for the implementation of the algorithms. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. From the results obtained, DTA performed better than ANN. The Root Mean Squared Error (RMSE) of MLP is 0.3913 that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.

Keywords: Artificial neural network, classification, decision tree, diabetes mellitus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2417

Authors: E. Khorram, S.M. Mirzababaei

Abstract:

Everyday the usages of the Internet increase and simply a world of the data become accessible. Network providers do not want to let the provided services to be used in harmful or terrorist affairs, so they used a variety of methods to protect the special regions from the harmful data. One of the most important methods is supposed to be the firewall. Firewall stops the transfer of such packets through several ways, but in some cases they do not use firewall because of its blind packet stopping, high process power needed and expensive prices. Here we have proposed a method to find a discriminate function to distinguish between usual packets and harmful ones by the statistical processing on the network router logs. So an administrator can alarm to the user. This method is very fast and can be used simply in adjacent with the Internet routers.

Keywords: Data Mining, Firewall, Optimization, Packetclassification, Statistical Pattern Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1410

Authors: Toshihiko Matsuka, James E. Corter

Abstract:

Most neural network (NN) models of human category learning use a gradient-based learning method, which assumes that locally-optimal changes are made to model parameters on each learning trial. This method tends to under predict variability in individual-level cognitive processes. In addition many recent models of human category learning have been criticized for not being able to replicate rapid changes in categorization accuracy and attention processes observed in empirical studies. In this paper we introduce stochastic learning algorithms for NN models of human category learning and show that use of the algorithms can result in (a) rapid changes in accuracy and attention allocation, and (b) different learning trajectories and more realistic variability at the individual-level.

Keywords: category learning, cognitive modeling, radial basis function, stochastic optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1631

Authors: Vijay Pal Singh, Yogesh Chandra Kotiyal

Abstract:

Structures are a combination of various load carrying members which transfer the loads to the foundation from the superstructure safely. At the design stage, the loading of the structure is defined and appropriate material choices are made based upon their properties, mainly related to strength. The strength of materials kept on reducing with time because of many factors like environmental exposure and deformation caused by unpredictable external loads. Hence, to predict the strength of materials used in structures, various techniques are used. Among these techniques, Non-destructive techniques (NDT) are the one that can be used to predict the strength without damaging the structure. In the present study, the compressive strength of concrete has been predicted using Artificial Neural Network (ANN). The predicted strength was compared with the experimentally obtained actual compressive strength of concrete and equations were developed for different models. A good co-relation has been obtained between the predicted strength by these models and experimental values. Further, the co-relation has been developed using two NDT techniques for prediction of strength by regression analysis. It was found that the percentage error has been reduced between the predicted strength by using combined techniques in place of single techniques.

Keywords: Rebound, ultra-sonic pulse, penetration, ANN, NDT, regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4386