Information Technology

Since the advent of the internet and mostly the birth of the social media, fake news has escalated significantly and because of this, traditional fact checking approaches such as reviewing each news article has become nearly impossible. Tackling this increase in fake news contents gave rise to the machine-based approach though they faced their limitations which include the absence of a unified database, ambiguities etc. The limitations of the machine-based approach led to the hybrid (Artificial Intelligence-human) approach that combine the efforts of both man and machine resulting to the flagging of news articles as fake. This has shown a lot of promise however; recent research has shown that flagging of news articles as fake has small effect in supporting users in classifying fake news because of a psychological effect called the Illusory truth effect. In this paper, we describe an extended hybrid fake news detection system that not only flags news as fake but also reduces their visibility to reduce Illusory truth effect.

The Nigeria Immigration Service (NIS) plays a pivotal role in shaping the nation's future by contributing to various critical aspects of development, security, and global engagement. This paper emphasizes the NIS's multifaceted responsibilities, highlighting its influence on national security, economic prosperity, diplomatic relations, social cohesion, and crisis management. The NIS actively participates in international forums, addresses emerging global migration trends, and fosters a skilled workforce for future challenges. With a focus on sustainable development goals, the NIS stands as a dynamic force steering Nigeria towards a future characterized by economic growth, cultural diversity, and positive global standing.

Routers have enhanced the way network devices communicate with each other in today's modern age. This comparative analysis aims to determine the effectiveness of different routing algorithm with convergence time being the key performance indicator by simulating a fairly large network with Riverbed Modeler academic edition. It was concluded that the router information protocol, RIP which implements the direct vector algorithm is the performing and slowest for the simulated relatively fairly large network.

The concept of the internet started over 50 years ago when computers filled the entire room, today it is an ubiquitous information infrastructure, the initial prototype of what J. C. R. Licklider called the inter-galactic computer network Its history is complex and involves many aspects-technological, organizational, and community; its influence reaches not only to the technical field of computer communications but throughout society. Categorizing internet into different generations seeks to give us a microscopic view of what the internet was, what its now and its future. The internet generation is divided into four (4) guided by its usage, number of users, technology, protocols device used and transmission technology.

Bagging and Voting are both types of ensemble learning, which is a type of machine learning where multiple classifiers are combined to get better classification results. This paper presents an experimental comparison of Bagging and Voting ensemble machine learning algorithms. The iris dataset which has 150 data instances and 5 attributes was used to conduct the experiment. It was observed that bagging is a better ensemble learning algorithm than voting based on the experimental data used for classification.

Arrhythmia is an abnormal condition of the heart that occurs when the electrical impulses that coordinate the heartbeats do not work properly, causing the heart to beat too fast, too slow, irregular or even have premature contractions; accurate and quick diagnosis can reduce fatalities, Thispaper focuses on design and development of a system that will automatically and accurately diagnose five super-class of arrhythmias recommended by theAssociation for the Advancement of Medical Instrumentation (AAMI) to be detectable by equipment/methodswhich includes: Normal(N), Supraventricular ectopicbeat (SVEB), Ventricular ectopic beat (VEB), Fusion beat (F) and Unknown beat (Q). To achieve this, the system uses a hybrid classification algorithm achieved by the combination of two better performing algorithm (Random Forest and J.48 ensembled with the stacking algorithm). The MIT-BIH ECG arrhythmia database accessible at Kaggle.com was used for training, testing and validation of the system. since this design is intended for edge devices or mobile devices, the design focuses on development of a system that uses less computation power, less application size and ability to give correct classification with less time. Our results showed that the designed system has an overall accuracy of 97.67%, average precision value of 0.977, average recall value of 0.977 and average F1-measure value of 0.977.

Arrhythmia is an abnormal condition of the heart that occurs when the electrical impulses that coordinate the heartbeats do not work properly, causing the heart to beat too fast, too slow, irregular or even have premature contractions; accurate and quick diagnosis can reduce fatalities, Thispaper focuses on design and development of a system that will automatically and accurately diagnose five super-class of arrhythmias recommended by theAssociation for the Advancement of Medical Instrumentation (AAMI) to be detectable by equipment/methodswhich includes: Normal(N), Supraventricular ectopicbeat (SVEB), Ventricular ectopic beat (VEB), Fusion beat (F) and Unknown beat (Q). To achieve this, the system uses a hybrid classification algorithm achieved by the combination of two better performing algorithm (Random Forest and J.48 ensembled with the stacking algorithm). The MIT-BIH ECG arrhythmia database accessible at Kaggle.com was used for training, testing and validation of the system. si...

Arrhythmias also known as dysrhythmia is a heart ailment that arises when electrical signals that coordinate the heartbeats do not work appropriately, they are often precursors to a number of heart diseases which may be terminal, and early detection and adequate treatment can save life, in this paper we propose a classification technique that blends two good performing machine learning algorithms to enhance the accuracy of detecting arrhythmia using Electrocardiogram (ECG) data and Weka machine learning tool, these algorithms include the J.48 and Random Forest algorithms combined with an ensemble algorithm called Stacking; For this experiment the MIT-BIH ECG dataset from Kaggle.com was used to train, test and validate the hybrid algorithm. This dataset used classified ECG data into the 5 super class of arrhythmia approved by the association for the advancement of medical instrumentation (AAMI) to be detectable by equipment and methods, they include normal sinus (N), fusion beat (F), supraventricular ectopic beat (SVEB), ventricular ectopic beat (VEB), and unknown beat (Q). the hybrid algorithm "stacked random forest and j.48) outperformed the other individual algorithms, the performance metrics gotten include 97.63% accuracy, an approximate sensitivity (recall) and Positive predictivity (precision) value of 0.98, other metrics includes a weighted precision recall curve area of 0.97, receiver operator characteristics area of 0.96 and test time of 1.66 seconds and finally a model size of 38.2mb which is suitable for building application for mobile devices.

Electrocardiogram is the record of electrical activity of heart. ECG is a test to detect and study normal rhythmic activity of the heart. Signal processing are very often used methods in a biomedical engineering research. This paper presents Bradycardia detection by utilization of digital signal filtering on electrocardiogram (ECG) using MATLAB. MATLAB was used to analyze and process ECG dataset gotten from Physionet online database with focus on R-R peaks to calculate the heartbeat, by applying high pass filtering and squaring the signal. The results obtained using MATLAB for ECG analysis and detection of arrhythmia is very fast and useful.

Routers have enhanced the way network devices communicate with each other in today's modern age. This comparative analysis aims to determine the effectiveness of different routing algorithm with convergence time being the key performance indicator by simulating a fairly large network with Riverbed Modeler academic edition. It was concluded that the router information protocol, RIP which implements the direct vector algorithm is the performing and slowest for the simulated relatively fairly large network.

There has been steady increase of the incidences of cyber-attacks in tertiary institutions in the last decade. These incidences are in diverse forms and focuses on students of the tertiary institutions. Students complaint of their phones and laptops being hacked. This study sought to find out how frequent undergraduate students make posts and how that relates to cyber-attack on social media at the Federal College of Education and the American University of Nigeria. The study area has a population of 3756. The study used deductive, quantitative research; therefore, hypothesis was made and tested using the Pearson's Product Moment Correlation (PPMC) in the Statistical Package for Social Sciences (SPSS). The philosophical underpinning adopted in the study was the positivist paradigm. A structured questionnaire was employed as an instrument for data collection, and using a simple random sampling method, was distributed to students. The study focused on Facebook. The research selected 0.05 as the level of significance. It was found that there is a strong correlation between a cyber-attack and frequent activeness on social media. It found that there is a strong correlation between cyber-attack and frequenting the social media but there is no significant evidence to conclude same on the population. It suggested that further research be carried out using a qualitative research approaches so that respondents may be observed through interview.

Due to the fact that rules and guidelines for cataloguing and classification are changing to accommodate online resources, librarians need to adapt with these changes. The study adopted a survey research design. This study sought to find out cataloguing tools and competencies available in selected academic libraries in Adamawa State, Nigeria. Three research objectives guided the study, which were to identify the existing cataloguing and classification tools, establish the competency level of cataloguing and classification staff, and to identify challenges in cataloguing and classification. The population of the study was 31 cataloguing and classification staff including professionals and paraprofessionals. A Questionnaire was used as an instrument for data collection. Out of 31 copies of questionnaires distributed, only 20 (65%) copies were completed and returned. Data collated were analysed using descriptive statistics of frequency count and mean. The mean was used to answer the research questions. The criterion mean that was used was 2.50. Values above that were termed positive and those below that were termed negative. It was found that cataloguers and classifiers are competent, some of the recent cataloguing tools like RDA and MARC were not in use and the most prominent problems bedeviling the libraries are lack of training opportunities and shortage of professional staff. Hence the study recommended that the staff be trained especially on RDA, adequate and updated versions of tools be provided among others.