SynapSense is a real-time behavioral monitoring system that bridges raw device activity data with inferred emotional responses. By combining network traffic analysis, storage activity tracking, and neurotechnology-driven modeling, SynapSense opens new pathways for cognitive research, mental health applications, and human-computer interaction studies.
- Real-Time Behavioral Inference: Analyzes device activity patterns to infer emotional and cognitive states.
- Neurotechnology Integration: Leverages NLP (BERT) models to correlate digital behavior with human responses.
- Scalable System Architecture: C++ backend processing, React/Next.js frontend visualization, secure networking.
- Research-Driven Applications: Supports studies in mental health detection (e.g., depression signs, spatial neglect).
- Backend: C++, Python, Linux networking tools.
- Machine Learning: BERT-based inference models for behavioral correlation.
- Frontend: React.js, Next.js, Node.js, TypeScript, Tailwind CSS.
- Infrastructure: Modular system designed for real-time data streaming and analysis.
- Behavioral Inference Complexity: Tuned data pipelines to extract meaningful insights from noisy network and storage data.
- Data Privacy and Security: Designed architecture to ensure that user device signals remained private while being analyzed.
- Real-Time Processing Efficiency: Built lightweight C++ modules and asynchronous pipelines to handle fast, continuous monitoring.
- Working Prototype Delivered: Functional demo system mapping device behavior to cognitive states.
- Cross-Disciplinary Integration: Successfully combined neurotech, machine learning, and backend engineering.
- Research Potential: Demonstrated early promise for cognitive health monitoring in non-invasive ways.
Due to the nature of the project (local VM setup, hardware-specific networking tools), this repository does not contain a runnable public demo.
Important Note:
Development was performed primarily on a local Virtual Machine environment for secure testing purposes.
As a result, commits may not fully reflect contributions made during the build process.