Mr. Xincheng Guo | Time Series Awards | Best Machine Learning for Sensing Award

Mr. Xincheng Guo, Shanghai University of Engineering Science, China

Xincheng Guo is a graduate student pursuing a Master’s degree in Electronic Information at Shanghai University of Engineering Science, with research focused on intelligent signal processing, deep learning, and IoT systems. His notable contributions include the development of an innovative CEEMDAN-WT-VMD framework for multi-source noise suppression in power load data and the design of advanced neural network models such as Bidirectional Temporal Convolutional Networks and Attention-based BiGRU for spatiotemporal modeling and signal denoising. He has published first-authored research on short-term power load forecasting in the journal Electronics (2025, Q1). Xincheng has also engineered a multi-sensor fire detection and patrol system integrating improved YOLOv5s vision algorithms with sensor fusion and high-precision positioning technologies. His technical expertise spans sensing algorithms, embedded systems, and AI frameworks like PyTorch and TensorFlow. He has received multiple honors, including the 2nd Prize in the 19th China Graduate Electronics Design Competition (Shanghai Division) and the National Graduate Scholarship.

Professional Profile:

ORCID

Summary of Suitability for Best Machine Learning for Sensing Award conclusion

Xincheng Guo is a highly promising candidate for the Research for Best Machine Learning for Sensing Award, demonstrating strong expertise in intelligent signal processing and deep learning applied to multi-modal sensing systems. Currently pursuing a Master’s degree in Electronic Information at Shanghai University of Engineering Science, Guo has developed innovative methods for sensing signal denoising and prediction, including a novel CEEMDAN-WT-VMD framework that achieves significant noise reduction and a Bidirectional Temporal Convolutional Network that outperforms state-of-the-art models in power load forecasting. His research is supported by the National Natural Science Foundation of China, reflecting its scientific merit and relevance. Beyond theoretical contributions, Guo has designed practical embedded sensing systems integrating advanced vision algorithms and multi-sensor fusion for real-time fire detection, showcasing his ability to translate machine learning innovations into impactful applications. With published Q1 journal papers, recognized technical skills in AI frameworks, and awards in national electronics competitions, Xincheng Guo embodies the excellence and innovation that the Best Machine Learning for Sensing Award seeks to honor.

🎓 Education

• Master of Electronic Information (2023.09 – 2026.09)
  Shanghai University of Engineering Science
  Focus: Intelligent Signal Processing, Deep Learning, IoT Systems

💼 Work Experience

• Graduate Student
  China Education and Research Network (CERNET), Beijing (Since 2023.09)

🏆 Achievements & Key Contributions

• Developed CEEMDAN-WT-VMD framework for multi-source noise suppression, achieving a 46.3% noise reduction (SNR 227.1 dB)

• Created Bidirectional Temporal Convolutional Network (BiTCN) with 0.65% MAPE on power load forecasting, outperforming top models

• Designed an Attention-based BiGRU model for dynamic temporal feature weighting in noisy data

• Published first-author paper:
  “Short-Term Power Load Forecasting Based on CEEMDAN-WT-VMD Joint Denoising” in Electronics (2025, Q1, IF=3.0)

• Built a Multi-Sensor Fire Detection and Patrol System using Raspberry Pi and MM32 with improved YOLOv5s vision algorithm (+8.2% mAP), flame/smoke sensor fusion, and GPS positioning

🎖️ Awards & Honors

• 🥈 2nd Prize, 19th China Graduate Electronics Design Competition (Shanghai Division), 2024

• 🥉 3rd Prize, 6th Yangtze River Delta Smart City Competition, 2024

• 🎓 National Graduate Scholarship, 2023-2024

• 🛫 Aerospace Inspirational Scholarship, 2022-2023

• 🏅 CET-4 Certificate (English Proficiency)

• 💻 National Computer Technology and Software Professional Qualification (Primary Level)

Publication Top Notes: