Search results for: neural machine translation
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 2416

Search results for: neural machine translation

316 Classification of Political Affiliations by Reduced Number of Features

Authors: Vesile Evrim, Aliyu Awwal

Abstract:

By the evolvement in technology, the way of expressing opinions switched direction to the digital world. The domain of politics, as one of the hottest topics of opinion mining research, merged together with the behavior analysis for affiliation determination in texts, which constitutes the subject of this paper. This study aims to classify the text in news/blogs either as Republican or Democrat with the minimum number of features. As an initial set, 68 features which 64 were constituted by Linguistic Inquiry and Word Count (LIWC) features were tested against 14 benchmark classification algorithms. In the later experiments, the dimensions of the feature vector reduced based on the 7 feature selection algorithms. The results show that the “Decision Tree”, “Rule Induction” and “M5 Rule” classifiers when used with “SVM” and “IGR” feature selection algorithms performed the best up to 82.5% accuracy on a given dataset. Further tests on a single feature and the linguistic based feature sets showed the similar results. The feature “Function”, as an aggregate feature of the linguistic category, was found as the most differentiating feature among the 68 features with the accuracy of 81% in classifying articles either as Republican or Democrat.

Keywords: Politics, machine learning, feature selection, LIWC.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2374
315 User-Based Cannibalization Mitigation in an Online Marketplace

Authors: Vivian Guo, Yan Qu

Abstract:

Online marketplaces are not only digital places where consumers buy and sell merchandise, and they are also destinations for brands to connect with real consumers at the moment when customers are in the shopping mindset. For many marketplaces, brands have been important partners through advertising. There can be, however, a risk of advertising impacting a consumer’s shopping journey if it hurts the use experience or takes the user away from the site. Both could lead to the loss of transaction revenue for the marketplace. In this paper, we present user-based methods for cannibalization control by selectively turning off ads to users who are likely to be cannibalized by ads subject to business objectives. We present ways of measuring cannibalization of advertising in the context of an online marketplace and propose novel ways of measuring cannibalization through purchase propensity and uplift modeling. A/B testing has shown that our methods can significantly improve user purchase and engagement metrics while operating within business objectives. To our knowledge, this is the first paper that addresses cannibalization mitigation at the user-level in the context of advertising.

Keywords: Cannibalization, machine learning, online marketplace, revenue optimization, yield optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 913
314 Influence of Active Packaging on the Shelf Life of Apple-Black Currant Marmalade Candies

Authors: Sandra Muizniece-Brasava, Lija Dukalska, Solvita Kampuse, Irisa Murniece, Martins Sabovics, IlonaDabina-Bicka, Emils Kozlinskis, Svetlana Sarvi

Abstract:

The research object was apple-black currant marmalade candies. Experiments were carried out at the Faculty of Food Technology of the Latvia University of Agriculture. An active packaging in combination with modified atmosphere (MAP, CO2 100%) was examined and compared with traditional packaging in air ambiance. Polymer Multibarrier 60 and paper bags were used. Influence of iron based oxygen absorber in sachets of 500 cc obtained from Mitsubishi Gas Chemical Europe Ageless® was tested on the quality during the shelf of marmalade. Samples of 80±5 g were packaged in polymer pouches (110 mm x 110 mm), hermetically sealed by MULTIVAC C300 vacuum chamber machine, and stored in room temperature +20.0±1.0 °C. The physiochemical properties – weight losses, moisture content, hardness, aw, pH, colour, changes of atmosphere content (CO2 and O2) in headspace of packs, and microbial conditions were analysed before packaging and in the 1st, 3rd , 5th, 8th, 11th and 15th weeks of storage.

Keywords: Active packaging, marmalade candies, shelf life

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2378
313 Analysis of Mechanical Properties for AP/HTPB Solid Propellant under Different Loading Conditions

Authors: Walid M. Adel, Liang Guo-Zhu

Abstract:

To investigate the characterization of the mechanical properties of composite solid propellant (CSP) based on hydroxyl-terminated polybutadiene (HTPB) at different temperatures and strain rates, uniaxial tensile tests were conducted over a range of temperatures -60 °C to +76 °C and strain rates 0.000164 to 0.328084 s-1 using a conventional universal testing machine. From the experimental data, it can be noted that the mechanical properties of AP/HTPB propellant are mainly dependent on the applied strain rate and the temperature condition. The stress-strain responses exhibited an initial yielding followed by the viscoelastic phase, which was strongly affected by the strain rate and temperature. It was found that the mechanical properties increased with both increasing strain rate and decreasing temperature. Based on the experimental tests, the master curves of the tensile properties are drawn using predetermined shift factor and the results were discussed. This work is a first step in preliminary investigation the nonlinear viscoelasticity behavior of CSP.

Keywords: AP/HTPB composite solid propellant, mechanical behavior, nonlinear viscoelastic, tensile test, master curves.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2062
312 Locating Center Points for Radial Basis Function Networks Using Instance Reduction Techniques

Authors: Rana Yousef, Khalil el Hindi

Abstract:

The behavior of Radial Basis Function (RBF) Networks greatly depends on how the center points of the basis functions are selected. In this work we investigate the use of instance reduction techniques, originally developed to reduce the storage requirements of instance based learners, for this purpose. Five Instance-Based Reduction Techniques were used to determine the set of center points, and RBF networks were trained using these sets of centers. The performance of the RBF networks is studied in terms of classification accuracy and training time. The results obtained were compared with two Radial Basis Function Networks: RBF networks that use all instances of the training set as center points (RBF-ALL) and Probabilistic Neural Networks (PNN). The former achieves high classification accuracies and the latter requires smaller training time. Results showed that RBF networks trained using sets of centers located by noise-filtering techniques (ALLKNN and ENN) rather than pure reduction techniques produce the best results in terms of classification accuracy. The results show that these networks require smaller training time than that of RBF-ALL and higher classification accuracy than that of PNN. Thus, using ALLKNN and ENN to select center points gives better combination of classification accuracy and training time. Our experiments also show that using the reduced sets to train the networks is beneficial especially in the presence of noise in the original training sets.

Keywords: Radial basis function networks, Instance-based reduction, PNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1695
311 Reducing SAGE Data Using Genetic Algorithms

Authors: Cheng-Hong Yang, Tsung-Mu Shih, Li-Yeh Chuang

Abstract:

Serial Analysis of Gene Expression is a powerful quantification technique for generating cell or tissue gene expression data. The profile of the gene expression of cell or tissue in several different states is difficult for biologists to analyze because of the large number of genes typically involved. However, feature selection in machine learning can successfully reduce this problem. The method allows reducing the features (genes) in specific SAGE data, and determines only relevant genes. In this study, we used a genetic algorithm to implement feature selection, and evaluate the classification accuracy of the selected features with the K-nearest neighbor method. In order to validate the proposed method, we used two SAGE data sets for testing. The results of this study conclusively prove that the number of features of the original SAGE data set can be significantly reduced and higher classification accuracy can be achieved.

Keywords: Serial Analysis of Gene Expression, Feature selection, Genetic Algorithm, K-nearest neighbor method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1617
310 Design of an Intelligent Location Identification Scheme Based On LANDMARC and BPNs

Authors: S. Chaisit, H.Y. Kung, N.T. Phuong

Abstract:

Radio frequency identification (RFID) applications have grown rapidly in many industries, especially in indoor location identification. The advantage of using received signal strength indicator (RSSI) values as an indoor location measurement method is a cost-effective approach without installing extra hardware. Because the accuracy of many positioning schemes using RSSI values is limited by interference factors and the environment, thus it is challenging to use RFID location techniques based on integrating positioning algorithm design. This study proposes the location estimation approach and analyzes a scheme relying on RSSI values to minimize location errors. In addition, this paper examines different factors that affect location accuracy by integrating the backpropagation neural network (BPN) with the LANDMARC algorithm in a training phase and an online phase. First, the training phase computes coordinates obtained from the LANDMARC algorithm, which uses RSSI values and the real coordinates of reference tags as training data for constructing an appropriate BPN architecture and training length. Second, in the online phase, the LANDMARC algorithm calculates the coordinates of tracking tags, which are then used as BPN inputs to obtain location estimates. The results show that the proposed scheme can estimate locations more accurately compared to LANDMARC without extra devices.

Keywords: BPNs, indoor location, location estimation, intelligent location identification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2019
309 Hydrodynamic Characteristics of Weis–Fogh Type Ship-s Propulsion Mechanism Having Elastic Wing

Authors: K. D. Ro, J. T. Park, J. H. Kim

Abstract:

This experiment was conducted in attempt of improving hydrodynamic efficiency of the propulsion mechanism by installing a spring to the wing so that the opening angle of the wing in one stroke can be changed automatically, compared to the existing method of fixed maximum opening angle in Weis-Fogh type ship propulsion mechanism. Average thrust coefficient was almost fixed with all velocity ratio with the prototype, but with the spring type, thrust coefficient increased sharply as velocity ratio increased. Average propulsive efficiency was larger with bigger opening angle in the prototype, but in the spring type, the one with smaller spring coefficient had larger value. In the range over 1.0 in velocity ratio where big thrust can be generated, spring type had more than twice of propulsive efficiency increase compared to the prototype.

Keywords: Hydraulic Machine, Propulsion Mechanism, FluidForce, Elastic Wing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1369
308 Feature-Based Summarizing and Ranking from Customer Reviews

Authors: Dim En Nyaung, Thin Lai Lai Thein

Abstract:

Due to the rapid increase of Internet, web opinion sources dynamically emerge which is useful for both potential customers and product manufacturers for prediction and decision purposes. These are the user generated contents written in natural languages and are unstructured-free-texts scheme. Therefore, opinion mining techniques become popular to automatically process customer reviews for extracting product features and user opinions expressed over them. Since customer reviews may contain both opinionated and factual sentences, a supervised machine learning technique applies for subjectivity classification to improve the mining performance. In this paper, we dedicate our work is the task of opinion summarization. Therefore, product feature and opinion extraction is critical to opinion summarization, because its effectiveness significantly affects the identification of semantic relationships. The polarity and numeric score of all the features are determined by Senti-WordNet Lexicon. The problem of opinion summarization refers how to relate the opinion words with respect to a certain feature. Probabilistic based model of supervised learning will improve the result that is more flexible and effective.

Keywords: Opinion Mining, Opinion Summarization, Sentiment Analysis, Text Mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2940
307 Multiclass Support Vector Machines with Simultaneous Multi-Factors Optimization for Corporate Credit Ratings

Authors: Hyunchul Ahn, William X. S. Wong

Abstract:

Corporate credit rating prediction is one of the most important topics, which has been studied by researchers in the last decade. Over the last decade, researchers are pushing the limit to enhance the exactness of the corporate credit rating prediction model by applying several data-driven tools including statistical and artificial intelligence methods. Among them, multiclass support vector machine (MSVM) has been widely applied due to its good predictability. However, heuristics, for example, parameters of a kernel function, appropriate feature and instance subset, has become the main reason for the critics on MSVM, as they have dictate the MSVM architectural variables. This study presents a hybrid MSVM model that is intended to optimize all the parameter such as feature selection, instance selection, and kernel parameter. Our model adopts genetic algorithm (GA) to simultaneously optimize multiple heterogeneous design factors of MSVM.

Keywords: Corporate credit rating prediction, feature selection, genetic algorithms, instance selection, multiclass support vector machines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1416
306 Unstructured-Data Content Search Based on Optimized EEG Signal Processing and Multi-Objective Feature Extraction

Authors: Qais M. Yousef, Yasmeen A. Alshaer

Abstract:

Over the last few years, the amount of data available on the globe has been increased rapidly. This came up with the emergence of recent concepts, such as the big data and the Internet of Things, which have furnished a suitable solution for the availability of data all over the world. However, managing this massive amount of data remains a challenge due to their large verity of types and distribution. Therefore, locating the required file particularly from the first trial turned to be a not easy task, due to the large similarities of names for different files distributed on the web. Consequently, the accuracy and speed of search have been negatively affected. This work presents a method using Electroencephalography signals to locate the files based on their contents. Giving the concept of natural mind waves processing, this work analyses the mind wave signals of different people, analyzing them and extracting their most appropriate features using multi-objective metaheuristic algorithm, and then classifying them using artificial neural network to distinguish among files with similar names. The aim of this work is to provide the ability to find the files based on their contents using human thoughts only. Implementing this approach and testing it on real people proved its ability to find the desired files accurately within noticeably shorter time and retrieve them as a first choice for the user.

Keywords: Artificial intelligence, data contents search, human active memory, mind wave, multi-objective optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 928
305 Effect of Vibration Amplitude and Welding Force on Weld Strength of Ultrasonic Metal Welding

Authors: Ziad. Sh. Al Sarraf

Abstract:

Ultrasonic metal welding has been the subject of ongoing research and development, most recently concentrating on metal joining in miniature devices, for example to allow solder-free wire bonding. As well as at the small scale, there are also opportunities to research the joining of thicker sheet metals and to widen the range of similar and dissimilar materials that can be successfully joined using this technology. This study presents the design, characterisation and test of a lateral-drive ultrasonic metal spot welding device. The ultrasonic metal spot welding horn is modelled using finite element analysis (FEA) and its vibration behaviour is characterised experimentally to ensure ultrasonic energy is delivered effectively to the weld coupon. The welding stack and fixtures are then designed and mounted on a test machine to allow a series of experiments to be conducted for various welding and ultrasonic parameters. Weld strength is subsequently analysed using tensile-shear tests. The results show how the weld strength is particularly sensitive to the combination of clamping force and ultrasonic vibration amplitude of the welding tip, but there are optimal combinations of these and also limits that must be clearly identified.

Keywords: Ultrasonic welding, vibration amplitude, welding force, weld strength.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2197
304 Adaptive Educational Hypermedia System for High School Students Based on Learning Styles

Authors: Stephen Akuma, Timothy Ndera

Abstract:

Information seekers get “lost in hyperspace” due to the voluminous documents updated daily on the internet. Adaptive Hypermedia Systems (AHS) are used to direct learners to their target goals. One of the most common AHS designed to help information seekers to overcome the problem of information overload is the Adaptive Education Hypermedia System (AEHS). However, this paper focuses on AEHS that adopts the learning preference of high school students and deliver learning content according to this preference throughout their learning experience. The research developed a prototype system for predicting students’ learning preference from the Visual, Aural, Read-Write and Kinesthetic (VARK) learning style model and adopting the learning content suitable to their preference. The predicting strength of several classifiers was compared and we found Support Vector Machine (SVM) to be more accurate in predicting learning style based on users’ preferences.

Keywords: Hypermedia, adaptive education, learning style, lesson content, user profile, prediction, feedback, adaptive hypermedia, learning style.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 862
303 Enhance the Power of Sentiment Analysis

Authors: Yu Zhang, Pedro Desouza

Abstract:

Since big data has become substantially more accessible and manageable due to the development of powerful tools for dealing with unstructured data, people are eager to mine information from social media resources that could not be handled in the past. Sentiment analysis, as a novel branch of text mining, has in the last decade become increasingly important in marketing analysis, customer risk prediction and other fields. Scientists and researchers have undertaken significant work in creating and improving their sentiment models. In this paper, we present a concept of selecting appropriate classifiers based on the features and qualities of data sources by comparing the performances of five classifiers with three popular social media data sources: Twitter, Amazon Customer Reviews, and Movie Reviews. We introduced a couple of innovative models that outperform traditional sentiment classifiers for these data sources, and provide insights on how to further improve the predictive power of sentiment analysis. The modeling and testing work was done in R and Greenplum in-database analytic tools.

Keywords: Sentiment Analysis, Social Media, Twitter, Amazon, Data Mining, Machine Learning, Text Mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3525
302 An Edge-based Text Region Extraction Algorithm for Indoor Mobile Robot Navigation

Authors: Jagath Samarabandu, Xiaoqing Liu

Abstract:

Using bottom-up image processing algorithms to predict human eye fixations and extract the relevant embedded information in images has been widely applied in the design of active machine vision systems. Scene text is an important feature to be extracted, especially in vision-based mobile robot navigation as many potential landmarks such as nameplates and information signs contain text. This paper proposes an edge-based text region extraction algorithm, which is robust with respect to font sizes, styles, color/intensity, orientations, and effects of illumination, reflections, shadows, perspective distortion, and the complexity of image backgrounds. Performance of the proposed algorithm is compared against a number of widely used text localization algorithms and the results show that this method can quickly and effectively localize and extract text regions from real scenes and can be used in mobile robot navigation under an indoor environment to detect text based landmarks.

Keywords: Landmarks, mobile robot navigation, scene text, text localization and extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2934
301 Design, Simulation and Experimental Realization of Nonlinear Controller for GSC of DFIG System

Authors: R.K. Behera, S.Behera

Abstract:

In a wind power generator using doubly fed induction generator (DFIG), the three-phase pulse width modulation (PWM) voltage source converter (VSC) is used as grid side converter (GSC) and rotor side converter (RSC). The standard linear control laws proposed for GSC provides not only instablity against comparatively large-signal disturbances, but also the problem of stability due to uncertainty of load and variations in parameters. In this paper, a nonlinear controller is designed for grid side converter (GSC) of a DFIG for wind power application. The nonlinear controller is designed based on the input-output feedback linearization control method. The resulting closed-loop system ensures a sufficient stability region, make robust to variations in circuit parameters and also exhibits good transient response. Computer simulations and experimental results are presented to confirm the effectiveness of the proposed control strategy.

Keywords: Doubly fed Induction Generator, grid side converter, machine side converter, dc link, feedback linearization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2131
300 Acceleration Analysis of a Rotating Body

Authors: R. Usubamatov

Abstract:

The velocity of a moving point in a general path is the vector quantity, which has both magnitude and direction. The magnitude or the direction of the velocity vector can change over time as a result of acceleration that the time rate of velocity changes. Acceleration analysis is important because inertial forces and inertial torques are proportional to rectilinear and angular accelerations accordingly. The loads must be determined in advance to ensure that a machine is adequately designed to handle these dynamic loads. For planar motion, the vector direction of acceleration is commonly separated into two elements: tangential and centripetal or radial components of a point on a rotating body. All textbooks in physics, kinematics and dynamics of machinery consider the magnitude of a radial acceleration at condition when a point rotates with a constant angular velocity and it means without acceleration. The magnitude of the tangential acceleration considered on a basis of acceleration for a rotating point. Such condition of presentation of magnitudes for two components of acceleration logically and mathematically is not correct and may cause further confusion in calculation. This paper presents new analytical expressions of the radial and absolute accelerations of a rotating point with acceleration and covers the gap in theoretical study of acceleration analysis.

Keywords: acceleration analysis, kinematics of mechanisms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2702
299 Improvement of GVPI Insulation System Characteristics by Curing Process Modification

Authors: M. Shadmand

Abstract:

The curing process of insulation system for electrical machines plays a determinative role for its durability and reliability. Polar structure of insulating resin molecules and used filler of insulation system can be taken as an occasion to leverage it to enhance overall characteristics of insulation system, mechanically and electrically. The curing process regime for insulating system plays an important role for its mechanical and electrical characteristics by arranging the polymerization of chain structure for resin. In this research, the effect of electrical field application on in-curing insulating system for Global Vacuum Pressurized Impregnation (GVPI) system for traction motor was considered by performing the dissipation factor, polarization and de-polarization current (PDC) and voltage endurance (aging) measurements on sample test objects. Outcome results depicted obvious improvement in mechanical strength of the insulation system as well as higher electrical characteristics with routing and long-time (aging) electrical tests. Coming together, polarization of insulation system during curing process would enhance the machine life time. 

Keywords: Insulation system, GVPI, PDC, aging.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1097
298 Evolution of Fashion Design in the Era of High-Tech Culture

Authors: Galina Mihaleva, C. Koh

Abstract:

Fashion, like many other design fields, undergoes numerous evolutions throughout the ages. This paper aims to recognize and evaluate the significance of advance technology in fashion design and examine how it changes the role of modern fashion designers by modifying the creation process. It also touches on how modern culture is involved in such developments and how it affects fashion design in terms of conceptualizing and fabrication. The methodology used is through surveying the various examples of technological applications to fashion design and drawing parallels between what was achievable then and what is achievable now. By comparing case studies, existing fashion design examples and crafting method experimentations; we then spot patterns in which to predict the direction of future developments in the field. A breakdown on the elements of technology in fashion design helps us understand the driving force behind such a trend. The results from explorations in the paper have shown that there is an observed pattern of a distinct increase in interest and progress in the field of fashion technology, which leads to the birth of hybrid crafting methods. In conclusion, it is shown that as fashion technology continues to evolve, their role in clothing crafting becomes more prominent and grows far beyond the humble sewing machine.

Keywords: Fashion design, functional aesthetics, smart textiles, 3D printing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4105
297 Categorizing Search Result Records Using Word Sense Disambiguation

Authors: R. Babisaraswathi, N. Shanthi, S. S. Kiruthika

Abstract:

Web search engines are designed to retrieve and extract the information in the web databases and to return dynamic web pages. The Semantic Web is an extension of the current web in which it includes semantic content in web pages. The main goal of semantic web is to promote the quality of the current web by changing its contents into machine understandable form. Therefore, the milestone of semantic web is to have semantic level information in the web. Nowadays, people use different keyword- based search engines to find the relevant information they need from the web. But many of the words are polysemous. When these words are used to query a search engine, it displays the Search Result Records (SRRs) with different meanings. The SRRs with similar meanings are grouped together based on Word Sense Disambiguation (WSD). In addition to that semantic annotation is also performed to improve the efficiency of search result records. Semantic Annotation is the process of adding the semantic metadata to web resources. Thus the grouped SRRs are annotated and generate a summary which describes the information in SRRs. But the automatic semantic annotation is a significant challenge in the semantic web. Here ontology and knowledge based representation are used to annotate the web pages.

Keywords: Ontology, Semantic Web, WordNet, Word Sense Disambiguation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1771
296 Quasi Multi-Pulse Back-to-Back Static Synchronous Compensator Employing Line Frequency Switching 2-Level GTO Inverters

Authors: A.M. Vural, K.C. Bayindir

Abstract:

Back-to-back static synchronous compensator (BtBSTATCOM) consists of two back-to-back voltage-source converters (VSC) with a common DC link in a substation. This configuration extends the capabilities of conventional STATCOM that bidirectional active power transfer from one bus to another is possible. In this paper, VSCs are designed in quasi multi-pulse form in which GTOs are triggered only once per cycle in PSCAD/EMTDC. The design details of VSCs as well as gate switching circuits and controllers are fully represented. Regulation modes of BtBSTATCOM are verified and tested on a multi-machine power system through different simulation cases. The results presented in the form of typical time responses show that practical PI controllers are almost robust and stable in case of start-up, set-point change, and line faults.

Keywords: Flexible AC Transmission Systems (FACTS), Backto-Back Static Synchronous Compensator (BtB-STATCOM), quasi multi-pulse voltage source converter, active power transfer; voltage control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2158
295 Customer Need Type Classification Model using Data Mining Techniques for Recommender Systems

Authors: Kyoung-jae Kim

Abstract:

Recommender systems are usually regarded as an important marketing tool in the e-commerce. They use important information about users to facilitate accurate recommendation. The information includes user context such as location, time and interest for personalization of mobile users. We can easily collect information about location and time because mobile devices communicate with the base station of the service provider. However, information about user interest can-t be easily collected because user interest can not be captured automatically without user-s approval process. User interest usually represented as a need. In this study, we classify needs into two types according to prior research. This study investigates the usefulness of data mining techniques for classifying user need type for recommendation systems. We employ several data mining techniques including artificial neural networks, decision trees, case-based reasoning, and multivariate discriminant analysis. Experimental results show that CHAID algorithm outperforms other models for classifying user need type. This study performs McNemar test to examine the statistical significance of the differences of classification results. The results of McNemar test also show that CHAID performs better than the other models with statistical significance.

Keywords: Customer need type, Data mining techniques, Recommender system, Personalization, Mobile user.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2153
294 Statistical Analysis of the Impact of Maritime Transport Gross Domestic Product on Nigeria’s Economy

Authors: K. P. Oyeduntan, K. Oshinubi

Abstract:

Nigeria is referred as the ‘Giant of Africa’ due to high population, land mass and large economy. However, it still trails far behind many smaller economies in the continent in terms of maritime operations. As we have seen that the maritime industry is the sparkplug for national growth, because it houses the most crucial infrastructure that generates wealth for a nation, it is worrisome that a nation with six seaports lag in maritime activities. In this research, we have studied how the Gross Domestic Product (GDP) of the maritime transport influences the Nigerian economy. To do this, we applied Simple Linear Regression (SLR), Support Vector Machine (SVM), Polynomial Regression Model (PRM), Generalized Additive Model (GAM) and Generalized Linear Mixed Model (GLMM) to model the relationship between the nation’s Total GDP (TGDP) and the Maritime Transport GDP (MGDP) using a time series data of 20 years. The result showed that the MGDP is statistically significant to the Nigerian economy. Amongst the statistical tool applied, the PRM of order 4 describes the relationship better when compared to other methods. The recommendations presented in this study will guide policy makers and help improve the economy of Nigeria.

Keywords: Economy, GDP, maritime transport, port, regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 165
293 Jobs Scheduling and Worker Assignment Problem to Minimize Makespan using Ant Colony Optimization Metaheuristic

Authors: Mian Tahir Aftab, Muhammad Umer, Riaz Ahmad

Abstract:

This article proposes an Ant Colony Optimization (ACO) metaheuristic to minimize total makespan for scheduling a set of jobs and assign workers for uniformly related parallel machines. An algorithm based on ACO has been developed and coded on a computer program Matlab®, to solve this problem. The paper explains various steps to apply Ant Colony approach to the problem of minimizing makespan for the worker assignment & jobs scheduling problem in a parallel machine model and is aimed at evaluating the strength of ACO as compared to other conventional approaches. One data set containing 100 problems (12 Jobs, 03 machines and 10 workers) which is available on internet, has been taken and solved through this ACO algorithm. The results of our ACO based algorithm has shown drastically improved results, especially, in terms of negligible computational effort of CPU, to reach the optimal solution. In our case, the time taken to solve all 100 problems is even lesser than the average time taken to solve one problem in the data set by other conventional approaches like GA algorithm and SPT-A/LMC heuristics.

Keywords: Ant Colony Optimization (ACO), Genetic algorithms (GA), Makespan, SPT-A/LMC heuristic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3480
292 Flow Discharge Determination in Straight Compound Channels Using ANNs

Authors: A. Zahiri, A. A. Dehghani

Abstract:

Although many researchers have studied the flow hydraulics in compound channels, there are still many complicated problems in determination of their flow rating curves. Many different methods have been presented for these channels but extending them for all types of compound channels with different geometrical and hydraulic conditions is certainly difficult. In this study, by aid of nearly 400 laboratory and field data sets of geometry and flow rating curves from 30 different straight compound sections and using artificial neural networks (ANNs), flow discharge in compound channels was estimated. 13 dimensionless input variables including relative depth, relative roughness, relative width, aspect ratio, bed slope, main channel side slopes, flood plains side slopes and berm inclination and one output variable (flow discharge), have been used in ANNs. Comparison of ANNs model and traditional method (divided channel method-DCM) shows high accuracy of ANNs model results. The results of Sensitivity analysis showed that the relative depth with 47.6 percent contribution, is the most effective input parameter for flow discharge prediction. Relative width and relative roughness have 19.3 and 12.2 percent of importance, respectively. On the other hand, shape parameter, main channel and flood plains side slopes with 2.1, 3.8 and 3.8 percent of contribution, have the least importance.

Keywords: ANN model, compound channels, divided channel method (DCM), flow rating curve

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2565
291 Operating System Based Virtualization Models in Cloud Computing

Authors: Dev Ras Pandey, Bharat Mishra, S. K. Tripathi

Abstract:

Cloud computing is ready to transform the structure of businesses and learning through supplying the real-time applications and provide an immediate help for small to medium sized businesses. The ability to run a hypervisor inside a virtual machine is important feature of virtualization and it is called nested virtualization. In today’s growing field of information technology, many of the virtualization models are available, that provide a convenient approach to implement, but decision for a single model selection is difficult. This paper explains the applications of operating system based virtualization in cloud computing with an appropriate/suitable model with their different specifications and user’s requirements. In the present paper, most popular models are selected, and the selection was based on container and hypervisor based virtualization. Selected models were compared with a wide range of user’s requirements as number of CPUs, memory size, nested virtualization supports, live migration and commercial supports, etc. and we identified a most suitable model of virtualization.

Keywords: Virtualization, OS based virtualization, container and hypervisor based virtualization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1954
290 Fusion Classifier for Open-Set Face Recognition with Pose Variations

Authors: Gee-Sern Jison Hsu

Abstract:

A fusion classifier composed of two modules, one made by a hidden Markov model (HMM) and the other by a support vector machine (SVM), is proposed to recognize faces with pose variations in open-set recognition settings. The HMM module captures the evolution of facial features across a subject-s face using the subject-s facial images only, without referencing to the faces of others. Because of the captured evolutionary process of facial features, the HMM module retains certain robustness against pose variations, yielding low false rejection rates (FRR) for recognizing faces across poses. This is, however, on the price of poor false acceptance rates (FAR) when recognizing other faces because it is built upon withinclass samples only. The SVM module in the proposed model is developed following a special design able to substantially diminish the FAR and further lower down the FRR. The proposed fusion classifier has been evaluated in performance using the CMU PIE database, and proven effective for open-set face recognition with pose variations. Experiments have also shown that it outperforms the face classifier made by HMM or SVM alone.

Keywords: Face recognition, open-set identification, hidden Markov model, support vector machines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1701
289 ECG Based Reliable User Identification Using Deep Learning

Authors: R. N. Begum, Ambalika Sharma, G. K. Singh

Abstract:

Identity theft has serious ramifications beyond data and personal information loss. This necessitates the implementation of robust and efficient user identification systems. Therefore, automatic biometric recognition systems are the need of the hour, and electrocardiogram (ECG)-based systems are unquestionably the best choice due to their appealing inherent characteristics. The Convolutional Neural Networks (CNNs) are the recent state-of-the-art techniques for ECG-based user identification systems. However, the results obtained are significantly below standards, and the situation worsens as the number of users and types of heartbeats in the dataset grows. As a result, this study proposes a highly accurate and resilient ECG-based person identification system using CNN's dense learning framework. The proposed research explores explicitly the caliber of dense CNNs in the field of ECG-based human recognition. The study tests four different configurations of dense CNN which are trained on a dataset of recordings collected from eight popular ECG databases. With the highest False Acceptance Rate (FAR)  of 0.04% and the highest False Rejection Rate (FRR)  of 5%, the best performing network achieved an identification accuracy of 99.94%. The best network is also tested with various train/test split ratios. The findings show that DenseNets are not only extremely reliable, but also highly efficient. Thus, they might also be implemented in real-time ECG-based human recognition systems.

Keywords: Biometrics, dense networks, identification rate, train/test split ratio.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 562
288 A Systematic Approach for Identifying Turning Center Capabilities with Vertical Machining Center in Milling Operation

Authors: J. Chen, N. Hundal

Abstract:

Conventional machining is a form of subtractive manufacturing, in which a collection of material-working processes utilizing power-driven machine tools are used to remove undesired material to achieve a desired geometry. This paper presents an approach for comparison between turning center and vertical machining center by optimization of cutting parameters at cylindrical workpieces leading to minimum surface roughness by using taguchi methodology. Aluminum alloy was taken to conduct experiments due to its unique high strength-weight ratio that is maintained at elevated temperatures and their exceptional corrosion resistance. During testing, the effects of the cutting parameters on the surface roughness were investigated. Additionally, by using taguchi methodology for each of the cutting parameters (spindle speed, depth of cut, insert diameter, and feed rate) minimum surface roughness for the process of turn-milling was determined according to the cutting parameters. A confirmation experiment demonstrates the effectiveness of taguchi method.

Keywords: Surface roughness, taguchi parameter design, turning center, turn-milling operations, vertical machining center.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2533
287 Facilitating a Cyber-Enabled Fraud Using the O.MG Cable to Incriminate the Victim

Authors: Damola O. Lawal, David W. Gresty, Diane E. Gan, Louise Hewitt

Abstract:

This paper investigates the feasibility of using a programmable USB such as the O.MG Cable to perform a file tampering attack. Here, the O.MG Cable, an apparently harmless mobile device charger is used in an unauthorised way, to alter the content of a file (an accounts record-January_Contributions.xlsx). The aim is to determine if a forensics analyst can reliably determine who has altered the target file; the O.MG Cable or the user of the machine. This work highlights some of the traces of the O.MG Cable left behind on the target computer itself such as the Product ID (PID) and Vendor ID (ID). Also discussed is the O.MG Cable’s behaviour during the experiments. We determine if a forensics analyst could identify if any evidence has been left behind by the programmable device on the target file once it has been removed from the computer to establish if the analyst would be able to link the traces left by the O.MG Cable to the file tampering. It was discovered that the forensic analyst might mistake the actions of the O.MG Cable for the computer users. Experiments carried out in this work could further the discussion as to whether an innocent user could be punished for the unauthorised changes made by a programmable device.

Keywords: O.MG Cable, programmable USB, file tampering attack, digital evidence credibility, miscarriage of justice, cyber fraud.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 686