🔔 Announcements
Bi-Monthly Journal (2 monthly)
📊 ISSN NO: 3108-1312
Subject: Multidisciplinary
🗞 News & Updates
✍️ Editorial Message
Welcome to the International Journal of Convergent Technologies and Future Systems (IJCTFS). Our journal aims to provide a platform for innovative research in AI, Machine Learning, Cloud, Cybersecurity, IoT, and other emerging technologies. We encourage interdisciplinary collaboration and the sharing of ideas that can shape the future of technology. IJCTFS is committed to publishing high-quality research that bridges theory with practical impact. We thank our contributors, reviewers, and readers for supporting this journey of innovation and knowledge dissemination.
With best regards,
Dr. D. M. Marathe
Founder & Editor-in-Chief
International Journal of Convergent Technologies and Future Systems (IJCTFS)
MauliKavyanshu Foundation
International Journal of Convergent Technologies and Future Systems (IJCTFS)
Papers (July - August 2026)
📚 Submitted Research Papers
1. Wireless Power Transfer Efficacy: A Study on Efficiency, Applications, and Future Scope
Author: RISHIKESH VIRENDRA PATIL
Email: rishikeshpatil626@gmail.com
Abstract: Wireless Power Transfer (WPT) is a modern technology that transfers electrical energy from one device to another without using physical wires. This technology is becoming popular in mobile charging, electric vehicles, medical devices, and smart electronics. The main purpose of this research paper is to study the efficacy and efficiency of wireless power transfer systems. The paper explains the working principle, advantages, limitations, and real-life applications of WPT. It also discusses different methods such as inductive coupling and resonant coupling. The study concludes that wireless power transfer can improve convenience and reduce cable dependency, but efficiency and distance limitations still need improvement. Future developments may help WPT become more reliable and widely used in daily life.
🔗 Download Paper🎓 Download CertificateSubmitted on: 2026-08-24 14:23:01
2. Student Mental Wellness Prediction Using Machine Learning
Author: Tejas Jijabrao Patil
Email: tejasjijabraopatil@gmail.com
Abstract: Mental wellness is an essential factor influencing students' academic achievement,personal growth,and overall quality of life. Increasing academic demands, prolonged screen time,social expectations,financial concerns, and lifestyle changes have contributed to higher levels of stress,anxiety,and emotional fatigue among students. Early identification of these concerns allows educational institutions to provide timely guidance and support before problems become more severe. This study proposes a machine learning-based approach for predicting student mental wellness by analyzing academic,behavioral, and lifestyle characteristics. The proposed framework considers factors such as attendance,study duration,sleep patterns,physical activity,academic performance, social interaction,and self reported stress levels.
🔗 Download Paper🎓 Download CertificateSubmitted on: 2026-08-26 12:45:50
3. Neuro-Symbolic Deep Learning: Bridging Neural Networks with Symbolic Reasoning for Explainable AI
Author: Mr. Yashvant Vishwakarma , Dr. Manjusha Yuvraj Patil
Email: yv615952@gmail.com
Abstract: Neuro-emblematic deep literacy combines the perceptual strengths of neural networks with the structured, interpretable logic of emblematic systems to make AI that's both important and resolvable. This paper proposes a modular neuro-emblematic armature that integrates a deep literacy – grounded perception module with a emblematic logic machine via a differentiable interface. We estimate the frame on standard tasks that bear both perception and logic( CLEVR, bAbI, and a custom VQA knowledge- graph task). Results show the mongrel model improves delicacy( ≈ 88 vs. 78 for pure deep literacy) while delivering high explanation dedication and logic correctness. We bandy methodological choices, training strategies( class literacy, cold-blooded loss), and criteria for explainability, and figure avenues for unborn work including unified training, dynamic knowledge graphs, and standardised cross-domain marks. Keywords: Neuro-symbolic AI, explainable AI (XAI), differentiable reasoning, deep learning, knowledge graphs, visual question answering (VQA)
🔗 Download Paper🎓 Download CertificateSubmitted on: 2026-08-29 13:13:13
4. Impact of Generative AI on College Education: Opportunities and Ethical Challenges
Author: Ms. Madhura Talreja, Dr. Manjusha Yuvraj Patil
Email: talrejamadhura@gmail.com
Abstract: The study examines how generative artificial intelligence is reshaping advanced literacy surroundings in India, pressing both its implicit benefits and associated moral dilemmas. The term generative artificial intelligence encompasses tools similar as ChatGPT, Gemini, Copilot, and DALL · E able of generating textbooks, canons, or visual content using expansive data sets. Across India, as its public educational policy accelerates growth inpost-secondary literacy openings under NEP 2020, artificial intelligence finds adding operation within seminaries, tests, and executive processes. This document examines how generative artificial intelligence facilitates personalized education by minimizing regulatory tasks, boosting invention through its use, yet it raises issues concerning academic deceitfulness, demarcation in algorithms, and securing particular information. This disquisition employs an logical approach through examining scholarly workshop across colorful regions, encompassing both domestic and foreign coffers similar as UN documents and educational accoutrements published in academia. Studies indicate that although artificial intelligence holds great pledge for enhancing educational access encyclopedically, India requires robust nonsupervisory structures, instructional juggernauts, and moral to guarantee that AI augments rather of displaces mortal cognitive capacities.
🔗 Download Paper🎓 Download CertificateSubmitted on: 2026-08-30 15:15:58
5. Deepfake Detection using Multimodal Forensics: A Unified Vision-Audio Framework with Cross-Modal Attention
Author: Mr. Ketan Vilas Patil
Email: ket.patil77@gmail.com
Abstract: The rapid growth of generative adversarial networks, diffusion models, neural rendering systems and high-fidelity voice cloning has made synthetic video and audio increasingly difficult to distinguish from authentic media. Conventional deepfake detectors usually operate on a single modality: either they analyze facial artifacts in frames or they inspect acoustic traces in speech. Such unimodal approaches are fragile because modern forgeries can suppress artifacts in one channel while leaving inconsistencies in the other. This paper presents MultiForensic-Net, a unified multimodal forensics framework that jointly analyzes facial video and speech audio for robust deepfake detection. The framework uses a dual-stream encoder composed of a Vision Transformer branch for spatial-temporal facial representation and a Conformer branch for log-mel audio representation. A Cross-Modal Attention Fusion module aligns visual and audio token streams, while a Contrastive Multimodal Pair Loss encourages coherent genuine pairs to be close in embedding space and manipulated pairs to be separable. The system is evaluated on FaceForensics++, DFDC, KoDF and a controlled AVSpeech-DF stress-test subset. MultiForensic-Net achieves 97.84 percent accuracy on FaceForensics++, 96.21 percent on DFDC, 95.60 percent on KoDF and 93.47 percent on AVSpeech-DF, with strong ROC-AUC scores across datasets. Ablation analysis confirms that bidirectional cross-attention and contrastive pair training provide consistent gains over simple concatenation and unimodal baselines. The final system also includes an interpretable forensic pipeline with attention visualizations, confusion matrix analysis, training convergence plots and deployment considerations for practical media verification workflows.
🔗 Download Paper🎓 Download CertificateSubmitted on: 2026-09-01 06:45:50
🖼 Journal Logo
🔗 Author Links
🔗 Editorial / Reviewer Links
- Reviewer Guidelines
- Editorial Board Guidelines
- Join Editorial/Reviewer Panel
- Editorial/Reviewer Panel
