Search results for: Data EnvelopmentAnalysis
5622 Performance Analysis of Artificial Neural Network with Decision Tree in Prediction of Diabetes Mellitus
Authors: J. K. Alhassan, B. Attah, S. Misra
Abstract:
Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. Medical dataset is a vital ingredient used in predicting patient’s health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. WEKA software was used for the implementation of the algorithms. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. From the results obtained, DTA performed better than ANN. The Root Mean Squared Error (RMSE) of MLP is 0.3913 that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.Keywords: Artificial neural network, classification, decision tree, diabetes mellitus.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 24115621 Combining the Deep Neural Network with the K-Means for Traffic Accident Prediction
Authors: Celso L. Fernando, Toshio Yoshii, Takahiro Tsubota
Abstract:
Understanding the causes of a road accident and predicting their occurrence is key to prevent deaths and serious injuries from road accident events. Traditional statistical methods such as the Poisson and the Logistics regressions have been used to find the association of the traffic environmental factors with the accident occurred; recently, an artificial neural network, ANN, a computational technique that learns from historical data to make a more accurate prediction, has emerged. Although the ability to make accurate predictions, the ANN has difficulty dealing with highly unbalanced attribute patterns distribution in the training dataset; in such circumstances, the ANN treats the minority group as noise. However, in the real world data, the minority group is often the group of interest; e.g., in the road traffic accident data, the events of the accident are the group of interest. This study proposes a combination of the k-means with the ANN to improve the predictive ability of the neural network model by alleviating the effect of the unbalanced distribution of the attribute patterns in the training dataset. The results show that the proposed method improves the ability of the neural network to make a prediction on a highly unbalanced distributed attribute patterns dataset; however, on an even distributed attribute patterns dataset, the proposed method performs almost like a standard neural network.
Keywords: Accident risks estimation, artificial neural network, deep learning, K-mean, road safety.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9365620 Game Theory Based Diligent Energy Utilization Algorithm for Routing in Wireless Sensor Network
Authors: X. Mercilin Raajini, R. Raja Kumar, P. Indumathi, V. Praveen
Abstract:
Many cluster based routing protocols have been proposed in the field of wireless sensor networks, in which a group of nodes are formed as clusters. A cluster head is selected from one among those nodes based on residual energy, coverage area, number of hops and that cluster-head will perform data gathering from various sensor nodes and forwards aggregated data to the base station or to a relay node (another cluster-head), which will forward the packet along with its own data packet to the base station. Here a Game Theory based Diligent Energy Utilization Algorithm (GTDEA) for routing is proposed. In GTDEA, the cluster head selection is done with the help of game theory, a decision making process, that selects a cluster-head based on three parameters such as residual energy (RE), Received Signal Strength Index (RSSI) and Packet Reception Rate (PRR). Finding a feasible path to the destination with minimum utilization of available energy improves the network lifetime and is achieved by the proposed approach. In GTDEA, the packets are forwarded to the base station using inter-cluster routing technique, which will further forward it to the base station. Simulation results reveal that GTDEA improves the network performance in terms of throughput, lifetime, and power consumption.Keywords: Cluster head, Energy utilization, Game Theory, LEACH, Sensor network.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18945619 Two-Level Identification of HVAC Consumers for Demand Response Potential Estimation Based on Setpoint Change
Authors: M. Naserian, M. Jooshaki, M. Fotuhi-Firuzabad, M. Hossein Mohammadi Sanjani, A. Oraee
Abstract:
In recent years, the development of communication infrastructure and smart meters have facilitated the utilization of demand-side resources which can enhance stability and economic efficiency of power systems. Direct load control programs can play an important role in the utilization of demand-side resources in the residential sector. However, investments required for installing control equipment can be a limiting factor in the development of such demand response programs. Thus, selection of consumers with higher potentials is crucial to the success of a direct load control program. Heating, ventilation, and air conditioning (HVAC) systems, which due to the heat capacity of buildings feature relatively high flexibility, make up a major part of household consumption. Considering that the consumption of HVAC systems depends highly on the ambient temperature and bearing in mind the high investments required for control systems enabling direct load control demand response programs, in this paper, a solution is presented to uncover consumers with high air conditioner demand among a large number of consumers and to measure the demand response potential of such consumers. This can pave the way for estimating the investments needed for the implementation of direct load control programs for residential HVAC systems and for estimating the demand response potentials in a distribution system. In doing so, we first cluster consumers into several groups based on the correlation coefficients between hourly consumption data and hourly temperature data using K-means algorithm. Then, by applying a recent algorithm to the hourly consumption and temperature data, consumers with high air conditioner consumption are identified. Finally, demand response potential of such consumers is estimated based on the equivalent desired temperature setpoint changes.
Keywords: Data-driven analysis, demand response, direct load control, HVAC system.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2195618 Effect of Incentives on Knowledge Sharing and Learning – Evidence from the Indian IT Sector
Authors: Asish O. Mathew, Lewlyn L. R. Rodrigues
Abstract:
The organizations in the knowledge economy era have recognized the importance of building knowledge assets for sustainable growth and development. In comparison to other industries, Information Technology (IT) enterprises, holds an edge in developing an effective Knowledge Management (KM) programmethanks to their in-house technological abilities. This paper tries to study the various knowledge based incentive programmes and its effect on Knowledge Sharing and Learning in the context of the Indian IT sector. A conceptual model is developed linking KM Incentives, Knowledge Sharing and Learning. A questionnaire study is conducted to collect primary data from the knowledge workers of the IT organizations located in India. The data was analysed using Structural Equation Modeling using Partial Least Square method. The results show a strong influence of knowledge management incentives on knowledge sharing and an indirect influence on learning.
Keywords: Knowledge Management, Knowledge Management Incentives, Knowledge Sharing, Learning.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 36775617 Estimating an Optimal Neighborhood Size in the Spherical Self-Organizing Feature Map
Authors: Alexandros Leontitsis, Archana P. Sangole
Abstract:
This article presents a short discussion on optimum neighborhood size selection in a spherical selforganizing feature map (SOFM). A majority of the literature on the SOFMs have addressed the issue of selecting optimal learning parameters in the case of Cartesian topology SOFMs. However, the use of a Spherical SOFM suggested that the learning aspects of Cartesian topology SOFM are not directly translated. This article presents an approach on how to estimate the neighborhood size of a spherical SOFM based on the data. It adopts the L-curve criterion, previously suggested for choosing the regularization parameter on problems of linear equations where their right-hand-side is contaminated with noise. Simulation results are presented on two artificial 4D data sets of the coupled Hénon-Ikeda map.Keywords: Parameter estimation, self-organizing feature maps, spherical topology.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 15075616 Privacy Protection Principles of Omnichannel Approach
Authors: Renata Mekovec, Dijana Peras, Ruben Picek
Abstract:
The advent of the Internet, mobile devices and social media is revolutionizing the experience of retail customers by linking multiple sources through various channels. Omnichannel retailing is a retailing that combines multiple channels to allow customers to seamlessly leverage all the distribution information online and offline while shopping. Therefore, today data are an asset more critical than ever for all organizations. Nonetheless, because of its heterogeneity through platforms, developers are currently facing difficulties in dealing with personal data. Considering the possibilities of omnichannel communication, this paper presents channel categorization that could enhance the customer experience of omnichannel center called hyper center. The purpose of this paper is fundamentally to describe the connection between the omnichannel hyper center and the customer, with particular attention to privacy protection. The first phase was finding the most appropriate channels of communication for hyper center. Consequently, a selection of widely used communication channels has been identified and analyzed with regard to the effect requirements for optimizing user experience. The evaluation criteria are divided into 3 groups: general, user profile and channel options. For each criterion the weight of importance for omnichannel communication was defined. The most important thing was to consider how the hyper center can make user identification while respecting the privacy protection requirements. The study carried out also shows what customer experience across digital networks would look like, based on an omnichannel approach owing to privacy protection principles.Keywords: Personal data, privacy protection, omnichannel communication, retail.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6185615 A Novel Interpolation Scheme and Apparatus to Extend DAC Usable Spectrum over Nyquist Frequency
Authors: Wang liguo, Wang zongmin, Kong ying
Abstract:
A novel interpolation scheme to extend usable spectrum and upconvert in high performance D/A converters is addressed in this paper. By adjusting the pulse width of cycle and the production circuit of code, the expansion code is a null code or complementary code that is interpolation process. What the times and codes of interpolation decide DAC works in one of a normal mode or multi-mixer mode so that convert the input digital data signal into normal signal or a mixed analog signal having a mixer frequency that is higher than the data frequency. Simulation results show that the novel scheme and apparatus most extend the usable frequency spectrum into fifth to sixth Nyquist zone beyond conventional DACs.Keywords: interpolation, upconversion, modulation, switching function, duty cycle.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14935614 Uvulars Alternation in Hasawi Arabic: A Harmonic Serialism Approach
Authors: Huda Ahmed Al Taisan
Abstract:
This paper investigates a phonological phenomenon, which exhibits variation ‘alternation’ in terms of the uvular consonants [q] and [ʁ] in Hasawi Arabic. This dialect is spoken in Alahsa city, which is located in the Eastern province of Saudi Arabia. To the best of our knowledge, no such research has systematically studied this phenomenon in Hasawi Arabic dialect. This paper is significant because it fills the gap in the literature about this alternation phenomenon in this understudied dialect. A large amount of the data is extracted from several interviews the author has conducted with 10 participants, native speakers of the dialect, and complemented by additional forms from social media. The latter method of collecting the data adds to the significance of the research. The analysis of the data is carried out in Harmonic Serialism Optimality Theory (HS-OT), a version of the Optimality Theoretic (OT) framework, which holds that linguistic forms are the outcome of the interaction among violable universal constraints, and in the recent development of OT into a model that accounts for linguistic variation in harmonic derivational steps. This alternation process is assumed to be phonologically unconditioned and in free variation in other varieties of Arabic dialects in the area. The goal of this paper is to investigate whether this phenomenon is in free variation or governed, what governs this alternation between [q] and [ʁ] and whether the alternation is phonological or other linguistic constraints are in action. The results show that the [q] and [ʁ] alternation is not free and it occurs due to different assimilation processes. Positional, segmental sequence and vowel adjacency factors are in action in Hasawi Arabic.
Keywords: Harmonic serialism, Hasawi, uvular, alternation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6395613 Exploring the Combinatorics of Motif Alignments Foraccurately Computing E-values from P-values
Authors: T. Kjosmoen, T. Ryen, T. Eftestøl
Abstract:
In biological and biomedical research motif finding tools are important in locating regulatory elements in DNA sequences. There are many such motif finding tools available, which often yield position weight matrices and significance indicators. These indicators, p-values and E-values, describe the likelihood that a motif alignment is generated by the background process, and the expected number of occurrences of the motif in the data set, respectively. The various tools often estimate these indicators differently, making them not directly comparable. One approach for comparing motifs from different tools, is computing the E-value as the product of the p-value and the number of possible alignments in the data set. In this paper we explore the combinatorics of the motif alignment models OOPS, ZOOPS, and ANR, and propose a generic algorithm for computing the number of possible combinations accurately. We also show that using the wrong alignment model can give E-values that significantly diverge from their true values.
Keywords: Motif alignment, combinatorics, p-value, E-value, OOPS, ZOOPS, ANR.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 12025612 Investigating Climate Change Trend Based on Data Simulation and IPCC Scenario during 2010-2030 AD: Case Study of Fars Province
Authors: Leila Rashidian, Abbas Ebrahimi
Abstract:
The development of industrial activities, increase in fossil fuel consumption, vehicles, destruction of forests and grasslands, changes in land use, and population growth have caused to increase the amount of greenhouse gases especially CO2 in the atmosphere in recent decades. This has led to global warming and climate change. In the present paper, we have investigated the trend of climate change according to the data simulation during the time interval of 2010-2030 in the Fars province. In this research, the daily climatic parameters such as maximum and minimum temperature, precipitation and number of sunny hours during the 1977-2008 time interval for synoptic stations of Shiraz and Abadeh and during 1995-2008 for Lar stations and also the output of HADCM3 model in 2010-2030 time interval have been used based on the A2 propagation scenario. The results of the model show that the average temperature will increase by about 1 degree centigrade and the amount of precipitation will increase by 23.9% compared to the observational data. In conclusion, according to the temperature increase in this province, the amount of precipitation in the form of snow will be reduced and precipitations often will occur in the form of rain. This 1-degree centigrade increase during the season will reduce production by 6 to 10% because of shortening the growing period of wheat.Keywords: Climate change, Lars.WG, HADCM3 model, Fars province, climatic parameters, A2 scenario.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 11585611 Integrating Computational Intelligence Techniques and Assessment Agents in ELearning Environments
Authors: Konstantinos C. Giotopoulos, Christos E. Alexakos, Grigorios N. Beligiannis, Spiridon D.Likothanassis
Abstract:
In this contribution an innovative platform is being presented that integrates intelligent agents and evolutionary computation techniques in legacy e-learning environments. It introduces the design and development of a scalable and interoperable integration platform supporting: I) various assessment agents for e-learning environments, II) a specific resource retrieval agent for the provision of additional information from Internet sources matching the needs and profile of the specific user and III) a genetic algorithm designed to extract efficient information (classifying rules) based on the students- answering input data. The agents are implemented in order to provide intelligent assessment services based on computational intelligence techniques such as Bayesian Networks and Genetic Algorithms. The proposed Genetic Algorithm (GA) is used in order to extract efficient information (classifying rules) based on the students- answering input data. The idea of using a GA in order to fulfil this difficult task came from the fact that GAs have been widely used in applications including classification of unknown data. The utilization of new and emerging technologies like web services allows integrating the provided services to any web based legacy e-learning environment.Keywords: Bayesian Networks, Computational Intelligencetechniques, E-learning legacy systems, Service Oriented Integration, Intelligent Agents, Genetic Algorithms.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 17325610 Exploring Causes of Homelessness and Shelter Entry: A Case Study Analysis of Shelter Data in New York
Authors: Lindsay Fink, Sarha Smith-Moyo, Leanne W. Charlesworth
Abstract:
In recent years, the number of individuals experiencing homelessness has increased in the United States. This paper analyzes 2019 data from 16 different emergency shelters in Monroe County, located in Upstate New York. The data were collected through the County’s Homeless Management Information System (HMIS), and individuals were de-identified and de-duplicated for analysis. The purpose of this study is to explore the basic characteristics of the homeless population in Monroe County, and the dynamics of shelter use. The results of this study showed gender as a significant factor when analyzing the relationship between demographic variables and recorded reasons for shelter entry. Results also indicated that age and ethnicity did not significantly influence odds of re-entering a shelter, but did significantly influence reasons for shelter entry. Overall, the most common recorded cause of shelter entry in 2019 in the examined county was eviction by primary tenant. Recommendations to better address recurrent shelter entry and potential chronic homelessness include more consideration for the diversity existing within the homeless population, and the dynamics leading to shelter stays, including enhanced funding and training for shelter staff, as well as expanded access to permanent supportive housing programs.
Keywords: Chronic homelessness, homeless shelter stays, permanent supportive housing, shelter population dynamics.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9625609 The Effect of Fixing Kinesiology Tape onto the Plantar Surface during the Loading Phase of Gait
Authors: Albert K. Chong, Jasim Ahmed Ali Al-Baghdadi, Peter B. Milburn
Abstract:
Precise capture of plantar 3D surface of the foot at the loading gait phases on rigid substrates was found to be valuable for the assessment of the physiology, health and problems of the feet. Photogrammetry, a precision 3D spatial data capture technique is suitable for this type of dynamic application. In this research, the technique is utilised to study the plantar deformation as a result of having a strip of kinesiology tape on the plantar surface during the loading phase of gait. For this pilot study, one healthy adult male subject was recruited under the University’s human research ethics guidelines for this preliminary study. The 3D plantar deformation data with and without applying the tape were analysed. The results and analyses are presented together with detailed findings.
Keywords: Gait, human plantar, loading, Kinesiology Tape.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 18945608 Urban Corridor Management Strategy Based on Intelligent Transportation System
Authors: Sourabh Jain, Sukhvir Singh Jain, Gaurav V. Jain
Abstract:
Intelligent Transportation System (ITS) is the application of technology for developing a user–friendly transportation system for urban areas in developing countries. The goal of urban corridor management using ITS in road transport is to achieve improvements in mobility, safety, and the productivity of the transportation system within the available facilities through the integrated application of advanced monitoring, communications, computer, display, and control process technologies, both in the vehicle and on the road. This paper attempts to present the past studies regarding several ITS available that have been successfully deployed in urban corridors of India and abroad, and to know about the current scenario and the methodology considered for planning, design, and operation of Traffic Management Systems. This paper also presents the endeavor that was made to interpret and figure out the performance of the 27.4 Km long study corridor having eight intersections and four flyovers. The corridor consisting of 6 lanes as well as 8 lanes divided road network. Two categories of data were collected on February 2016 such as traffic data (traffic volume, spot speed, delay) and road characteristics data (no. of lanes, lane width, bus stops, mid-block sections, intersections, flyovers). The instruments used for collecting the data were video camera, radar gun, mobile GPS and stopwatch. From analysis, the performance interpretations incorporated were identification of peak hours and off peak hours, congestion and level of service (LOS) at mid blocks, delay followed by the plotting speed contours and recommending urban corridor management strategies. From the analysis, it is found that ITS based urban corridor management strategies will be useful to reduce congestion, fuel consumption and pollution so as to provide comfort and efficiency to the users. The paper presented urban corridor management strategies based on sensors incorporated in both vehicles and on the roads.
Keywords: Congestion, ITS Strategies, Mobility, Safety.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16345607 Influence of Locus of Control and Job Involvement to Organizational Culture Applied by Employees on Bank X
Authors: Sri Suwarsi, Nadia Budianti
Abstract:
As one of the big government bank, Bank X is paying attention its performance, so that it can compete. One of them is the existence of organizational culture which recognized with term TIPEC (Trust, Integrity, Professionalism, Costumer Focus, and Excellence). In application of organizational culture, it is needed the existence of employee involvement (job involvement). It can be influenced by various factors, such as Locus of Control. Related to above mentioned, the problems are how employee tendency of Locus of Control, how job involvement, how organizational culture applied by employees and how influence of Locus of Control and job involvement to the organizational culture applied by employees. Researchers collected data with questioner spreading, and respondents number of 30 people. After that, the data were analyzed with SPSS software constructively. The influence of Locus of Control and job involvement to the application of organizational culture was strong, i.e. 58.3%.
Keywords: Organizational culture, bank, employee locus of control, job involvement.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 25185606 WormHex: A Volatile Memory Analysis Tool for Retrieval of Social Media Evidence
Authors: Norah Almubairik, Wadha Almattar, Amani Alqarni
Abstract:
Social media applications are increasingly being used in our everyday communications. These applications utilise end-to-end encryption mechanisms which make them suitable tools for criminals to exchange messages. These messages are preserved in the volatile memory until the device is restarted. Therefore, volatile forensics has become an important branch of digital forensics. In this study, the WormHex tool was developed to inspect the memory dump files for Windows and Mac based workstations. The tool supports digital investigators by enabling them to extract valuable data written in Arabic and English through web-based WhatsApp and Twitter applications. The results confirm that social media applications write their data into the memory, regardless of the operating system running the application, with there being no major differences between Windows and Mac.
Keywords: Volatile memory, REGEX, digital forensics, memory acquisition
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 8965605 Case-Based Reasoning: A Hybrid Classification Model Improved with an Expert's Knowledge for High-Dimensional Problems
Authors: Bruno Trstenjak, Dzenana Donko
Abstract:
Data mining and classification of objects is the process of data analysis, using various machine learning techniques, which is used today in various fields of research. This paper presents a concept of hybrid classification model improved with the expert knowledge. The hybrid model in its algorithm has integrated several machine learning techniques (Information Gain, K-means, and Case-Based Reasoning) and the expert’s knowledge into one. The knowledge of experts is used to determine the importance of features. The paper presents the model algorithm and the results of the case study in which the emphasis was put on achieving the maximum classification accuracy without reducing the number of features.
Keywords: Case based reasoning, classification, expert's knowledge, hybrid model.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14085604 Statistical Screening of Medium Components on Ethanol Production from Cashew Apple Juice using Saccharomyces diasticus
Authors: Karuppaiya Maruthai, Viruthagiri Thangavelu, Manikandan Kanagasabai
Abstract:
In the present study, effect of critical medium components (a total of fifteen components) on ethanol production from waste cashew apple juice (CAJ) using yeast Saccharomyces diasticus was studied. A statistical response surface methodology (RSM) based Plackett-Burman Design (PBD) was used for the design of experiments. The design contains a total of 32 experimental trails. The effect of medium components on ethanol was studied at two different levels such as low concentration level (-) and high concentration levels (+). The dependent variables selected in this study were ethanol concentration (g/L) and cellmass concentration (g/L). Data obtained from RSM on ethanol production were subjected to analysis of variance (ANOVA). In general, initial substrate concentration significantly influenced the microbial growth and product formation. Of the medium components evaluated, CAJ concentration, yeast extract, (NH4)2SO4, and malt extract showed significant effect on ethanol fermentation. A second-order polynomial model was used to predict the experimental data and the model fitted the data with a high correlation coefficient (R2 > 0.98). Maximum ethanol (15.3 g/L) and biomass (6.4 g/L) concentrations were obtained at the optimum medium composition and at optimum condition (temperature-30°C; initial pH-6.8) after 72 h fermentation using S.diasticus.
Keywords: cashew apple juice, ethanol, fermentation, yeast, response surface methodology
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 27015603 Multi-Objective Evolutionary Computation Based Feature Selection Applied to Behaviour Assessment of Children
Authors: F. Jiménez, R. Jódar, M. Martín, G. Sánchez, G. Sciavicco
Abstract:
Abstract—Attribute or feature selection is one of the basic strategies to improve the performances of data classification tasks, and, at the same time, to reduce the complexity of classifiers, and it is a particularly fundamental one when the number of attributes is relatively high. Its application to unsupervised classification is restricted to a limited number of experiments in the literature. Evolutionary computation has already proven itself to be a very effective choice to consistently reduce the number of attributes towards a better classification rate and a simpler semantic interpretation of the inferred classifiers. We present a feature selection wrapper model composed by a multi-objective evolutionary algorithm, the clustering method Expectation-Maximization (EM), and the classifier C4.5 for the unsupervised classification of data extracted from a psychological test named BASC-II (Behavior Assessment System for Children - II ed.) with two objectives: Maximizing the likelihood of the clustering model and maximizing the accuracy of the obtained classifier. We present a methodology to integrate feature selection for unsupervised classification, model evaluation, decision making (to choose the most satisfactory model according to a a posteriori process in a multi-objective context), and testing. We compare the performance of the classifier obtained by the multi-objective evolutionary algorithms ENORA and NSGA-II, and the best solution is then validated by the psychologists that collected the data.Keywords: Feature selection, multi-objective evolutionary computation, unsupervised classification, behavior assessment system for children.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 14355602 Corporate Social Responsibility and Corporate Reputation: A Bibliometric Analysis
Authors: Songdi Li, Louise Spry, Tony Woodall
Abstract:
Nowadays, Corporate Social responsibility (CSR) is becoming a buzz word, and more and more academics are putting efforts on CSR studies. It is believed that CSR could influence Corporate Reputation (CR), and they hold a favourable view that CSR leads to a positive CR. To be specific, the CSR related activities in the reputational context have been regarded as ways that associate to excellent financial performance, value creation, etc. Also, it is argued that CSR and CR are two sides of one coin; hence, to some extent, doing CSR is equal to establishing a good reputation. Still, there is no consensus of the CSR-CR relationship in the literature; thus, a systematic literature review is highly in need. This research conducts a systematic literature review with both bibliometric and content analysis. Data are selected from English language sources, and academic journal articles only, then, keyword combinations are applied to identify relevant sources. Data from Scopus and WoS are gathered for bibliometric analysis. Scopus search results were saved in RIS and CSV formats, and Web of Science (WoS) data were saved in TXT format and CSV formats in order to process data in the Bibexcel software for further analysis which later will be visualised by the software VOSviewer. Also, content analysis was applied to analyse the data clusters and the key articles. In terms of the topic of CSR-CR, this literature review with bibliometric analysis has made four achievements. First, this paper has developed a systematic study which quantitatively depicts the knowledge structure of CSR and CR by identifying terms closely related to CSR-CR (such as ‘corporate governance’) and clustering subtopics emerged in co-citation analysis. Second, content analysis is performed to acquire insight on the findings of bibliometric analysis in the discussion section. And it highlights some insightful implications for the future research agenda, for example, a psychological link between CSR-CR is identified from the result; also, emerging economies and qualitative research methods are new elements emerged in the CSR-CR big picture. Third, a multidisciplinary perspective presents through the whole bibliometric analysis mapping and co-word and co-citation analysis; hence, this work builds a structure of interdisciplinary perspective which potentially leads to an integrated conceptual framework in the future. Finally, Scopus and WoS are compared and contrasted in this paper; as a result, Scopus which has more depth and comprehensive data is suggested as a tool for future bibliometric analysis studies. Overall, this paper has fulfilled its initial purposes and contributed to the literature. To the author’s best knowledge, this paper conducted the first literature review of CSR-CR researches that applied both bibliometric analysis and content analysis; therefore, this paper achieves its methodological originality. And this dual approach brings advantages of carrying out a comprehensive and semantic exploration in the area of CSR-CR in a scientific and realistic method. Admittedly, its work might exist subjective bias in terms of search terms selection and paper selection; hence triangulation could reduce the subjective bias to some degree.
Keywords: Corporate social responsibility, corporate reputation, bibliometric analysis, software data analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9215601 Detection of New Attacks on Ubiquitous Services in Cloud Computing and Countermeasures
Authors: L. Sellami, D. Idoughi, P. F. Tiako
Abstract:
Cloud computing provides infrastructure to the enterprise through the Internet allowing access to cloud services at anytime and anywhere. This pervasive aspect of the services, the distributed nature of data and the wide use of information make cloud computing vulnerable to intrusions that violate the security of the cloud. This requires the use of security mechanisms to detect malicious behavior in network communications and hosts such as intrusion detection systems (IDS). In this article, we focus on the detection of intrusion into the cloud sing IDSs. We base ourselves on client authentication in the computing cloud. This technique allows to detect the abnormal use of ubiquitous service and prevents the intrusion of cloud computing. This is an approach based on client authentication data. Our IDS provides intrusion detection inside and outside cloud computing network. It is a double protection approach: The security user node and the global security cloud computing.
Keywords: Cloud computing, intrusion detection system, privacy, trust.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 10935600 Facilitating Factors for the Success of Mobile Service Providers in Bangkok Metropolitan
Authors: Yananda Siraphatthada
Abstract:
The objectives of this research were to study the level of influencing factors, leadership, supply chain management, innovation, competitive advantages, business success, and affecting factors to the business success of the mobile phone system service providers in Bangkok Metropolitan. This research was done by the quantitative approach and the qualitative approach. The quantitative approach was used for questionnaires to collect data from the 331 mobile service shop managers franchised by AIS, Dtac and TrueMove. The mobile phone system service providers/shop managers were randomly stratified and proportionally allocated into subgroups exclusive to the number of the providers in each network. In terms of qualitative method, there were in-depth interviews of 6 mobile service providers/managers of Telewiz and Dtac and TrueMove shop to find the agreement or disagreement with the content analysis method. Descriptive Statistics, including Frequency, Percentage, Means and Standard Deviation were employed; also, the Structural Equation Model (SEM) was used as a tool for data analysis. The content analysis method was applied to identify key patterns emerging from the interview responses. The two data sets were brought together for comparing and contrasting to make the findings, providing triangulation to enrich result interpretation. It revealed that the level of the influencing factors – leadership, innovation management, supply chain management, and business competitiveness had an impact at a great level, but that the level of factors, innovation and the business, financial success and nonbusiness financial success of the mobile phone system service providers in Bangkok Metropolitan, is at the highest level. Moreover, the business influencing factors, competitive advantages in the business of mobile system service providers which were leadership, supply chain management, innovation management, business advantages, and business success, had statistical significance at .01 which corresponded to the data from the interviews.Keywords: Business success, mobile service providers.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 10925599 Integration of Educational Data Mining Models to a Web-Based Support System for Predicting High School Student Performance
Authors: Sokkhey Phauk, Takeo Okazaki
Abstract:
The challenging task in educational institutions is to maximize the high performance of students and minimize the failure rate of poor-performing students. An effective method to leverage this task is to know student learning patterns with highly influencing factors and get an early prediction of student learning outcomes at the timely stage for setting up policies for improvement. Educational data mining (EDM) is an emerging disciplinary field of data mining, statistics, and machine learning concerned with extracting useful knowledge and information for the sake of improvement and development in the education environment. The study is of this work is to propose techniques in EDM and integrate it into a web-based system for predicting poor-performing students. A comparative study of prediction models is conducted. Subsequently, high performing models are developed to get higher performance. The hybrid random forest (Hybrid RF) produces the most successful classification. For the context of intervention and improving the learning outcomes, a feature selection method MICHI, which is the combination of mutual information (MI) and chi-square (CHI) algorithms based on the ranked feature scores, is introduced to select a dominant feature set that improves the performance of prediction and uses the obtained dominant set as information for intervention. By using the proposed techniques of EDM, an academic performance prediction system (APPS) is subsequently developed for educational stockholders to get an early prediction of student learning outcomes for timely intervention. Experimental outcomes and evaluation surveys report the effectiveness and usefulness of the developed system. The system is used to help educational stakeholders and related individuals for intervening and improving student performance.
Keywords: Academic performance prediction system, prediction model, educational data mining, dominant factors, feature selection methods, student performance.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9545598 Power Line Carrier Equipment Supporting IP Traffic Transmission in the Enterprise Networks of Energy Companies
Authors: M. S. Anton Merkulov
Abstract:
This article discusses the questions concerning of creating small packet networks for energy companies with application of high voltage power line carrier equipment (PLC) with functionality of IP traffic transmission. The main idea is to create converged PLC links between substations and dispatching centers where packet data and voice are transmitted in one data flow. The article contents description of basic conception of the network, evaluation of voice traffic transmission parameters, and discussion of header compression techniques in relation to PLC links. The results of exploration show us, that convergent packet PLC links can be very useful in the construction of small packet networks between substations in remote locations, such as deposits or low populated areas.
Keywords: packet PLC, VoIP, time delay, packet traffic, overhead compression
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 21565597 Land Use around Metro Stations: A Case Study
Authors: A. Roukouni, S. Basbas, M. Giannopoulou
Abstract:
Transport and land use are two systems that are mutually influenced. Their interaction is a complex process associated with continuous feedback. The paper examines the existing land use around an under construction metro station of the new metro network of Thessaloniki, Greece, through the use of field investigations, around the station-s predefined location. Moreover, except from the analytical land use recording, a sampling questionnaire survey is addressed to several selected enterprises of the study area. The survey aims to specify the characteristics of the enterprises, the trip patterns of their employees and clients, as well as the stated preferences towards the changes the new metro station is considered to bring to the area. The interpretation of the interrelationships among selected data from the questionnaire survey takes place using the method of Principal Components Analysis for Categorical Data. The followed methodology and the survey-s results contribute to the enrichment of the relevant bibliography concerning the way the creation of a new metro station can have an impact on the land use pattern of an area, by examining the situation before the operation of the station.Keywords: land use, metro station, questionnaire survey
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 30955596 Synchrotron X-Ray Based Investigation of As and Fe Bonding Environment in Collard Green Tissue Samples at Different Growth Stages
Authors: Sunil Dehipawala, Aregama Sirisumana, P. Schneider, G. Tremberger Jr, D. Lieberman, Todd Holden T. Cheung
Abstract:
The arsenic and iron environments in different growth stages have been studied with EXAFS and XANES using Brookhaven Synchrotron Light Source. Collard Greens plants were grown and tissue samples were harvested. The project studied the EXAFS and XANES of tissue samples using As and Fe K-edges. The Fe absorption and the Fourier transform bond length information were used as a control comparison. The Fourier transform of the XAFS data revealed the coexistence of As (III) and As (V) in the As bonding environment inside the studied plant tissue samples, although the soil only had As (III). The data suggests that Collard Greens has a novel pathway to handle arsenic absorption in soil.Keywords: EXAFS, Fourier Transform, metalloproteins, XANES.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 19255595 Validation of a Fluid-Structure Interaction Model of an Aortic Dissection versus a Bench Top Model
Authors: K. Khanafer
Abstract:
The aim of this investigation was to validate the fluid-structure interaction (FSI) model of type B aortic dissection with our experimental results from a bench-top-model. Another objective was to study the relationship between the size of a septectomy that increases the outflow of the false lumen and its effect on the values of the differential of pressure between true lumen and false lumen. FSI analysis based on Galerkin’s formulation was used in this investigation to study flow pattern and hemodynamics within a flexible type B aortic dissection model using boundary conditions from our experimental data. The numerical results of our model were verified against the experimental data for various tear size and location. Thus, CFD tools have a potential role in evaluating different scenarios and aortic dissection configurations.
Keywords: Aortic dissection, fluid-structure interaction, in vitro model, numerical.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 9345594 Empirical and Indian Automotive Equity Portfolio Decision Support
Authors: P. Sankar, P. James Daniel Paul, Siddhant Sahu
Abstract:
A brief review of the empirical studies on the methodology of the stock market decision support would indicate that they are at a threshold of validating the accuracy of the traditional and the fuzzy, artificial neural network and the decision trees. Many researchers have been attempting to compare these models using various data sets worldwide. However, the research community is on the way to the conclusive confidence in the emerged models. This paper attempts to use the automotive sector stock prices from National Stock Exchange (NSE), India and analyze them for the intra-sectorial support for stock market decisions. The study identifies the significant variables and their lags which affect the price of the stocks using OLS analysis and decision tree classifiers.
Keywords: Indian Automotive Sector, Stock Market Decisions, Equity Portfolio Analysis, Decision Tree Classifiers, Statistical Data Analysis.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 20265593 A Text Classification Approach Based on Natural Language Processing and Machine Learning Techniques
Authors: Rim Messaoudi, Nogaye-Gueye Gning, François Azelart
Abstract:
Automatic text classification applies mostly natural language processing (NLP) and other artificial intelligence (AI)-guided techniques to automatically classify text in a faster and more accurate manner. This paper discusses the subject of using predictive maintenance to manage incident tickets inside the sociality. It focuses on proposing a tool that treats and analyses comments and notes written by administrators after resolving an incident ticket. The goal here is to increase the quality of these comments. Additionally, this tool is based on NLP and machine learning techniques to realize the textual analytics of the extracted data. This approach was tested using real data taken from the French National Railways (SNCF) company and was given a high-quality result.
Keywords: Machine learning, text classification, NLP techniques, semantic representation.
Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 181