P
Patrick Goh
Researcher at Universiti Sains Malaysia
Publications - 44
Citations - 244
Patrick Goh is an academic researcher from Universiti Sains Malaysia. The author has contributed to research in topics: Computer science & Artificial neural network. The author has an hindex of 6, co-authored 36 publications receiving 143 citations. Previous affiliations of Patrick Goh include University of Illinois at Urbana–Champaign.
Papers
More filters
Journal ArticleDOI
Multi-Sensor Obstacle Detection System Via Model-Based State-Feedback Control in Smart Cane Design for the Visually Challenged
TL;DR: A multi-sensor obstacle detection system for a smart cane is proposed via a model-based state-feedback control strategy to regulate the detection angle of the sensors and minimize the false alerts to the user.
Journal ArticleDOI
Partitioned Latency Insertion Method With a Generalized Stability Criteria
Patrick Goh,Jose E. Schutt-Aine,D.V. Klokotov,Jilin Tan,Ping Liu,Wenliang Dai,Feras Al-Hawari +6 more
TL;DR: A robust method is formulated that is able to perform transient simulations significantly faster than the conventional LIM method and is verified with existing commercial tools for circuit simulations.
Journal ArticleDOI
Jitter Decomposition of High-Speed Data Signals From Jitter Histograms With a Pole–Residue Representation Using Multilayer Perceptron Neural Networks
TL;DR: A machine learning approach is presented to extract the random and deterministic jitter components from the timing histograms of the eye diagram using the dual-Dirac model and results show that the preprocessing step is able to accelerate the training process and improve the overall performance of the neural networks significantly.
Journal ArticleDOI
Comparative Study of Convolution and Order Reduction Techniques for Blackbox Macromodeling Using Scattering Parameters
Jose E. Schutt-Aine,Patrick Goh,Yidnekachew S. Mekonnen,Jilin Tan,Feras Al-Hawari,Ping Liu,Wenliang Dai +6 more
TL;DR: In this paper, a fast convolution method using scattering parameters is presented for the macromodeling of blackbox multiport networks, which is compared to model-order reduction passive macrommodeling techniques in terms of robustness and computational efficiency.
Journal ArticleDOI
Self-Adaptive Filtering Approach for Improved Indoor Localization of a Mobile Node with Zigbee-Based RSSI and Odometry.
TL;DR: This study presents a new technique to improve the indoor localization of a mobile node by utilizing a Zigbee-based received-signal-strength indicator (RSSI) and odometry, and contributes to a novel methodological framework in which coordinates of the mobile node can more accurately be predicted by improving the path-loss propagation model.