Papers
2
Total Citations
53
H-Index
2
About
Akash Saha’s research bridges the gap between human–machine interaction and intelligent fault diagnostics, with a focus on low-cost, real-world applications. In his early work, Saha pioneered the use of the Myo armband for gesture recognition, developing a system that translates human arm and finger movements into game commands for the popular South Asian game of hand cricket. This 2017 study, which has garnered 33 citations, demonstrated that affordable, wearable sensors could replace expensive motion-capture systems, opening doors for accessible bio-robotic interfaces. More recently, Saha has turned his attention to industrial reliability, comparing machine learning methods—Random Forest, Artificial Neural Networks, and Autoencoders—for bearing fault detection. His 2021 paper, with 20 citations, provides a clear benchmark for selecting robust, data-driven models in predictive maintenance. By combining gesture-based control with advanced fault diagnosis, Saha’s work exemplifies how sensor technology and AI can be adapted for both entertainment and critical infrastructure, making him a versatile contributor to applied robotics and condition monitoring.
Research Focus
Key Achievements
Top Papers
- 1
- 2