A5047842287- Advanced Multi-Objective Optimization Algorithms
- Scheduling and Optimization Algorithms
- Metaheuristic Optimization Algorithms Research
- Statistical Methods and Inference
- Evolutionary Algorithms and Applications
- Gene expression and cancer classification
- Complex Network Analysis Techniques
- Molecular Biology Techniques and Applications
- Fault Detection and Control Systems
- Privacy-Preserving Technologies in Data
- Advanced Causal Inference Techniques
- Erosion and Abrasive Machining
- Advanced Manufacturing and Logistics Optimization
- Particle Dynamics in Fluid Flows
- interferon and immune responses
- Spectroscopy and Chemometric Analyses
- Advanced Graph Neural Networks
- Influenza Virus Research Studies
- Genomics and Rare Diseases
- Natural Language Processing Techniques
- Advanced Text Analysis Techniques
- Data Quality and Management
- Cancer Genomics and Diagnostics
- Coal Combustion and Slurry Processing
- Topic Modeling
Baylor College of Medicine
2020-2022
University of Tulsa
2018-2021
Abstract Summary Feature selection can improve the accuracy of machine-learning models, but appropriate steps must be taken to avoid overfitting. Nested cross-validation (nCV) is a common approach that chooses classification model and features represent given outer fold based on give maximum inner-fold accuracy. Differential privacy related technique overfitting uses privacy-preserving noise mechanism identify are stable between training holdout sets. We develop consensus nested (cnCV)...
Vaccination is an effective prevention of influenza infection. However, certain individuals develop a lower antibody response after vaccination, which may lead to susceptibility subsequent An important challenge in human health find baseline gene signatures help identify who are at higher risk for infection despite vaccination. We developed multi-level machine learning strategy build predictive model vaccine using pre−vaccination titers and network interactions between expression levels. The...
Abstract Discovering rare cancer driver genes is difficult because their mutational frequency too low for statistical detection by computational methods. EPIMUTESTR an integrative nearest-neighbor machine learning algorithm that identifies such marginal modeling the fitness of mutations with phylogenetic Evolutionary Action (EA) score. Over cohorts sequenced patients from The Cancer Genome Atlas representing 33 tumor types, detected 214 previously inferred and 137 new candidates never...
Abstract Motivation Feature selection can improve the accuracy of machine learning models, but appropriate steps must be taken to avoid overfitting. Nested cross-validation (nCV) is a common approach that chooses classification model and features represent given outer fold based on give maximum inner-fold accuracy. Differential privacy related technique overfitting uses preserving noise mechanism identify are stable between training holdout sets. Methods We develop consensus nested CV (cnCV)...
An important challenge in gene expression analysis is to improve hub selection enrich for biological relevance or classification accuracy a given phenotype. In order incorporate phenotypic context into co-expression, we recently developed an epistasis-expression network centrality method that blends the importance of gene-gene interactions (epistasis) and main effects genes. Further blending prior knowledge from functional has potential relevant genes stabilize classification.We develop two...
Non-polynomial hard (NP-hard) problems are challenging due to time-constraint. The bacteria foraging optimisation (BFO) algorithm is a metaheuristics that used for NP-hard problems. BF...
In this paper we explore the problem of document summarization in Persian language from two distinct angles. our first approach, modify a popular and widely cited framework to see how it works on realistic corpus news articles. Human evaluation generated summaries shows that graph-based methods perform better than modified systems. We carry intuition forward second probe deeper into nature systems by designing several summarizers based centrality measures. Ad hoc using ROUGE score these...
Non-polynomial hard (NP-hard) problems are challenging because no polynomial-time algorithm has yet been discovered to solve them in polynomial time. The Bacteria Foraging Optimization (BFO) is one of the metaheuristics algorithms that mostly used for NP-hard problems. BFO inspired by behavior bacteria foraging such as Escherichia coli (E-coli). aim eliminate those have weak properties and maintain breakthrough toward optimum. Despite strength this algorithm, most reaching optimal solutions...
Non-polynomial hard (NP-hard) problems are challenging due to time-constraint. The bacteria foraging optimisation (BFO) algorithm is a metaheuristics that used for NP-hard problems. BFO inspired by the behaviour of such as E. coli. aim eliminate weak properties and maintain breakthrough toward optimum. However, reaching optimal solutions time-demanding. In this paper, we modified single objective multi-objective (MOBFO) adding mutation crossover from genetic operators update in each...