I’m very interested in network models for neuroscience, brain imaging analysis, with applications concentrating on HIV and AIDS. My past research has involved: the inherent capacity of ensemblelearning and recurrent neural networks on epileptic seizure recognition data.

Representative Work

[1] Wu, Q., Fokoue, E., & Kudithipudi, D. (2018). An Ensemble Learning Approach to the Predictive Stability of Echo State Networks. Journal Of Informatics And Mathematical Sciences, 10(1 & 2), 181 - 199. doi: 10.26713/jims.v10i1-2.827 [link]

[2] Wu, Q. (2018). Statistical Aspects of Music Mining: Naive Dictionary Representation. Thesis. RIT Scholar Works. [link]

[3] Wu, Q., Fokoue, E., R. G. A. (2017). Epileptic seizure recognition data set. UC Irvine Machine Learning Repository [link] [code]

Echo State Networks

Echo state networks are powerful recurrent neural networks. However, they are often unstable and shaky, making the process of finding an good ESN for a specific dataset quite hard. Obtaining a superb accuracy by using the Echo State Network is a challenging task. We create, develop and implement a family of predictably optimal robust and stable ensemble of Echo State Networks via regularizing the training and perturbing the input. In this research work we demonstrate the inherent capacity of the ensemble learning approach to stabilize the notoriously difficult to tune echo state network (ESN) learning machines. We harness the high predictive variance by building ensembles made up of lightly tuned ESNs, and then combining those ESNs (base learners) rather than seeking the daunting task of selecting a single one. 

More details can be found here: [link]

Epileptic Seizure Recognition Data

The original dataset consists of 5 different folders, each with 100 files, with each file representing a single subject/person. Each file is a recording of brain activity for 23.6 seconds. The corresponding time-series is sampled into 4097 data points. Each data point is the value of the EEG recording at a different point in time. Our motivation for creating this version of the data was to simplify access to the data via the creation of a .csv version of it. Although there are 5 classes most authors have done binary classification, namely class 1 (Epileptic seizure) against the rest.

More details can be found here: [link] [code]


Other Research Work

Using Format