Journal of Advanced Computing Technology and Application (JACTA)

The DEVELOPMENT OF IOT BASED SMART DOOR LOCK AND FIRE ALERT SYSTEM USING FACIAL RECOGNITION

Wed, 30 Jul 2025 00:00:00 +0000

The purpose of this study is to develop an IoT home security system that integrates facial recognition technology and offers remote access control. In an era where smart technologies revolutionize conventional home security systems, this research introduces an IoT-based smart door lock system including facial recognition technology. The proposed system integrates Raspberry Pi, a Raspberry Pi camera, a solenoid door lock, and a flame sensor to offer advanced security features while ensuring user convenience. Operating within a cloud-based framework, users gain unparalleled accessibility to their home security. Through a mobile application, users can remotely monitor and control their door lock status from anywhere in the world. In order to enable smooth authentication upon detection, the technology makes it possible to save recognised faces inside the mobile application. When a recognized face approaches the door, it triggers automatic unlocking, streamlining entry for authorized individuals. Furthermore, the system enhances security measures by promptly notifying users of any unfamiliar faces detected. Beyond access control, the system prioritizes safety by incorporating a flame sensor. Upon detecting fire within the premises, the system activates, sending an immediate notification to the user and initiating automatic door unlocking. This critical feature ensures swift evacuation during emergencies, potentially mitigating property damage and ensuring occupants safety. Implemented as a cloud-based solution leveraging Google Firebase, the system seamlessly updates real-time data, enhancing responsiveness and reliability.

ENHANCING DATA SECURITY AND DRIVING ECONOMIC DEVELOPMENT THROUGH BLOCKCHAIN ADOPTION IN NIGERIAN FINANCIAL INSTITUTIONS

EMMANUEL JOHN ANAGU — Wed, 30 Jul 2025 00:00:00 +0000

Nigeria’s financial sector can achieve significant benefits through blockchain technology because it strengthens data protection and reduces fraud likelihood and introduces total transaction visibility to the financial environment. Numerous obstacles prevent this groundbreaking technology adoption because officials in charge remain indecisive about the use of blockchain and professionals in the sector fail at understanding blockchain. Additionally, there are technological hurdles and funding constraints together with regulatory complexities. The research examines blockchain technology implementation in Nigerian financial operations by reviewing its economic benefits and discussing adoption obstacles across financial networks. The research adopts qualitative documentary analysis as its methodology to study blockchain implementation in financial institutions through academic peer-reviewed studies and industrial reports with field-relevant case studies. Banking security and broad financial accessibility improve through blockchain technology based on evidence from this study yet investors need to navigate through unknown challenges since existing rules provide insufficient regulatory guidelines in blockchain fields. Both infrastructure deficiencies and low internet penetration rates in different regions as well as minimal technical proficiency of professionals slow down the integration and deployment of blockchain methods. For blockchain technology implementation to succeed there needs to be policy adjustments and improvements to digital infrastructure while also developing specific blockchain training programs to increase understanding and literacy among people. The study provides fundamental information about blockchain adoption basics in Nigeria's financial sector as well as guidelines to optimize data protection and economic sustainability.

FORTRAN IMPLEMENTATION FOR NUCLIDE LIQUID DROP MODEL CALCULATIONS WITH NUMERICAL TECHNIQUES

Ruliyanta Ruliyanta, Budi Santoso — Wed, 30 Jul 2025 00:00:00 +0000

This research proposes a numerical variation method developed to find the best parameters of the nuclide liquid drop model in calculating its mass. This method was developed because there was no systematic method for finding empirical model parameters in calculating the nuclide mass or binding energy. The modelling used in this study uses the Fortran programming language or formula translation. The results obtained provide a very significant improvement in the model for calculating the mass of stable nuclides. The closeness of the empirical model calculation results to the experimental results shows the model's validity. The delta deviation results from the proposed numerical method give the smallest value compared to existing methods at 111. Meanwhile, the error rate in the proposed method is 0.00088% or 8.84 x 10^-6.

A WEB-BASED FLOOD INFORMATION MANAGEMENT SYSTEM FOR IMPROVED RESCUE AND RECOVERY DECISIONS

Md Shadman Zoha, Nor Aiza Moketar, Massila Kamalrudin, Suriati Akmal — Wed, 30 Jul 2025 00:00:00 +0000

This paper presents the development of the Flood Rescue and Recovery Management System, designed to address inefficiencies in current flood response methods, which often rely on slow manual coordination and limited data sharing. The study aims to develop a user-friendly web-based platform that streamlines flood information sharing, enhances accessibility and improves decision-making for rescue and recovery. Core functionalities encompass user-submitted help requests, real-time flood alerts, risk heatmap visualization, resource allocation based on risk scores, task management and a chat room for coordination. Built on Agile principles like rapid communication and flexible planning, this system tackles issues such as delayed responses and poor data sharing. While the tool has not yet been validated in real-world scenario, it simplifies coordination, increases community engagement and provides reliable data for stakeholders. This paper explains how the tool was built, its benefits, and how it can support faster and smarter flood response. Future work will focus on real-world deployment and user testing to validate its effectiveness.

A WEB-BASED MACHINE LEARNING MODEL FOR PREDICTING STUDENT ACADEMIC PERFORMANCE IN TERTIARY INSTITUTIONS

EMMANUEL JOHN ANAGU, Rande Wella — Wed, 30 Jul 2025 00:00:00 +0000

Educational data mining plays a crucial role in analyzing student performance to identify those at risk and enhance academic success. Traditional statistical methods often fail to capture the complex factors influencing student achievement. This research presents a machine learning-based predictive system integrated into a web application to forecast student academic performance. The study utilizes a dataset from Taraba State University, comprising students from diverse demographics. The dataset undergoes preprocessing, feature selection, and modeling using three machine learning algorithms: Random Forest, Support Vector Machine (SVM), and Decision Tree. The evaluation results demonstrate that Random Forest achieved the highest accuracy (94%), followed by SVM (93%) and Decision Tree (92%). The developed web-based system allows educators to input student data and receive real-time performance predictions, facilitating early intervention strategies. The study highlights the potential of machine learning in educational decision-making and recommends further research on ensemble learning techniques for real-time academic performance prediction.