Dr Pavan Kumar M P
Assistant Professor – 沙巴体育
沙巴体育 School of Information Sciences
CURRENT ACADEMIC ROLE & RESPONSIBILITIES
Pavan Kumar M P is?Assistant Professor – 沙巴体育 at the 沙巴体育 School of Information Sciences, 沙巴体育 Academy of Higher Education.
ACADEMIC QUALIFICATIONS
| Degree | Specialisation | Institute | Year of passing |
|---|---|---|---|
| Ph.D. | Computer Science Engineering | National Sun Yat-Sen University, Kaohsiung, Taiwan | 2024 |
| M.Tech | VLSI Design and Embedded Systems | BNM Institute of Technology, Bangalore, India | 2019 |
| B.E. | Electronics and Communication | Visvesvaraya Technological University, India | 2016 |
Experience
| Institution / Organisation | Designation | Role | Tenure |
|---|---|---|---|
| Infinite Uptime, Pune, India (Remote) | Data Scientist | Trend analysis, predictive modeling, stakeholder communication | Jan 2025 – March 2025 |
| National Center for High Performance Computing, Taiwan | ML 沙巴体育 Intern | Developed AI models integrating PDEs and ML using NVIDIA Modulus Sym | Jan 2024 – May 2024 |
| CERES Lab, NSYSU, Taiwan | 沙巴体育 Assistant | ML frameworks for machinery health monitoring, signal processing, fault diagnosis | Aug 2020 – Oct 2024 |
| Sion Semiconductors Pvt Ltd, Bangalore, India | SoC Design Verification Intern | Verification of protocols and memory controllers using Verilog/SystemVerilog | Aug 2018 – Nov 2018 |
| Sierra Circuits India Pvt Ltd, Bangalore, India | PCB Check-in Engineer | Review fabrication details, suggest optimal alternatives | Oct 2016 – Oct 2020 |
AREAS OF INTEREST, EXPERTISE AND RESEARCH
Area of Interest
Machine Learning, Deep Learning, Transfer Learning, Computer Vision, Predictive Maintenance, Time Series Analysis
Area of Expertise
Feature Extraction, Unsupervised Domain Adaptation, Signal Processing, Computer Vision
Area of 沙巴体育
Transfer Learning in Time Series, Source-Free Unsupervised Domain Adaptation, Negative Transfer Mitigation, Industry 4.0
Journal/Transactions Articles
1. Mitigating negative transfer learning in source-free unsupervised domain adaptation for rotating machinery fault diagnosis
IEEE Transactions on Instrumentation and Measurement, 2024. DOI: https://doi.org/10.1109/TIM.2024.3476610
2. Enhancing learning in fine-tuned transfer learning for rotating machinery via negative transfer mitigation
IEEE Transactions on Instrumentation and Measurement, 2024. DOI: https://doi.org/10.1109/TIM.2024.3480201
3. Time series-based sensor selection and lightweight neural architecture search for RUL estimation in future industry 4.0
IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2023. DOI: https://doi.org/10.1109/JETCAS.2023.3248642
Conference Proceedings
1. Fine-tuned based transfer learning with temporal attention and physics-informed loss
IEEE AICAS’24, Apr. 2024.
2. Mitigate the negative TL using adaptive thresholding for fault diagnosis
IEEE COINS 2023, Berlin, Germany. DOI: https://doi.org/10.1109/COINS57856.2023.10189313
3. NN-based bearing fault diagnosis using exponential power entropy and a decision threshold
IEEE COINS 2023, Berlin, Germany. DOI: https://doi.org/10.1109/COINS57856.2023.10189273
4. Composite fault diagnosis of rotating machinery with collaborative learning
VLSI-DAT 2022, Hsinchu, Taiwan. DOI: https://doi.org/10.1109/VLSI-DAT54769.2022.9768050
5. Bearing fault diagnosis using exponential power entropy and decision threshold
2022 VLSI Design/CAD Symposium, Aug. 2022.
6. Design and verification of DDR SDRAM memory controller using SystemVerilog for higher coverage
ICCS 2019, Madurai, India. DOI: https://doi.org/10.1109/ICCS45141.2019.9065407