Bin Yang

About

Bin Yang is a versatile researcher whose work spans two compelling and high-impact domains: intelligent fault diagnosis in industrial machinery and 3D computer vision for autonomous systems. In the realm of machine health monitoring, Yang has made significant strides in addressing real-world challenges such as data decentralization and contamination. His 2023 paper on targeted transfer learning through distribution barycenter medium — already amassing 111 citations — introduces an innovative approach to fault diagnosis when data is distributed across multiple sources, a critical problem in modern industrial settings. Complementing this, his graph neural network-based data cleaning method (35 citations) tackles the equally pressing issue of data contamination, strengthening the reliability of AI-driven diagnostics. On the computer vision front, Yang contributed to the development of PLUMENet, an efficient stereo-camera-based framework for 3D object detection that offers a cost-effective alternative to expensive LiDAR sensors, earning 38 citations and demonstrating relevance to self-driving vehicle technology. With a growing citation profile reflecting both breadth and depth, Yang stands out as a researcher bridging industrial intelligence and autonomous perception — two of the most transformative fields in modern engineering.

Research Focus

Key Achievements

Top Papers

1. 1
   Targeted transfer learning through distribution barycenter medium for intelligent fault diagnosis of machines with data decentralization

   111 citations · 2023
2. 2
   PLUMENet: Efficient 3D Object Detection from Stereo Images

   38 citations · 2021
3. 3
   A graph neural network-based data cleaning method to prevent intelligent fault diagnosis from data contamination

   35 citations · 2023
4. 4
   PLUME: Efficient 3D Object Detection from Stereo Images.

   11 citations · 2021

Key Collaborators

Contact & Links