Wireless Communications and Networks Lab (WHYNET)
Research Topics
- Semantic Communication
The basic idea of semantic communications is to extract the “meanings” or “features” of sent information from a source, and “interpret” the semantic information at a destination. Conversly, traditional communication systems aim to offer a high data transmission rate and a low symbol (bit) error rate.
Machine Learning (ML) to design end-to-end semantic communication systems for:
Source reconstruction
Specific tasks execution
Multi-modal Semantic Communication Systems with various data types
Leveraging transfer learning and incremental learning for Knowledge Base design in semantic communication system
2. Privacy-preserving Machine Learning (PPML)
PPML is designed to protect and preserve the privacy of data while training and deploying machine learning models. These methods allow the extraction of insights and patterns from data without exposing sensitive information, using perceptual encryption. PPML is particularly valuable in scenarios where data privacy is crucial, such as in healthcare, finance, and personal data analysis.
Cryptographic approach towards PPML
Centralized scenario and decentralized (such as federated learning) scenario
End-to-end communication system design for PPML schemes
3. Deep learning-based communication system design
DL-based End-to-End learning is a promising technology for future wireless communication systems. Its key idea is to implement the transmitter, channel, and receiver as a single neural network (NN). Various DL algrotihms can be leveraged to achieve end-to-end optimization over practical wireless systems such as OFDM, MIMO-OFDM, NOMA, etc.
Data-driven End-to-End Communication System
ML-based Physical layer architecture
ML algorithms for End-to-End optimization
Channel modeling for DL-based end-to-end communication system
High data-rate image communication system
Analysis of transmission distortions impact on an AI algorithm implemented for a downstream task
4. Wireless Communication Systems in IoT environment
AI is revolutionizing the Internet of Things (IoT) ecosystem, particularly in the realm of wireless communication systems. By integrating ML algorithms, these advanced systems can autonomously analyze and optimize data transmission, enhancing efficiency and reliability. This enables smarter, more responsive IoT networks, where devices seamlessly adapt to changing environments and user demands.
ML-based IoT Connectivity Controls
ML-based resource allocation in wireless communication systems
Low power communication protocols in IoT ecosystem
Feasibility of DL computations in resource constrained IoT ecosystem
Edge-cloud Collaboration
Transfer Learning
5. Network Security and Privacy Techniques
Source Location Privacy (SLP) is a security measure in wireless sensor networks that aims to protect the location of a source node from being disclosed to unauthorized entities. It is crucial in scenarios where the source's location is sensitive or confidential, such as in military or surveillance applications, preventing adversaries from tracking or targeting the source based on its transmitted signals.
Design of routing protocols (preferably, the design should be based on AI) to achieve a better tradeoff between source location privacy and energy efficiency in wireless sensor networks
Projects
이미지 통신 시스템에서 네트워킹 환경을 고려한 Perceptual Encryption 기반 Privacy Preserving Deep Learning 응용서비스 기술 연구 (중견연구 2023.09.01~2027.02.28)
Research Team for IT Convergence in Hyper-Connected Society Based on AI, BK21 Phase 4, 2020.09.01~2027.08.31, NRF
대규모 IoT 환경에서의 초저지연 매체 접속 제어 알고리즘 및 응용 기술 연구, 이공학개인기초연구 (기본연구 2018.06.01~2023.05.31
해양 IoT용 MAC(위탁과제), 수산실용화 기술개발사업 어구 자동식별 모니터링 시스템 개발, 해양수산부, 2018.01.01~2019.12.31
스마트인터넷기반 융합콘텐츠기술 인력양성사업팀, BK21 플러스, 2013.9.1 ~ 2020.2.29
eHealth WBAN을 위한 이종망 연동 최적화 기술 연구, 이공학개인기초연구(기본연구), 2015.11.01~2018.10.30
보안관제 신기술 연구 (익명통신 기술 연구), 2015.04.15~2015.11.14, ETRI
미래 이동통신 기술에 대한 타당성 검증 연구, 2014. 08.01 ~ 2015. 01. 31, ETRI
보안관제 신기술 연구 (관제용 Tor 노드 확보 방안 연구), 2014.03.17~2014.10.31, ETRI
가상머신 기반 병렬화 에뮬레이션 환경 구축 및 성능 분석, 2013.11.06~2014.05.06, ETRI
고속 인체통신 및 인체매질 전력전송 기술 개발, 2012.07.01 ~ 2014. 06. 30, 지경부
Study on packet-based Femtocell synchronization techniques for 1 microsecond accuracy in wireless communications, 2012.5.1 ~2015.4.30, NRF
차세대 국가통합무선망을 위한 멀티모드 스테이션 운용 기술 연구, 2012.5.1~2013.1.31, ETRI
차세대 국가통합무선망을 위한 다중기능 기지국 및 단말의 동적 자기구성 기술 연구, 2011.9.1~2012.1.31, ETRI
LTE/LTE-Advanced 펨토 기지국을 위한 동기화 기술, 2011.5.1~2011.12.31, ETRI
차세대 이동통신을 위한 저전력/고효율 MIMO-aware MAC control 기법(일반기본연구), 2009.5.1~2012.4.30
자동차 연쇄사고 예방을 위한 Ad-hoc 통신기술 분석 및 시뮬레이터 개발, 2008.10.17~ 2008.11.27, KT
2008가을학기 외국인유학생유치사업(푸다사이니수보드), 2008.9.1~2012.8.30, 정보통신연구진흥원
3GE 시스템에서 Synch. RA 기반의 상향링크 패킷 전송에 관한 연구, 2007.4.1 ~2007.12.15, ETRI
모바일 네트워크기반 문화콘텐츠 연구인력양성 사업 (BK21), 2006.3.1~2013.2.28
3GE 시스템에서 상향링크 임의접근 방식 및 스케줄링 기법에 관한 연구, 2006.4.1 ~2006.11.30, ETRI
광주지역 전자회로모듈 시제품생산 역량강화 지원사업, 2005.7.1~2007.6.30, RIS
OFDMA/FDD 시스템에서의 Random Access 특성을 고려한 상향링크 패킷 스케쥴링 방식 성능 연구, 2005.5.1 ~2005.11.30, ETRI
OFDMA/FDD 시스템에서의 Random Access, 2004.6.1 ~2004.12.15, ETRI
차세대 광 무선 가입자망연구센: MMoF 기반 다중 셀 광-무선 LAN 기술 연구, ITRC, 2003-08-01 ~ 2007-08-31, 정보통신부