Massive data generated by connected smart devices, particularly in distributed computer networks, contributed to the large network traffic burden caused by the ever-increasing use of the Internet infrastructure and web caching systems. Such connected smart devices generate massive data, shared and synchronized together in real-time over the connected nodes using various emerging technologies through the Web. However, the performance of classical web caching methods usually degrades when caching web objects due to various factors. Therefore, this study presents a comprehensive review of machine learning and deep learning-based web cache replacement models that could be effectively used to improve the performance of web caching systems. The study revealed that random forest, artificial neural networks, support vector machine, LSTM and fuzzy approaches are among web cache replacement models that have been used to improve the performance of web caching systems. However, due to the sparse use of web object features, some models are typically unable to handle today's unpredictable web caching demands. Therefore, to deal with rising web usage, high latency, increased user-perceived delays, web cache overload, network traffic congestion, increased web object size, real-time data sharing, and limited bandwidth size, various web object attributes should be included in the next-generation adaptive and robust machine and deep learning-based web cache replacement models. In addition to web object features such as recency, frequency, cost, hit rate, modification and expiration time, more features are required in developing adaptive web caching algorithms to improve the performance of web caching systems.

This paper analyses and implements a rule-based approach for phishing detection using the three machine learning models trained on a dataset consisting of fourteen (14) features. The machine learning algorithms are; k-Nearest Neighbor (KNN), Random Forest, and Support Vector Machine (SVM). Among the three algorithms used, it was discovered that Random Forest model proved to deliver the best performance.Rules were extracted from the Random Forest Model and embedded into a Google chrome browser extension called PhishNet. PhishNet is built during the course of this research using web technologies such as HTML, CSS, and Javascript. As a result, PhishNet facilitates highly efficient phishing detection for the web.

In the contemporary world, the security of data and privacy policies are major concerns in cloud computing. Data stored on the cloud has been claimed to be unsafe and liable to be hacked. Users have found it difficult to trust their data in the cloud. Users want to know that their data is accessible from anywhere and that an unauthorized user will not be able to access it. Another area of concern is the authentication of users over the cloud. There are a number of security concerns with Cloud Computing which include Distributed Denial of Service, Data leakage, and many more, just to mention a few. In this paper, an Elliptic Curve Cryptography (ECC) algorithm is used for the encryption and decryption of the information stored on the cloud, so that if someone gains access to the server, it would be unable to access the original information. Performance evaluation of the developed system is performed by comparing ECC with the RSA algorithm. The results show that the ECC method is more efficient than RSA when used to secure information in the cloud.

Predicting maize crop yields especially in maize production is paramount in order to alleviate poverty and contribute towards food security. Many regions experience food shortage especially in Africa because of uncertain climatic changes, poor irrigation facilities, reduction in soil fertility and traditional farming techniques. Therefore, predicting maize crop yields helps policymakers to make timely import and export decisions to strengthen national food security. However, none of the published work has been done to predict maize crop yields using machine learning in Eswatini, Africa. This paper aimed at applying machine learning (ML) to predict maize yields for a single season in Eswatini. A ML model was trained and tested using open-source data and local data. This is done by using three different data splits with the open-source predictor data consisting of 48 data points each with 7 attributes and open-source response data consisting of 48 data points each with a single attribute, adjusted R² values were 0.784 (at 70:30), 0.849 (at 80:20), and 0.878 (at 90:10) before being normalized, 1.00 across the board after normalization, and 0.846 (at 70:30), 0.886 (at 80:20), and 0.885 (at 90:10) after backward elimination. At the second attempt, it is done by using the combined predictor data of 68 data points with 7 attributes each and combined response data of 68 data points with a single attribute each, with the same data splits and methods adjusted R² values were 0.966 (at 70:30), 0.972 (at 80:20), and 0.978 (at 90:10) before being normalized, 1.00 across the board after normalization, and 0.967 (at 70:30), 0.973 (at 80:20), and 0.978 (at 90:10) after backward elimination.

The high mortality rate associated with cancer and the inability to detect the disease early has led to a catastrophic reduction in the rate of survivability of the disease in women. We have attempted to improve on the rate of survival by using Fuzzy logic to develop a risk factor system for detection of breast cancer. The system has been implemented using the Mamdani fuzzy logic approach in MATLAB. A graphical user interface (GUI) has been developed using Microsoft Visual Studio 2012. The GUI was powered by a Fuzzy Logic Library and Visual C# was used as its programming language. Keywords: Breast Cancer, Disease, Risk factor, Fuzzy Logic.

Machine learning has become one of the foremost techniques used for extracting knowledge from large amounts of data. The programming expertise required to implement machine learning algorithms has led to the rise of software products that simplify the process. Many of these systems however, have sacrificed simplicity as they evolved and included more features. In this study, a machine learning software with a simple graphical user interface was developed with a special focus on enhancing usability. The system made use of basic graphical interface elements such as buttons and textboxes. Comparison of the system with other similar open-source tools revealed that the developed system showed an improvement in usability over the other tools.

Prostate cancer has been known as one of the most deadly diseases in the world that flourished in men. History has discovered that the epidemic is a slow growing disease that occurs in the life of men without the carriers’ knowledge that the disease is already in the gland. Prostate cancer is a disease that grows in the prostate which is a gland in the reproductive system. The purpose of this research paper is to use an artificial neural network to predict the occurrence of prostate cancer in men. We were privileged to have access to data of certain known cases of prostate cancer and non prostate cancers collected from government hospitals. In the proposed system, users can enter their parameters and it would be compared with the already stored parameters in the database for early possible detection of prostate. The proposed system can then predict whether there is possibility of prostate cancer from the parameters entered.

The primary purpose of Denial of Service attack (DoS) is to cripple resources so that the resources are made unavailable to the legitimate users. Due to the inadequate monitoring of activities on the network, it has resulted into huge financial losses. Bandwidth which is one of the resources being used on the network, if not properly monitored could result into misused and attack. This paper proposes a real time system for securing and monitoring the amount of bandwidth consumed on the network using the multi-agent framework technology. It also keeps a record of internet protocol (IP) addresses visiting the network and may be used as a starting point for the aspect of response in providing a comprehensive solution to DoS attacks. The bandwidth is pre-entered and an agent is assigned to monitor bandwidth consumption rate against the set threshold. If the bandwidth is consumed above the bandwidth limit and time set, then a DoS attack is suspected taking into considerations the DoS attack framework This framework can be used as a replicate of what happen in the network scenario environment.

The soil is composed of several nutrients which are important for the effective growth of plants. Nitrogen, phosphorus, and potassium are micronutrients which are very important for plant growth. There have been several methods and soil tests developed to test the compositions of these nutrients in the soil. Interpreting the results gotten from such tests has been a herculean task for farmers. Employing the use of a soft computing method to interpret such result would be a noble idea. In this paper, we describe the use of fuzzy logic to interpret the values of nitrogen, phosphorus, and potassium (NPK) gotten from conventional soil test to know their levels in the soil and predict possible NPK inputs.

Aim: The aim of this study is to assist medical practitioners in Nigeria in reducing rate at which data are lost, mismanaged and/or interchanged in hospital record systems in Nigeria by providing a system that helps the doctor performs both accurate record keeping and prompt healthcare delivery conveniently and efficiently. Materials and Methods: The proposed system is designed to function as a real time information system for prompt health care delivery. It is designed for use only by the health care to replace the traditional method of record keeping in Nigeria. An algorithm and flowchart were developed for the proposed system. Results: This results in this study focuses on the Doctor’s Appointment Reminder system as a Real Time Information System. Its aim is to remind doctors of their appointments with patients. It works by allowing the Doctor keeps track of patients, inputting details about the patient, including time and date of appointments. The system sends an alert to the doctor through an already provided email address containing all the details provided by the Doctor during the patients’ registration. Conclusion: The Doctors’ Appointment Reminder System is a web-based system developed using Hypertext Preprocessor (PHP) embedded in (Hypertext Markup Language) HTML, and MySQL for the database.

Background and Objective: The already existing Bank Verification Number (BVN) software doesnʼt generate the 10 digit BVN immediately it goes through a number of sources for allocation of BVN to a customer.Furthermore, because of the crime rate in the banking sector it is very onerous to access the BVN application or update information on this platform so there is a long procedure in updating information on the platform.The objective of this study was to propose a faster and new approach of generating a BVN number through the web.Methodology: In this study, a new method was adopted to replace the traditional method of generating the BVN number.A linear congruential algorithm was adapted to generate the BVN randomly.Results: The results in this study provide a faster method of generating an online BVN numbers for Bank customers.The study demonstrated that how the users can register, verify and have the BVN numbers generated on the web.Consequently, the results tallies with the present situation in the banking sector thereby addressing the challenges in the sector.Conclusion: The results will serve as a form of relieve to the financial institutions and bank customers in Nigeria.

CRIME is one of the major problems encountered in any society and universities together with other higher institutions of learning are not exceptions. Thus, there is an urgent need for security agents and agencies to battle and eradicate crime. The Directorate of Students and Services Development (DSSD) are responsible for investigating and detecting criminals of any crime committed within the Redeemer’s University. DSSD faces major challenges when it comes to detecting the real perpetrators of several crimes. An improvement in their strategy can produce positive results and high success rates, which is the basic objective of this project. Several methods have been applied to solve similar problems in the literature but none was tailored to solving the problem in Redeemer’s University and other universities. This work therefore applied classification rule mining method to develop a system for detecting crimes in universities. Past data for both crimes and criminals were collected from DSSD. In order to develop and test the proposed model, the data was pre-processed to get clean and accurate data. The Iterative Dichotomiser 3 (ID3) decision tree algorithm obtained from WEKA mining software was used to analyze and train the data. The model obtained was then used to develop a system that showed the hidden relationships between the crime-related data, in form of decision trees. This result was then used as a knowledge base for the development of the crime prediction system. The developed system could effectively predict a list of possible suspects by simply analyzing data retrieved from the crime scene with already existing data in the database. This system has all the potentials of helping the students’ affairs department and security apparatus of any university and other institutions to quickly detect either the real or possible perpetrators of crimes in the system.

This paper presented a new multilingual language for Automated Teller Machine (ATM) in Uganda which serves as an extension to the existing Languages. The existing ATMs have only English, Kiswahili and Luganda as the only available languages. Hence, findings revealed that there are still some prevalent languages e.g. Ateso language that are widely spoken among the people of Uganda which the present ATMs in the country have not captured. The objective of this paper was to propose the integration of the new language (Ateso language) to the existing languages. In this paper, a new language was adopted when it was realized that some people especially in the Buganda region could not manage to interact with the ATMs because they were illiterate. The developed multilingual system prototype was tested using some empirical data and was found to successfully imitate ATM transactions in the local Uganda languages. The results of the study supported the positive impacts on customers that reside in the rural areas since its improved interaction of more users on the ATMs. This paper demonstrated the use of Ateso language for different transactions on the ATM system. The implementation by the banking institutions can aid the ATM users to make more flexible decisions on the usage of the ATM machines.

The inability of a region to access a webpage, because of the ban being placed on users from that region as a result of its location policy, has led to this study. This problem is often solved by anonymizing web traffic by using The Onion Router (TOR). These tools, however, suffer from the problem of exposure of identity and also lack the ability to monitor web users. This study describes in detail a web proxy server service solution within the context of a tertiary institution in Nigeria and explains how this service improves the user experience. An identity management system using a web proxy server was developed to tackle these problems. The new system proxy was designed using a transparent proxy model with some additional translational features where no modification was done to the response or request of resources, other than the addition of its identification information or that of the server from which the message was recovered, and mediation of resources. Redeemer’s University proxy was used as a case study in this research work. This system is also able to effectively monitor users’ (staffs and students) operations on the web. Key words: Web proxy, web anonymity, identity management, The Onion Router (TOR).

BACKGROUND:The practice of exclusive breastfeeding is still low despite the associated benefits. Improving the uptake and appropriating the benefits will require an understanding of breastfeeding as an embodied experience within a social context. This study investigates breastfeeding practices and experiences of nursing mothers and the roles of grandmothers, as well as the work-related constraints affecting nurses in providing quality support for breastfeeding mothers in Southwest Nigeria.METHODS:Using a concurrent mixed method approach, a structured questionnaire was administered to 200 breastfeeding mothers. In-depth interviews were also held with breastfeeding mothers (11), nurses (10) and a focus group discussion session with grandmothers.RESULTS:Breastfeeding was perceived as essential to baby's health. It strengthens the physical and spiritual bond between mothers and their children. Exclusive breastfeeding was considered essential but demanding. Only a small proportion (19%) of the nursing mothers practiced exclusive breastfeeding. The survey showed the major constraints to exclusive breastfeeding to be: the perception that babies continued to be hungry after breastfeeding (29%); maternal health problems (26%); fear of babies becoming addicted to breast milk (26%); pressure from mother-in-law (25%); pains in the breast (25%); and the need to return to work (24%). In addition, the qualitative findings showed that significant others played dual roles with consequences on breastfeeding practices. The desire to practice exclusive breastfeeding was often compromised shortly after child delivery. Poor feeding, inadequate support from husband and conflicting positions from the significant others were dominant constraints. The nurses decried the effects of their workload on providing quality supports for nursing mothers.CONCLUSION:Breastfeeding mothers are faced with multiple challenges as they strive to practice exclusive breastfeeding. Thus, scaling up of exclusive breastfeeding among mothers requires concerted efforts at the macro, meso and micro levels of the Nigerian society.

Virtual Knowledge Communities (VKC) are current popular media on the internet through which the access and sharing of knowledge and information among communities of similar interest groups are made possible. Agent’s technologies are presently being deployed to facilitate the success of VKC, which is a virtual place where knowledge agents can meet, communicate and interact among themselves. Recently, quite a number of works have been done on agent-based knowledge communities but most of these works have not actually considered the possibilities of intrusion and the consequences of these malicious attacks on those systems. This paper therefore addresses the issue of intrusion detection problems in the sharing of knowledge in virtual knowledge communities. Intelligent agents are proposed as measures to guide against any spy or intruder into the VKC. The method proposed shows potential evidences of promising results.