Abstract:
The integration of artificial intelligence (AI) into adaptive virtual reality (VR) training systems represents a transformative advancement in educational methodologies across various sectors, including healthcare, military, corporate training, and education. This paper examines how AI enhances the adaptability and effectiveness of VR training environments, allowing for personalized learning experiences that cater to individual user needs. By leveraging AI-driven algorithms, these systems can assess user performance in real time, analyzing factors such as response times, accuracy, and decision-making patterns, and adjust training scenarios accordingly. This capability fosters improved engagement, skill retention, and learner autonomy, ultimately enhancing the overall effectiveness of training programs. For instance, in healthcare, AI-enhanced VR can simulate complex surgical procedures, providing medical professionals with tailored feedback to refine their skills. In military training, adaptive VR scenarios can replicate dynamic combat environments, ensuring that soldiers are prepared for various situations. Corporate training programs benefit from AI’s ability to create customized onboarding experiences, adapting content to suit different learning styles and paces. However, challenges such as technical limitations, user acceptance, and data privacy concerns must be addressed to fully realize the potential of AI-enhanced VR training. The reliance on accurate data collection raises ethical considerations regarding user privacy and data security, necessitating stringent protocols and regulations.
Cite this Article
Amit K.. The Role of Artificial Intelligence in Adaptive Virtual Reality Training Systems. International Research Journal of Engineering & Applied Sciences (IRJEAS). 13(1), pp. 01-09, 2025. 10.55083/irjeas.2025.v13i01001
Abstract:
The digital transformation of supply chains has introduced significant improvements in operational efficiency, transparency, and responsiveness. However, this evolution has also brought about new cybersecurity risks, with increased interconnectedness creating numerous vulnerabilities across global supply networks. Cyber threats, including data breaches, ransomware attacks, and vulnerabilities in Internet of Things (IoT) devices, pose substantial risks to the integrity and functionality of digital supply chains. This review explores the intersection of digital supply chains and cybersecurity, examining the key challenges and risks, and providing an in-depth analysis of effective strategies for risk mitigation and protection. The paper highlights essential practices such as risk assessment, encryption, third-party risk management, and the use of emerging technologies like AI and blockchain for enhancing security. By offering comprehensive strategies and technological solutions, this paper aims to assist organizations in securing their digital supply chains and ensuring business continuity in the face of evolving cyber threats.
Cite this Article
Anurag D., Digital Supply Chains and Cybersecurity- Strategies for Protection and Risk Mitigation. International Research Journal of Engineering & Applied Sciences (IRJEAS). 13(1), pp. 10-18, 2025. 10.55083/irjeas.2025.v13i01002.
Abstract:
The integration of artificial intelligence (AI) with autonomous drone technology has emerged as a transformative solution for precision pest control in agriculture. This review explores the role of AI-powered drones in enhancing pest management practices by enabling real-time pest detection, targeted interventions, and data-driven decision-making. Through advancements in machine learning, computer vision, and autonomous navigation, drones can efficiently identify pest infestations, monitor crop health, and apply pest control measures with high precision, thereby reducing the environmental impact of traditional methods. While challenges such as data accuracy, regulatory concerns, and cost remain, the future of AI-driven drones in pest control holds significant promise for sustainable agricultural practices. This paper provides a comprehensive analysis of current applications, technological developments, and the potential for AI-powered drones to revolutionize pest management in agriculture.
Cite this Article
S. K. Verma. Exploring the Role of AI in Autonomous Drone Technology for Precision Pest Control in Agriculture. International Research Journal of Engineering & Applied Sciences (IRJEAS). 13(1), pp. 19-28, 2025. 10.55083/irjeas.2025.v13i01003
Abstract:
The rapid growth of big data in various domains has led to an increasing need for real-time anomaly detection systems capable of identifying unusual patterns or behaviors as they occur. Traditional methods for anomaly detection often struggle to scale effectively in big data environments due to the high volume, velocity, and variety of data. Machine learning (ML) techniques have emerged as powerful tools for developing real-time anomaly detection frameworks, leveraging their ability to learn from data and detect complex patterns. This paper explores machine learning-based frameworks for real-time anomaly detection, focusing on key approaches such as supervised, unsupervised, and semi-supervised learning. It also highlights their applications in sectors such as cybersecurity, finance, healthcare, and IoT. Furthermore, the paper discusses the challenges faced in real-time anomaly detection, including scalability, latency, and model adaptation. Finally, it examines future research directions, such as explainability, federated learning, and hybrid approaches, aimed at enhancing the effectiveness and reliability of these frameworks in dynamic, real-world environments.
Cite this Article
Anurag Shrivashtav, Amit Kushwaha. Machine Learning-Based Frameworks for Real-Time Anomaly Detection in Big Data Environments. International Research Journal of Engineering & Applied Sciences (IRJEAS). 13(1), pp. 29-38, 2025. 10.55083/irjeas.2025.v13i01004
Abstract:
Water is essential for life and its continued existence on Earth. It also plays a critical role in maintaining the Earth’s climate, providing the foundation for agriculture, human development, and ecosystems. In this research paper, we explore the rainfall patterns across India, with a primary focus on Bihar’s rainfall pattern. We have used a dataset containing rainfall patterns from all over India from 1901 to 2015, which is a very comprehensive dataset given its century-long span. We have applied several machine learning models including LSTM, XGBoost, Random Forest Regression, Gradient Boosting, and CatBoost, and compared their performances. The analysis of the research reveals that Bihar experiences lower levels of rainfall compared to the national average. The LSTM model proved to be more accurate for short-term pattern predictions of rainfall in Bihar and outperformed other models in terms of mean absolute error, mean squared error, and root mean squared error. The XGBoost model also provided accurate predictions and showed comparable performance to the LSTM model. Random Forest Regression, Gradient Boosting, and CatBoost models also demonstrated strong predictive capabilities. Overall, this study highlights the value of machine learning models in predicting rainfall patterns and their potential to assist in decision-making related to agriculture, water management, and disaster-related alertness.
Cite this Article
Ayushman Pranav, Ankit Dubey, Umesh, Rajesh Kumar Modi. Towards Better Water Management- Predictive Models for Bihar’s Rainfall. International Research Journal of Engineering & Applied Sciences (IRJEAS). 13(1), pp. 39-55, 2025. 10.55083/irjeas.2025.v13i01005.
Abstract:
This paper presents a comprehensive energy management approach for a hybrid DC microgrid integrating solar, wind, and battery storage systems. The primary objective is to develop an advanced control strategy for electric vehicle (EV) charging stations, ensuring robust and resilient grid-connected operation. The proposed methodology addresses key aspects such as power balancing, DC bus voltage regulation, and battery state-of-charge (SoC) optimization. To meet these objectives, a hierarchical control architecture is implemented, structured into primary, secondary, and tertiary levels. The primary control ensures real-time power matching between renewable sources and load demand, while the secondary control manages battery operations to smooth fluctuations and improve system stability. A bi-directional DC-DC converter with a dual-switch topology is designed specifically for efficient battery charging and discharging control.
Cite this Article
Dileep Sahu, Manish Sawale, Nivedita Singh. Grid Integrated Renewable Energy Based EV-Charging Station. International Research Journal of Engineering & Applied Sciences (IRJEAS). 13(1), pp. 56-62, 2025. 10.55083/irjeas.2025.v13i01006.