Papers
3
Total Citations
34
H-Index
3
About
Ahmad Patooghy’s research bridges the critical gap between robust hardware systems and intelligent tactile perception, with a focus on embedded systems, fault tolerance, and deep learning. His most impactful work, “An Embedded System for Collection and Real-Time Classification of a Tactile Dataset” (26 citations), tackles the formidable challenge of enabling tiny embedded devices to classify material properties in real time—a capability essential for advancing robotics, prosthetics, and augmented reality. By integrating machine learning directly into resource-constrained systems, Patooghy has pushed the boundaries of how machines can “feel” and interact with their environment. Earlier, he addressed a fundamental reliability issue in industrial control and robotics with “A Solution to Single Point of Failure Using Voter Replication and Disagreement Detection” (5 citations), introducing a distributed voting method that masks faults in Triple Modular Redundancy (TMR) systems without a single point of failure. More recently, his work “Tactile Sensing with Contextually Guided CNNs: A Semisupervised Approach for Texture Classification” (3 citations) advances semi-supervised deep learning, using accelerometer data to identify surface textures without precisely replicating human touch. Patooghy’s contributions are shaping more reliable, perceptive, and autonomous systems across robotics and industrial applications.
Research Focus
Key Achievements
Top Papers
- 1
- 2
- 3