i-manager's Journal on Software Engineering (JSE)


Volume 19 Issue 4 April - June 2025

Research Paper

Developing a Personality Based Song Recommendation System

Vaibhav Baladhare* , Sujata Wankhede**, Vaibhav Baladhare***, Riya Walde****, Vedant Dhande*****, Isha Gothwad******, Rugved Deshmukh*******
*-****** Department of Computer Science and Engineering, S.B. Jain Institute of Technology, Management and Research, Nagpur Maharashtra, India.
Wankhede, S., Baladhare, V., Walde, R., Dhande, V., Gothwad, I., and Deshmukh, R. (2025). Developing a Personality Based Song Recommendation System. i-manager’s Journal on Software Engineering, 19(4), 1-12.

Abstract

This paper presents an Emotion-Based Music Recommendation System that utilizes facial expression analysis to provide personalized music suggestions based on a user's real-time emotional state. By integrating computer vision, deep learning, and the YouTube Data API, the system detects emotions such as happiness, sadness, anger, and neutrality, mapping them to appropriate music moods. It further refines recommendations based on user preferences like genre and language, ensuring a customized experience. The system also offers a mood adjustment feature, allowing users to either embrace or alter their emotional state through music. With a secure authentication system and an intuitive user interface, this approach enhances emotional well-being by combining artificial intelligence and music, making recommendations more dynamic, adaptive, and engaging.

Research Paper

Machine Learning for Habitable Exoplanet Exploration

Rohan Kumar*
Department of Computer Science and Engineering, Bhilai Institute of Technology, Durg, Chhattisgarh, India.
Kumar, R. (2025). Machine Learning for Habitable Exoplanet Exploration. i-manager’s Journal on Software Engineering, 19(4), 13-22.

Abstract

This research explores the discovery and habitability assessment of exoplanets using advanced computational techniques. A combination of machine learning algorithms, Generative Adversarial Networks (GANs), and MongoDB is employed to process and manage extensive datasets related to exoplanet characteristics. Detection methods such as direct imaging, transit photometry, and radial velocity are integrated, with a particular focus on radial velocity, which identifies exoplanets by measuring Doppler shifts in stellar light and analyzing flux luminosity from space-based signals. Through spectral analysis of these signals, the study forecasts biosignatures—chemical markers vital for evaluating the potential for life. The GAN model generates spectral images that enable predictions of current atmospheric compositions, supporting the estimation of environmental conditions conducive to habitability. A user-friendly web interface presents these findings in an accessible graphical format, making the system both intuitive and informative for researchers and general users. The trained classification model achieved an accuracy of 93.7% in distinguishing habitable from non-habitable exoplanets, while ExoGAN exhibited high fidelity in synthesizing biosignature images across diverse atmospheric profiles. This approach offers a scalable, instrument-agnostic framework suitable for application in upcoming space missions, aiding in the prioritization of potentially Earth-like worlds. The framework also supports real-time updates as new observational data becomes available. Moreover, its modular design allows integration with future astronomical databases and APIs. The methodology ensures adaptability across telescopic platforms and observational conditions. Ultimately, this study bridges the gap between AI-driven modeling and astrobiological discovery, pushing the frontier of life detection beyond the solar system.

Research Paper

Leveraging Deep Learning and Grad-Cam for AI-Based Detection and Mitigation of Botnet Attacks in Software-Defined Networks

Uppe Nanaji* , Srivalli Cherukupalli**, Ashok Kumar N. V.***, Uppe Nanaji****
*-*** Department of Computer Science and Engineering, Avanthi Institute of Engineering and Technology, Anakapalle, Andhra Pradesh, India.
Cherukupalli, S., Kumar, N. V. A., and Nanaji, U. (2025). Leveraging Deep Learning and Grad-Cam for AI-Based Detection and Mitigation of Botnet Attacks in Software-Defined Networks. i-manager’s Journal on Software Engineering, 19(4), 23-33.

Abstract

In recent years, Software-Defined Networks (SDNs) have emerged as a revolutionary approach to network management, offering centralized control and enhanced flexibility. However, this centralized architecture also introduces new security challenges, particularly in detecting and mitigating botnet attacks. Botnets, which consist of compromised devices controlled by malicious actors, can cause significant damage by launching Distributed Denial of Service (DDoS) attacks and other forms of network disruptions. Traditional detection methods frequently fall short in handling the evolving complexity of botnet tactics. This paper presents a novel AI-driven approach for the detection and mitigation of botnet attacks in SDNs using Deep Learning (DL) and Grad-CAM (Gradient-weighted Class Activation Mapping). The proposed method leverages deep learning algorithms to detect botnet traffic patterns, while Grad-CAM is employed to visualize and interpret the decision-making process of the model, improving transparency and enabling better insights into attack behaviors. The integration of these technologies enhances the accuracy and interpretability of botnet detection, allowing for more efficient attack mitigation strategies. Experimental results demonstrate that the AI- driven system significantly outperforms traditional detection methods, providing a scalable, real-time solution for securing SDNs against evolving botnet threats.

Research Paper

Access Control Mechanisms for Securing Data during Transmissions

Manoj*
Vasireddy Venkatadri Institute of Technology, Andhra Pradesh, India.
Manoj. (2025). Access Control Mechanisms for Securing Data during Transmissions. i-manager’s Journal on Software Engineering, 19(4), 34-48.

Abstract

Access control is a critical component of modern information security systems, ensuring the protection of sensitive resources in increasingly complex organizational environments. This study presents the design and implementation of a scalable, flexible, and security-centric access control system based on Role-Based Access Control (RBAC). The proposed system integrates essential features such as user registration, authentication, RBAC-driven authorization, and secure data handling. To enhance protection, the design employs multiple security layers, including Django's built-in safeguards against SQL injection, CSRF, and XSS, as well as Fernet encryption for sensitive data and OTP-based authentication for strengthened login security. The solution demonstrates strong compliance with web security best practices while maintaining usability and performance. Furthermore, it provides a foundation for future enhancements such as activity tracking, fine-grained authorization, and machine learning integration for access pattern analysis. The results highlight RBAC's effectiveness in managing user permissions, reducing insider threats, and supporting regulatory compliance, making the system suitable for diverse organizational contexts.

Review Paper

Advancements and Applications of Artificial Intelligence in Python Programming: Trends, Challenges, and Future Directions

Anu Thind*
Chandigarh Engineering College, CGC Landran, Mohali, Punjab, India.
Thind, A. (2025). Advancements and Applications of Artificial Intelligence in Python Programming: Trends, Challenges, and Future Directions. i-manager’s Journal on Software Engineering, 19(4), 49-54.

Abstract

Artificial Intelligence (AI) has rapidly evolved into a cornerstone of technological innovation in the 21st century, transforming sectors such as healthcare, education, finance, transportation, and manufacturing. Simultaneously, Python has emerged as the de facto programming language for AI development, owing to its ease of learning, syntax simplicity, extensive support libraries, and active global community. This paper explores the synergy between AI and Python programming by tracing historical developments, reviewing a variety of practical applications, and analyzing key challenges faced by developers and researchers. The discussion extends to state-of-the-art areas such as explainable AI (XAI), edge AI, federated learning, and the integration of AI with quantum computing. Ethical considerations, computational limitations, and the demand for model transparency are also examined. This comprehensive analysis aims to guide future research and application development in AI using Python, ensuring scalable, inclusive, and responsible innovation.