Appling Deep learning with Human activity recognition on pseudo-free-living dataset and public data (WISDOM)
Appling Transfer learning to improve the prediction of Human activity recognition
Apply time-series based forecasting techniques to our alfalfa and weather data with the goal of discovering or developing such a technique that helps with our prediciton problem
Contribute to sustainability research by using weather data patterns from previous years to predict crop yields in subsequent years
Propose a system where farmers can plan crops under "what if" scenarios, making predictions based on variables adjusted by users
Appling Genetic Algorithms for congressional redistricting in Georgia
Previous Projects
Identification of Cancer-Causing Mutations in the Human Genome
Machine Learning Methods for Alzheimer Disease Detection and Prediction
Sensitivity Analysis and Linkage Detection in Genetic Algorithms with Continuous Genes
Knowledge Modelling and Classification of Quran and Hadith Corpus
GWAS (Genome-Wide Association Studies)
Detection of long non-coding RNAs
Accelerating Machine Learning and Evolutionary Computing with GPU
Short Text Classification of Clinical Questions
Analysis of Clustering Algorithms
Development of an automated scorer for measuring Conceptual /Integrative complexity in English Text using Machine Learning techniques
Machine Learning Methods for Biomaterial Modeling
Genetic Algorithms for Standard VLSI Cell Design
Machine Learning Methods for Financial Market Prediction
Real Time System Scheduler Optimization with Evolutionary Computation Tehniques
Adaptive Surrogate Assisted Evolution
Genetic Algorithms for Engineering Design Optimization (GADO)
Scalability and Performance Analysis of Machine Learning Approaches for Gene Classification and Metagenomics
Artificial Intelligence in Clothing Fashion
Welcome
Research in the Evolutionary Computation & Machine Learning (ECML) Lab is centered around Genetic and Evolutionary Algorithms, Machine Learning and the intersection/ cross-fertilization of the two fields. We conduct research in genetic algorithm methodologies and applications in science and engineering with emphasis on using machine learning approaches to enhance evolutionary optimization. We also develop, apply and analyze machine learning approaches for numerous Bioinformatics and computational biology domains. The following are some of the ongoing and recently published projects.