Cloud momentum seems unstoppable in Nigeria, as businesses and organizations in the country see less and less advantage in the slog of maintaining their infrastructure. The shift to the cloud in today's COVID-19 driven world has created an opportunity for investments to improve local cloud computing services. However, there are key challenges that must be addressed by the local cloud service providers in the country in order not to lose out to the foreign cloud service providers. This paper assessed the challenges to local cloud computing services adoption among sixty-seven (67) businesses and organizations in Nigeria. The research employed a non-probability purposive sampling approach. The surveyed data were obtained through an online form which was distributed via Linkedln. Descriptive and inferential analysis was used in analyzing the collected data via IBM SPSS software. Findings from the research showed the key challenges to include inadequate awareness of local cloud service vendors, poor innovation and local content, inadequate cloud infrastructure, local cloud vendor interoperability issue, national insecurity, shortages in skilled personnel, Service Level Agreement (SLA), security strategies, privacy, compliance terms, and requirements issues. Thus, adequate local cloud service offerings, skilled personnel, and the IT infrastructural backbone of the country have to be well established to increase the trust in local cloud computing, open up Nigeria to offshore markets while driving economic competitiveness and growth.

Autism Spectrum Disorder (ASD) is a neuro developmental disorder that affects a person's ability to communicate and interact with others for rest of the life. It affects a person's comprehension and social interactions. Furthermore, people with ASD experience a wide range of symptoms, including difficulties while interacting with others, repeated behaviors, and an inability to function successfully in other areas of everyday life. Autism can be diagnosed at any age and is referred to as a "behavioral disorder" since symptoms usually appear in the life's first two years. The majority of individuals are unfamiliar with the illness and so don't know whether or not a person is disordered. Rather than aiding the sufferer, this typically leads to his or her isolation from society. The problem with ASD starts in childhood and extends into adolescence and adulthood. In this paper, we studied 25 research articles on autism spectrum disorder (ASD) prediction using machine learning techniques. The data and findings of those publications using various approaches and algorithms are analyzed. Techniques are primarily assessed using four publicly accessible non-clinically ASD datasets. We found that support vector machine (SVM) and Convolutional Neural Network (CNN) provides most accurate results compare to other techniques. Therefore, we developed an interactive dashboard using Tableau and Python to analyze Autism data.

This paper focuses on the quantitative analysis of RFID based vehicle toll collection system. Since we conduct the quantitative analysis long before the implementation of the infrastructure, the approach is realized by the UML and SPN to capture the system dynamics and carry out multiple performance tests of the possible infrastructure. Thus, the performance tests ensure the installation of correct number of RFID vehicle toll collection booth in the entrance of a bridge or a highway so that the traffic congestion can be kept as minimal as possible as well as financial viability can be confirmed. We analyze the response time and throughput to know the maximum limit for the diverse number of arrival vehicles that is served by the different number of toll booths. This finally gives us a better understanding of the number of units necessary for toll collection to decrease the traffic congestion in a budget constraint manner.

As the information put together by the blend of smartphones, the cloud, the IOT, and ubiquitous computing continue to expand at an alarming rate, a data breach increases. Today, users' strong authentication and authorization approaches are increasingly important to secure sensitive, confidential, secret information. Possession and knowledge-based authentication techniques for computers, the internet, email accounts, etc., are commonly used to access vital information; they do not link a user to an established identity, resulting in most security vulnerabilities. Biometric authentication, on the other hand, has the privilege of being more reliable than traditional authentication as biometric characteristics of a person can’t be lost; they are tough to distribute, exchange or duplicate; and it requires the user to be present during the authentication process, thereby relating the users to established identities. Biometrics provides a higher level of assurance that the individual attempting to ascertain is the individual in question. Thus, resulting in a more reliable, usable, and cost-effective model with a higher level of protection to deter an attacker from obtaining entry to a computer or network and gaining access to confidential data. This paper introduces a novel fingerprint-based authentication scheme for mobile environments, enabling user authentication based on fingerprint features using a challenge-response-based authentication process. In this study, the proposed authentication system has been developed on a real Android-based smartphone, tested on actual users, and performance analysis has been carried out; empirical results reveal that the proposed authentication scheme achieves increased performance. Moreover, a usability analysis has been done to determine efficiency, effectiveness, and user satisfaction. The evaluation results indicate its feasibility to use it as an effective authentication mechanism for mobile phone environments.

The usefulness of Collaborative filtering recommender system is affected by its ability to capture users' preference changes on the recommended items during recommendation process. This makes it easy for the system to satisfy users' interest over time providing good and quality recommendations. The Existing system studied fails to solicit for user inputs on the recommended items and it is also unable to incorporate users' preference changes with time which lead to poor quality recommendations. In this work, an Enhanced Movie Recommender system that recommends movies to users is presented to improve the quality of recommendations. The system solicits for users' inputs to create a user profiles. It then incorporates a set of new features (such as age and genre) to be able to predict user's preference changes with time. This enabled it to recommend movies to the users based on users new preferences. The experimental study conducted on Netflix and Movielens datasets demonstrated that, compared to the existing work, the proposed work improved the recommendation results to the users based on the values of Precision and RMSE obtained in this study which in turn returns good recommendations to the users.