Search results for: data validation

Authors: Femi Elegbeleye, Seani Rananga

Abstract:

This paper focused on cost effective storage architecture using fog and cloud data storage gateway, and presented the design of the framework for the data privacy model and data analytics framework on a real-time analysis when using machine learning method. The paper began with the system analysis, system architecture and its component design, as well as the overall system operations. Several results obtained from this study on data privacy models show that when two or more data privacy models are integrated via a fog storage gateway, we often have more secure data. Our main focus in the study is to design a framework for the data privacy model, data storage, and real-time analytics. This paper also shows the major system components and their framework specification. And lastly, the overall research system architecture was shown, including its structure, and its interrelationships.

Keywords: IoT, fog storage, cloud storage, data analysis, data privacy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 244

Authors: Marcelo Hayashi, João Lima, Bruno Chieregatti, Ernani Volpe

Abstract:

The adjoint method has been used as a successful tool to obtain sensitivity gradients in aerodynamic design and optimisation for many years. This work presents an alternative approach to the continuous adjoint formulation that enables one to compute gradients of a given measure of merit with respect to control parameters other than those pertaining to geometry. The procedure is then applied to the steady 2–D compressible Euler and incompressible Navier–Stokes flow equations. Finally, the results are compared with sensitivities obtained by finite differences and theoretical values for validation.

Keywords: Adjoint method, optimisation, non–geometric sensitivities, boundary conditions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1773

Authors: Amal M. Alrayes

Abstract:

Data and system quality play a central role in organizational success, and the quality of any existing information system has a major influence on the effectiveness of overall system performance. Given the importance of system and data quality to an organization, it is relevant to highlight their importance on organizational performance in the Kingdom of Bahrain. This research aims to discover whether system quality and data quality are related, and to study the impact of system and data quality on organizational success. A theoretical model based on previous research is used to show the relationship between data and system quality, and organizational impact. We hypothesize, first, that system quality is positively associated with organizational impact, secondly that system quality is positively associated with data quality, and finally that data quality is positively associated with organizational impact. A questionnaire was conducted among public and private organizations in the Kingdom of Bahrain. The results show that there is a strong association between data and system quality, that affects organizational success.

Keywords: Data quality, performance, system quality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2119

Authors: Edward A. Osifodunrin, Jose Manuel Dias Lopes

Abstract:

In Nigeria, enormous efforts/resources had, over the years, been expended on promoting financial inclusion (FI); however, it is seemingly discouraging that many of its self-declared targets on FI remained unachieved, especially amongst the Rural Dwellers and Actors in the Informal Sectors (RDAIS). Expectedly, many reasons had been earmarked for these failures: low literacy level, huge informal/rural sectors etc. This study posits that in spite of these truly-debilitating factors, these FI policy failures could have been avoided or mitigated if the principles of active and better-managed citizens’ participation had been strictly followed in the (re)design/implementation of its FI policies. In other words, in a bid to mitigate the prevalent financial exclusion (FE) in Nigeria, this study hypothesizes the significant positive impact of involving the RDAIS in policy-wide decision making in the FI domain, backed by a preliminary empirical validation. Also, the study introduces the RDAIS-focused Participatory Financial Inclusion Policy (PFIP) as a major FI policy regeneration/improvement tool. The three categories of respondents that served as research subjects are FI experts in Nigeria (n = 72), RDAIS from the very rural/remote village of Unguwar Dogo in Northern Nigeria (n = 43) and RDAIS from another rural village of Sekere (n = 56) in the Southern region of Nigeria. Using survey design (5-point Likert scale questionnaires), random/stratified sampling, and descriptive/inferential statistics, the study often recorded independent consensus (amongst these three categories of respondents) that RDAIS’s active participation in iterative FI policy initiation, (re)design, implementation, (re)evaluation could indeed give improved FI outcomes. However, few questionnaire items also recorded divergent opinions and various statistically (in)significant differences on the mean scores of these three categories. The PFIP (or any customized version of it) should then be carefully integrated into the NFIS of Nigeria (and possibly in the NFIS of other developing countries) to truly/fully provide FI policy integration for these excluded RDAIS and arrest the prevalence of FE.

Keywords: Citizens’ participation, development, financial inclusion, formal financial services, national financial inclusion strategy, participatory financial inclusion policy, rural dwellers and actors in the informal sectors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 666

Authors: K. Jitkue, W. Srisang, C. Yaiprasert, K. Jaroensutasinee, M. Jaroensutasinee

Abstract:

This study aims at using multi-source data to monitor coral biodiversity and coral bleaching. We used coral reef at Racha Islands, Phuket as a study area. There were three sources of data: coral diversity, sensor based data and satellite data.

Keywords: Coral reefs, Remote sensing, Sea surfacetemperatue, Satellite imagery.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1553

Authors: Yang Bao, LuJing Zhang

Abstract:

Typical Intelligent Decision Support System is 4-based, its design composes of Data Warehouse, Online Analytical Processing, Data Mining and Decision Supporting based on models, which is called Decision Support System Based on Data Warehouse (DSSBDW). This way takes ETL,OLAP and DM as its implementing means, and integrates traditional model-driving DSS and data-driving DSS into a whole. For this kind of problem, this paper analyzes the DSSBDW architecture and DW model, and discusses the following key issues: ETL designing and Realization; metadata managing technology using XML; SQL implementing, optimizing performance, data mapping in OLAP; lastly, it illustrates the designing principle and method of DW in DSSBDW.

Keywords: Decision Support System, Data Warehouse, Data Mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3863

Authors: Hossein Morshedlou, Ahmad Abdollahzade Barforoush

Abstract:

Recent developments in storage technology and networking architectures have made it possible for broad areas of applications to rely on data streams for quick response and accurate decision making. Data streams are generated from events of real world so existence of associations, which are among the occurrence of these events in real world, among concepts of data streams is logical. Extraction of these hidden associations can be useful for prediction of subsequent concepts in concept shifting data streams. In this paper we present a new method for learning association among concepts of data stream and prediction of what the next concept will be. Knowing the next concept, an informed update of data model will be possible. The results of conducted experiments show that the proposed method is proper for classification of concept shifting data streams.

Keywords: Data Stream, Classification, Concept Shift, History.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1278

Authors: Takahiro Nishigaki, Katsumi Nitta, Takashi Onoda

Abstract:

In this paper, we present a method of applying Independent Topic Analysis (ITA) to increasing the number of document data. The number of document data has been increasing since the spread of the Internet. ITA was presented as one method to analyze the document data. ITA is a method for extracting the independent topics from the document data by using the Independent Component Analysis (ICA). ICA is a technique in the signal processing; however, it is difficult to apply the ITA to increasing number of document data. Because ITA must use the all document data so temporal and spatial cost is very high. Therefore, we present Incremental ITA which extracts the independent topics from increasing number of document data. Incremental ITA is a method of updating the independent topics when the document data is added after extracted the independent topics from a just previous the data. In addition, Incremental ITA updates the independent topics when the document data is added. And we show the result applied Incremental ITA to benchmark datasets.

Keywords: Text mining, topic extraction, independent, incremental, independent component analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1059

Authors: Kamaldeep Kaur, Arvinder Kaur, Ruchika Malhotra

Abstract:

The aim of this paper is to rank the impact of Object Oriented(OO) metrics in fault prediction modeling using Artificial Neural Networks(ANNs). Past studies on empirical validation of object oriented metrics as fault predictors using ANNs have focused on the predictive quality of neural networks versus standard statistical techniques. In this empirical study we turn our attention to the capability of ANNs in ranking the impact of these explanatory metrics on fault proneness. In ANNs data analysis approach, there is no clear method of ranking the impact of individual metrics. Five ANN based techniques are studied which rank object oriented metrics in predicting fault proneness of classes. These techniques are i) overall connection weights method ii) Garson-s method iii) The partial derivatives methods iv) The Input Perturb method v) the classical stepwise methods. We develop and evaluate different prediction models based on the ranking of the metrics by the individual techniques. The models based on overall connection weights and partial derivatives methods have been found to be most accurate.

Keywords: Artificial Neural Networks (ANNS), Backpropagation, Fault Prediction Modeling.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1758

Authors: M. A. Serag-Eldin

Abstract:

The paper presents the results of simple measurements conducted on a model of a wind-driven venturi-type room ventilator. The ventilator design is new and was developed employing mathematical modeling. However, the computational model was not validated experimentally for the particular application considered. The paper presents the performance of the ventilator model under laboratory conditions, for five different wind tunnel speeds. The results are used to both demonstrate the effectiveness of the new design and to validate the computational model employed to develop it.

Keywords: Venturi-flow, ventilation, Wind-energy, Wind flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1357

Authors: Jian-hua Yeh, Shi-yi Kuo

Abstract:

This paper discusses the classification process for medical data. In this paper, we use the data from ACM KDDCup 2008 to demonstrate our classification process based on latent topic discovery. In this data set, the target set and outliers are quite different in their nature: target set is only 0.6% size in total, while the outliers consist of 99.4% of the data set. We use this data set as an example to show how we dealt with this extremely biased data set with latent topic discovery and noise reduction techniques. Our experiment faces two major challenge: (1) extremely distributed outliers, and (2) positive samples are far smaller than negative ones. We try to propose a suitable process flow to deal with these issues and get a best AUC result of 0.98.

Keywords: classification, latent topics, outlier adjustment, feature scaling

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1642

Authors: Nouha Mhimdi, Wahiba Ben Abdessalem Karaa, Henda Ben Ghezala

Abstract:

Many methods are used to collect data like questionnaires, surveys, focus group interviews. Or the collection of poor-quality data resulting, for example, from poorly designed questionnaires, the absence of good translators or interpreters, and the incorrect recording of data allow conclusions to be drawn that are not supported by the data or to focus only on the average effect of the program or policy. There are several solutions to avoid or minimize the most frequent errors, including obtaining expert advice on the design or adaptation of data collection instruments; or use technologies allowing better "anonymity" in the responses. In this context, and to overcome the aforementioned problems, we suggest in this paper an approach to achieve the collection of relevant data, by carrying out a large-scale questionnaire-based survey. We have been able to collect good quality, consistent and practical data on hospital emergencies to improve emergency services in hospitals, especially in the case of epidemics or pandemics.

Keywords: Data collection, survey, database, data analysis, hospital emergencies.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 668

Authors: J. D. D. Daniel, K. N. Goh, S. M. Yusop

Abstract:

Trends in business intelligence, e-commerce and remote access make it necessary and practical to store data in different ways on multiple systems with different operating systems. As business evolve and grow, they require efficient computerized solution to perform data update and to access data from diverse enterprise business applications. The objective of this paper is to demonstrate the capability of DTS [1] as a database solution for automatic data transfer and update in solving business problem. This DTS package is developed for the sales of variety of plants and eventually expanded into commercial supply and landscaping business. Dimension data modeling is used in DTS package to extract, transform and load data from heterogeneous database systems such as MySQL, Microsoft Access and Oracle that consolidates into a Data Mart residing in SQL Server. Hence, the data transfer from various databases is scheduled to run automatically every quarter of the year to review the efficient sales analysis. Therefore, DTS is absolutely an attractive solution for automatic data transfer and update which meeting today-s business needs.

Keywords: Data Transformation Services (DTS), ObjectLinking and Embedding Database (OLEDB), Data Mart, OnlineAnalytical Processing (OLAP), Online Transactional Processing(OLTP).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2040

Authors: P. S. Hiremath, Siddu P. Algur

Abstract:

With the explosive growth of information sources available on the World Wide Web, it has become increasingly difficult to identify the relevant pieces of information, since web pages are often cluttered with irrelevant content like advertisements, navigation-panels, copyright notices etc., surrounding the main content of the web page. Hence, tools for the mining of data regions, data records and data items need to be developed in order to provide value-added services. Currently available automatic techniques to mine data regions from web pages are still unsatisfactory because of their poor performance and tag-dependence. In this paper a novel method to extract data items from the web pages automatically is proposed. It comprises of two steps: (1) Identification and Extraction of the data regions based on visual clues information. (2) Identification of data records and extraction of data items from a data region. For step1, a novel and more effective method is proposed based on visual clues, which finds the data regions formed by all types of tags using visual clues. For step2 a more effective method namely, Extraction of Data Items from web Pages (EDIP), is adopted to mine data items. The EDIP technique is a list-based approach in which the list is a linear data structure. The proposed technique is able to mine the non-contiguous data records and can correctly identify data regions, irrespective of the type of tag in which it is bound. Our experimental results show that the proposed technique performs better than the existing techniques.

Keywords: Web data records, web data regions, web mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1901

Authors: H. W. Ker

Abstract:

Longitudinal data typically have the characteristics of changes over time, nonlinear growth patterns, between-subjects variability, and the within errors exhibiting heteroscedasticity and dependence. The data exploration is more complicated than that of cross-sectional data. The purpose of this paper is to organize/integrate of various visual-graphical techniques to explore longitudinal data. From the application of the proposed methods, investigators can answer the research questions include characterizing or describing the growth patterns at both group and individual level, identifying the time points where important changes occur and unusual subjects, selecting suitable statistical models, and suggesting possible within-error variance.

Keywords: Data exploration, exploratory analysis, HLMs/LMEs, longitudinal data, visual-graphical methods.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2095

Authors: H. Ahmad, S. Kermanshahani, A. Simonet, M. Simonet

Abstract:

The data exchanged on the Web are of different nature from those treated by the classical database management systems; these data are called semi-structured data since they do not have a regular and static structure like data found in a relational database; their schema is dynamic and may contain missing data or types. Therefore, the needs for developing further techniques and algorithms to exploit and integrate such data, and extract relevant information for the user have been raised. In this paper we present the system OSIX (Osiris based System for Integration of XML Sources). This system has a Data Warehouse model designed for the integration of semi-structured data and more precisely for the integration of XML documents. The architecture of OSIX relies on the Osiris system, a DL-based model designed for the representation and management of databases and knowledge bases. Osiris is a viewbased data model whose indexing system supports semantic query optimization. We show that the problem of query processing on a XML source is optimized by the indexing approach proposed by Osiris.

Keywords: Data integration, semi-structured data, views, XML.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1590

Authors: Rajneesh Rani, Renu Dhir, G. S. Lehal

Abstract:

Script identification is one of the challenging steps in the development of optical character recognition system for bilingual or multilingual documents. In this paper an attempt is made for identification of English numerals at word level from Punjabi documents by using Gabor features. The support vector machine (SVM) classifier with five fold cross validation is used to classify the word images. The results obtained are quite encouraging. Average accuracy with RBF kernel, Polynomial and Linear Kernel functions comes out to be greater than 99%.

Keywords: Script identification, gabor features, support vector machines.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2128

Authors: Mustafa Al Sukar, Azzam Sleit, Abdullatif Abu-Dalhoum, Bassam Al-Kasasbeh

Abstract:

Use and abuse of drugs by teens is very common and can have dangerous consequences. The drugs contribute to physical and sexual aggression such as assault or rape. Some teenagers regularly use drugs to compensate for depression, anxiety or a lack of positive social skills. Teen resort to smoking should not be minimized because it can be "gateway drugs" for other drugs (marijuana, cocaine, hallucinogens, inhalants, and heroin). The combination of teenagers' curiosity, risk taking behavior, and social pressure make it very difficult to say no. This leads most teenagers to the questions: "Will it hurt to try once?" Nowadays, technological advances are changing our lives very rapidly and adding a lot of technologies that help us to track the risk of drug abuse such as smart phones, Wireless Sensor Networks (WSNs), Internet of Things (IoT), etc. This technique may help us to early discovery of drug abuse in order to prevent an aggravation of the influence of drugs on the abuser. In this paper, we have developed a Decision Support System (DSS) for detecting the drug abuse using Artificial Neural Network (ANN); we used a Multilayer Perceptron (MLP) feed-forward neural network in developing the system. The input layer includes 50 variables while the output layer contains one neuron which indicates whether the person is a drug addict. An iterative process is used to determine the number of hidden layers and the number of neurons in each one. We used multiple experiment models that have been completed with Log-Sigmoid transfer function. Particularly, 10-fold cross validation schemes are used to access the generalization of the proposed system. The experiment results have obtained 98.42% classification accuracy for correct diagnosis in our system. The data had been taken from 184 cases in Jordan according to a set of questions compiled from Specialists, and data have been obtained through the families of drug abusers.

Keywords: Artificial Neural Network, Decision Support System, drug abuse, drug addiction, Multilayer Perceptron.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1682

Authors: Abeba Nigussie Turi, Xiangming Samuel Li

Abstract:

Data-driven business models are more typical for established businesses than early-stage startups that strive to penetrate a market. This paper provided an extensive discussion on the principles of data analytics for early-stage digital entrepreneurial businesses. Here, we developed data-driven decision-making (DDDM) framework that applies to startups prone to multifaceted barriers in the form of poor data access, technical and financial constraints, to state some. The startup DDDM framework proposed in this paper is novel in its form encompassing startup data analytics enablers and metrics aligning with startups' business models ranging from customer-centric product development to servitization which is the future of modern digital entrepreneurship.

Keywords: Startup data analytics, data-driven decision-making, data acquisition, data generation, digital entrepreneurship.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 828

Authors: D. Fodorean, D.C. Popa, F. Jurca, M. Ruba

Abstract:

the paper presents the optimization results for several electrical machines dedicated for powered electric wheel-chairs. The optimization, using the Hook-Jeeves algorithm, was employed based on a design approach which takes into consideration the road conditions. Also, through numerical simulations (based on finite element method), the analytical approach was validated. The optimization approach gave satisfactory results and the best suited variant was chosen for the motorization of the wheel-chair.

Keywords: electrical machines, numerical validation, optimization, electric wheel chair.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2072

Authors: Minsoo Lee, Yearn Jeong Kim, Yun-mi Kim, Sujeung Cheong, Sookyung Song

Abstract:

Bio-chips are used for experiments on genes and contain various information such as genes, samples and so on. The two-dimensional bio-chips, in which one axis represent genes and the other represent samples, are widely being used these days. Instead of experimenting with real genes which cost lots of money and much time to get the results, bio-chips are being used for biological experiments. And extracting data from the bio-chips with high accuracy and finding out the patterns or useful information from such data is very important. Bio-chip analysis systems extract data from various kinds of bio-chips and mine the data in order to get useful information. One of the commonly used methods to mine the data is classification. The algorithm that is used to classify the data can be various depending on the data types or number characteristics and so on. Considering that bio-chip data is extremely large, an algorithm that imitates the ecosystem such as the ant algorithm is suitable to use as an algorithm for classification. This paper focuses on finding the classification rules from the bio-chip data using the Ant Colony algorithm which imitates the ecosystem. The developed system takes in consideration the accuracy of the discovered rules when it applies it to the bio-chip data in order to predict the classes.

Keywords: Ant Colony System, DNA chip data, Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1469

Authors: Klaus Stranacher, Vesna Krnjic, Thomas Zefferer

Abstract:

The public sector holds large amounts of data of various areas such as social affairs, economy, or tourism. Various initiatives such as Open Government Data or the EU Directive on public sector information aim to make these data available for public and private service providers. Requirements for the provision of public sector data are defined by legal and organizational frameworks. Surprisingly, the defined requirements hardly cover security aspects such as integrity or authenticity. In this paper we discuss the importance of these missing requirements and present a concept to assure the integrity and authenticity of provided data based on electronic signatures. We show that our concept is perfectly suitable for the provisioning of unaltered data. We also show that our concept can also be extended to data that needs to be anonymized before provisioning by incorporating redactable signatures. Our proposed concept enhances trust and reliability of provided public sector data.

Keywords: Trusted Public Sector Data, Integrity, Authenticity, Reliability, Redactable Signatures.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1758

Authors: C. A. Barros, Ana P. Barroso

Abstract:

Any industrial company needs to determine the amount of variation that exists within its measurement process and guarantee the reliability of their data, studying the performance of their measurement system, in terms of linearity, bias, repeatability and reproducibility and stability. This issue is critical for automotive industry suppliers, who are required to be certified by the 16949:2016 standard (replaces the ISO/TS 16949) of International Automotive Task Force, defining the requirements of a quality management system for companies in the automotive industry. Measurement System Analysis (MSA) is one of the mandatory tools. Frequently, the measurement system in companies is not connected to the equipment and do not incorporate the methods proposed by the Automotive Industry Action Group (AIAG). To address these constraints, an R&D project is in progress, whose objective is to develop a web and cloud-based MSA tool. This MSA tool incorporates Industry 4.0 concepts, such as, Internet of Things (IoT) protocols to assure the connection with the measuring equipment, cloud computing, artificial intelligence, statistical tools, and advanced mathematical algorithms. This paper presents the preliminary findings of the project. The web and cloud-based MSA tool is innovative because it implements all statistical tests proposed in the MSA-4 reference manual from AIAG as well as other emerging methods and techniques. As it is integrated with the measuring devices, it reduces the manual input of data and therefore the errors. The tool ensures traceability of all performed tests and can be used in quality laboratories and in the production lines. Besides, it monitors MSAs over time, allowing both the analysis of deviations from the variation of the measurements performed and the management of measurement equipment and calibrations. To develop the MSA tool a ten-step approach was implemented. Firstly, it was performed a benchmarking analysis of the current competitors and commercial solutions linked to MSA, concerning Industry 4.0 paradigm. Next, an analysis of the size of the target market for the MSA tool was done. Afterwards, data flow and traceability requirements were analysed in order to implement an IoT data network that interconnects with the equipment, preferably via wireless. The MSA web solution was designed under UI/UX principles and an API in python language was developed to perform the algorithms and the statistical analysis. Continuous validation of the tool by companies is being performed to assure real time management of the ‘big data’. The main results of this R&D project are: MSA Tool, web and cloud-based; Python API; New Algorithms to the market; and Style Guide of UI/UX of the tool. The MSA tool proposed adds value to the state of the art as it ensures an effective response to the new challenges of measurement systems, which are increasingly critical in production processes. Although the automotive industry has triggered the development of this innovative MSA tool, other industries would also benefit from it. Currently, companies from molds and plastics, chemical and food industry are already validating it.

Keywords: Automotive industry, Industry 4.0, internet of things, IATF 16949:2016, measurement system analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 996

Authors: Abdelhadi Lotfi, Abdelkader Benyettou

Abstract:

In this work, a training algorithm for probabilistic neural networks (PNN) is presented. The algorithm addresses one of the major drawbacks of PNN, which is the size of the hidden layer in the network. By using a cross-validation training algorithm, the number of hidden neurons is shrunk to a smaller number consisting of the most representative samples of the training set. This is done without affecting the overall architecture of the network. Performance of the network is compared against performance of standard PNN for different databases from the UCI database repository. Results show an important gain in network size and performance.

Keywords: Classification, probabilistic neural networks, network optimization, pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1226

Authors: Ekachai Phaisangittisagul, Rapeepol Chongprachawat

Abstract:

Obtaining labeled data in supervised learning is often difficult and expensive, and thus the trained learning algorithm tends to be overfitting due to small number of training data. As a result, some researchers have focused on using unlabeled data which may not necessary to follow the same generative distribution as the labeled data to construct a high-level feature for improving performance on supervised learning tasks. In this paper, we investigate the impact of the relationship between unlabeled and labeled data for classification performance. Specifically, we will apply difference unlabeled data which have different degrees of relation to the labeled data for handwritten digit classification task based on MNIST dataset. Our experimental results show that the higher the degree of relation between unlabeled and labeled data, the better the classification performance. Although the unlabeled data that is completely from different generative distribution to the labeled data provides the lowest classification performance, we still achieve high classification performance. This leads to expanding the applicability of the supervised learning algorithms using unsupervised learning.

Keywords: Autoencoder, high-level feature, MNIST dataset, selftaught learning, supervised learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1832

Authors: M. Klimavicius

Abstract:

This paper proposes a modeling methodology for the development of data analysis solution. The Author introduce the approach to address data warehousing issues at the at enterprise level. The methodology covers the process of the requirements eliciting and analysis stage as well as initial design of data warehouse. The paper reviews extended business process model, which satisfy the needs of data warehouse development. The Author considers that the use of business process models is necessary, as it reflects both enterprise information systems and business functions, which are important for data analysis. The Described approach divides development into three steps with different detailed elaboration of models. The Described approach gives possibility to gather requirements and display them to business users in easy manner.

Keywords: Data warehouse, data analysis, business processmanagement.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1393

Authors: Aleksandra Zysk, Pawel Badura

Abstract:

Recognizing and controlling vocal registers during singing is a difficult task for beginner vocalist. It requires among others identifying which part of natural resonators is being used when a sound propagates through the body. Thus, an application has been designed allowing for sound recording, automatic vocal register recognition (VRR), and a graphical user interface providing real-time visualization of the signal and recognition results. Six spectral features are determined for each time frame and passed to the support vector machine classifier yielding a binary decision on the head or chest register assignment of the segment. The classification training and testing data have been recorded by ten professional female singers (soprano, aged 19-29) performing sounds for both chest and head register. The classification accuracy exceeded 93% in each of various validation schemes. Apart from a hard two-class clustering, the support vector classifier returns also information on the distance between particular feature vector and the discrimination hyperplane in a feature space. Such an information reflects the level of certainty of the vocal register classification in a fuzzy way. Thus, the designed recognition and training application is able to assess and visualize the continuous trend in singing in a user-friendly graphical mode providing an easy way to control the vocal emission.

Keywords: Classification, singing, spectral analysis, vocal emission, vocal register.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1313

Authors: Muslihah Wook, Zawiyah M. Yusof, Mohd Zakree Ahmad Nazri

Abstract:

Data mining has been integrated into application systems to enhance the quality of the decision-making process. This study aims to focus on the integration of data mining technology and Knowledge Management System (KMS), due to the ability of data mining technology to create useful knowledge from large volumes of data. Meanwhile, KMS vitally support the creation and use of knowledge. The integration of data mining technology and KMS are popularly used in business for enhancing and sustaining organizational performance. However, there is a lack of studies that applied data mining technology and KMS in the education sector; particularly students- academic performance since this could reflect the IHL performance. Realizing its importance, this study seeks to integrate data mining technology and KMS to promote an effective management of knowledge within IHLs. Several concepts from literature are adapted, for proposing the new integrative data mining technology and KMS framework to an IHL.

Keywords: Data mining, Institutions of Higher Learning, Knowledge Management System, Students' academic performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2142

Authors: Mohamed Elkholy, Ahmed Elfatatry

Abstract:

Cloud computing has emerged as a flexible computing paradigm that reshaped the Information Technology map. However, cloud computing brought about a number of security challenges as a result of the physical distribution of computational resources and the limited control that users have over the physical storage. This situation raises many security challenges for data integrity and confidentiality as well as authentication and access control. This work proposes a security mechanism for data integrity that allows a data owner to be aware of any modification that takes place to his data. The data integrity mechanism is integrated with an extended Kerberos authentication that ensures authorized access control. The proposed mechanism protects data confidentiality even if data are stored on an untrusted storage. The proposed mechanism has been evaluated against different types of attacks and proved its efficiency to protect cloud data storage from different malicious attacks.

Keywords: Access control, data integrity, data confidentiality, Kerberos authentication, cloud security.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1772

Authors: W. Katsarapong, W. Srisang, K. Jaroensutasinee, M. Jaroensutasinee

Abstract:

National Biodiversity Database System (NBIDS) has been developed for collecting Thai biodiversity data. The goal of this project is to provide advanced tools for querying, analyzing, modeling, and visualizing patterns of species distribution for researchers and scientists. NBIDS data record two types of datasets: biodiversity data and environmental data. Biodiversity data are specie presence data and species status. The attributes of biodiversity data can be further classified into two groups: universal and projectspecific attributes. Universal attributes are attributes that are common to all of the records, e.g. X/Y coordinates, year, and collector name. Project-specific attributes are attributes that are unique to one or a few projects, e.g., flowering stage. Environmental data include atmospheric data, hydrology data, soil data, and land cover data collecting by using GLOBE protocols. We have developed webbased tools for data entry. Google Earth KML and ArcGIS were used as tools for map visualization. webMathematica was used for simple data visualization and also for advanced data analysis and visualization, e.g., spatial interpolation, and statistical analysis. NBIDS will be used by park rangers at Khao Nan National Park, and researchers.

Keywords: GLOBE protocol, Biodiversity, Database System, ArcGIS, Google Earth and webMathematica.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1984