William Streilein

Papers

Total Citations

H-Index

About

William Streilein is a researcher whose work lies at the intersection of neural networks, sensor fusion, and autonomous robotics. His primary research areas include adaptive resonance theory (ART) neural networks, sonar-based object recognition, and machine learning for sensor data classification. Streilein’s major contributions center on developing neural network architectures for real-time, stable learning in dynamic environments. His most cited work, "ARTMAP-FTR: a neural network for fusion target recognition with application to sonar classification" (1998, 13 citations), introduced a fusion target recognition system that integrates multiple sensor inputs for robust classification, demonstrating applications in sonar, satellite mapping, and medical prediction. In "A neural network for object recognition through sonar on a mobile robot" (2002, 11 citations), he pioneered a method using inexpensive Polaroid sonar sensors coupled with fuzzy ARTMAP neural networks to enable autonomous robots to recognize objects in real time. This work is notable for its practical, low-cost approach to robotic perception, bridging theoretical neural network research with tangible robotic applications. Streilein’s research has influenced fields ranging from autonomous navigation to industrial monitoring, showcasing the versatility of ART-based systems. His achievements highlight a commitment to advancing machine learning for real-world sensor fusion challenges, making his work a valuable reference for students and researchers in robotics and neural computation.