Search results for: network data envelopment analysis

Authors: Essam Al-Daoud

Abstract:

Several combinations of the preprocessing algorithms, feature selection techniques and classifiers can be applied to the data classification tasks. This study introduces a new accurate classifier, the proposed classifier consist from four components: Signal-to- Noise as a feature selection technique, support vector machine, Bayesian neural network and AdaBoost as an ensemble algorithm. To verify the effectiveness of the proposed classifier, seven well known classifiers are applied to four datasets. The experiments show that using the suggested classifier enhances the classification rates for all datasets.

Keywords: AdaBoost, Bayesian neural network, Signal-to-Noise, support vector machine, MCMC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2020

Authors: Nelson F.F. Ebecken, Gilberto C. Pereira

Abstract:

The objective of this work is to explicit knowledge on the interactions between the chlorophyll-a and nine meroplankton larvae of epibenthonic fauna. The studied case is the Arraial do Cabo upwelling system, Southeastern of Brazil, which provides different environmental conditions. To assess this information a network approach based in probability estimative was used. Comparisons among the generated graphs are made in the light of different water masses, application of Shannon biodiversity index, and the closeness and betweenness centralities measurements. Our results show the main pattern among different water masses and how the core organisms belonging to the network skeleton are correlated to the main environmental variable. We conclude that the approach of complex networks is a promising tool for environmental diagnostic.

Keywords: Coastal upwelling, Ecological networks, Plankton - interactions, Environmental analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1636

Authors: Ladan Darougaran, Hossein Shahinzadeh, Hajar Ghotb, Leila Ramezanpour

Abstract:

In ad hoc networks, the main issue about designing of protocols is quality of service, so that in wireless sensor networks the main constraint in designing protocols is limited energy of sensors. In fact, protocols which minimize the power consumption in sensors are more considered in wireless sensor networks. One approach of reducing energy consumption in wireless sensor networks is to reduce the number of packages that are transmitted in network. The technique of collecting data that combines related data and prevent transmission of additional packages in network can be effective in the reducing of transmitted packages- number. According to this fact that information processing consumes less power than information transmitting, Data Aggregation has great importance and because of this fact this technique is used in many protocols [5]. One of the Data Aggregation techniques is to use Data Aggregation tree. But finding one optimum Data Aggregation tree to collect data in networks with one sink is a NP-hard problem. In the Data Aggregation technique, related information packages are combined in intermediate nodes and form one package. So the number of packages which are transmitted in network reduces and therefore, less energy will be consumed that at last results in improvement of longevity of network. Heuristic methods are used in order to solve the NP-hard problem that one of these optimization methods is to solve Simulated Annealing problems. In this article, we will propose new method in order to build data collection tree in wireless sensor networks by using Simulated Annealing algorithm and we will evaluate its efficiency whit Genetic Algorithm.

Keywords: Data aggregation, wireless sensor networks, energy efficiency, simulated annealing algorithm, genetic algorithm.

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

Authors: Jun Seok Kim, Cheong-Sool Park, Jun-Geol Baek, Sung-Shick Kim

Abstract:

Control chart pattern recognition is one of the most important tools to identify the process state in statistical process control. The abnormal process state could be classified by the recognition of unnatural patterns that arise from assignable causes. In this study, a wavelet based neural network approach is proposed for the recognition of control chart patterns that have various characteristics. The procedure of proposed control chart pattern recognizer comprises three stages. First, multi-resolution wavelet analysis is used to generate time-shape and time-frequency coefficients that have detail information about the patterns. Second, distance based features are extracted by a bi-directional Kohonen network to make reduced and robust information. Third, a back-propagation network classifier is trained by these features. The accuracy of the proposed method is shown by the performance evaluation with numerical results.

Keywords: Control chart pattern recognition, Multi-resolution wavelet analysis, Bi-directional Kohonen network, Back-propagation network, Feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2480

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: Convolutional Neural Network, Deep Learning, Deep Learning Based FER, Facial Emotion Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1370

Authors: D. Naga Ravi Kiran, C. G. Dethe

Abstract:

Wireless Sensor Network (WSN) routing is complex due to its dynamic nature, computational overhead, limited battery life, non-conventional addressing scheme, self-organization, and sensor nodes limited transmission range. An energy efficient routing protocol is a major concern in WSN. LEACH is a hierarchical WSN routing protocol to increase network life. It performs self-organizing and re-clustering functions for each round. This study proposes a better sensor networks cluster head selection for efficient data aggregation. The algorithm is based on Tabu search.

Keywords: Wireless Sensor Network (WSN), LEACH, Clustering, Tabu Search.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2027

Authors: Han Bing, Yin Zhenjie

Abstract:

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

Keywords: Fault prediction, Neural network, GM (1.5), Genetic algorithm, GBPGA.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1302

Authors: Chia-Feng Lu, Yuh-Jen Wang, Shin Teng, Yu-Te Wu, Sui-Hing Yan

Abstract:

Brain functional networks based on resting-state EEG data were compared between patients with mild Alzheimer’s disease (mAD) and matched patients with amnestic subtype of mild cognitive impairment (aMCI). We integrated the time–frequency cross mutual information (TFCMI) method to estimate the EEG functional connectivity between cortical regions and the network analysis based on graph theory to further investigate the alterations of functional networks in mAD compared with aMCI group. We aimed at investigating the changes of network integrity, local clustering, information processing efficiency, and fault tolerance in mAD brain networks for different frequency bands based on several topological properties, including degree, strength, clustering coefficient, shortest path length, and efficiency. Results showed that the disruptions of network integrity and reductions of network efficiency in mAD characterized by lower degree, decreased clustering coefficient, higher shortest path length, and reduced global and local efficiencies in the delta, theta, beta2, and gamma bands were evident. The significant changes in network organization can be used in assisting discrimination of mAD from aMCI in clinical.

Keywords: EEG, functional connectivity, graph theory, TFCMI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2505

Authors: Tae Kyung Kim, Hee Suk Seo

Abstract:

Sensor networks are often deployed in unattended environments, thus leaving these networks vulnerable to false data injection attacks in which an adversary injects forged reports into the network through compromised nodes, with the goal of deceiving the base station or depleting the resources of forwarding nodes. Several research solutions have been recently proposed to detect and drop such forged reports during the forwarding process. Each design can provide the equivalent resilience in terms of node compromising. However, their energy consumption characteristics differ from each other. Thus, employing only a single filtering scheme for a network is not a recommendable strategy in terms of energy saving. It's very important the threshold determination for message authentication to identify. We propose the recursive contract net protocols which less energy level of terminal node in wireless sensor network.

Keywords: Data filtering, recursive CNP, simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1503

Authors: Jung-Hyun Kim, Jihyung Kim, Kwangjae Lim, Dong Seung Kwon

Abstract:

Network coding has recently attracted attention as an efficient technique in multicast/broadcast services. The problem of finding the optimal network coding mechanism maximizing the bandwidth efficiency is hard to solve and hard to approximate. Lots of network coding-based schemes have been suggested in the literature to improve the bandwidth efficiency, especially network coding-based automatic repeat request (NCARQ) schemes. However, existing schemes have several limitations which cause the performance degradation in resource limited systems. To improve the performance in resource limited systems, we propose NCARQ with overlapping selection (OS-NCARQ) scheme. The advantages of OS-NCARQ scheme over the traditional ARQ scheme and existing NCARQ schemes are shown through the analysis and simulations.

Keywords: ARQ, Network coding, Multicast/Broadcast services, Packet-based systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1510

Authors: Dhinu Johnson, Gurdip Singh

Abstract:

Sensor network applications are often data centric and involve collecting data from a set of sensor nodes to be delivered to various consumers. Typically, nodes in a sensor network are resource-constrained, and hence the algorithms operating in these networks must be efficient. There may be several algorithms available implementing the same service, and efficient considerations may require a sensor application to choose the best suited algorithm. In this paper, we present a systematic evaluation of a set of algorithms implementing the data gathering service. We propose a modular infrastructure for implementing such algorithms in TOSSIM with separate configurable modules for various tasks such as interest propagation, data propagation, aggregation, and path maintenance. By appropriately configuring these modules, we propose a number of data gathering algorithms, each of which incorporates a different set of heuristics for optimizing performance. We have performed comprehensive experiments to evaluate the effectiveness of these heuristics, and we present results from our experimentation efforts.

Keywords: Data Centric Protocols, Shortest Paths, Sensor networks, Message passing systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1444

Authors: Garima Gupta, Daya Gupta

Abstract:

Virtually all existing networked system management tools use a Manager/Agent paradigm. That is, distributed agents are deployed on managed devices to collect local information and report it back to some management unit. Even those that use standard protocols such as SNMP fall into this model. Using standard protocol has the advantage of interoperability among devices from different vendors. However, it may not be able to provide customized information that is of interest to satisfy specific management needs. In this dissertation work, different approaches are used to collect information regarding the devices attached to a Local Area Network. An SNMP aware application is being developed that will manage the discovery procedure and will be used as data collector.

Keywords: ICMP Scanner, Network Discovery, NetworkManagement, SNMP Scanner.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1666

Authors: K. Jayakumar, S. Thangavel

Abstract:

In this paper proposed the effective fault detection of industrial drives by using Biorthogonal Posterior Vibration Signal-Data Probabilistic Wavelet Neural Network (BPPVS-WNN) system. This system was focused to reducing the current flow and to identify faults with lesser execution time with harmonic values obtained through fifth derivative. Initially, the construction of Biorthogonal vibration signal-data based wavelet transform in BPPVS-WNN system localizes the time and frequency domain. The Biorthogonal wavelet approximates the broken bearing using double scaling and factor, identifies the transient disturbance due to fault on induction motor through approximate coefficients and detailed coefficient. Posterior Probabilistic Neural Network detects the final level of faults using the detailed coefficient till fifth derivative and the results obtained through it at a faster rate at constant frequency signal on the industrial drive. Experiment through the Simulink tool detects the healthy and unhealthy motor on measuring parametric factors such as fault detection rate based on time, current flow rate, and execution time.

Keywords: Biorthogonal Wavelet Transform, Posterior Probabilistic Neural Network, Induction Motor.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1018

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

Abstract:

Prediction of highly non linear behavior of suspended sediment flow in rivers has prime importance in the field of water resources engineering. In this study the predictive performance of two Artificial Neural Networks (ANNs) namely, the Radial Basis Function (RBF) Network and the Multi Layer Feed Forward (MLFF) Network have been compared. Time series data of daily suspended sediment discharge and water discharge at Pari River was used for training and testing the networks. A number of statistical parameters i.e. root mean square error (RMSE), mean absolute error (MAE), coefficient of efficiency (CE) and coefficient of determination (R2) were used for performance evaluation of the models. Both the models produced satisfactory results and showed a good agreement between the predicted and observed data. The RBF network model provided slightly better results than the MLFF network model in predicting suspended sediment discharge.

Keywords: ANN, discharge, modeling, prediction, suspendedsediment,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1725

Authors: Javier Parra-Domínguez, Juan Manuel Corchado

Abstract:

At present, public efficiency is a concept that intends to maximize return on public investment focus on minimizing the use of resources and maximizing the outputs. The concept takes into account statistical criteria drawn up according to techniques such as DEA (Data Envelopment Analysis). The purpose of the current work is to consider, more precisely, the theoretical application of CBR (Case-Based Reasoning) from economics and computer science, as a preliminary step to improving the efficiency of law enforcement agencies (public sector). With the aim of increasing the efficiency of the public sector, we have entered into a phase whose main objective is the implementation of new technologies. Our main conclusion is that the application of computer techniques, such as CBR, has become key to the efficiency of the public sector, which continues to require economic valuation based on methodologies such as DEA. As a theoretical result and conclusion, the incorporation of CBR systems will reduce the number of inputs and increase, theoretically, the number of outputs generated based on previous computer knowledge.

Keywords: Case-based reasoning, knowledge, police, public efficiency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 603

Authors: Emna Benmohamed, Hela Ltifi, Mounir Ben Ayed

Abstract:

Bayesian Network (BN) is one of the most efficient classification methods. It is widely used in several fields (i.e., medical diagnostics, risk analysis, bioinformatics research). The BN is defined as a probabilistic graphical model that represents a formalism for reasoning under uncertainty. This classification method has a high-performance rate in the extraction of new knowledge from data. The construction of this model consists of two phases for structure learning and parameter learning. For solving this problem, the K2 algorithm is one of the representative data-driven algorithms, which is based on score and search approach. In addition, the integration of the expert's knowledge in the structure learning process allows the obtainment of the highest accuracy. In this paper, we propose a hybrid approach combining the improvement of the K2 algorithm called K2 algorithm for Parents and Children search (K2PC) and the expert-driven method for learning the structure of BN. The evaluation of the experimental results, using the well-known benchmarks, proves that our K2PC algorithm has better performance in terms of correct structure detection. The real application of our model shows its efficiency in the analysis of the phosphate laundry effluents' impact on the watershed in the Gafsa area (southwestern Tunisia).

Keywords: Classification, Bayesian network; structure learning, K2 algorithm, expert knowledge, surface water analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 512

Authors: Radek Malinský, Ivan Jelínek

Abstract:

This article deals with the popularity of candidates for the president of the United States of America. The popularity is assessed according to public comments on the Web 2.0. Social networking, blogging and online forums (collectively Web 2.0) are for common Internet users the easiest way to share their personal opinions, thoughts, and ideas with the entire world. However, the web content diversity, variety of technologies and website structure differences, all of these make the Web 2.0 a network of heterogeneous data, where things are difficult to find for common users. The introductory part of the article describes methodology for gathering and processing data from Web 2.0. The next part of the article is focused on the evaluation and content analysis of obtained information, which write about presidential candidates.

Keywords: Sentiment Analysis, Web 2.0, Webometrics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3233

Authors: S. P. Singh

Abstract:

This paper measures technical and scale efficiencies of 40 Indian sugar companies for the period from 2004-05 to 2013-14. The efficiencies are estimated through input-oriented DEA models using one output variable—value of output (VOP) and five input variables—capital cost (CA), employee cost (EMP), raw material (RW), energy & fuel (E&F) and other manufacturing expenses (OME). The sugar companies are classified into integrated and non-integrated categories to know which one achieves higher level of efficiency. Sources of inefficiency in the industry are identified through decomposing the overall technical efficiency (TE) into pure technical efficiency (PTE) and scale efficiency (SE). The paper also estimates input-reduction targets for relatively inefficient companies and suggests measures to improve their efficiency level. The findings reveal that the TE does not evince any trend rather it shows fluctuations across years, largely due to erratic and cyclical pattern of sugar production. Further, technical inefficiency in the industry seems to be driven more by the managerial inefficiency than the scale inefficiency, which implies that TE can be improved through better conversion of inputs into output.

Keywords: Sugar industry, companies, technical efficiency, data envelopment analysis, targets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1343

Authors: Sanae Attioui, Said Najah

Abstract:

The Earth's surface is constantly changing through forces of nature and human activities. Reliable, accurate, and timely change detection is critical to environmental monitoring, resource management, and planning activities. Recently, interest in deep learning algorithms, especially convolutional neural networks, has increased in the field of image change detection due to their powerful ability to extract multi-level image features automatically. However, these networks are prone to drawbacks that limit their applications, which reside in their inability to capture spatial relationships between image instances, as this necessitates a large amount of training data. As an alternative, Capsule Network has been proposed to overcome these shortcomings. Although its effectiveness in remote sensing image analysis has been experimentally verified, its application in change detection tasks remains very sparse. Motivated by its greater robustness towards improved hierarchical object representation, this study aims to apply a capsule network for PolSAR image Change Detection. The experimental results demonstrate that the proposed change detection method can yield a significantly higher detection rate compared to methods based on convolutional neural networks.

Keywords: Change detection, capsule network, deep network, Convolutional Neural Networks, polarimetric synthetic aperture radar images, PolSAR images.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 498

Authors: Danilo López, Nelson Vera, Luis Pedraza

Abstract:

This paper analyzes fundamental ideas and concepts related to neural networks, which provide the reader a theoretical explanation of Long Short-Term Memory (LSTM) networks operation classified as Deep Learning Systems, and to explicitly present the mathematical development of Backward Pass equations of the LSTM network model. This mathematical modeling associated with software development will provide the necessary tools to develop an intelligent system capable of predicting the behavior of licensed users in wireless cognitive radio networks.

Keywords: Neural networks, multilayer perceptron, long short-term memory, recurrent neuronal network, mathematical analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1562

Authors: Thiang, Handry Khoswanto, Rendy Pangaldus

Abstract:

Inverse kinematics analysis plays an important role in developing a robot manipulator. But it is not too easy to derive the inverse kinematic equation of a robot manipulator especially robot manipulator which has numerous degree of freedom. This paper describes an application of Artificial Neural Network for modeling the inverse kinematics equation of a robot manipulator. In this case, the robot has three degree of freedoms and the robot was implemented for drilling a printed circuit board. The artificial neural network architecture used for modeling is a multilayer perceptron networks with steepest descent backpropagation training algorithm. The designed artificial neural network has 2 inputs, 2 outputs and varies in number of hidden layer. Experiments were done in variation of number of hidden layer and learning rate. Experimental results show that the best architecture of artificial neural network used for modeling inverse kinematics of is multilayer perceptron with 1 hidden layer and 38 neurons per hidden layer. This network resulted a RMSE value of 0.01474.

Keywords: Artificial neural network, back propagation, inverse kinematics, manipulator, robot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2288

Authors: Emad Alenany, M. Adel El-Baz

Abstract:

In this paper, the flow of different classes of patients into a hospital is modelled and analyzed by using the queueing network analyzer (QNA) algorithm and discrete event simulation. Input data for QNA are the rate and variability parameters of the arrival and service times in addition to the number of servers in each facility. Patient flows mostly match real flow for a hospital in Egypt. Based on the analysis of the waiting times, two approaches are suggested for improving performance: Separating patients into service groups, and adopting different service policies for sequencing patients through hospital units. The separation of a specific group of patients, with higher performance target, to be served separately from the rest of patients requiring lower performance target, requires the same capacity while improves performance for the selected group of patients with higher target. Besides, it is shown that adopting the shortest processing time and shortest remaining processing time service policies among other tested policies would results in, respectively, 11.47% and 13.75% reduction in average waiting time relative to first come first served policy.

Keywords: Queueing network, discrete-event simulation, health applications, SPT.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1529

Authors: Mouhammad Alkasassbeh, Mohammad Almseidin

Abstract:

Network security engineers work to keep services available all the time by handling intruder attacks. Intrusion Detection System (IDS) is one of the obtainable mechanisms that is used to sense and classify any abnormal actions. Therefore, the IDS must be always up to date with the latest intruder attacks signatures to preserve confidentiality, integrity, and availability of the services. The speed of the IDS is a very important issue as well learning the new attacks. This research work illustrates how the Knowledge Discovery and Data Mining (or Knowledge Discovery in Databases) KDD dataset is very handy for testing and evaluating different Machine Learning Techniques. It mainly focuses on the KDD preprocess part in order to prepare a decent and fair experimental data set. The J48, MLP, and Bayes Network classifiers have been chosen for this study. It has been proven that the J48 classifier has achieved the highest accuracy rate for detecting and classifying all KDD dataset attacks, which are of type DOS, R2L, U2R, and PROBE.

Keywords: IDS, DDoS, MLP, KDD.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 727

Authors: Seyoung Kim, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

A database that records average traffic speeds measured at five-minute intervals for all the links in the traffic network of a metropolitan city. While learning from this data the models that can predict future traffic speed would be beneficial for the applications such as the car navigation system, building predictive models for every link becomes a nontrivial job if the number of links in a given network is huge. An advantage of adopting k-nearest neighbor (k-NN) as predictive models is that it does not require any explicit model building. Instead, k-NN takes a long time to make a prediction because it needs to search for the k-nearest neighbors in the database at prediction time. In this paper, we investigate how much we can speed up k-NN in making traffic speed predictions by reducing the amount of data to be searched for without a significant sacrifice of prediction accuracy. The rationale behind this is that we had a better look at only the recent data because the traffic patterns not only repeat daily or weekly but also change over time. In our experiments, we build several different k-NN models employing different sets of features which are the current and past traffic speeds of the target link and the neighbor links in its up/down-stream. The performances of these models are compared by measuring the average prediction accuracy and the average time taken to make a prediction using various amounts of data.

Keywords: Big data, k-NN, machine learning, traffic speed prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1376

Authors: Maryam Jamela Ismail, Rosdiazli Ibrahim, Idris Ismail

Abstract:

In the oil and gas industry, energy prediction can help the distributor and customer to forecast the outgoing and incoming gas through the pipeline. It will also help to eliminate any uncertainties in gas metering for billing purposes. The objective of this paper is to develop Neural Network Model for energy consumption and analyze the performance model. This paper provides a comprehensive review on published research on the energy consumption prediction which focuses on structures and the parameters used in developing Neural Network models. This paper is then focused on the parameter selection of the neural network prediction model development for energy consumption and analysis on the result. The most reliable model that gives the most accurate result is proposed for the prediction. The result shows that the proposed neural network energy prediction model is able to demonstrate an adequate performance with least Root Mean Square Error.

Keywords: Energy Prediction, Multilayer Feedforward, Levenberg-Marquardt, Root Mean Square Error (RMSE)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2643

Authors: Won Sup Kim, Xue-Mei Cui, Seung Kee Han

Abstract:

We present on the method of inverse coherence matrix for the estimation of network connectivity from multivariate time series of a complex system. In a model system of coupled chaotic oscillators, it is shown that the inverse coherence matrix defined as the inverse of cross coherence matrix is proportional to the network connectivity. Therefore the inverse coherence matrix could be used for the distinction between the directly connected links from indirectly connected links in a complex network. We compare the result of network estimation using the method of the inverse coherence matrix with the results obtained from the coherence matrix and the partial coherence matrix.

Keywords: Chaotic oscillator, complex network, inverse coherence matrix, network estimation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2003

Authors: Guo Yanru, Zhu Xiaobo, Lee Chu Keong

Abstract:

This paper maps the structure of the social network of the 2011 class ofsixty graduate students of the Masters of Science (Knowledge Management) programme at the Nanyang Technological University, based on their friending relationships on Facebook. To ensure anonymity, actual names were not used. Instead, they were replaced with codes constructed from their gender, nationality, mode of study, year of enrollment and a unique number. The relationships between friends within the class, and among the seniors and alumni of the programme wereplotted. UCINet and Pajek were used to plot the sociogram, to compute the density, inclusivity, and degree, global, betweenness, and Bonacich centralities, to partition the students into two groups, namely, active and peripheral, and to identify the cut-points. Homophily was investigated, and it was observed for nationality and study mode. The groups students formed on Facebook were also studied, and of fifteen groups, eight were classified as dead, which we defined as those that have been inactive for over two months.

Keywords: Facebook, friending relationships, Social network analysis, social network sites, structural position

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1745

Authors: Myriam Noureddine

Abstract:

During their activity, all systems must be operational without failures and in this context, the dependability concept is essential avoiding disruption of their function. As computer networks are systems with the same requirements of dependability, this article deals with an analysis of failures for a computer network. The proposed approach integrates specific tools of the plat-form KB3, usually applied in dependability studies of industrial systems. The methodology is supported by a multi-agent system formed by six agents grouped in three meta agents, dealing with two levels. The first level concerns a modeling step through a conceptual agent and a generating agent. The conceptual agent is dedicated to the building of the knowledge base from the system specifications written in the FIGARO language. The generating agent allows producing automatically both the structural model and a dependability model of the system. The second level, the simulation, shows the effects of the failures of the system through a simulation agent. The approach validation is obtained by its application on a specific computer network, giving an analysis of failures through their effects for the considered network.

Keywords: Computer network, dependability, KB3 plat-form, multi-agent system, failure.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 640

Authors: S. Pattanapairoj, D. Chetchotsak

Abstract:

This paper proposed classification models that would be used as a proxy for hard disk drive (HDD) functional test equitant which required approximately more than two weeks to perform the HDD status classification in either “Pass" or “Fail". These models were constructed by using committee network which consisted of a number of single neural networks. This paper also included the method to solve the problem of sparseness data in failed part, which was called “enforce learning method". Our results reveal that the constructed classification models with the proposed method could perform well in the sparse data conditions and thus the models, which used a few seconds for HDD classification, could be used to substitute the HDD functional tests.

Keywords: Sparse data, Classifications, Committee network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1736