A5035370466- Evolutionary Algorithms and Applications
- Advanced Multi-Objective Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Multimodal Machine Learning Applications
- Domain Adaptation and Few-Shot Learning
- Bioinformatics and Genomic Networks
- Computational Drug Discovery Methods
- Video Analysis and Summarization
- Genomics and Phylogenetic Studies
- Computational Fluid Dynamics and Aerodynamics
- Context-Aware Activity Recognition Systems
- Gene expression and cancer classification
- Protein Structure and Dynamics
- Neural Networks and Applications
- Time Series Analysis and Forecasting
- Advanced Text Analysis Techniques
- Human Pose and Action Recognition
- Machine Learning in Bioinformatics
- Anomaly Detection Techniques and Applications
- Data Mining Algorithms and Applications
- Machine Learning and Data Classification
- COVID-19 diagnosis using AI
- Manufacturing Process and Optimization
- Generative Adversarial Networks and Image Synthesis
- Data Management and Algorithms
University of Georgia
2016-2025
Franklin College
2016-2023
Rutgers, The State University of New Jersey
1996-2004
Glycosyltransferases (GTs) are prevalent across the tree of life and regulate nearly all aspects cellular functions. The evolutionary basis for their complex diverse modes catalytic functions remain enigmatic. Here, based on deep mining over half million GT-A fold sequences, we define a minimal core component shared among functionally enzymes. We find that variations in common emergence hypervariable loops extending from contributed to diversity. provide phylogenetic framework relating...
Predicting alfalfa biomass and crop yield for livestock feed is important to the daily lives of virtually everyone, many features data from this domain combined with corresponding weather can be used train machine learning models prediction. In work, we different varieties multiple years in Kentucky Georgia, compared impact feature selection methods on (ML) trained predict yield. Linear regression, regression trees, support vector machines, neural networks, Bayesian nearest neighbors were...
Computationally identifying transcription factor binding sites in the promoter regions of genes is an important problem computational biology and has been under intensive research for a decade. To predict site locations efficiently, many algorithms that incorporate either approximate or heuristic techniques have developed. However, prediction accuracy not satisfactory thus remains challenging problem. In this paper, we develop approach can be used to motifs using genetic algorithm. Based on...
Signaling proteins such as protein kinases adopt a diverse array of conformations to respond regulatory signals in signaling pathways. Perhaps the most fundamental conformational change kinase is transition between active and inactive states, defining features associated with activation critical for selectively targeting abnormally regulated diseases. While manual examination crystal structures have led identification key structural activation, large number (~3,500) extensive diversity...
Recent advances in artificial general intelligence (AGI), particularly large language models and creative image generation systems have demonstrated impressive capabilities on diverse tasks spanning the arts humanities. However, swift evolution of AGI has also raised critical questions about its responsible deployment these culturally significant domains traditionally seen as profoundly human. This paper provides a comprehensive analysis applications implications for text, graphics, audio,...
Human activity recognition (HAR) has many important applications in health care. While machine learning-based techniques have been applied for wearable sensor-based HAR, very few researchers comprehensively studied the effects of various factors on accuracy and robustness classification. This paper presents a detailed empirical study HAR schemes. The objective is to improve human based that do not increase computational overheads. We describe evaluate feature extraction, selection perform...
Mating behaviors are crucial for bird welfare, reproduction, and productivity in breeding flocks. During mating, a rooster mounts hen, which may result the hen overlapping or disappearing from top-view of vision system. The objective this research was to develop Deep learning models (DLM) identify mating behavior based on count changes bio-characteristics mating. Twenty broiler breeder hens 2-3 roosters (56 weeks) Ross 708 breed were monitored four experimental pens. DLM framework included...
Genetic algorithms (GAs) used in complex optimization domains usually need to perform a large number of fitness function evaluations order get near-optimal solutions. In real world application such as the engineering design problems, might be extremely expensive computationally. It is therefore common estimate or approximate using certain methods. A popular method construct so called surrogate meta-model original function, which can simulate behavior but evaluated much faster. difficult...
Cancer is a genetic disease that develops through series of somatic mutations, subset which drive cancer progression. Although genome sequencing studies are beginning to reveal the mutational patterns genes in various cancers, identifying small "causative" mutations from large "non-causative" accumulate as consequence disease, challenge. In this article, we present an effective machine learning approach for cancer-associated human protein kinases, class signaling proteins known be frequently...
The total boll count from a plant is one of the most important phenotypic traits for cotton breeding and also an factor growers to estimate final yield. With recent advances in deep learning, many supervised learning approaches have been implemented perform trait measurement images various crops, but few studies conducted bolls field images. Supervised models require vast number annotated training, which has become bottleneck machine model development. goal this study develop both fully...
A multilevel design strategy for supersonic missile inlet is developed. The combines an efe cient simple physical model analysis tool and a sophisticated computational e uid dynamics (CFD) Navier ‐ Stokes tool. incorporated into the optimization loop, CFD used to verify, select, lter nal design. genetic algorithms multistart gradient line search optimizers are nonsmooth space. geometry that starts at Mach 2.6 cruises 4 was designed. Signie cant improvement of total pressure recovery has been...