Search results for: Data Center

Authors: Varun Singh, Mainak Bandyopadhyay, Maharana Pratap Singh

Abstract:

The shortest path (SP) problem concerns with finding the shortest path from a specific origin to a specified destination in a given network while minimizing the total cost associated with the path. This problem has widespread applications. Important applications of the SP problem include vehicle routing in transportation systems particularly in the field of in-vehicle Route Guidance System (RGS) and traffic assignment problem (in transportation planning). Well known applications of evolutionary methods like Genetic Algorithms (GA), Ant Colony Optimization, Particle Swarm Optimization (PSO) have come up to solve complex optimization problems to overcome the shortcomings of existing shortest path analysis methods. It has been reported by various researchers that PSO performs better than other evolutionary optimization algorithms in terms of success rate and solution quality. Further Geographic Information Systems (GIS) have emerged as key information systems for geospatial data analysis and visualization. This research paper is focused towards the application of PSO for solving the shortest path problem between multiple points of interest (POI) based on spatial data of Allahabad City and traffic speed data collected using GPS. Geovisualization of results of analysis is carried out in GIS.

Keywords: GIS, Outliers, PSO, Traffic Data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2890

Authors: Salima Kouici, Abdelkader Khelladi

Abstract:

In this work, we begin with the presentation of the Tθ family of usual similarity measures concerning multidimensional binary data. Subsequently, some properties of these measures are proposed. Finally the impact of the use of different inter-elements measures on the results of the Agglomerative Hierarchical Clustering Methods is studied.

Keywords: Binary data, similarity measure, Tθ measures, Agglomerative Hierarchical Clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3444

Authors: C. Edwards, P. Parker

Abstract:

Flight school members are facing a major disruption in the technologies available for them to fly as electric planes enter the aviation industry. The year 2020 marked a new era in aviation with the first type certification of an electric plane. The Pipistrel Velis Electro is a two-seat electric aircraft (e-plane) designed for flight training. Electric flight training has the potential to deeply reduce emissions, noise, and cost of pilot training. Though these are all attractive features, understanding must be developed on the perceptions of the essential actor of the technology, the pilot. This study asks student pilots, flight instructors, flight center managers, and other members of flight schools about their perceptions of e-planes. The questions were divided into three categories: safety and trust of the technology, expected costs in comparison to conventional planes, and interest in the technology, including their desire to fly electric planes. Participants were recruited from flight schools using a protocol approved by the Office of Research Ethics. None of these flight schools have an e-plane in their fleet so these views are based on perceptions rather than direct experience. The results revealed perceptions that were strongly positive with many qualitative comments indicating great excitement about the potential of the new electric aviation technology. Some concerns were raised regarding battery endurance limits. Overall, the flight school community is clearly in favor of introducing electric propulsion technology and reducing the environmental impacts of their industry.

Keywords: electric planes, flight training, green aircraft, student pilots, sustainable aviation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1174

Authors: M. Saravanan, M. Madheswaran

Abstract:

Wireless Sensor Network (WSN) clustering architecture enables features like network scalability, communication overhead reduction, and fault tolerance. After clustering, aggregated data is transferred to data sink and reducing unnecessary, redundant data transfer. It reduces nodes transmitting, and so saves energy consumption. Also, it allows scalability for many nodes, reduces communication overhead, and allows efficient use of WSN resources. Clustering based routing methods manage network energy consumption efficiently. Building spanning trees for data collection rooted at a sink node is a fundamental data aggregation method in sensor networks. The problem of determining Cluster Head (CH) optimal number is an NP-Hard problem. In this paper, we combine cluster based routing features for cluster formation and CH selection and use Minimum Spanning Tree (MST) for intra-cluster communication. The proposed method is based on optimizing MST using Simulated Annealing (SA). In this work, normalized values of mobility, delay, and remaining energy are considered for finding optimal MST. Simulation results demonstrate the effectiveness of the proposed method in improving the packet delivery ratio and reducing the end to end delay.

Keywords: Wireless sensor network, clustering, minimum spanning tree, genetic algorithm, low energy adaptive clustering hierarchy, simulated annealing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1785

Authors: Isao Taguchi, Yasuo Sugai

Abstract:

This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. Comparing to recent neural networks; pulse neural networks, quantum neuro computation, etc, the multilayer network is widely used due to its simple structure. When learning objects are complicated, the problems, such as unsuccessful learning or a significant time required in learning, remain unsolved. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that makes large errors and interferes with the learning process. Our method devides the learning process into several stages. In general, input characteristics to an output layer unit show oscillation during learning process for complicated problems. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of learning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. In learning, oscillatory phenomena of a learning curve serve an important role in learning performance. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.

Keywords: data selection, function approximation problem, multistage leaning, neural network, voluntary oscillation.

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

Authors: Guy Leshem, Ya'acov Ritov

Abstract:

Traffic Management and Information Systems, which rely on a system of sensors, aim to describe in real-time traffic in urban areas using a set of parameters and estimating them. Though the state of the art focuses on data analysis, little is done in the sense of prediction. In this paper, we describe a machine learning system for traffic flow management and control for a prediction of traffic flow problem. This new algorithm is obtained by combining Random Forests algorithm into Adaboost algorithm as a weak learner. We show that our algorithm performs relatively well on real data, and enables, according to the Traffic Flow Evaluation model, to estimate and predict whether there is congestion or not at a given time on road intersections.

Keywords: Machine Learning, Boosting, Classification, TrafficCongestion, Data Collecting, Magnetic Loop Detectors, SignalizedIntersections, Traffic Signal Timing Optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3908

Authors: T. Sattarpour, D. Nazarpour

Abstract:

This paper investigates the effect of simultaneous placement of DGs and smart meters (SMs), on voltage profile improvement in active distribution networks (ADNs). A substantial center of attention has recently been on responsive loads initiated in power system problem studies such as distributed generations (DGs). Existence of responsive loads in active distribution networks (ADNs) would have undeniable effect on sizing and siting of DGs. For this reason, an optimal framework is proposed for sizing and siting of DGs and SMs in ADNs. SMs are taken into consideration for the sake of successful implementing of demand response programs (DRPs) such as direct load control (DLC) with end-side consumers. Looking for voltage profile improvement, the optimization procedure is solved by genetic algorithm (GA) and tested on IEEE 33-bus distribution test system. Different scenarios with variations in the number of DG units, individual or simultaneous placing of DGs and SMs, and adaptive power factor (APF) mode for DGs to support reactive power have been established. The obtained results confirm the significant effect of DRPs and APF mode in determining the optimal size and site of DGs to be connected in ADN resulting to the improvement of voltage profile as well.

Keywords: Active distribution network (ADN), distributed generations (DGs), smart meters (SMs), demand response programs (DRPs), adaptive power factor (APF).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1769

Authors: Sumiko Anno, Keiji Imaoka, Takeo Tadono, Tamotsu Igarashi, Subramaniam Sivaganesh, Selvam Kannathasan, Vaithehi Kumaran, Sinnathamby Noble Surendran

Abstract:

Dengue outbreaks are affected by biological, ecological, socio-economic and demographic factors that vary over time and space. These factors have been examined separately and still require systematic clarification. The present study aimed to investigate the spatial-temporal clustering relationships between these factors and dengue outbreaks in the northern region of Sri Lanka. Remote sensing (RS) data gathered from a plurality of satellites were used to develop an index comprising rainfall, humidity and temperature data. RS data gathered by ALOS/AVNIR-2 were used to detect urbanization, and a digital land cover map was used to extract land cover information. Other data on relevant factors and dengue outbreaks were collected through institutions and extant databases. The analyzed RS data and databases were integrated into geographic information systems, enabling temporal analysis, spatial statistical analysis and space-time clustering analysis. Our present results showed that increases in the number of the combination of ecological factor and socio-economic and demographic factors with above the average or the presence contribute to significantly high rates of space-time dengue clusters.

Keywords: ALOS/AVNIR-2, Dengue, Space-time clustering analysis, Sri Lanka.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2283

Authors: Syed Muhammad Aqil Burney, Tahseen Ahmed Jilani, C. Ardil

Abstract:

Minimization methods for training feed-forward networks with Backpropagation are compared. Feedforward network training is a special case of functional minimization, where no explicit model of the data is assumed. Therefore due to the high dimensionality of the data, linearization of the training problem through use of orthogonal basis functions is not desirable. The focus is functional minimization on any basis. A number of methods based on local gradient and Hessian matrices are discussed. Modifications of many methods of first and second order training methods are considered. Using share rates data, experimentally it is proved that Conjugate gradient and Quasi Newton?s methods outperformed the Gradient Descent methods. In case of the Levenberg-Marquardt algorithm is of special interest in financial forecasting.

Keywords: Backpropagation algorithm, conjugacy condition, line search, matrix perturbation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3641

Authors: Herti Utami, Sutijan, Roto, Wahyudi Budi Sediawan

Abstract:

α-Pinene is the main component of the most turpentine oils. The hydration of α-pinene with acid catalysts leads to a complex mixture of monoterpenes. In order to obtain more valuable products, the α-pinene in the turpentine can be hydrated in dilute mineral acid solutions to produce α-terpineol. The design of separation processes requires information on phase equilibrium and related thermodynamic properties. This paper reports the results of study on liquid-liquid equilibrium (LLE) of system containing α- pinene + water and α-terpineol + water. Binary LLE for α-pinene + water system, and α-terpineol + water systems were determined by experiment at 301K and atmospheric pressure. The two component mixture was stirred for about 30min, then the mixture was left for about 2h for complete phase separation. The composition of both phases was analyzed by using a Gas Chromatograph. The experimental data were correlated by considering both NRTL and UNIQUAC activity coefficient models. The LLE data for the system of α-pinene + water and α-terpineol + water were correlated successfully by the NRTL model. The experimental data were not satisfactorily fitted by the UNIQUAC model. The NRTL model (α =0.3) correlates the LLE data for the system of α-pinene + water at 301K with RMSD of 0.0404%. And the NRTL model (α =0.61) at 301K with RMSD of 0.0058 %. The NRTL model (α =0.3) correlates the LLE data for the system of α- terpineol + water at 301K with RMSD of 0.1487% and the NRTL model (α =0.6) at 301K with RMSD of 0.0032%, between the experimental and calculated mole fractions.

Keywords: α-Pinene, α-Terpineol, Liquid-liquid Equilibrium, NRTL model, UNIQUAC model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4975

Authors: M. G. C. A. Cimino, G. Frosini, B. Lazzerini, F. Marcelloni

Abstract:

In the last decades, a number of robust fuzzy clustering algorithms have been proposed to partition data sets affected by noise and outliers. Robust fuzzy C-means (robust-FCM) is certainly one of the most known among these algorithms. In robust-FCM, noise is modeled as a separate cluster and is characterized by a prototype that has a constant distance δ from all data points. Distance δ determines the boundary of the noise cluster and therefore is a critical parameter of the algorithm. Though some approaches have been proposed to automatically determine the most suitable δ for the specific application, up to today an efficient and fully satisfactory solution does not exist. The aim of this paper is to propose a novel method to compute the optimal δ based on the analysis of the distribution of the percentage of objects assigned to the noise cluster in repeated executions of the robust-FCM with decreasing values of δ . The extremely encouraging results obtained on some data sets found in the literature are shown and discussed.

Keywords: noise prototype, robust fuzzy clustering, robustfuzzy C-means

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1821

Authors: Raif Parlakkaya, Ahmet Diken, Erkan Kara

Abstract:

This paper examines the relationship between corporate governance rating and stock prices of 26 Turkish firms listed in Turkish stock exchange (Borsa Istanbul) by using panel data analysis over five-year period. The paper also investigates the stock performance of firms with governance rating with regards to the market portfolio (i.e. BIST 100 Index) both prior and after governance scoring began. The empirical results show that there is no relation between corporate governance rating and stock prices when using panel data for annual variation in both rating score and stock prices. Further analysis indicates surprising results that while the selected firms outperform the market significantly prior to rating, the same performance does not continue afterwards.

Keywords: Corporate governance, stock price, performance, panel data analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2525

Authors: Dmitry V. Fomichev, Vladimir I. Solonin

Abstract:

This paper presents the findings from a numerical simulation of the flow in 37-rod fuel assembly models spaced by a double-wire trapezoidal wrapping as applied to the BREST-OD-300 experimental nuclear reactor. Data on a high static pressure distribution within the models, and equations for determining the fuel bundle flow friction factors have been obtained. Recommendations are provided on using the closing turbulence models available in the ANSYS Fluent. A comparative analysis has been performed against the existing empirical equations for determining the flow friction factors. The calculated and experimental data fit has been shown.

An analysis into the experimental data and results of the numerical simulation of the BREST-OD-300 fuel rod assembly hydrodynamic performance are presented.

Keywords: BREST-OD-300, ware-spaces, fuel assembly, computation fluid dynamics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2226

Authors: Sándor Juhász, Renáta Iváncsy

Abstract:

This paper describes an enhanced cookie-based method for counting the visitors of web sites by using a web log processing system that aims to cope with the ambitious goal of creating countrywide statistics about the browsing practices of real human individuals. The focus is put on describing a new more efficient way of detecting human beings behind web users by placing different identifiers on the client computers. We briefly introduce our processing system designed to handle the massive amount of data records continuously gathered from the most important content providers of the Hungary. We conclude by showing statistics of different time spans comparing the efficiency of multiple visitor counting methods to the one presented here, and some interesting charts about content providers and web usage based on real data recorded in 2007 will also be presented.

Keywords: Cookie based identification, real data, user activitytracking, web auditing, web log processing

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1312

Authors: Amit Sachan

Abstract:

The network designing and data modeling developments which are the two significant research tasks in direction to tolerate power control of Microgrid concluded using IEC 61850 data models and facilities. The current casing areas of IEC 61580 include infrastructures in substation automation systems, among substations and to DERs. So, for LV microgrid power control, previously using the IEC 61850 amenities to control the smart electrical devices, we have to model those devices as IEC 61850 data models and design a network topology to maintenance all-in-one communiqué amid those devices. In adding, though IEC 61850 assists modeling a portion by open-handed several object models for common functions similar measurement, metering, monitoring…etc., there are motionless certain missing smithereens for building a multiplicity of functions for household appliances like tuning the temperature of an electric heater or refrigerator.

Keywords: IEC 61850, RCMC, HCMC, DER Unit Controller.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2497

Authors: S. Bourennane, A. Bendjama

Abstract:

This paper deals with the localization of the wideband sources. We develop a new approach for estimating the wide band sources parameters. This method is based on the high order statistics of the recorded data in order to eliminate the Gaussian components from the signals received on the various hydrophones.In fact the noise of sea bottom is regarded as being Gaussian. Thanks to the coherent signal subspace algorithm based on the cumulant matrix of the received data instead of the cross-spectral matrix the wideband correlated sources are perfectly located in the very noisy environment. We demonstrate the performance of the proposed algorithm on the real data recorded during an underwater acoustics experiments.

Keywords: Higher-order statistics, high resolution array processing techniques, localization of acoustics sources, wide band sources.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1597

Authors: Chia-Hau Liu, Tai-Yue Wang

Abstract:

Traditional multivariate control charts assume that measurement from manufacturing processes follows a multivariate normal distribution. However, this assumption may not hold or may be difficult to verify because not all the measurement from manufacturing processes are normal distributed in practice. This study develops a new multivariate control chart for monitoring the processes with non-normal data. We propose a mechanism based on integrating the one-class classification method and the adaptive technique. The adaptive technique is used to improve the sensitivity to small shift on one-class classification in statistical process control. In addition, this design provides an easy way to allocate the value of type I error so it is easier to be implemented. Finally, the simulation study and the real data from industry are used to demonstrate the effectiveness of the propose control charts.

Keywords: Multivariate control chart, statistical process control, one-class classification method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2268

Authors: Isti Surjandari, Riara Novita

Abstract:

Maintenance is one of the most important activities in the shipyard industry. However, sometimes it is not supported by adequate services from the shipyard, where inaccuracy in estimating the duration of the ship maintenance is still common. This makes estimation of ship maintenance duration is crucial. This study uses Data Mining approach, i.e., CART (Classification and Regression Tree) to estimate the duration of ship maintenance that is limited to dock works or which is known as dry docking. By using the volume of dock works as an input to estimate the maintenance duration, 4 classes of dry docking duration were obtained with different linear model and job criteria for each class. These linear models can then be used to estimate the duration of dry docking based on job criteria.

Keywords: Classification and regression tree (CART), data mining, dry docking, maintenance duration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2432

Authors: Ching Louis Liu, Edmund Kazmierczak, Tim Miller

Abstract:

Safety analysis for multi-agent systems is complicated by the, potentially nonlinear, interactions between agents. This paper proposes a method for analyzing the safety of multi-agent systems by explicitly focusing on interactions and the accident data of systems that are similar in structure and function to the system being analyzed. The method creates a Bayesian network using the accident data from similar systems. A feature of our method is that the events in accident data are labeled with HAZOP guide words. Our method uses an Ontology to abstract away from the details of a multi-agent implementation. Using the ontology, our methods then constructs an “Interaction Map,” a graphical representation of the patterns of interactions between agents and other artifacts. Interaction maps combined with statistical data from accidents and the HAZOP classifications of events can be converted into a Bayesian Network. Bayesian networks allow designers to explore “what it” scenarios and make design trade-offs that maintain safety. We show how to use the Bayesian networks, and the interaction maps to improve multi-agent system designs.

Keywords: Multi-agent system, safety analysis, safety model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1086

Authors: Jihyung Kim, Taejin Kim, Sungho Park, Jun-Dong Cho

Abstract:

In this paper, we address the problem of reducing the switching activity (SA) in on-chip buses through the use of a bus binding technique in high-level synthesis. While many binding techniques to reduce the SA exist, we present yet another technique for further reducing the switching activity. Our proposed method combines bus binding and data sequence reordering to explore a wider solution space. The problem is formulated as a multiple traveling salesman problem and solved using simulated annealing technique. The experimental results revealed that a binding solution obtained with the proposed method reduces 5.6-27.2% (18.0% on average) and 2.6-12.7% (6.8% on average) of the switching activity when compared with conventional binding-only and hybrid binding-encoding methods, respectively.

Keywords: low power, bus binding, switching activity, multiple traveling salesman problem, data sequence reordering

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1332

Authors: Ifeyinwa E. Achumba, Djamel Azzi, Rinat Khusainov

Abstract:

There are three approaches to complete Bayesian Network (BN) model construction: total expert-centred, total datacentred, and semi data-centred. These three approaches constitute the basis of the empirical investigation undertaken and reported in this paper. The objective is to determine, amongst these three approaches, which is the optimal approach for the construction of a BN-based model for the performance assessment of students- laboratory work in a virtual electronic laboratory environment. BN models were constructed using all three approaches, with respect to the focus domain, and compared using a set of optimality criteria. In addition, the impact of the size and source of the training, on the performance of total data-centred and semi data-centred models was investigated. The results of the investigation provide additional insight for BN model constructors and contribute to literature providing supportive evidence for the conceptual feasibility and efficiency of structure and parameter learning from data. In addition, the results highlight other interesting themes.

Keywords: Bayesian networks, model construction, parameterlearning, structure learning, performance index, model comparison.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1726

Authors: M. Sitoe, O. Zacarias

Abstract:

University education is influenced by several factors that range from the adoption of strategies to strengthen the whole process to the academic performance improvement of the students themselves. This work uses data mining techniques to develop a predictive model to identify students with a tendency to evasion and retention. To this end, a database of real students’ data from the Department of University Admission (DAU) and the Department of Mathematics and Informatics (DMI) was used. The data comprised 388 undergraduate students admitted in the years 2009 to 2014. The Weka tool was used for model building, using three different techniques, namely: K-nearest neighbor, random forest, and logistic regression. To allow for training on multiple train-test splits, a cross-validation approach was employed with a varying number of folds. To reduce bias variance and improve the performance of the models, ensemble methods of Bagging and Stacking were used. After comparing the results obtained by the three classifiers, Logistic Regression using Bagging with seven folds obtained the best performance, showing results above 90% in all evaluated metrics: accuracy, rate of true positives, and precision. Retention is the most common tendency.

Keywords: Evasion and retention, cross validation, bagging, stacking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 118

Authors: Anatoli Torokhti, Stan Miklavcic

Abstract:

We study a new technique for optimal data compression subject to conditions of causality and different types of memory. The technique is based on the assumption that some information about compressed data can be obtained from a solution of the associated problem without constraints of causality and memory. This allows us to consider two separate problem related to compression and decompression subject to those constraints. Their solutions are given and the analysis of the associated errors is provided.

Keywords: stochastic signals, optimization problems in signal processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1330

Authors: Rafat Alshorman, Walter Hussak

Abstract:

Existing work in temporal logic on representing the execution of infinitely many transactions, uses linear-time temporal logic (LTL) and only models two-step transactions. In this paper, we use the comparatively efficient branching-time computational tree logic CTL and extend the transaction model to a class of multistep transactions, by introducing distinguished propositional variables to represent the read and write steps of n multi-step transactions accessing m data items infinitely many times. We prove that the well known correspondence between acyclicity of conflict graphs and serializability for finite schedules, extends to infinite schedules. Furthermore, in the case of transactions accessing the same set of data items in (possibly) different orders, serializability corresponds to the absence of cycles of length two. This result is used to give an efficient encoding of the serializability condition into CTL.

Keywords: computational tree logic, serializability, multi-step transactions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1175

Authors: Jack R. McKenzie, Peter A. Appleby, Thomas House, Neil Walton

Abstract:

Cold-start is a notoriously difficult problem which can occur in recommendation systems, and arises when there is insufficient information to draw inferences for users or items. To address this challenge, a contextual bandit algorithm – the Fast Approximate Bayesian Contextual Cold Start Learning algorithm (FAB-COST) – is proposed, which is designed to provide improved accuracy compared to the traditionally used Laplace approximation in the logistic contextual bandit, while controlling both algorithmic complexity and computational cost. To this end, FAB-COST uses a combination of two moment projection variational methods: Expectation Propagation (EP), which performs well at the cold start, but becomes slow as the amount of data increases; and Assumed Density Filtering (ADF), which has slower growth of computational cost with data size but requires more data to obtain an acceptable level of accuracy. By switching from EP to ADF when the dataset becomes large, it is able to exploit their complementary strengths. The empirical justification for FAB-COST is presented, and systematically compared to other approaches on simulated data. In a benchmark against the Laplace approximation on real data consisting of over 670, 000 impressions from autotrader.co.uk, FAB-COST demonstrates at one point increase of over 16% in user clicks. On the basis of these results, it is argued that FAB-COST is likely to be an attractive approach to cold-start recommendation systems in a variety of contexts.

Keywords: Cold-start, expectation propagation, multi-armed bandits, Thompson sampling, variational inference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 550

Authors: K. Abuzayan, H. Alabed, K. Zarug

Abstract:

The objectives of this study (baseline study, n = 20) were to implement Matlab procedures for quantifying selected static  balance variables, establish baseline data of selected variables which characterize static balance activities in a population of healthy young adult males, and to examine any trial effects on these variables. The results indicated that the implementation of Matlab procedures for quantifying selected static balance variables was practical and enabled baseline data to be established for selected variables. There was no significant trial effect. Recommendations were made for suitable tests to be used in later studies. Specifically it was found that one foot-tiptoes tests either in static balance is too challenging for most participants in normal circumstances. A one foot-flat eyes open test was considered to be representative and challenging for static balance.

Keywords: Static Balance, Base of support, Baseline Data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1812

Authors: Shiuh-Jer Huang, Chen-Zon Yan, C. K. Huang, Chun-Chien Ting

Abstract:

Since the vision system application in industrial environment for autonomous purposes is required intensely, the image recognition technique becomes an important research topic. Here, deep learning algorithm is employed in image system to recognize the industrial object and integrate with a 7A6 Series Manipulator for object automatic gripping task. PC and Graphic Processing Unit (GPU) are chosen to construct the 3D Vision Recognition System. Depth Camera (Intel RealSense SR300) is employed to extract the image for object recognition and coordinate derivation. The YOLOv2 scheme is adopted in Convolution neural network (CNN) structure for object classification and center point prediction. Additionally, image processing strategy is used to find the object contour for calculating the object orientation angle. Then, the specified object location and orientation information are sent to robotic controller. Finally, a six-axis manipulator can grasp the specific object in a random environment based on the user command and the extracted image information. The experimental results show that YOLOv2 has been successfully employed to detect the object location and category with confidence near 0.9 and 3D position error less than 0.4 mm. It is useful for future intelligent robotic application in industrial 4.0 environment.

Keywords: Deep learning, image processing, convolution neural network, YOLOv2, 7A6 series manipulator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1093

Authors: María-Dolores Cubiles-de-la-Vega, Rafael Pino-Mejías, Esther-Lydia Silva-Ramírez

Abstract:

A dissimilarity measure between the empiric characteristic functions of the subsamples associated to the different classes in a multivariate data set is proposed. This measure can be efficiently computed, and it depends on all the cases of each class. It may be used to find groups of similar classes, which could be joined for further analysis, or it could be employed to perform an agglomerative hierarchical cluster analysis of the set of classes. The final tree can serve to build a family of binary classification models, offering an alternative approach to the multi-class SVM problem. We have tested this dendrogram based SVM approach with the oneagainst- one SVM approach over four publicly available data sets, three of them being microarray data. Both performances have been found equivalent, but the first solution requires a smaller number of binary SVM models.

Keywords: Cluster Analysis, Empiric Characteristic Function, Multi-class SVM, R.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1876

Authors: N. Gigauri, V. Kukhalashvili, A. Surmava, L. Intskirveli, L. Gverdtsiteli

Abstract:

Tbilisi, a large city of the South Caucasus, is a junction point connecting Asia and Europe, Russia and republics of the Asia Minor. Over the last years, its atmosphere has been experienced an increasing anthropogenic load. Numerical modeling method is used for study of Tbilisi atmospheric air pollution. By means of 3D non-linear non-steady numerical model a peculiarity of city atmosphere pollution is investigated during background western light air. Dust concentration spatial and time changes are determined. There are identified the zones of high, average and less pollution, dust accumulation areas, transfer directions etc. By numerical modeling, there is shown that the process of air pollution by the dust proceeds in four stages, and they depend on the intensity of motor traffic, the micro-relief of the city, and the location of city mains. In the interval of time 06:00-09:00 the intensive growth, 09:00-15:00 a constancy or weak decrease, 18:00-21:00 an increase, and from 21:00 to 06:00 a reduction of the dust concentrations take place. The highly polluted areas are located in the vicinity of the city center and at some peripherical territories of the city, where the maximum dust concentration at 9PM is equal to 2 maximum allowable concentrations. The similar investigations conducted in case of various meteorological situations will enable us to compile the map of background urban pollution and to elaborate practical measures for ambient air protection.

Keywords: Numerical modelling, source of pollution, dust propagation, western light air.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 488

Authors: Nasser M. Amaitik, Nabil A. Alfagi

Abstract:

The world-s largest Pre-stressed Concrete Cylinder Pipe (PCCP) water supply project had a series of pipe failures which occurred between 1999 and 2001. This has led the Man-Made River Authority (MMRA), the authority in charge of the implementation and operation of the project, to setup a rehabilitation plan for the conveyance system while maintaining the uninterrupted flow of water to consumers. At the same time, MMRA recognized the need for a long term management tool that would facilitate repair and maintenance decisions and enable taking the appropriate preventive measures through continuous monitoring and estimation of the remaining life of each pipe. This management tool is known as the Pipe Risk Management System (PRMS) and now in operation at MMRA. Both the rehabilitation plan and the PRMS require the availability of complete and accurate pipe construction and manufacturing data This paper describes a systematic approach of data collection, analysis, evaluation and correction for the construction and manufacturing data files of phase I pipes which are the platform for the PRMS database and any other related decision support system.

Keywords: Asbuilt, History, IMD, MMRA, PDBMS & PRMS

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2013