Empowering Cybersecurity: A Deep Dive into AI-Driven Security Intelligence Modelling
Smart Incubator for Empowering Poultry Farmers by Maximizing Egg Hatching Success
Early Disease Detection of Black Gram Plant Leaf using Cloud Computing Based YOLO V8 Model
Data Retrieval in Cancer Documents using Various Weighting Schemes
Securing Healthcare Data in Smart Cities: A Machine Learning Approach
COVID-19 is a new virus that originated in China, which is one of the dangerous and widespread infectious diseases. More than one lakh deaths have been reported to date, and the death toll continues to rise. This is a comprehensive survey of what aspects need to be considered for developing an accurate classifier to predict the variations in death rate. After this step, a novel and robust classifier with a Deep Convolution Network augmented with Hybrid Non-Linear Cellular Automata rules(DCNHCAC) was proposed to predict the rate, in which the deaths are varying. Eighty thousand plus datasets are collected from Kaggle, data world for training and testing the proposed classifier. The proposed classifier is compared with the existing methods such as SVM, Regression, K-Means, Adaboost, SVR. DCNAHNLCA has reported an accuracy of 86.7%, precision of 0.86, and recall of 0.82, which is the best available at this moment.
Cognitive Networks were introduced to resolve issues by incorporating intelligence into the network functions. Hence, a hybrid algorithm was developed to improve spectrum resource allocation in a cognitive network for distributed computing. Five hundred thousand datasets were collected from Nigeria Communication Commission (NCC) repository. Artificial Neural Network was used to divide the dataset into 4 stages: UHF, FM, GSM 900 and DCS 1800. The hybrid algorithm was achieved using Hidden Markov Models (HMMs) which was combined with Markov-based Channel Prediction Algorithm (MCPA) in CN for dynamic spectrum allocation and higher efficiency of the spectrum holes to improve the accuracy. The combination of the mentioned two algorithms were simulated using MATLAB simulator 2019b for accuracy test. The result showed that the efficiency of the radio networks was found to be closed. Power efficiency increased from 76.66% to 86.82% for FM Broadcast, 76.91% to 86.82% for GSM-900, 78.19% to 89.04% for DCS-1800 and 78% to 88.55% for UHF TV. The computation results showed a level of improvement in spectrum occupancy license distribution from 19.6 to 61.1%. In conclusion, it was demonstrated that a hybrid algorithm offered a better solution in wireless networking by using an improved algorithm to provide a cognitive spectrum occupancy technique in a wireless network. It was recommended that telecommunication companies should adopt an improved algorithm for enhancing CN in their operations.
The pandemic of Corona Virus Disease (COVID-19) has shaken the globe with its wide spread, resulting in human deaths due to limited understanding of medical community and scarcity of medical resources. The rapid rise in the number of COVID-19 incidents has promoted the need for public awareness and effective preventive measures to control the disastrous effects of this epidemic. In the current context, it is necessary to predict the trend of COVID-19 to support the public health sector to effectively prevent and control this epidemic in order to save mankind. Traditional pandemic models consume lot of time to predict the number of infections as these models consider all individuals with corona virus have the same infection rate. These prediction results can only provide general trends which are not useful for epidemic control and prevention at the right time. Therefore, we proposed a machine learning approach for scenario analysis and forecasting time series data of COVID-19 to visualize its impact globally and accelerate the containment of the virus. The results analyzed through this forecasting model will help the people better understand the potential implications of corona virus and predict the possible future cases of COVID-19.
The innovation and advancement of Information Technology (IT) makes electronic payment (e-payment) a common st part of the global economy. In 21 century, many advanced nations are collecting their revenues using online platforms. In Nigeria, the Central Bank of Nigeria (CBN) has been promoting a 'cash-less policy' to foster development and adopt Nigeria's vision of a digital economy. This paper designs and implements a USSD based cashless revenue collection system using a mobile phone as a database that holds the information needed to conduct transactions and effect payments. The user's data is stored in a digital wallet on the user's mobile phone, which is digitally processed by the revenue collector. Java Programming Language is used for both the desktop and mobile application. Apache Tomcat server was the web server and MySQL was the database. Africa's Talking USSD simulator was used to simulate mobile service providers. The prototype was tested to evaluate its feasibility and usability. The evaluation of the system shows that the prototype implementation can support the collection of revenue from the informal sector of the economy to enhance the efficiency of the revenue collection process and block revenue leakages.
Results processing is a continuous process of converting data (scores, grade points and credit units) into definite and meaningful information such as statement of result and transcript etc. These results are used to access the performance of students in various courses. The current method of students' academic results generating and processing was found to be error-prone, tedious and time consuming and the bulk of work rest on the shoulders of Examination Officer (EO), especially when carried out for a very large number of students. This makes the entire process tedious and error prone. In view of the foregoing, this research developed a computer software application (using Hyper Text Mark Up Language 5 (HTML 5) for client-side, Hyper Text Pre-Processor (PHP) for server-side and My Structured Query Language (MySQL) was used for relational database) to facilitate the automatic uploading of results by individual lecturers, through the Examination Officer who doubles as system administrator. The implemented system makes it possible to compute Grade Point Average (GPA) and Cumulative Grade Point Average (CGPA) for each student based on scores uploaded. The system saves time of the EO in processing students result, enhanced accuracy, effectiveness, and eliminate redundancies and equally afford the students the opportunity to view their results online.
