Loading article...
Loading article...
Stream/Area:
-
Subject:
-
Paper ID:
IJSREM62732
Volume:
10 |
5 |
May 2026
Pages:
1-5
Publication Frequency:
Monthly (12 issues per year)
License:International Journal of Scientific Research in Engineering and Management follows the Creative Commons Attribution 4.0 (CC BY 4.0) License, allowing free use and distribution with proper attribution.
computer Engineering
Matoshri college of Engineering research center Nashik
computer Engineering
Matoshri college of Engineering research center Nashik
computer Engineering
Matoshri college of Engineering research center Nashik
computer Engineering
Matoshri college of Engineering research center Nashik
Computer Engineering
Matoshri college of Engineering research center Nashik
- In the modern digital era, mental health concerns such as stress, anxiety, and emotional exhaustion are rising rapidly, while timely access to professional support continues to be constrained by factors like affordability, social stigma, and limited availability. The proposed system, NeuroVibe Conversational AI System for Real-Time Mental Health Support, aims to address this gap by integrating artificial intelligence, emotion detection, and interactive assistance to provide accessible and continuous mental health support. The system utilizes real-time facial emotion recognition through deep learning architectures such as MobileNetV2 in combination with OpenCV, enabling accurate identification of users’ emotional states via webcam input. Based on the detected emotional cues, an intelligent conversational agent powered by Google Generative AI and LangChain delivers context-sensitive, empathetic responses that resemble supportive therapeutic interaction. In addition to conversational support, the platform incorporates two complementary modules to enhance user well-being: a Therapist Integration Module that facilitates connections with certified professionals for personalized guidance, and a Relaxation Recommendation Module that suggests engaging activities or games to alleviate stress during critical moments. The primary objective of the system is to establish a secure, adaptive, and user-centric environment that fosters emotional awareness, resilience, and early intervention through personalized engagement. By combining real-time emotion analysis with conversational intelligence and optional human support, the system contributes toward the development of scalable, inclusive, and intelligent mental health solutions. Furthermore, the platform is implemented as a web-based application, ensuring accessibility, data security, and scalability, with potential future enhancements including wearable device integration and multilingual capabilities.
KEYWORDS
NeuroVibe demonstrates the effective integration of Artificial Intelligence, Natural Language Processing, and real-time emotion recognition to develop an intelligent mental health support system. By combining AI-driven conversational assistance, therapist connectivity, and activity-based relaxation recommendations, the platform enhances accessibility and user engagement in mental health care. The system emphasizes personalization, data security, and adaptive interaction to provide a holistic digital solution for emotional well-being. Despite existing limitations related to dataset diversity and emotion recognition accuracy, NeuroVibe establishes a strong foundation for next-generation AI-assisted mental health technologies. The proposed framework encourages further research and innovation toward scalable, inclusive, and intelligent digital mental healthcare systems.
[1] P. Ekman, Emotions Revealed: Recognizing Faces and Feelings to Improve Communication and Emotional Life, 2nd ed., Times Books, 2007. [2] A. Howard et al., “MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications,” arXiv preprint arXiv:1704.04861, 2017. [3] M. Sandler et al., “MobileNetV2: Inverted Residuals and Linear Bottlenecks,” in Proc. IEEE CVPR, 2018. [4] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. [5] Z. Zhang et al., “Facial Expression Recognition Based on Deep Learning: A Survey,” IEEE Access, vol. 8, pp. 139–153, 2020. [6] K. Fitzpatrick, A. Darcy, and M. Vierhile, “Delivering Cognitive Behavior Therapy to Young Adults With Symptoms of Depression and Anxiety Using a Fully Automated Conversational Agent (Woebot),” JMIR Mental Health, vol. 4, no. 2, 2017. [7] T. Brown et al., “Language Models are Few-Shot Learners,” in Advances in Neural Information Processing Systems (NeurIPS), 2020. [8] H. Touvron et al., “LLaMA: Open and Efficient Foundation Language Models,” arXiv preprint arXiv:2302.13971, 2023. [9] LangChain Documentation, “LangChain: Building Applications with LLMs,” [Online]. Available: https://www.langchain.com
Publication Date
5/7/2026
Peer Review Type
Double-Blind Peer Review
Review Rounds: 2
Documents
Article Views
0
Total views since publication
PDF Downloads
5
Total downloads since publication
Geographic Reach
5
Digital Preservation: This article is permanently archived on Zenodo and complies with all data preservation standards across major indexing platforms.
Plagiarism Screening
This manuscript has been checked for plagiarism using TurnitinPlagiarismChecker software.
Conflict of Interest
The authors declare no conflict of interest related to this research work.
Funding Information
No funding information available for this research.
Related research in the same subject area
Loading similar articles...