Sunday O. Ojo

EXPLOITING IMAGE CONTENT IN LOCATION-BASED SHOPPING RECOMMENDER SYSTEMS FOR MOBILE USERS

This paper demonstrates how image content can be used to realize a location-based shopping recommender system for intuitively supporting mobile users in decision making. Generic Fourier Descriptors (GFD) image content of an item was extracted to exploit knowledge contained in item and user profile databases for learning to rank recommendations. Analytic Hierarchy Process (AHP) was used to automatically select a query item from a user profile. Single Criterion Decision Ranking (SCDR) and Multiple-Criteria Decision-Ranking (MCDR) techniques were compared to study the effect of multidimensional ratings of items on recommendations effectiveness. The SCDR and MCDR techniques are, respectively, based on Image Content Similarity Score (ICSS) and Relative Ratio (RR) aggregating function. Experimental results of a real user study showed that an MCDR system increases user satisfaction and improves recommendations effectiveness better than an SCDR system.

Mitigating Rural E-Learning Sustainability Challenges Using Cloud Computing Technology

Internet technology is leading in transforming educational system by allowing different types of interactions among various educational institutions, all participating in global online innovations. In particular, educators have realized that technology enhanced learning, e-learning to be specific offers flexible and potent ways to accomplish wide spectrum of opportunities to relieve academic staff of excess workload and provide them with sufficient time to improve performance. Cloud computing technology can benefit educational institutions to provide human and material resources including course experts, digital contents, virtual laboratories and interactive classes, facilitate research, share knowledge, establish collaboration, support user mobility and perform computationally intensive laboratory experiments. However, extending cloud novelty and numerous benefits to rural e-learning raises many sustainability challenges. This work probes into how cloud computing can be effectively explored to mitigate rural e-learning sustainability challenges by utilizing descriptive research and scoping review approaches. The purpose is to raise awareness among stakeholders of educational institutions about prospects of using cloud computing. New issues of e-learning sustainability are discovered for future studies by considering focused areas of previous researchers and existing gaps. This work found energy and security as emerging sustainability issues in cloud computing applications to education.

Filtering of Mobile Short Messaging Service Communication Using Latent Dirichlet Allocation with Social Network Analysis

In this study, we introduce Latent Dirichlet Allocation (LDA) with Social Network Analysis (SNA) to extract and evaluate latent features arising from mobile Short Messaging Services (SMSs) communication. This would help to automatically filter unsolicited SMS messages in order to proactively prevent their delivery. In addition, content-based filters may have their performance seriously jeopardized, because SMS messages are fairly short and their meanings are generally rife with idioms, onomatopoeias, homophones, phonemes and acronyms. As a result, the problem of text-mining was explored to understand the linguistic or statistical properties of mobile SMS messages in order to improve the performance of filtering applications. Experiments were successfully performed by collecting time-stamped short messages via mobile phones across a number of different categories on the Internet, using an English language-based platform, which is available on streaming APIs. The derived filtering system can in the future contribute in optimal decision-making, for instance, in a scenario where an imposter attempts to illegally gain confidential information from a subscriber or an operator by sending SMS messages.

An intelligent integrative assistive system for dyslexic learners

Purpose – The objective of this paper is to present a comprehensive literature survey on dyslexic learners and to propose a model for integrated assistive technology of dyslexic learners. Design/methodology/approach – The use of the proposed model through real-life scenarios categorized as “phonological, reading and writing scenarios”. We have also surveyed some systems for use with dyslexic learners currently in use and have compared them on the basis of number of barriers, technological innovation, age group and fostering. Findings – Dyslexic learners are characterized by slow learning, poor handwriting, poor spelling skills and difficulties in planning, organizing, revising and editing texts; technology plays a major role in the educational environment; it has become crucial in impacting knowledge across the globe; and open research issues and challenges that have to be addressed in the design of the current dyslexic system have been presented in detail. Research limitations/implications – Full impleme...

Exploring Support Vector Machines and Random Forests to Detect Advanced Fee Fraud Activities on Internet

In this study, we experiment with Support Vector Machines (SVM) and Random Forests (RF), which are two of the state-of-the-art machine learning algorithms. The purpose was to examine their suitability for detecting Advanced Fee Fraud (AFF) activities on internet, which due to its inherent vulnerability is often abused for various criminal activities. A set of cluster features was discovered using global CM algorithm to characterize AFF activities on internet. These features were used to train SVM and RF to classify an e-mail document as either containing AFF related information or not. The results of experiments performed show that both SVM and RF have a satisfactory performance in detecting AFF activities. However, SVM comparatively shows superior result than RF and can effectively detect the dynamic nature of AFF activities on internet.

An Adaptive Multi Agent Service Discovery for Peer to Peer Cloud Services

Cloud computing is evolving into a popular platform that enables on-demand provisioning of computing resources to a growing population of clients. Core to the provisioning of service in the cloud is the discovery of these services in an efficient and timely manner. Centralized and hierarchical approaches to service discovery have exhibited bottlenecks as network load increases and limitation in scalability. Efforts have been made in combining cloud systems and Peer to peer P2P systems to address the problem encountered in the conventional service discovery approaches but not without a new set of challenges ranging from network flooding to poor performance in dynamic networks. This paper presents an efficient and scalable approach for semantic cloud service discovery in a P2P cloud environment. The approach is based on Learning Automata LA and Ant Colony Optimization ACO. The ability of ACO to adapt to changes in real time makes it a better choice in dynamic environments such as cloud. We evaluate this approach against the some existing P2P service discovery approaches, the proposed mechanism showed an improved performance.

A framework for the choreography of intelligent e-services

In this paper a framework for the choreography of intelligent electronic services (e-services) that follows the Service-Oriented Architecture principle is presented. The composition abilities of intelligent e-services in the framework enable them to match a users request for service consumption. The framework is based on a dynamic model of message query-based with casual knowledge-based expansion. A practical illustration of the application of the framework relies on a domain-specific e-service aggregation following an e-mentoring business scenario. The e-mentoring scenario is chosen in order to take advantage of the innovative features offered by the current World Wide Web, which has evolved into a provider of services.

Cross-impact analysis experimentation using two techniques to revise marginal probabilities of interdependent events

Cross-impact analysis relies on decision makers to provide marginal probability estimates of interdependent events. Generally, these have to be revised in order to ensure overall system coherency. This paper describes cross-impact analysis experimentation in which a Monte Carlo based approach and a difference equation approach, respectively, were used to revise these marginal probabilities. The objective of the study was to determine the consequences of such revisions on the expected impact rankings of these events. A cross-impact analysis system was developed and used to conduct the experiments. The experiments show that the impact ranking of interdependent events may indeed depend on the technique used for revising event marginal probabilities. Moreover, the Monte Carlo technique generates a world view closer to the one of the decision makers, while the world view generated by the difference equation technique differs from that of the decision makers.

Session hijacking attacks in wireless networks: A review of existing mitigation techniques

Wireless networks are open to various attacks such as Session Hijacking Attack (SHA) with attackers exploiting the vulnerability that is inherent in IEEE 802.11 networks. A SHA is an exploitation of a valid computer session where an attacker takes over a session through acquiring the session identifier (ID) of victim and masquerading as the authorized user. We conducted a review study of the existing session hijacking attacks mitigation techniques. Literature review papers that were published from 2012 to 2016 have been reviewed in this paper. Electronic digital databases were used to identify existing literature studies related to session hijacking attacks mitigation techniques. Various approaches, mostly based on media access control address, have been proposed in the literature for mitigating SHAs, with varied level of impact on network performance resources consumption. The existing SHA techniques are not adequately addressing efficiency and accuracy in terms of mitigating SHA. This paper categorizes mitigation techniques in terms of strengths and weaknesses, the gaps and areas of improvements. The review of existing literature will provide a basis for reasoning about the SHA mitigation techniques in future which will exploit the synergy of two or more SHA mitigation techniques.

A framework for appropriate pedagogical use of conceptual metaphor in computing

The inherent abstractness in nature and intangibility in essence of computer programming concepts, present weak mental models that make them to be intuitively challenging to be easily understood by students. This remains a key factor in general underperformance of students in computer programming courses. Pedagogical use of metaphors is widely acknowledged as a means of addressing the challenge. As a result, the literature is replete with proposals for metaphor use to enhance understanding of various computer programming concepts, and positive results have been reported. However, the lack of a theory-driven methodological framework for appropriate pedagogical use of metaphors, has slowed progress in this direction. To fill this gap in the literature, a framework for appropriate pedagogical use of metaphors in the teaching and learning of programming concepts is proposed. The framework is developed, employing a triangulation of the theories of Conceptual Metaphor, Experiential Learning, Structure Mapping, and ontology modelling, to provide theoretical and methodological underpinnings for the framework. The result of a proof of concept using the ATM metaphor and programming concepts of Data Processing and Control Structures, stands promising.