A5099380961- Plant Disease Resistance and Genetics
- Cutaneous Melanoma Detection and Management
- Epigenetics and DNA Methylation
- CCD and CMOS Imaging Sensors
- Biomedical Text Mining and Ontologies
- AI in Service Interactions
- Topic Modeling
- Metabolomics and Mass Spectrometry Studies
- Bioinformatics and Genomic Networks
- Artificial Intelligence in Healthcare and Education
- Microbial infections and disease research
- Brain Tumor Detection and Classification
- Functional Brain Connectivity Studies
Virginia Tech
2024
Large Vision Language Models (LVLMs) have demonstrated remarkable capabilities in understanding and describing visual content, achieving state-of-the-art performance across various vision-language tasks. However, these models frequently exhibit hallucination behavior, where they generate descriptions containing objects or details absent the input image. Our work investigates this phenomenon by analyzing attention patterns transformer layers heads, revealing that hallucinations often stem...
In the realm of dermatology, complexity diagnosing skin conditions manually necessitates expertise dermatologists. Accurate identification various ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly accurately diseases across diverse tones, with a notable performance gap darker skin. Additionally, scarcity publicly available, unbiased datasets hampers development inclusive AI...
Pathogen identification is pivotal in diagnosing, treating, and preventing diseases, crucial for controlling infections safeguarding public health. Traditional alignment-based methods, though widely used, are computationally intense reliant on extensive reference databases, often failing to detect novel pathogens due their low sensitivity specificity. Similarly, conventional machine learning techniques, while promising, require large annotated datasets feature engineering prone overfitting....
Abstract Pathogen identification is pivotal in diagnosing, treating, and preventing diseases, crucial for controlling infections safeguarding public health. Traditional alignment-based methods, though widely used, are computationally intense reliant on extensive reference databases, often failing to detect novel pathogens due their low sensitivity specificity. Similarly, conventional machine learning techniques, while promising, require large annotated datasets feature engineering prone...
Abstract Accurate prediction of biological age from DNA methylation data is a critical endeavor in understanding the molecular mechanisms aging and developing age-related disease interventions. Traditional epigenetic clocks rely on linear regression or basic machine learning models, which often fail to capture complex, non-linear interactions within data. This study introduces DeepAge, novel deep framework utilizing Temporal Convolutional Networks (TCNs) enhance profiles using selected CpGs...
In the realm of dermatology, complexity diagnosing skin conditions manually necessitates expertise dermatologists. Accurate identification various ailments, ranging from cancer to inflammatory diseases, is paramount. However, existing artificial intelligence (AI) models in dermatology face challenges, particularly accurately diseases across diverse tones, with a notable performance gap darker skin. Additionally, scarcity publicly available, unbiased datasets hampers development inclusive AI...
Abstract Alzheimer’s Disease (AD) is a progressive neurodegenerative disorder, posing growing public health challenge. Traditional machine learning models for AD prediction have relied on single omics data or phenotypic assessments, limiting their ability to capture the disease’s molecular complexity and resulting in poor performance. Recent advances high-throughput multi-omics provided deeper biological insights. However, due scarcity of paired datasets, existing rely unpaired data, where...
Accurate prediction of biological age from DNA methylation data is a critical endeavor in understanding the molecular mechanisms aging and developing age-related disease interventions. Traditional epigenetic clocks rely on linear regression or basic machine learning models, which often fail to capture complex, non-linear interactions within data. This study introduces DeepAge, novel deep framework utilizing Temporal Convolutional Networks (TCNs) enhance profiles using selected CpGs by...