A5059294404- Recommender Systems and Techniques
- Video Analysis and Summarization
- Topic Modeling
- Nutritional Studies and Diet
- Multimodal Machine Learning Applications
- Big Data and Business Intelligence
- Diet and metabolism studies
- Human Mobility and Location-Based Analysis
- Obesity, Physical Activity, Diet
- Semantic Web and Ontologies
- Dietetics, Nutrition, and Education
- Digital Transformation in Industry
- Image Retrieval and Classification Techniques
- Child Nutrition and Feeding Issues
- Nutrition, Genetics, and Disease
- Blockchain Technology Applications and Security
Ulsan National Institute of Science and Technology
2018-2022
In this work, we introduce a novel approach called Scaling to Emphasize Attention for Long-context retrieval (SEAL), which enhances the performance of large language models (LLMs) over extended contexts. Previous studies have shown that each attention head in LLMs has unique functionality and collectively contributes overall behavior model. Similarly, observe specific heads are closely tied long-context retrieval, showing positive or negative correlation with scores. Built on insight,...
Diet planning in childcare centers is difficult because of the required knowledge nutrition and development as well high design complexity associated with large numbers food items. Artificial intelligence (AI) expected to provide diet-planning solutions via automatic effective application professional knowledge, addressing optimal diet design. This study presents results evaluation utility AI-generated diets for children provides related implications.We developed 2 AI aged 3-5 yrs using a...
Diet planning is a basic and regular human activity. Previous studies have considered diet combinatorial optimization problem to generate solutions that satisfy diet's nutritional requirements. However, this approach does not consider the composition of diets, which critical for recipients' accept enjoy menus with high quality. Without consideration, feasible could be provided in practice. This suggests necessity machine learning, extracts implicit patterns from real data applies these when...
With the current advancements in mobile and sensing technologies used to collect real-time data offline stores, retailers wholesalers have attempted develop recommender systems enhance sales customer experience. However, existing studies on primarily focused e-commerce platforms other online services. They did not consider unique features of indoor shopping real stores such as physical environments objects, which significantly affect movement purchase behaviors customers, thereby...