International Journal of Informatics, Information System and Computer Engineering (INJIISCOM)

Plant Nutrition Monitoring System for Water Spinach Based on Internet of Things

Sopian Alviana, Rizki Dwi Nugraha, Bobi Kurniawan — Tue, 23 Apr 2024 00:00:00 +0700

The concept of plants using a hydroponic system has been widely used. Currently, the weakness in the management of the hydroponic system is the difficulty in managing the nutritional needs of plants. Nutrition is the main requirement for plants with the concept of a hydroponic system. In this research, a system will be proposed that can monitor the nutritional needs of hydroponic plants with a concentration of water spinach plants. The use of internet of things technology is proposed to be able to monitor in real time. With the existence of a monitoring system in real time, it can make it easier to monitor and control the nutritional needs of kangkong plants using a smartphone.

Detection of SQL Injection Attacks Based on Supervised Machine Learning Algorithms: A Review

Hilmi Salih Abdullah, Adnan Mohsin Abdulazeez — Thu, 25 Apr 2024 00:00:00 +0700

In the ever-changing world of cybersecurity, it is becoming more important to ensure integrity of web applications as well as securing sensitive data. Among a variety of vulnerabilities, SQL injection is considered a significant risk with severe consequences. Addressing this crucial threat has always attracted the researchers to explore various approaches to identify and detect SQL injection attacks. The machine learning has captured the attention of the researchers to explore its potential due to its success in several different fields and the limitation of other rule-based approaches. This study provides a comprehensive review on a variety of the most recent researches that have been carried out using supervised learning algorithms. The study reveals that machine learning has a huge potential in the process of identification and detection of SQL injection attacks.

Bibliometric Analysis using Vos Viewer with Publish or Perish of Intelligent Tutoring System in Private Universities

Mon, 29 Apr 2024 00:00:00 +0700

The objective of this study is to analyze the development of intelligent tutoring systems in private universities. We conducted the analysis using bibliometric methods, utilizing the Publish or Perish and VOSviewer applications. Data was obtained by using the publish or perish application with the keyword "intelligent tutoring system in private university" from the Google Scholar database from 2019 to 2024. According to search results, the number of research papers has decreased from 117 to 23 from 2020 to 2024. Mapping using VOSviewer application produces three types of visualization, namely network, overlay, and density visualization. In its conclusion, this research notes a decrease in the number of studies discussing in private universities since 2020, but still shows great potential for development by other researchers.

Revolutionizing Cybersecurity: The GPT-2 Enhanced Attack Detection and Defense (GEADD) Method for Zero-Day Threats

Rebet Jones, Marwan Omar — Tue, 30 Apr 2024 00:00:00 +0700

The escalating sophistication of cyber threats, particularly zero-day attacks, necessitates advanced detection methodologies in cybersecurity. This study introduces the GPT-2 Enhanced Attack Detection and Defense (GEADD) method, an innovative approach that integrates the GPT-2 model with metaheuristic optimization techniques for enhanced detection of zero-day threats. The GEADD method encompasses data preprocessing, Equilibrium Optimization (EO)-based feature selection, and Salp Swarm Algorithm-Based Optimization (SABO) for hyperparameter tuning, culminating in a robust framework capable of identifying and classifying zero-day attacks with high accuracy. Through a comprehensive evaluation using standard datasets, the GEADD method demonstrates superior performance in detecting zero-day threats compared to existing models, highlighting its potential as a significant contribution to the field of cybersecurity. This study not only presents a novel application of deep learning for cyber threat detection but also sets a foundation for future research in AI-driven cybersecurity solutions

A Low-Cost Prototype for Edge-Computing Powered Smart Display Board

Thu, 30 May 2024 08:40:44 +0700

This study examines how Edge Computing technology, through the creation and use of smart notice boards, has changed the way that organizations communicate. Notice boards have historically relied on manually operated or wired electronic devices, which provide drawbacks like slowness, security flaws, and a lack of adaptability. But a new way of looking at notice board systems has developed with the advent of Edge Computing, which is driven by hardware like the ESP8266 server and communication protocols like MQTT (Message Queuing Telemetry Transport). We explore the advantages of Edge Computing in the context of smart notice boards in this study, emphasizing its capacity to support real-time data processing, improve security via local data management, login credentials, and provide users with user-friendly interfaces for content management. Smart notice boards can outperform traditional systems in terms of efficiency, security, and adaptability by utilizing the concepts of Edge Computing.

Smartphone-Based Heart Disease Classification Using Machine Learning Techniques

Yonten Jamtsho, Sonam Wangmo — Mon, 08 Jul 2024 14:56:54 +0700

Patients having heart diseases are diagnosed with a severe delay at times and further diagnosis in the absence of medical personnel can be fatal if the prediction is inaccurate. Therefore, this paper proposes the use of heart disease datasets to predict heart disease using various machine learning methods (Logistic Regression, Naive Bayes, Random Forest, k-nearest Neighbor, Support Vector Machine, Decision Tree Classifier, XGBoost Classifier, Artificial Neural Network). Cleveland, Hungarian, Switzerland, Long Beach VA and Statlog (Heart) datasets were used in this study which has 11 features of 1190 instances. The dataset was split into train and test sets with a ratio of 80:20. The performance was evaluated based on the accuracy, precision, recall, and F1 score for each of the models. From the eight models, the XGBoost Classifier outperformed other models with an accuracy of 93.7%. The trained model was integrated with the Android Studio framework to create the mobile application for the classification of heart disease.