로봇 AI foundation (VLA) 모델 개발 (삼성미래육성재단), 감성 챗봇시스템 "이루다" 생성 언어 모델 (LLM), NL2SQL 질의응답 시스템, 기업형 신뢰할수 있는 생성AI (RAG, LLM with No Hallucination), 신기술&전문가 탐색/발견 시스템, 온라인 커뮤니티 댓글 감성 분석

네비게이션을 위한 POI 추천시스템, 온라인 판매자를 위한 추천시스템, on-demand / TV프로그램 실시간 추천시스템, 멀티모달 학습을 통한 온라인 쇼핑 검색 & 추천시스템, 온라인 호텔 관광 추천시스템

에너지 시계열 분석 시스템 (예측, 최적화, 비정상탐지), 제조 공정에서의 비정상 탐지 및 제어 최적화, 딥러닝을 이용한 네트워크 장애 탐지 및 예측, 심전도 시계열 데이터 원인 인자 추출/분석, 스마트 빌딩을 위한 제어 최적화

In this project, we aim to develop a novel multi-lingual artificial intelligence news agent, Milaina, which provides reliable news with various perspectives on a single issue to suit the needs of each individual. Compared to existing news platforms, Milaina has the following strengths.

In this project, we aim to develop a novel decision support system, METIS, which is short for ML-based Decision Support Information System.

Data on the web are not only large-scale, but also extremely high-dimensional, highly multi-class, and heterogeneous types. In addition, most web data is dynamically changing over time and is not structured. We define data with such characteristics as “Big Complex Type Data.” Since Big Complex Type Data on the web consists of various types of information, it is challenging to analyze it. Thanks to the recent technology improvements, the methods to analyze Big Complex Type Data are now available. Our goal is to invent strong methods for mining Big Complex Type Data in order to help develop the technologies to extract information from Big Complex Type Data, to integrate the extracted information, and to generate knowledge based on inference on the integrated data.

This project aims for the development of machine learning technology optimized for low-power embedded systems. Currently, researchers tend to use complex models to obtain highly accurate models via machine learning from big data. However, the training process consumes more power as the size of the model increases, which becomes the main obstacle for utilizing machine learning in embedded systems with limited power. Therefore, this project suggests developing machine learning technology minimizing power consumption during training while keeping the accuracy of the model by exploiting various techniques such as model compression, utilizing various computing resources（flash memory, GPU, and ultimately the framework （MELOW: Machine learning for Embedded LOW-power system, combining those methodologies. Furthermore, this project will show the practicability of MELOW by developing machine learning applications running on the MELOW framework.

The goal of this project is the development of enabling software technologies for big data mining. Through this project, we will research data mining techniques for big data in natural sciences and social networks. We will also develop personalized service technologies based on unstructured big data analysis and customer behavior models. Furthermore, we will produce well-trained software engineers who are experts in big data mining.

Combining the highly profitable information search industry and the mobile computing paradigm, the mobile information search industry has been growing rapidly despite the global economic recession. Thus, the development of mobile search technology will have a positive impact on the economy. This project aims to advance the technologies in the areas of mobile search and mining, low-power consumption utility mining, and mining for mobile online advertising.

PubMed MEDLINE, a database of biomedical and life science journal articles, is one of the most important information sources for medical doctors and bioresearchers. Finding the right information from MEDLINE is nontrivial because it is not easy to express the intended relevance using the current PubMed query interface, and its query processor focuses on fast matching rather than accurate relevance ranking. This project develops techniques for building a user-friendly MEDLINE search engine.