Статьи журнала - International Journal of Information Technology and Computer Science
Все статьи: 1165
Unsupervised Learning based Modified C- ICA for Audio Source Separation in Blind Scenario
Статья научная
Separating audio sources from a convolutive mixture of signals from various independent sources is a very fascinating area in personal and professional context. The task of source separation becomes trickier when there is no idea about mixing environment and can be termed as blind audio source separation (BASS). Mixing scenario becomes more complicated when there is a difference between number of audio sources and number of recording microphones, under determined and over determined mixing. The main challenge in BASS is quality of separation and separation speed and the convergence speed gets compromised when separation techniques focused on quality of separation. This work proposed divergence algorithm designed for faster convergence speed along with good quality of separation. Experiments are performed for critically determined audio recording, where number of audio sources is equal to number of microphones and no noise component is taken into consideration. The result advocates that the modified convex divergence algorithm enhance the convergence speed by 20-22% and good quality of separation than conventional convex divergence ICA, Fast ICA, JADE.
Бесплатно
Uplink Capacity Estimation and Enhancement in WCDMA Network
Статья научная
Uplink planification in a WCDMA network consists of estimating the maximum capacity that a cell can support, by using the quality of service equation designed by (E_b)/(N_0). We are interested in this work on two different scenarios: an isolated cell and multiple cells. This capacity is adversely affected by interferences due to own mobile stations and to others belonging to neighboring cells. In order to enhance capacity and minimize the blocking probability of new requests in the cell, we have proposed a Freeing Resources algorithm which consists of releasing some mobile stations in the handover area with the overloaded cell. This algorithm is based on freeing 1, 2 and 3 mobile stations of 12.2 kbps and 1 mobile station of 64 kbps.
Бесплатно
Usability Evaluation Criteria for Internet of Things
Статья научная
The field of usability, user experience (UX) design and human-computer interaction (HCI) arose in the realm of desktop computers and applications. The current experience in computing has radically evolved into ubiquitous computing over the preceding years. Interactions these days take place on different devices: mobile phones, e-readers and smart TVs, amid numerous smart devices. The use of one service across multiple devices is, at present, common with different form factors. Academic researchers are still trying to figure out the best design techniques for new devices and experiences. The Internet of Things (IoT) is growing, with an ever wider range of daily objects acquiring connectivity, sensing ability and increased computing power. Designing for IoT raises a lot of challenges; the obvious difference being the much wider variety of device form factors. IoT is still a technically driven field, thus the usability of many of IoT products is, in some way, of the level anticipated of mature consumer products. This study focuses on proposing a usability evaluation criterion for the generic IoT architecture and essential technological components.
Бесплатно
Usability and Security in User Interface Design: A Systematic Literature Review
Статья научная
Systems carry sensitive data where users are involved. There is need for security concern for the modern software applications. We can term them as 'untrusted clients'. Internet usage has rapidly grown over the years and, more users are opening their information system to their clientele, it is essential to understand users' data that need protecting and to control system access as well and the rights of users of the system. Because of today's increasingly nomadic lifestyle, where they allow users to connect to information systems from anywhere with all the devices in the market, the users need to carry part of the information system out of the secure infrastructure. Insecurity in user interfaces is caused by user ignoring functionalities in the system where some are not only a threat but can harm the system e.g. leaving network services active even though the user does not need them, or when a user is having little or no information of the available security measures. This research paper aims critically address through a review of existing literature, the importance of balance or trade-off between usability and the security of the system. Systematic review method involved a physical exploration of some conference proceedings and journals to conduct the literature review. Research questions relating to usability and security were asked and the criteria for usability and security evaluations were identified. This systematic literature review is valuable in closing the gap between usability and security in software development process, where usability and security engineering needs to be considered for a better quality end-user software.
Бесплатно
Usability of Cloud Computing to Improve Higher Education
Статья научная
Cloud computing as a new paradigm has grown from a promising idea to one of the fastest research and development paradigm in education sector. It is a hot research area that applies in all sectors where we require high performance and fast access to resources and services. Cloud computing usability in education is wide-ranging, as acknowledged by many educational institutions around the world. This paper attempts to address the need for utilizing cloud computing in higher education in Kingdom of Saudi Arabia for all the disciplines to raise its level and solve the obstacles that faced the learning process. In addition, cloud computing facilitates educators and students to be more experienced in cloud computing and it prepares them to get benefits of usefulness to become more motivated and effective. Survey is used as a research design to validate the proposed solution. The results show that the proposal to improve higher education is highly supported by the professionals working in the industry and academia.
Бесплатно
Use of API’s for Comparison of different product information under one roof: analysis using SVM
Статья научная
The internet has grown in leaps and bounds and hence all the data is now available online; be it shopping, banking, private and public institutes or universities, private public sectors are all making their presence felt online. The online data is just a click away thanks to ubiquitous systems today. The browser does not require any specific program set up hence easier for the end user. Earlier the data online was static used HTML now it’s dynamic uses ASP, ASP.NET, Servlet, JSP and other operational tools therefore the internet operation is broken down into many categories. The problem arises with the customer while trying to buy something online. There are lots of online stores sometimes it’s difficult to browse through all products to get a better deal. The pricing of products are different on different sites, this is the first gap at the customer end. The second problem arises at the provider end. The second gap here is to understand the customer need. How can the variation in prices be checked? ; The existing prices available on sites cannot be changed but the customer can be provided with options to select the best deal of the same product. For the first problem the paper deals with an API implementation wherein the information of at least some products is compared under one roof. How can the provider know the genuine customer? ; The second problem is resolved by the use of SVM. Last problem is in detecting if a customer visiting a site will actually buy the product being compared. The paper focuses on the selection of ASP.NET to deal with the implementation problems stated and find solution to the forecasting problem using SVM. SVM and C4.5 are used for comparison.
Бесплатно
Статья научная
Non-conformance to quality in a project often can lead to a major reason for project failure resulted in not meeting the triple constraints of project management, scope, time and cost. To prevent it from happening, a quality check against the standard for quality needs to be conducted at the critical stages of ERP implementation project. Proactive quality management by the quality gate process is embedded in the implementation methodology to help secure quality outcomes for the customers. However, getting the schedule of each quality gate timely fixed by the independent quality reviewer with the project manager of a newly started project can often be problematic without having a systematic approach implemented. Recent research has provided an application with the use of project management information systems (PMIS) for such implementations in improvement of quality management systems requirements [1]. This article describes how PMIS was used to implement the project quality gate process for ERP implementation projects conducted by the solution provider for their customers in the various industries in Japan. PMIS was found to be effective in identifying, notifying and influencing the project managers to timely initiate the quality gate process based on the schedule fixed for each quality gate review.
Бесплатно
Using AHP Method for Educational and Vocational Guidance
Статья научная
This work focuses on the use of multi-criteria decision-making method AHP for using in educational and vocational guidance. Analytical Hierarchy Process (AHP), proposed by the mathematician Thomas Saaty in 1980, is a method of analysis greatly used in the context of a multi-criteria analysis; it allows the comparison and the choice between the preset options. To achieve this goal, a vital work, preceded the use of the AHP method, which consists in doing a prototyping of trades according to the guidance criteria and sub-criteria. The IT system based on this method allows the student to find, firstly, the activities' sectors which are the most appropriate to his/her profile, to choose subsequently the trades and finally, to identify, the potential training paths.
Бесплатно
Using Fuzzy Logic to Evaluate Normalization Completeness for an Improved Database Design
Статья научная
A new approach, to measure normalization completeness for conceptual model, is introduced using quantitative fuzzy functionality in this paper. We measure the normalization completeness of the conceptual model in two steps. In the first step, different normalization techniques are analyzed up to Boyce Codd Normal Form (BCNF) to find the current normal form of the relation. In the second step, fuzzy membership values are used to scale the normal form between 0 and 1. Case studies to explain schema transformation rules and measurements. Normalization completeness is measured by considering completeness attributes, preventing attributes of the functional dependencies and total number of attributes such as if the functional dependency is non-preventing then the attributes of that functional dependency are completeness attributes. The attributes of functional dependency which prevent to go to the next normal form are called preventing attributes.
Бесплатно
Using Logic Programming to Represent Information Content Inclusion Relations
Статья научная
Datalog is a widely recognised language for a certain class of deductive databases. Information Content Inclusion Relation (IIR) formulates a general, information theoretic relationship between: data constructs; between data constructs and real world objects, and between real world objects. IIR is particularly concerned with the information that data carry. It would therefore seem desirable to find out whether IIR and reasoning based on IIR may be implemented by using 'safe' Datalog. We present and prove the following theorem: Any database system that can be modelled using IIR can be represented as a 'safe' Datalog program.} This paper explores the nature of the relationship between the two frameworks for representing domains of application, in order that such representations of IIR by 'safe' Datalog can then be used as a tool for the analysis of any site that can be approached with the notion of information content, and in particular any given database, and hence how a database works may be approached in terms of information content of events.
Бесплатно
Using Negative Binomial Regression Analysis to Predict Software Faults: A Study of Apache Ant
Статья научная
Negative binomial regression has been proposed as an approach to predicting fault-prone software modules. However, little work has been reported to study the strength, weakness, and applicability of this method. In this paper, we present a deep study to investigate the effectiveness of using negative binomial regression to predict fault-prone software modules under two different conditions, self-assessment and forward assessment. The performance of negative binomial regression model is also compared with another popular fault prediction model—binary logistic regression method. The study is performed on six versions of an open-source objected-oriented project, Apache Ant. The study shows (1) the performance of forward assessment is better than or at least as same as the performance of self-assessment; (2) in predicting fault-prone modules, negative binomial regression model could not outperform binary logistic regression model; and (3) negative binomial regression is effective in predicting multiple errors in one module.
Бесплатно
Using String Kernel for Document Clustering
Статья научная
In this paper, we present a string kernel based method for documents clustering. Documents are viewed as sequences of strings, and documents similarity is calculated by the kernel function. According to the documents similarity, spectral clustering algorithm is used to group documents. Experimental results shows that string kernel method outperform the standard k-means algorithm on the Reuters-21578 dataset.
Бесплатно
Using Web Services Standards for Dealing with Complexities of Multiple Incompatible Applications
Статья научная
Organizations’ dependence on custom enterprise software and web applications from independent software developers and software companies create a lot of problems such as integration, interoperability, security, and system maintenance. This paper seeks to provide a better approach by using Web services standards in dealing with the complexity of multiple incompatible applications that were written in different programming languages on multiple computers and also making it possible for organizations to add a new layer of abstraction that is open, standards-based, and easy to integrate with any new or existing system. The combination of Service Oriented Architecture and Web services will be used to provide a rapid integration solution that will quickly and easily align Information Technology investments and corporate strategies by focusing on shared data and reusable services rather than proprietary integration products.
Бесплатно
Using an MST based Value for ε in DBSCAN Algorithm for Obtaining Better Result
Статья научная
In this paper, an objective function based on minimal spanning tree (MST) of data points is proposed for clustering and a density-based clustering technique has been used in an attempt to optimize the specified objective function in order to detect the “natural grouping” present in a given data set. A threshold based on MST of data points of each cluster thus found is used to remove noise (if any present in the data) from the final clustering. A comparison of the experimental results obtained by DBSCAN (Density Based Spatial Clustering of Applications with Noise) algorithm and the proposed algorithm has also been incorporated. It is observed that our proposed algorithm performs better than DBSCAN algorithm. Several experiments on synthetic data set in R^2 and R^3 show the utility of the proposed method. The proposed method has also found to provide good results for two real life data sets considered for experimentation. Note thatK-means is one of the most popular methods adopted to solve the clustering problem. This algorithm uses an objective function that is based on minimization of squared error criteria. Note that it may not always provide the “natural grouping” though it is useful in many applications.
Бесплатно
Статья научная
This paper studies the forecasting mechanism of the most widely used machine learning algorithms, namely linear discriminant analysis, logistic regression, k-nearest neighbors, random forests, artificial neural network, naive Bayes, classification and regression trees, support vector machines, adaptive boosting, and stacking ensemble model, in forecasting first-generation college students’ six-year graduation using the first college year’s data. Five standard evaluating metrics are used to evaluate these models. The results show that these machine learning models can significantly predict first-generation college students’ six-year graduation with mean forecasting accuracy rate spanning from 69.58% to 75.17% and median forecasting accuracy rate spanning from 70.37% to 74.52%. Among these machine learning algorithms, stacking ensemble model, logistic regression model, and linear discriminant analysis are the best three ones in terms of mean forecasting accuracy rate. Furthermore, the results from the repeated ten-fold cross-validation process reveal that the variations of the five evaluating metrics exhibit remarkably different patterns across the ten machine learning algorithms.
Бесплатно
Utilizing Conceptual Indexing to Enhance the Effectiveness of Vector Space Model
Статья научная
One of the main purposes of the semantic Web is to improve the retrieval performance of search systems. Unlike keyword based search systems, the semantic search systems aim to discover pages related to the query's concepts rather than merely collecting all pages instantiating its keywords. To that end, the concepts must be defined to be used as a semantic index instead of the traditional lexical one. In fact, The Arabic language is still far from being semantically searchable. Therefore, this paper proposed a model that exploits the Universal Word Net ontology for producing an Arabic Concepts-Space to be used as the index of Semantic Vector Space Model. The Vector Space Model is one of the most common information retrieval models due to its capability of expressing the documents' structure. However, like all keyword-based search systems, its sensitivity to the query's keywords reduces its retrieval effectiveness. The proposed model allows the VSM to represent Arabic documents by their topic, and thus classify them semantically. This, consequently, enhances the retrieval effectiveness of the search system.
Бесплатно
Utilizing Neural Networks for Stocks Prices Prediction in Stocks Markets
Статья научная
The neural networks, AI applications, are effective prediction methods. Therefore, in the current research a prediction system was proposed using these neural networks. It studied the technical share indices, viewing price not only as a function of time, but also as a function depending on several indices among which were the opening and closing, top and bottom trading session prices or trading volume. The above technical indices of a number of Egyptian stock market shares during the period from 2007 to 2017, which can be used for training the proposed system, were collected and used as follows: The data were divided into two sets. The first one contained 67% of the total data and was used for training neural networks and the second contained 33% and was used for testing the proposed system. The training set was segmented into subsets used for training a number of neural networks. The output of such networks was used for training another network hierarchically. The system was, then, tested using the rest of the data.
Бесплатно
Validated CMS: Towards New Generation of Web Content Management Systems on Web 2.0
Статья научная
Web 2.0 makes users the main actors for publishing content and creating applications on the web. The increasing of information overload and consequently the decrease of its quality are the main problems of this domain. Content Management Systems (CMS) provide the ability to publish on the web by offering simple publishing tools for ordinary users with no technical skills. Content available on the web created using the CMS is not well controlled and requires efficient process that evaluates its quality. Therefore, Content Management Systems contribute to the problem related to information and content quality similarly to Web 2.0 tools. The mechanism of validating content has proved a high-level of content’s quality control by involving users in the process according to Web 2.0 philosophy. From these perspectives, we develop Validated Content Management System (VCMS) as a new Web 2.0 tool that supports content validation mechanisms. This article presents the VCMS and its ability to provide an effective quality control for web content. We introduce a new manner of collaborative publishing and we give an overview about features of our system and its core architecture.
Бесплатно
Validation of Novel Approach to Detect Type Mismatch Problem Using Component Based Development
Статья научная
Adaptation software component is a crucial problem in component-based software engineering (CBSE). Components that assembled or reused sometimes cannot perfectly fit one another because of the incompatibility issues between them. The focus today is on finding adaptation technique, to solve the mismatch between component interfaces and to guarantee that the software components are able to interact in the right way. This paper will focus on detecting mismatch, which considers as an important step through adaptation process. We propose a solution to detect mismatch, by suggesting improvement in Symbolic Transition Systems that used in representing component interface, and synchronous vector algorithm to deal with parameters data type mismatch.
Бесплатно
Variant-Order Statistics based Model for Real-Time Plant Species Recognition
Статья научная
There are an urgent need of categorizing plant by its species, to help botanist setting up a plant species database. However, plant recognition model is still very challenging task in computer vision and can be onerous and time consuming because of inefficient representation approaches. This paper, proposes a recognition model for classifying botanical species from leaf images, using combination of variant-order statistics based measures. Hence, the spatial coordinates values of gray pixels defines the qualities of texture, for the proposed model a gray-scale approach is adopted for analyzing the local patterns of leaves images using second and higher order statistical measures. While, first order statistical measures are used to extract color descriptors from leaves images. Evaluation of the proposed model shows the importance of combining variant-order statistics measures for enhancing the plant leaf recognition accuracy. Several experiments on Flavia dataset and swedish dataset are conducted. Experimental results indicates that; the proposed model yields to improve the recognition rate up to 97.1% and 94.7% for both Flavia and Swedish dataset respectively; while taking less execution time.
Бесплатно
