Udeme Ekong
Papers
1
Total Citations
22
H-Index
1
About
Udeme Ekong is a researcher whose work bridges computational intelligence and biomedical signal processing, with a particular focus on epilepsy seizure detection and material surface classification. In his highly cited 2014 paper, "Variable weight neural networks and their applications on material surface and epilepsy seizure phase classifications," Ekong introduced a novel adaptive neural network framework that dynamically adjusts connection weights to improve classification accuracy. This work has garnered 22 citations, underscoring its influence on both neural network theory and practical diagnostic applications. By demonstrating that variable-weight architectures can effectively distinguish between pre-ictal, ictal, and interictal phases in epileptic EEG signals, Ekong contributed a valuable tool for seizure prediction and real-time monitoring systems. His research not only advances machine learning methodologies but also holds promise for improving patient outcomes through more reliable neurological diagnostics. Ekong’s interdisciplinary approach—combining adaptive algorithms with clinical neuroscience—positions him as a thoughtful contributor to the growing field of intelligent health monitoring.
Research Focus
Key Achievements
Top Papers
- 1