A food system is composed of a complex network of activities and processes for production, distribution, transportation and consumption, which interact with each other, thus leading to changeable behaviour. Most existing empirical studies on cassava processing have focused on the technical efficiency analysis of the cassava crop processing techniques among processors indicating that the modelling of the events and operations involved in the processing of the cassava crop is highly limited. In this context, different strategies have been used to solve difficult environmental and agro-informatic systems model-based problems such as system dynamics, agent based, rule-based knowledge and mathematical modeling. However, the structural comprehension and behavioral investigation of this modeling are constrained. In this regard, formal computational modeling is a method that enables modeling and simulation of the dynamical characteristics of these food systems to be examined. In this study, the system specification is designed using Unified Modelling language (UML) to show the structural process and system design modelled and simulated using Coloured Petri Net (CPN), a formal method for analyzing the behavioural properties of complex system because of its efficient analysis. For the purpose of observing and analyzing the behaviour of the cassava food process, a series of simulation runs was proposed.

Customer service is an important area in the success of a system or a service. For services that have a relatively large customer base, the efficiency with which complaints are attended to becomes an issue. The Computer Centre of the Obafemi Awolowo University attends to students with various complaints majorly in relation to their e-portal accounts. Although efforts are in place to manage the crowd, there is still a major need for the complaint management service to save time and energy. The need for a system that can handle the enormous request and complaints of the undergraduate students of the institution is the thesis of this work. Design and implementation was done using the range of tools provided by the Microsoft Bot Framework. C# Programming language was used to implement the decision algorithm. Online web services were used to handle natural language understanding and the Bot Connector to implement the Web Canvas. Microsoft Azure Service was used to host the web after which evaluations were drawn through surveys. Thus, this study projected an easier flow of operations involving logging of complaints by students.

This study compared two neural network models (Multilayer Perceptron and Generalized Regression Neural Network) with a view to identifying the best model for predicting students’ academic performance based on single performance factor. Only academic factor (students’ results) was considered as the single performance factor of the study. One cohort of graduated students’ academic data was collected from the Computer Science and Engineering Department of Obafemi Awolowo University, Nigeria using documents and records technique. The models were simulated using MATLAB version 2015a and evaluated using mean square error, receiver operating characteristics and accuracy as the performance metrics. The results obtained show that although Multilayer Perceptron had prediction accuracy of 75%, Generalized Regression Neural Network had a better accuracy. The response time of Generalized Regression Neural Network (0.016sec) was faster than Multilayer Perceptron (0.03sec) and its memory consumption size (5kb) lower than that of Multilayer Perceptron (8kb). The simulated models were further compared with t-test method using a confidence interval of 95%. The attained t-test result from p-value (0.6854) suggests acceptance of null hypothesis, which shows that there is no significant difference between the predicted Grade Point Average and the actual Grade Point Average. The findings therefore reveal that the overall performance of Generalized Regression Neural Network outperforms the Multilayer Perceptron model with an accuracy of 95%. The study concluded that Generalized Regression Neural Network model which was simulated and with 95 % accuracy could be deployed by educationists to predict students’ academic performance using single performance factor.