Machine Learning (ML)

ML Applications in Wireless Communication Networks

The project aims to detect user anomalies and inference patterns in wireless networks, targeting to improve the data rates of communication systems.

*The results of the tests were published at an international conference. The statistical method was adopted by a local startup company (GOHM) for vehicle localization and data.

All the slides:


ML Applications in Magnetic Domain Pattern Images

Benefit: An opportunity to create domains that have out-of-range parameters (you can’t execute in micromagnetic simulation). 

In order to extract parameters from and/or generate new images of magnetization patterns using micromagnetic simulation data, the images of simulated magnetization patterns will be input into Convolutional Neural Networks (CNNs) and Generative Adversarial Networks (GANs) for training.

*Worked on the latest technology - Heat Assisted Magnetic Recording (HAMR), the leading high-capacity drive technology. 


Decoding Motor imagery-based EEG Signals using Machine Learning

Brain-computer interfaces represent a life-changing possibility for disabled patients to regain control of their lives, for example through highly functional prosthetics or movement devices. However, everyday movements, like walking, and the increased brain activity it causes pose significant difficulty for BCI decoders. 

This paper proposes a method to clean EEG data and create a decoder that is resistant to walking-induced artifacts so left and right-hand motor imagery can be classified. We first perform Artifact Subspace Reconstruction to remove major artifacts, then bandpass in the alpha and mu bands to find physiologically relevant frequencies, Common Average Reference Filter to improve spatial resolution, extract trials and samples, find the mean percent difference in power spectrum density between resting and motor imagery to best identify event-related desynchronization, perform fisher score feature selection to reduce dimensionality, and finally train and cross-validate our model offline and test online with evidence accumulation.

The paper is attached under publications. 

Some of the code for this work is available at

EEG data before and after ASR processing. The upper subplot shows raw and the lower illustrates the filtered signal where the spike is not present.

The topological plot of the grand averaged mu power from the last 0.5s of the task trials, with and without spatial filtering.

Feature Extraction/Selection

Fischer scores measuring statistical significance for the first experimental run 1 to 4 in session one for subject 41. The y-axis shows Fischer score values ranging from 8 to 30 Hz with ∆2. The x-axis shows the number of channels from one to fifty-five. The color represents the discriminant power of the Fischer score with higher scores indicating features that better differentiate the conditions/classes:

Feature extraction for testing the ML model

Advanced Reinforcement Learning Agent for Pong Using TensorFlow and Keras

Keras implementation of a blog post (Deep Reinforcement Learning: Pong from Pixels) that originally used Python's numpy library for neural network operations.

Training process.

During testing, the trained model was executed using pure Python in Jupyter Notebook.

Representation Learning using Multi-Layer Perceptrons (MLPs)

Here's a summary of the MLP results as compared to other methods:

* Results obtained after randomly flipping sensitive attributes to augment the data.