International STEM Journal

The Impact of AI-Driven Tools on Learning Motivation: A Case Study of ChatGPT Usage Among Thai Undergraduates

2024-11-19T16:14:51+08:00

This study investigates the impact of ChatGPT on the learning motivation of undergraduate students in Thailand, where the adoption of artificial intelligence in education is rapidly growing, reflecting a broader shift towards integrating AI tools into learning environments. The research employs the Motivated Strategies for Learning Questionnaire (MSLQ) framework, focusing on six motivational dimensions: Test Anxiety, Intrinsic Goal Value, Control Beliefs, Extrinsic Goal Orientation, and Self-Efficacy for Learning and Performance. Given the unique challenges faced by Thai undergraduates in maintaining engagement and motivation in a competitive academic environment, this study highlights the critical role of learning motivation in fostering academic success. Data from Thai university students reveal that the Task Value group demonstrated the highest Orientation, Task usage of ChatGPT (100%), while the Control Beliefs group exhibited the lowest (60%). These findings align with Bandura's self-efficacy theory and studies emphasizing the role of task relevance in motivating technology use. This research underscores ChatGPT's potential to address diverse learner needs and provides actionable insights for educators and institutions to integrate AI tools effectively and ethically, fostering a supportive and dynamic learning environment.

SMS Spam Detection Using Machine Learning Approach

2025-05-27T23:41:02+08:00

Currently, as the popularity of mobile phones has increased, Short Message Service (SMS) has grown tremendously. The minimal cost of messaging services has increased spam or unsolicited messages sent to mobile phones. There are differences between spam filtering for text messages and emails. Emails have a set of big datasets, while the actual databases for SMS spam are very limited. Because of the small size of text messages, the features used for classification are smaller than the equivalent number in emails. Text messages consist of abbreviations and have less formal language than that of emails. Short Message Services (SMS) spam has become a pressing issue in mobile communication, disrupting user experiences and posing privacy threats. This study develops a useful system for identifying spam messages in SMS communications. It presents a machine learning-based framework for detecting SMS spam, utilizing a Multi Layer classifier. This is aimed at tackling the problem of spam messages in SMS communications through the development of a robust and efficient spam detection system. This entails a data preprocessing procedure to prepare the raw SMS dataset. The TF-IDF technique was used to handle feature extraction to represent the text data numerically. This enables the model to capture relevant characteristics distinguishing spam from non-spam messages. The model was trained using the preprocessed data and evaluated through cross-validation. The results highlight the scalability and reliability of this approach, providing a practical solution for enhancing SMS spam detection systems and improving user security in mobile communication, employing the multi-layer classifier for an effective spam detection system, ensuring the models' optimal performance while preventing overfitting to deliver a comprehensive solution to the persistent issue of SMS spam.

Enhancing STEM Interest and Science Stream Enrolment Among B40 Students in Rural Pahang, Malaysia through the STEMA Garden Module

2025-06-18T11:45:21+08:00

STEM education is essential for future career readiness, yet rural B40 students in Pahang, Malaysia face challenges in accessing engaging and practical learning opportunities. This case study examines the STEMA Garden Module, an initiative designed to increase students' awareness of agriculture’s economic value, impart agricultural science and entrepreneurship knowledge, and enhance STEM and art interest through hands-on agricultural activities. Implemented at SMK Sg Lembing, Kuantan, the program engaged 82 Form 1 students, 7 teachers, and 17 university mentors, integrating an IoT-powered fertigation system, plant management, and agribusiness training. A mixed-methods approach was used, including pre- and post program surveys and teacher interviews. Findings revealed improvements were recorded in general interest in STEM education (Q1, p = 0.0011), the intention to further one’s studies in STEM (Q2,p = 0.0336), excitement and readiness to engage in hands-on activities (Q5, p = 0.0017), interest in learning how to think creatively to solve real-life problems (Q11, p = 0.0169), and interest in learning science and entrepreneurship to become an agropreneur (Q12, p 0.0093). The thematic analysis of teacher reflections highlighted technology-driven learning, project-based teaching, improved student engagement, entrepreneurial mindset development, and school-wide STEM transformation as key outcomes. Students gained practical
exposure to agricultural technology and entrepreneurship, leading to their first harvest of 8.127 kg of chili, generating RM229.00 in revenue. Despite challenges such as fungal infections and WiFi interruptions affecting the IoT fertigation system, students demonstrated adaptability and problem-solving skills. This study highlights the potential of agriculture-based STEM education in fostering engagement, interdisciplinary learning, and real-world applications among rural area students. The STEMA Garden Module serves as a scalable model for integrating STEM with agriculture and entrepreneurship, making STEM education more accessible and
relevant. Future implementations should explore long-term impact assessment and technological advancements to further enhance learning outcomes and STEM career aspirations.

Machine Learning-Based Intrusion Detection and Prevention System for IoT Smart Metering Networks: Challenges and Solutions

2025-05-27T23:15:27+08:00

The Internet of Things (IoT) has revolutionized industries by enabling automation, real time data exchange, and smart decision making. However, its increased connectivity introduces cybersecurity threats, particularly in smart metering networks, which play a crucial role in monitoring and optimizing energy consumption. This paper explores the challenges associated with securing IoT-based smart metering networks and proposes a Machine Learning (ML)-based Intrusion Detection and Prevention System (IDPS) for safeguarding edge devices. The study reviews various intrusion detection approaches, highlighting the strengths and limitations of both signature based and anomaly-based detection techniques. The integration of ML-based IDPS in IoT smart metering networks significantly improves security by enhancing anomaly detection accuracy and reducing false positives. Advanced models like SVM, CNN, and CNN LSTM effectively detect threats such as DoS, spoofing, and abnormal usage patterns across network layers. These systems also support real-time monitoring and adapt to evolving attacks, increasing system resilience. However, most models are tested on outdated datasets and overlook deployment challenges on resource-constrained devices. Therefore, lightweight and scalable solutions are needed to ensure effective, energy-efficient protection in real-world smart metering environments.

A Resilient and Energy-Efficient Smart Metering Infrastructure Utilizing a Self-Organizing UAV Swarm

2025-05-27T22:59:50+08:00

The effective and secure gathering of energy consumption data has become essential as smart cities develop. High costs, safety hazards, and data latency are some of the enduring issues that traditional smart metering infrastructures (SMIs), which depend on manual data acquisition, must deal with. In this paper, a novel SMI architecture for autonomous, energy-efficient, and resilient smart meter data collection is presented, utilizing a self-organizing swarm of Unmanned Aerial Vehicles (UAVs). To guarantee system dependability, our design integrates a hierarchical drone network with leader and slave drones, backed by strong communication protocols and dynamic task reallocation mechanisms. The system's scalability, low latency, and fault tolerance are confirmed by means of comprehensive OPNET-based simulations and real-world use-case modelling, which includes COVID-19 testing applications. To extend operational lifespan, the suggested system also incorporates a battery sizing strategy and an energy consumption model. The findings show that UAV swarms can significantly improve SMI performance and resilience, which is a big step toward smarter and greener urban infrastructure.