No Abstract.

The advent of the internet with its attendant democratization of data and deluge of information had given rise to the avalanche of news media agencies. These agencies publish news articles with varying emotional reports especially stories conveying bad sentiments to the public. As major news agencies operate micro-blogging websites and establish their presence on social media channels, the distribution of bad news increases. It has been shown that constant exposure to bad news presented in a body of texts, graphics, and videos/audios contribute to increase in high blood pressure, anxiety attacks, bowel disorders, stroke and/or heart failure. In this work, we presented a sentiment analysis framework to extract news articles from FrontPage of online newspapers and generate contextual wordlists to support positive news broadcasting. Using a set of 12 Nigerian online news channels, we employed a hybrid method of dictionary and corpus-based lexicon approaches to achieve the wordlist derivation. The result advocates for an alternative way of reporting negative news to reduce the adverse impact it has on the masses.

Selection of a suitable Software Development Life Cycle (SDLC) model for project implementation is somewhat confusing as there are a lot of SDLC models with similar strengths and weaknesses. Also, the solutions proffered among the researchers so far have been the qualitative comparative analysis of SDLC models. Hence, this paper proposes a comparative analysis of SDLC models using quantitative approach in relation to strengths and weaknesses of SDLC models. The study adapted comparative analysis and Software Development Life Cycle (SDLC) models features’ classification using ten characteristics such as project complexity, project size, project duration, project with risk, implementation/initial cost, error discovery, associated cost, risk analysis, maintenance and cost estimation. A quantitative measure that employs online survey using experts in software design and engineering, project management and system analysis was carried out for the evaluation of SDLC models. Purposeful Stratified Random Sampling (SRS) technique was used to gather the data for analysis using XLSTAT after pre-processing, taking into consideration both benefit and cost criteria. The overall performance evaluation showed that Spiral-Model is the best followed by V-Model and lastly Waterfall Model with comparative values of 38.63%, 35.76% and 25.61% respectively. As regards cost estimation, Waterfall Model is the most efficient with value of 41%, then V-Model with 31% and lastly Spiral Model with 28%. V-Model has great error recovery capability with value of 45% which is closely followed by Spiral Model with 37% and lastly Waterfall Model with 18%. The study revealed that, a model with efficient risk assurance does not guarantee efficient cost management. In the future work, more characteristics regarding SDLC models shall be considered.

The COVID–19 pandemic is, without any doubt, changing our world in ways that are beyond our wildest imagination. In a bid to curb the spiraling negative fallouts from the virus that has resulted in a large number of casualties and security concerns. The World Health Organization, amongst other safety protocols, recommended the compulsory wearing of face masks by individuals in public spaces. The problem with the enforcement of this and other relevant safety protocols, all over the world, is the reluctance and outright refusal of citizens to comply and the inability of relevant agencies to monitor and enforce compliance. This paper explores the development of a CCTV–enabled facial mask recognition software that will facilitate the monitoring and enforcement of this protocol. Such models can be particularly useful for security purposes in checking if the disease transmission is being kept in check. A constructive research methodology was adopted, where a pre-trained deep convolutionary neural network (CNN) (mostly eyes and forehead regions) used and the most probable limit (MPL) was use for the classification process. The designed method uses two datasets to train in order to detect key facial features and apply a decision-making algorithm. Experimental findings on the Real-World-Masked-Face-Dataset indicate high success in recognition. A proof of concept as well as a development base are provided towards reducing the spread of COVID-19 by allowing people to validate the face mask via their webcam. We recommend that the use of the app and to further investigate the development of highly robust detectors by training a deep learning model with respect to specified face-feature categories or to correctly and incorrectly wear mask categories.

Ontology is considered as a kind of agreement on a domain representation. It is very essential in achieving semantics information processing as well as information sharing between agents or systems processing same or related data. Despite the importance of ontologies in information system, several ontological operations remain without formal definition as well as a formal description on how they should be achieved or proved. In this paper, the concept of soft set initiated by Molodtsov is used to define Description logics ontologies and to formalize its basic operations. We show that, by approximating ontologies using soft set, basic ontological operations and their properties are preserved and can be formally defined as well as proved algebraically as sets operations.Keywords: Ontologies, Description Logics, Soft set, ontology Algebra

During the last decade, increasing attention has been focused on ontologies and Ontological Engineering. The application of ontological engineering technique to e-learning, though still in its early stage, has become a phenomena tool in the integration and adaptation of a dynamic and flexible elearning environment, where tutors and learners are provided with the functionality of personalizing their learning process, this has not fully considered the generality of an entire field of study. This paper presents an ontology-based framework for classification of the entire courses of computer science at the university level. A model of an e-learning domain in the context of material classification that enables students retrieve information about a particular course in personalized ways was presented the method adopted elicited e-learning knowledge using documented materials, observation, consultation, prototyping among others. With domain expertise developed, the knowledge elicited was analyzed and formally represented using OWL-Description Logic. The design was implemented using Protégé 5.0 editor. The validation for accuracy and completeness was carried out with the domain and ontology experts using consistency checking reasoned, DL-Query. The results of the implementation show that elearning materials can be searched and retrieved easily and timely. The study also established and formalised an effective computational approach for representing information content of educational resources thereby helping to improve the flexibility of content representation in an e-learning system.Keywords: e-learning, Ontological Engineering, Ontology, Ontology Web Language (OWL), Knowledge Management, Description LogicVol. 26, No 1, June 2019

Language is essential for human existence; it enhances understanding between individuals whilst aiding communication. The Yorùbá language is one of the major Nigerian languages, that is gradually being eroded due to different reasons such as westernization, colonial legacy, modernization and economic development, advancement of technology amongst other reasons, it is therefore necessary for Africans especially of Yorùbá descent to save Yorùbá language. In this paper, an Onscreen Keyboard model is presented with an attempt to save Yorùbá language by prolonging its’ use through technology as it evolves. Data was collected on Yorùbá alphabets and a computational model was formulated (using unified modelling language) based on the output of the collected data. The On screen keyboard’s model was implemented using visual C#, and the system was evaluated to test its effectiveness. The model allows user input into the computer using Yorùbá language whilst predicting text as the user types thereby enhancing easy typing and learning experience. Although, the model was tested on Windows operating system, the model design can easily be adapted to other operating systems environments. In this study, we have successfully localized the typical English Language keyboard to allow input in Yorùbá language.Keywords: Language, Yorùbá, Endangered, Onscreen keyboardVol. 26 No 1, June 2019

The increasing demand for high-quality medical services coupled with the scarcity of medical experts leads to the use of electronic devices, information technology and its infrastructure in delivering health service. In line with that, this work proposes a solution to the problems of scarcity of experts especially in the remote regions of developing countries by developing a system that uses NLP and Nearest Neighbors Algorithms to learn from an online case-based repository built on a network of experts’ hospitals to aid remote health Centers in diagnosis and treatment. The results obtained from the empirical evaluation of the system show the efficiency of the system in assisting non-experts in decision making and could, therefore, improve the quality of service in the remote health center with a very minimal cost.Keywords: Case-Based system, NLP, Diagnosis, Nearest NeighborsVol. 26 No 1, June 2019

E-commerce helps businesses to increase production flexibility by ensuring timely availability of components from suppliers. However, of paramount concern is the issue of trust. Some trust models such as Pretty Good Privacy (PGP) and Public Key Infrastructure based on X.509 (PKIX) are based on the notion of delegation whereby one entity gives some of its authority to other entities. The problems with these models are: leaked public-key certificate, false owner's identity and how to manage the details about certificate. This study presents a flexible trust model based on human interactions. It involves dynamic evolution of trust between entities which is independent of the usage of certificates from trusted third parties. We describe trust in three folds: the default, initial and final trust. A prototype of this model was implemented using ASP.NET and C#. The result shows that while initial trust bestowed on a consumer is unstable and unpredictable, final trust of a consumer is partially stable and therefore fulfils integrity, competence and benevolence.Keywords: E-Commerce, Trust, Integrity, Open Distributed environment, Trust Management.

The webscape is swarmed with increasing numbers of emails and websites that attempts to deceive users into providing identity information by purporting to emanate from trusted entities. These e-mails referred to as “phishing e-mails” masquerade trusted party emblems, logos and trademarks and contains phony weblinks that compromise users accounts with malware and keyloggers. Traditional spam filters are not efficient in adequately detecting these undesirable e-mails thus making consumers and businesses vulnerable online. The tendency in the cyber security domain is to perceive this problem as a simple text classification problem. However, classification is compounded by the fact that these classes of “phishing” emails are identical to the class of real e-mails. Using Netbeans IDE (which offers a wide range of functionalities from source code editor to program GUI's construction) we developed a plug-in for Mozilla Firefox browser to enhancing the browser's functionality. The plug-in called “PhisermanPro” is a toolbar extension that monitors the address bar” of browsers to ensure that users do not navigate to “phishing” sites. Preliminary tests and application in an academic context to identify fake conference and workshop sites showed very promising results.Keywords: Phishing, security, malware, PhishermanPro, webscape.