Analyzing the academic performance of students is of utmost importance for academic institutions and educationists, so as to know the ways of improving individual student’s performance. The project analyzed the past results of students including their individual attributes including age, demographic distribution, family background and attitude to study and tests this data using machine learning tools. Three models which are; Linear regression for supervised learning, linear regression with deep learning and neural network were tested using the test and train data with the Linear regression for supervised learning having the best mean average error (MAE).
The wind speed of a location is a critical parameter for analyzing wind energy conversion systems. Background knowledge has revealed that the two-parameter Weibull distribution is commonly used for fitting wind speed data because of its simplicity, flexibility and suitability. This research study examines wind speed data from five locations in Nigeria (Kano, Maiduguri, Jos, Abuja and Akure). It employs five numerical techniques, namely the maximum likelihood method, method of moment, power density method, empirical method and the logarithmic moment method, to estimate the Weibull parameters based on the locations’ data. The goodness of fit test is used to determine which numerical method best fits the distribution. The paper also considers the techno-economic design of wind electricity of five 25 kW pitch-controlled wind turbines with dissimilar characteristics. The test result presents the method of moment and empirical method as the best methods for calculating the Weibull parameters. Results also show that wind turbine-3 has the least cost of energy and wind turbine-5 has the highest cost of energy. ABSTRAK: Kelajuan angin sesuatu lokasi adalah parameter kritikal bagi menganalisa sistem penukaran tenaga angin. Latar belakang berkaitan telah mendedahkan 2-parameter taburan Weibull (Wbl) lazimnya digunakan bagi memadan data kelajuan angin berdasarkan kesederhanaan, fleksibiliti dan kesesuaian. Kajian penyelidikan ini adalah berkaitan ujian data kelajuan angin pada lima lokasi di Nigeria (Kano, Maiduguri, Jos, Abuja dan Akure). Ia menggunakan lima teknik berangka iaitu kaedah kemungkinan maksimum, kaedah momen, kaedah ketumpatan kuasa, kaedah empirikal dan kaedah momen logaritma bagi menganggar parameter Weibull berdasarkan lokasi data. Ujian kesesuaian digunakan bagi memastikan kaedah berangka adalah padanan paling sesuai bagi taburan. Kajian ini juga turut menimbang reka bentuk tekno-ekonomi elektrik angin bagi lima turbin angin 25 kW kawalan anggul dengan ciri berbeza. Dapatan kajian menunjukkan momen dan kaedah empirikal adalah kaedah terbaik bagi mengira parameter Weibull. Ini menunjukkan bahawa turbin angin-3 mempunyai kos tenaga paling rendah dan turbin angin-5 mempunyai kos tenaga tertinggi.
30 August 2023 in Expert Systems with Applications
The emerging trend in the world of semiconductor integration has brought about so many opportunities in the area of microcontrollers. This paper deals with the design and implementation of a microcontroller-based timer for home appliances using an Arduino microcontroller. This system is developed for the users to predetermine the time of operation of any home appliances using the electric cooker for implementation. The system is majorly comprised of the power supply unit, microcontroller unit, timer circuits and LCD display. The user can set any of the time given in the timer switch using keypad. The settings are stored in the microcontroller and the details are displayed in the LCD display. The appliance is controlled to run for the particular period set by the timer switch. The timer switch automatically makes the appliance off once the period is over. This system has been designed to be efficient, reliable and reduce energy wastage.
31 August 2024 in Sakarya University Journal of Computer and Information Sciences
The determination of the concrete compressive strength remains a challenging task in the concrete industry. Machine learning (ML) algorithms offer an alternative and this study presents a comparative analysis of five ML regression models; Gradient Boosting (GB), Random Forest (RF), Decision Tree (DT), K-Nearest Neighbors (KNN), and Linear Regression (LR) on a dataset of 1030 concrete samples. The findings indicate that the GB model achieved the best performance. The developed GB model achieved R-squared values of 91.60%, 91.43%, and 90.18% for the 10-fold, 5-fold, and 3-fold cross-validations, respectively, with mean absolute error, root mean squared error, and mean absolute percentage error values of 2.6776, 4.3523, and 9.19%, respectively. The GB model trained and evaluated was deployed to a web application using Streamlit for real-time prediction of the concrete compressive strength. The results of this research offer a precise and practical method for judging the quality of concrete constructions.
1 January 2024 in ITEGAM-Journal of Engineering and Technology for Industrial Applications (ITEGAM-JETIA)
The reliance on paper-based educational certificates and the lack of a robust and tamper-proof system for verifying academic credentials in the Nigerian education system make them vulnerable to forgery and alterations. The situation poses challenges in guaranteeing the legitimacy of such qualifications, and a need arises for a secure system to verify academic credentials. The proposed solution is a blockchain-based digital certificate verification system (BCVS) that utilizes the Celo blockchain as the underlying blockchain platform to store each digital certificate hash and meta-data, which is unique, secure, and permanently recorded on the blockchain. The system also includes a QR code feature to verify the certificate's authenticity instantly. Ten users evaluated the system, and the average scores are as follows: the user interface had 78%, the application database security scored 66%, the blockchain data security achieved 82%, the revocation mechanism achieved a score of 67%, and the maintainability achieved a score of 46%. While the system is designed to cater to university requirements and can revoke certificates if needed, it represents an advancement in certificate verification, thereby simplifying the process and improving the overall experience for everyone involved, with the potential to be scaled and customized for other universities, institutions, and use cases.