Dynamic Control and Performance Evaluation of Microcontroller-Based Smart Industrial Heat Extractor (Published)
Dynamic control and performance evaluation of a microcontroller-based smart industrial heat extractor involves the implementation of control strategies and the assessment of its performance under dynamic operating conditions. Performance evaluation aims to assess the effectiveness and efficiency of the microcontroller-based smart industrial heat extractor under dynamic conditions. Industrial heat extraction systems are often complex, involving multiple components, sensors, actuators, and control algorithms. Understanding and modelling the dynamic behaviour of these systems can be challenging, especially when considering factors like heat transfer rates, thermal delays, and interactions between different system elements. The effectiveness of dynamic control is significantly dependent on precise and dependable measurements from sensors. Sensors deployed in industrial settings may encounter severe environmental conditions, which can result in possible inaccuracies, drift, or even malfunctions. The objective of this research is to propose a simulated methodology for verifying the efficacy of a microcontroller-driven intelligent heat extractor utilised in industrial settings. The execution of experiments or tests within industrial environments can be a costly and time-intensive endeavour, and may entail potential hazards. The efficacy of a smart industrial heat extractor in practical industrial settings can be ascertained through the simulation of its evaluation process, thereby mitigating potential risks. The model designed and simulated in this work utilises an integrated temperature sensor to determine the ambient temperature and transmits a signal to the Arduino UNO microcontroller when the temperature sensor detects variant temperatures ranges. The evaluation is performed by comparing the behaviour and performance of the simulated system with predefined performance metrices.
Keywords: Microcontroller, Neural network, cooling system, heat extraction, sensor.
A Model for Malicious Website Detection Using Feed Forward Neural Network (Published)
Malicious websites are the most unsafe criminal exercises in cyberspace. Since a large number of users go online to access the services offered by the government and financial establishments, there has been a notable increase in malicious websites attacks for the past few years. This paper presents a model for Malicious website URL detection using Feed Forward Neural Network. The design methodology used here is Object-Oriented Analysis and Design. The model uses a Malicious website URLs dataset, which comprises 48,006 legitimate website URLs and 48,006 Malicious website URLs making 98,012 website URLs. The dataset was pre-processed by removing all duplicate and Nan values, therefore making it fit for better training performance. The dataset was segmented into X_train and y_train, X_test and y_test which holds 60% training data and 40% testing data. The X_train contains the dataset of malicious and benign websites, while the y_train holds the label which indicates if the dataset is malicious or not. For the testing dataset the X_test contains both the malicious and non-malicious websites, while the y_test holds label which indicates if the dataset is malicious or not. The model was trained using Feed Forward Neural Network, which had an optimal accuracy 97%.
Keywords: Model, Neural network, detection, feed, malicious website
An Improved Model for Financial Institutions Loan Management System: A Machine Learning Approach (Published)
The inability of financial instructions, especially the Microfinance Banks, to forecast for the need of borrowers in order to make provision for them has been a cause for concern. Applications are made and most times the reply is that funds are not available. This paper demonstrated the design and implementation of neural network model for development of an improved loan-based application management system. The back propagation algorithm was used to train the neural network model to ascertain corrections between the data and to obtain the threshold value. The data was collected over a period of three years from UCL machine learning repository. The system was designed using object oriented methodology and implemented with Java programming language and MATLAB. The results obtained showed the mean squared error values 1.09104e-12, 5.56228e-9 and 5.564314e-4 for the training, testing and validation respectively. It was seen from the result that neural network can forecast the financial market with minimum error.
Keywords: Mean Square Error, Neural network, Regression, Validation, and Forecasting.