University of Jordan

About: University of Jordan is a education organization based out in Amman, Jordan. It is known for research contribution in the topics: Population & Medicine. The organization has 7796 authors who have published 13764 publications receiving 213526 citations.

Simultaneous Feature Selection and Support Vector Machine Optimization Using the Grasshopper Optimization Algorithm

Abstract: Support vector machine (SVM) is considered to be one of the most powerful learning algorithms and is used for a wide range of real-world applications. The efficiency of SVM algorithm and its performance mainly depends on the kernel type and its parameters. Furthermore, the feature subset selection that is used to train the SVM model is another important factor that has a major influence on it classification accuracy. The feature subset selection is a very important step in machine learning, specially when dealing with high-dimensional data sets. Most of the previous researches handled these important factors separately. In this paper, we propose a hybrid approach based on the Grasshopper optimisation algorithm (GOA), which is a recent algorithm inspired by the biological behavior shown in swarms of grasshoppers. The goal of the proposed approach is to optimize the parameters of the SVM model, and locate the best features subset simultaneously. Eighteen low- and high-dimensional benchmark data sets are used to evaluate the accuracy of the proposed approach. For verification, the proposed approach is compared with seven well-regarded algorithms. Furthermore, the proposed approach is compared with grid search, which is the most popular technique for tuning SVM parameters. The experimental results show that the proposed approach outperforms all of the other techniques in most of the data sets in terms of classification accuracy, while minimizing the number of selected features.

Factors influencing students’ adoption of e-learning: a structural equation modeling approach

Abstract: Purpose This research aims to examine the factors that may hinder or enable the adoption of e-learning systems by university students. Design/methodology/approach A conceptual framework was developed through extending the unified theory of acceptance and use of technology (performance expectancy, effort expectancy, hedonic motivation, habit, social influence, price value and facilitating conditions) by incorporating two additional factors, namely, trust and self-efficacy. Data were collected from students at two universities in England using a cross-sectional questionnaire survey between January and March 2015. Findings The results showed that behavioral intention (BI) was significantly influenced by performance expectancy, social influence, habit, hedonic motivation, self-efficacy, effort expectancy and trust, in their order of influencing the strength and explained 70.6 per cent of the variance in behavioral intention. Contrary to expectations, facilitating conditions and price value did not have an influence on behavioral intention. Originality/value The aforementioned factors are considered critical in explaining technology adoption but, to the best of the authors’ knowledge, there has been no study in which all these factors were modeled together. Therefore, this study will contribute to the literature related to social networking adoption by integrating all these variables and the first to be tested in the UK universities.

Secure and Sustainable Load Balancing of Edge Data Centers in Fog Computing

Abstract: Fog computing is a recent research trend to bring cloud computing services to network edges. EDCs are deployed to decrease the latency and network congestion by processing data streams and user requests in near real time. EDC deployment is distributed in nature and positioned between cloud data centers and data sources. Load balancing is the process of redistributing the work load among EDCs to improve both resource utilization and job response time. Load balancing also avoids a situation where some EDCs are heavily loaded while others are in idle state or doing little data processing. In such scenarios, load balancing between the EDCs plays a vital role for user response and real-time event detection. As the EDCs are deployed in an unattended environment, secure authentication of EDCs is an important issue to address before performing load balancing. This article proposes a novel load balancing technique to authenticate the EDCs and find less loaded EDCs for task allocation. The proposed load balancing technique is more efficient than other existing approaches in finding less loaded EDCs for task allocation. The proposed approach not only improves efficiency of load balancing; it also strengthens the security by authenticating the destination EDCs.

A multi-verse optimizer approach for feature selection and optimizing SVM parameters based on a robust system architecture

Abstract: Support vector machine (SVM) is a well-regarded machine learning algorithm widely applied to classification tasks and regression problems. SVM was founded based on the statistical learning theory and structural risk minimization. Despite the high prediction rate of this technique in a wide range of real applications, the efficiency of SVM and its classification accuracy highly depends on the parameter setting as well as the subset feature selection. This work proposes a robust approach based on a recent nature-inspired metaheuristic called multi-verse optimizer (MVO) for selecting optimal features and optimizing the parameters of SVM simultaneously. In fact, the MVO algorithm is employed as a tuner to manipulate the main parameters of SVM and find the optimal set of features for this classifier. The proposed approach is implemented and tested on two different system architectures. MVO is benchmarked and compared with four classic and recent metaheuristic algorithms using ten binary and multi-class labeled datasets. Experimental results demonstrate that MVO can effectively reduce the number of features while maintaining a high prediction accuracy.