International Journal of Computer (IJC - Global Society of Scientific Research and Researchers, GSSRR)
Not a member yet
459 research outputs found
Sort by
A Comparative Study on Business Forecasting Accuracy among Neural Networks and Time Series
Get PDFThis study shows that neural networks have been advocated as an alternative to traditional statistical forecasting methods. Numerous articles comparing performances of statistical and Neural Networks (NNs) models are available in the literature. The need for increased accuracies in time series forecasting has motivated the researchers to develop innovative models. The results obtained in this study suggest that the approach of combining the strengths of the conventional and ANN techniques provides a robust modeling framework capable of capturing the non-linear nature of the complex time series and thus producing more accurate forecasts
Autonomic Cloud Computing: A Review
Get PDFThe wide acceptability of cloud computing and its adoption, though remarkable, also gave the technology its greatest challenge in \u27user expectation\u27. These challenges include; Reliability and availability, integration and interoperability, scalability, virtual machine migration policies, failure prediction, and resource management. In this paper, a general review of cloud computing was done highlighting its challenges. Autonomic Cloud computing was also reviewed. Future research areas were identified
Binary Image Segmentation Using Classification Methods: Support Vector Machines, Artificial Neural Networks and Kth Nearest Neighbours
Get PDFThe principal objective of this work is to demonstrate efficient parameter selection for various networks used in binary image segmentation. The Support Vector Machines using four kernel functions (i.e., Radial Basis Function, Quadratic, Polynomial, and Linear), Neural Networks (i.e., Feed-forward Back-propagation) and Kth Nearest Neighbours algorithm were applied to five different datasets that had been generated from a given image. Pixel coordinates (x,y) were considered as inputs. Grid search and cross-validation were performed to identify the optimal network parameters. All experiments were repeated five times in order to develop confidence in the obtained results. High accuracy was achieved in most cases 95% for SVM-RBF, 90.4% for SVM-Quadratic, 90.8% for SVM-Polynomial, 60% for SVM-Linear, 88% for Neural Networks and 97% for K-NN. After grid search for SVM-RBF, the accuracy reached 98%. In this project, SVM-RBF showed a high level of accuracy and consistency. It was also found that the selected features (pixel coordinates) were discriminative
Review Aspects of Using Social Annotation for Enhancing Search Engine Performance
Get PDFRecently, search engines have improved to be more efficient in supporting user’s search process. Although they enhanced their capabilities to support user, still searcher spend long times in navigation. This is due to the different nature of users, where users have changeable interest and different culture, domain, and expressions. So, for improving search and make it closed to user’s expectation; user’s preferences have to be discovered. Nowadays, Information Retrieval researchers concern with Personalized Search which provides user’s preferences discovering. In this contribution, many efforts put path extracting user’s preferences through follow their behaviors, and action. Recently, researches focus on social annotations as additional metadata that may be used for extracting user’s preferences and interests.This paper reviews different aspects of using social annotation (as additional metadata) for enhancing search engines capabilities. Moreover, it especially focuses on personalized search which became today part of web 3.0 improvements. So, it proposes to categorize efforts in this field into two parts. The first concerns with improving personalized search by extracting user’s interests, and the second is for supporting personalized search by linking search phases to standard model
Assessing Information Quality of Blackboard System
Get PDFThis paper reports on how a positivist research paradigm was conducted with the aim to assess the information quality of the Blackboard system. It outlines the application of the IS-Impact Measurement Model for the purpose of testing the variables for the construct of “Information Quality.” The investigation in this paper is a part of a research project aiming to measure the success of the Blackboard system adopted in a higher education institute. Data for this investigation are gathered from students in Saudi Electronic University in the Kingdom of Saudi Arabia. This paper explores the factors related to information quality affecting the success of the use of the Blackboard system. It concludes by confirming that information quality positively affects the use of the Blackboard system.
Hybrid DWT-SVD Digital Image Watermarking
Get PDFThe protection of the multimedia data is one of the main issue in the global village. Several procedures are implemented to protect the digital data. Watermarking provide the robust solution for multimedia contents security. It can be easily used to protect the digital color images form illegal use and increase the stoutness of images against intentional and unintentional attacks by computer hackers and crackers. Singular Value Decomposition (SVD) and Discrete Wavelet Transformation (DWT) is a hybrid watermarking process because it is efficiently implemented during the embedding and extracting stages of digital images watermarking. Embedding information does not affect the quality of original images. Embedded information is hidden from the non-authorized person. Using DWT-SVD method, the original and watermark images was divided into separate color channels RGB. R channels of both images were selected for embedding using secret beta key. Reverse procedure was applied to extract the watermark image for authentication or verification of contents. The values of PSNR, NC, MSE, SSIM, RMSE, SNR were determined seemed well sheltered.
Development of a Secure Mobile E-Banking System
Get PDFMobile banking refers to the usage of a telephone or different cellular device to carry out on-line banking responsibilities. Those responsibilities encompass account balance enquiry, funds transfer, bill payment, finding an ATM, etc. Considering the excessive fee of adoption of this technology, quite a few concerns are raised as regards user authentication, data confidentiality, non-repudiation, data integrity and service availability. This research, therefore, introduces a more advantageous comfortable model to help conquer challenges mentioned earlier. In other to attain the set goals, the proposed model uses a popular salted Secure Hash Algorithm (SHA-512) Cryptographic Hash Algorithm to hash personal information, which include account information, and passwords. Advanced Encryption Standard (AES) approach was used for encryption and decryption, One Time Password (OTP) also turned into used to beef up user authentication. The design was carried out using Hypertext Preprocessor (PHP), JavaScript, CSS and MySQL database. Cain and Abel that is a password recovery tool that allows smooth recovery of various passwords by sniffing the network, cracking encrypted password using dictionary, brute-force and cryptanalysis attacks, revealing password bins, uncovering cached passwords and analyzing routing protocols was used to envision the validity and dependability of the model and also to obtain result. Results obtained suggests that the model is viable as data encrypted and hashed could not be decrypted by an attacker compared to other existing models
An Overview of the Algorithm Selection Problem
Get PDFUsers of machine learning algorithms need methods that can help them to identify algorithm or their combinations (workflows) that achieve the potentially best performance. Selecting the best algorithm to solve a given problem has been the subject of many studies over the past four decades. This survey presents an overview of the contributions made in the area of algorithm selection problems. We present different methods for solving the algorithm selection problem identifying some of the future research challenges in this domain
Framework for Evaluation of Enterprise Software in IT Service Management of Small and Medium Enterprises
Get PDFThe paper is concerned with problems arising in the process of management of enterprise software integration for better fitting to business needs through evaluation its performance and user’s satisfaction. The method assumed to be used on the small and medium enterprises (SMEs) to substitute expensive and high human recourse demanded methods. The paper describes the enterprise software evaluation method which was tested in three SMEs. The method and findings of this work can certainly be useful for SMEs that need to evaluate their enterprise software to clarify how it suits to their business processes and what the end-users experiences in working process
New Media and Privacy the Privacy Paradox in the Digital World: I Will Not Disclose My Data. Actually, I Will ... It Depends
Get PDFThe inconsistency of privacy attitudes and privacy behavior is often referred to as the “privacy paradox”. In this study, we analyze the privacy paradox through a methodology that allows investigating user behavior in relation to transferring personal data or not in a real context. Our intention is to investigate privacy as a negotiation by verifying whether the incongruous consumer behavior known as the privacy paradox also occurs in a real and blind context, and how this is affected by the data commoditization trend.The classical methodology in these types of studies is based on questionnaires administered to participants in an experiment and the questions relate to their intention to disclose their personal information in different hypothetical scenarios. In all these types of research, the respondents know they are participating in an experiment without any real gains or losses as a result of their actions. To understand how users behave when facing the disclosure or otherwise of personal data in a real context, we analyzed ex-post data from different digital campaigns through one of the most frequently used data vault platforms. Via this platform, a company can configure a series of user actions by rewarding them for every action with a discount on a product. Through this platform, we therefore had the opportunity to investigate how real users in real contexts manage the exchange of personal data for discounts on one or more products