Optimization · Reinforcement Learning · Communication Systems · Embedded
BE in Electronics, Communication & Information Engineering — Thapathali Campus, IOE TU (2022–2026)
Based in Kathmandu, Nepal
- 🔬 Published researcher — 3 papers (CNN-LSTM, 6G Cognitive Radio, Assistive Tech)
- 🧬 Building multi-objective optimization engines (NSGA-II, MOEA/D, RL hybrids)
- 📡 6G Cognitive Radio, Dynamic Spectrum Access, SDR signal processing
- 🤖 Reinforcement Learning — DQN, PPO for scheduling, trading, and spectrum allocation
- 📈 Quantitative finance — RL trading agents, time series analysis, 15+ NEPSE repos
- ⚡ Embedded systems — STM32, ESP32, custom PCB design
Languages
ML, RL & Optimization
Signal Processing & Comms
Embedded & Hardware
Simulation & Tools
| Project | Description |
|---|---|
| uctp-metaheuristic-framework | Hybrid metaheuristic–RL framework for multi-objective university course timetabling. NSGA-II + PPO/DQN + Multi-Armed Bandit operator selection + CP-SAT decomposition repair |
| nepse-rl-agent-rbs-experiment | Quantitative trading research platform for NEPSE — 7 rule-based strategies, LightGBM signal filtering, PPO RL agents, 15k+ LOC, 99 tests |
| vrp-solver | Multi-objective VRP solver using NSGA-II — 4-objective optimization (distance, lateness, idle time, fairness) with Kathmandu traffic modeling and demand forecasting |
| automatic-rf-identification-...-cnn-lstm | CNN-LSTM hybrid for over-the-air Automatic Modulation Classification using SDR. Published in JIEE 2025. 93.48% accuracy across 10 modulation schemes |
- PHY-Aware TACAN for Dynamic Spectrum Access in Next-Gen SD-IoT Networks — 2026, Under Publication
- CNN-LSTM Hybrid for Over-the-Air Automatic Modulation Classification using SDR — JIE, 2025 · DOI
- PoC for Low Cost Hall Effect Sensor Based Sign Language Translator — 2025 · DOI
