A5018693051- Bioinformatics and Genomic Networks
- Technology Adoption and User Behaviour
- Machine Learning in Bioinformatics
- Gene expression and cancer classification
- Neurobiology and Insect Physiology Research
- Handwritten Text Recognition Techniques
- Face recognition and analysis
- Innovation and Knowledge Management
- Rheumatoid Arthritis Research and Therapies
- Imbalanced Data Classification Techniques
- Olfactory and Sensory Function Studies
- Insect Resistance and Genetics
- Invertebrate Immune Response Mechanisms
- Knowledge Management and Sharing
- Smart Agriculture and AI
- Insect symbiosis and bacterial influences
- Water Quality Monitoring and Analysis
- Spectroscopy and Chemometric Analyses
- Biometric Identification and Security
- Water Quality Monitoring Technologies
University of Embu
2021-2023
Jomo Kenyatta University of Agriculture and Technology
2021-2022
High throughput sequencing generates large volumes of high dimensional data. Identifying informative features from the generated big data is always a challenge. Feature selection reduces complex into smaller number variables while preserving information as much possible. In this study, we used DaMiRseq, DESeq2, edgeR and Limma + voom to identify differentially expressed genes in 79 small cell lung cancer (sclc) 7 normal controls. A gene network was any coexpressed genes. Association rule...
Analysis of high-dimensional data, with more features (p) than observations (N) (p>N), places significant demand in cost and memory computational usage attributes. Feature selection can be used to reduce the dimensionality data. We a graph-based approach, principal component analysis (PCA) recursive feature elimination select for classification from RNAseq datasets two lung cancer datasets. The selected were discretized association rule mining where support lift generate informative...
Abstract Biometric systems have been used extensively in the identification and verification of persons. Fingerprint biometrics stands out as most effective due to their characteristics Permanence, uniqueness, ergonomics, throughput, low cost, lifelong usability. By reducing number comparisons, biometric recognition can effectively deal with large‐scale databases. classification is an important task reduce comparisons by dividing fingerprints into classes. Deep learning models demonstrated...
High-throughput sequencing generates large volumes of biological data that must be interpreted to make meaningful inference on the function. Problems arise due number characteristics p (dimensions) describe each record [n] in database. Feature selection using a subset variables extracted from datasets is one approaches towards solving this problem.In study we analyzed transcriptome Glossina morsitans (Tsetsefly) antennae after exposure either repellant (δ-nonalactone) or an attractant...
Tsetse flies use antennal expressed genes to navigate their environment. While most canonical associated with chemoreception are annotated, potential gaps important uncharacterized in Glossina morsitans . We generated antennae-specific transcriptomes from adult male G m fed/unfed on bloodmeal and/or exposed an attractant (ε-nonalactone), a repellant (δ-nonalactone) or paraffin diluent. Using bioinformatics approach, we mapped raw reads onto gene-set VectorBase and collected un-mapped...
An imbalanced classification problem occurs when the distribution of samples among different classes is uneven or biased. Handling small and training datasets poses a notable challenge in machine learning, especially domains such as bioinformatics medical research. These challenges can result biased models, leading to poor performance on under-represented an overemphasis specific features, failing capture genuine patterns present data. The study proposes feature selection approach-based...