Corporate social responsibility (CSR) has become vital to the competitiveness of organizations. However, there is very limited research on CSR in the context of higher education. Therefore, this study investigates the impact of CSR factors on the university competitiveness with other universities. The contribution of this study includes applying a multi-analytical methodology by applying Partial Least Squares-Structural Equation Modelling (PLS-SEM) and Artificial Neural Network (ANN). First, PLS-SEM analysis was applied to measure which CSR factor has the most significant influence on the increased competitiveness of Saudi Arabian universities. Then, an ANN model analysis was applied to rank the relative influence of the significant CSR factors attained from the PLS-SEM analysis. The findings show that the CSR factors such as market-oriented CSR activities, society-oriented CSR activities and workforce-oriented CSR activities have a significant positive impact on increased competitiveness of Saudi Arabian universities. However, based on the ANN findings, society-oriented CSR is the most significant predictor of a university's increased competitiveness, followed by workforce-oriented CSR and finally by market-oriented CSR. The practical implications of this study provide Saudi universities to focus on society-oriented CSR to maintain and sustain their competitive advantage over other universities.INDEX TERMS ANN, corporate social responsibility, education, PLS SEM, Saudi Arabia.

Technology business incubators support economic growth by developing innovative technologies. However, assessing the performance of technology business incubators in Saudi Arabia has not been well recognised. This study provides a conceptual framework for assessing technology business incubators based on knowledge sharing practices and sharing, diffusion of innovation and individual creativity. Partial least squares structural equation modelling, such as (PLS-SEM) path modelling was used to test the model. The results provide empirical insights about the performance of technology business incubators. The findings show knowledge donation and collection has positive effects on technology business incubator. The importance–performance map analysis shows additional findings and conclusions for managerial actions.

With the advancement in ICT, web search engines have become a preferred source to find health-related information published over the Internet. Google alone receives more than one billion health-related queries on a daily basis. However, in order to provide the results most relevant to the user, WSEs maintain the users’ profiles. These profiles may contain private and sensitive information such as the user’s health condition, disease status, and others. Health-related queries contain privacy-sensitive information that may infringe user’s privacy, as the identity of a user is exposed and may be misused by the WSE and third parties. This raises serious concerns since the identity of a user is exposed and may be misused by third parties. One well-known solution to preserve privacy involves issuing the queries via peer-to-peer private information retrieval protocol, such as useless user profile (UUP), thereby hiding the user’s identity from the WSE. This paper investigates the level of protection offered by UUP. For this purpose, we present QuPiD (query profile distance) attack: a machine learning-based attack that evaluates the effectiveness of UUP in privacy protection. QuPiD attack determines the distance between the user’s profile (web search history) and upcoming query using our proposed novel feature vector. The experiments were conducted using ten classification algorithms belonging to the tree-based, rule-based, lazy learner, metaheuristic, and Bayesian families for the sake of comparison. Furthermore, two subsets of an America Online dataset (noisy and clean datasets) were used for experimentation. The results show that the proposed QuPiD attack associates more than 70% queries to the correct user with a precision of over 72% for the clean dataset, while for the noisy dataset, the proposed QuPiD attack associates more than 40% queries to the correct user with 70% precision.

Resource limited networks have various applications in our daily life. However, a challenging issue associated with these networks is a uniform load balancing strategy to prolong their lifespan. In literature, various schemes try to improve the scalability and reliability of the networks, but majority of these approaches assume homogeneous networks. Moreover, most of the technique uses distance, residual energy and hop count values to balance the energy consumption of participating nodes and prolong the network lifetime. Therefore, an energy efficient load balancing scheme for heterogeneous wireless sensor networks (WSNs) need to be developed. In this article, an energy gauge node (EGN) based communication infrastructure is presented to develop a uniform load balancing strategy for resource-limited networks. EGN measures the residual energy of the participating nodes i.e., C i ∈ Network. Moreover, EGN nodes advertise hop selection information in the network which is used by ordinary nodes to update their routing tables. Likewise, ordinary nodes use this information to uni-cast its collected data to the destination. EGN nodes work on built-in configuration to categorize their neighboring nodes such as powerful, normal and critical energy categories. EGN uses the strength of packet reply (SPR) and round trip time (RTT) values to measure the neighboring node's residual energy (E r ) and those node(s) which have a maximum E r values are advertised as reliable paths for communication. Furthermore, EGN transmits a route request (RREQ) in the network and receives route reply (RREP) from every node reside in its closed proximity which is used to compute the E r energy values of the neighboring node(s). If E r value of a neighboring node is less than the defined category threshold value then this node is advertised as non-available for communication as a relaying node. The simulation results show that our proposed scheme surpasses the existing schemes in terms of lifespan of individual nodes, throughput, packet loss ratio (PLR), latency, communication costs and computation costs, etc,. Moreover, our proposed scheme prolongs the lifespan of WSNs and as well as an individual node against exiting schemes in the operational environment.INDEX TERMS Wireless sensor network, routing protocol, heterogeneous WSNs, low power devices, load balancing, EGN nodes, connectivity of wireless nodes.

Despite the fact that several studies have been conducted to study the adoption of smart-government services, little consideration has been paid to exploring the main factors that influence the adoption of smart-government services at the three main stages of smart-government services (the static, interaction, and transaction stages). Based on the results of this study, each of these three stages has different requirements in terms of system compatibility, security, information quality, awareness, perceived functional benefit, self-efficacy, perceived image, perceived uncertainty, availability of resources, and perceived trust. In addition, the results demonstrate that the requirements and perceptions of users towards the adoption and use of smart-government services in the three stages significantly differ. This study makes a unique contribution to the existing research by examining the perceptions and needs of consumers, in terms of adoption throughout the three stages.

The fact that ensemble methods enhance the prediction performance. Therefore, we focused on developing a weighted ensemble method using a novel combination of Cerebrospinal Fluid (CSF) protein biomarkers to predict AD's earlier stages with greater accuracy than the stateof-the-art CSF protein biomarkers. In this regard, two feature selection methods, namely the Recursive Feature Elimination (RFE) and L1 regularization method were used to screen the most important subset of features for building a classification model using the Mild Cognitive Impairment (MCI) dataset. A novel combination of three biomarkers, namely Cystatin C, Matrix metalloproteinases (MMP10), and tau protein, was screened using the linear Support Vector Machine (SVM) and Logistic Regression (LR) classifier based RFE method. Two-tailed unpaired t-test analysis at a 5 % significance level showed a significant difference between the mean levels of Cystatin C, MMP10, and tau protein between cognitive normal and cognitively impaired groups. An ensemble model using a weighted average of two best performing classifiers (LR and Linear SVM) was created using a novel subset of three most informative features. Our ensemble model's weighted average results performed significantly better than LR and Linear SVM base classifiers' performance. The Receiver Operating Characteristic Curve (ROC_AUC) and Area under Precision-Recall values (AUPR) of our proposed model were observed to be 0.9799 ± 0.055 0.9108 ± 0.015, respectively. The performance of our proposed weighted averaged ensemble model built using a novel combination of CSF protein biomarkers was significantly better (p < 0.001) than models generated using different combinations of CSF protein biomarkers obtained from recent studies. An ensemble-learning based application was implemented and deployed at Heroku at https://appsalzheimer.herokuapp.com.

Heart diseases are characterized as heterogeneous diseases comprising multiple subtypes. Early diagnosis and prognosis of heart disease are essential to facilitate the clinical management of patients. In this research, a new computational model for predicting early heart disease is proposed. The predictive model is embedded in a new regularization based on decaying the weights according to the weight matrices’ standard deviation and comparing the results against its parents (RSD-ANN). The performance of RSD-ANN is far better than that of the existing methods. Based on our experiments, the average validation accuracy computed was 96.30% using either the tenfold cross-validation or holdout method.

Anomaly detection is a problem with roots dating back over 30 years. The NSL-KDD dataset has become the convention for testing and comparing new or improved models in this domain. In the field of network intrusion detection, the UNSW-NB15 dataset has recently gained significant attention over the NSL-KDD because it contains more modern attacks. In the present paper, we outline two cutting-edge architectures that push the boundaries of model accuracy for these datasets, both framed in the context of anomaly detection and intrusion classification. We summarize training methodologies, hyperparameters, regularization, and other aspects of model architecture. Moreover, we also utilize the standard deviation of weight values to design a new regularization technique. Then, we embed it on both models and report the models’ performance. Finally, we detail potential improvements aimed at increasing models’ accuracy.