High Tech, High Touch

Search
Close
Search
 

Research

  • home
  • Research
  • Labs

Research

Labs

Search article
All
  • Very Large Database Lab - Prof.SANG-WON LEE

    Major research interests

    Database, Data Science

    Cloud Computing

    Flash memory System Software

    Non-Volatile memory


    Major research achievements (2021~present)

    "LRU-C: Parallelizing Database I/Os for Flash Storage," (under revision)

    "NV-SQL: Boosting OLTP Performance with NVDIMM,” Proceedings of VLDB Endowment, August 2023 (to appear)

    " In-page shadowing and two-version timestamp ordering for mobile DBMSs," Proceedings of VLDB Endowment, August 2022

    "Avoiding Read Stalls on Flash Storage," ACM SIGMOD, June 2022

    "Your read is our priority in flash storage," Proceedings of VLDB Endowment, August 2022

    "When F2FS meets address remapping," ACM HOTSTORAGE Workshop, May 2022

    ES4D: Accelerating Exact Similarity Search for High-Dimensional Vectors via Vector Slicing and In-SSD Computation," IEEE International Conference on Computer Design (ICCD), May 2022

    "SaS: SSD as SQL database system," Proceedings of VLDB Endowment, August 2021


  • Digital Environment and Human Behavior Lab - Prof. DAEHO LEE

    Major research interests

    Human-computer interaction in Internet services

    Value estimation of user experience


    Major research achievements (2022~present)

    Changes in users experience and satisfaction as media technology evolves: The reciprocal between video games and video game-related media. Technological Forecasting and Social Change, 174, 121219, 2022.

    Should a small-sized store have both online and offline channels? An efficiency analysis of the O2O platform strategy. Journal of Retailing and Consumer Services, 64, 102823, 2022.

    To produce or resell? Which content strategy is more efficient for program providers?. Telematics and Informatics, 70, 101813, 2022.

    Customer Shopping Experience in a South Korea’s Government-Run Home Shopping Channel for Small and Medium Enterprises Based on Critical, Telematics and Informatics, 2022.

    When, How, and What Kind of Information Should Internet Service Providers Disclose? A Study on the Transparency that Users Want. Telematics and Informatics, 101799, 2022.

    Changes in consumption patterns during the COVID-19 pandemic: Analyzing the revenge spending motivations of different emotional groups. Journal of Retailing and Consumer Services, 65, 102874, 2022.

    Virtual Audience Providing AI-Generated Emotional Reactions to Enhance Self-Disclosure in Self-Introduction. Intertational Journal of Human-Computer Interaction, 1-12, 2022.

    Avatar-Mediated Communication in Video Conferencing: Effect of Self-Affirmation on Debating Participation Focusing on Moderation Effect of Avatar. International Journal of Human-Computer Interaction, 1-12, 2022.

    User acceptance on content optimization algorithms: predicting filter bubbles in conversational AI services. Universal Access in the Information Society, 1-14, 2022.

    Under watching eyes in news comment sections: effects of audience cue on self-awareness and commenting behaviour. Behaviour & Information Technology, 1-17, 2022.



  • Computer Systems & Intelligence (CSI) Lab - Prof. HONGUK WOO

    Research interests

    Intelligent Cyber-physical System (CPS)

    Offline Reinforcement Learning

    Embodied Agent, Multimodal Agent

    Multi-task and Meta Learning


    Recent research achievements

    Publication

    “Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning”, Advanced in Neural Information Processing Systems (NeurIPS), Nov.2022

    “An Efficient Combinatorial Optimization Model Using Learning-to-Rank Distillation”, AAAI Conference on Artificial intelligence (AAAI), Feb.2022

    “Structure Learning-Based Task Decomposition for Reinforcement Learning In Non-Stationary Environment”, AAAI Conference on Artificial intelligence (AAAI), Feb.2022

    Project

    Self-directive Multimodal Intelligence for Solving unknown Open Domain Problems (2022-2026, IITP)

    Adaptive Personality for Intelligent Agents (2022-2026, IITP)

    AI Software for Drones (2020-2024, ETRI)

    Policy Generalization via Multimodal Skill Transfer (2023-2025, NRF)


  • DASH Lab - Prof. SIMON S. WOO

    Main research interests

    Multimedia Forensics (Deepfake, AI-based Forgery Detection)

    Cyber Security, AI Security and Data Privacy

    Time-series Forecasting and Anomaly Detection

    Applied Data Science

    Object Detection


    Major research achievements (2021~present)

    "Samba: Identifying Inappropriate Videos for Young Children on YouTube", Simon S. Woo* et al, CIKM, 2022

    "Learning Sparse Latent Graph Representations for Anomaly Detection in Multivariate Time Series", Siho Han and Simon S. Woo*, ACM SIG KDD, Washington, DC, USA, 2022

    "Am I a Real or Fake Celebrity? Evaluating Face Recognition and Verification APIs under Deepfake Impersonation Attack", Shahroz Tariq, Sowon Jeon, and Simon S. Woo*, The 31st Web Conference (WWW), France, April 2022

    "BZNet: Unsupervised Multi-scale Branch Zooming Network for Detecting Low-quality Deepfake Videos", Sangyup Lee, Jaeju An, and Simon S. Woo*, The 31st Web Conference (WWW), France, April 2022

    "ADD: Frequency Attention and Multi-View based Knowledge Distillation to Detect Low-Quality Compressed Deepfake Images", Binh M. Le and Simon S. Woo*, AAAI, 2022  

    "FakeAVCeleb: A Novel Audio-Video Multimodal Deepfake Dataset" Simon S. Woo* et al, NeurIPS Datasets and Benchmarks Track, 2021

    "VFP290K: A Large-Scale Benchmark Dataset for Vision-based Fallen Person Detection", Simon S. Woo*, et al, NeurIPS Datasets and Benchmarks Track, 2021

    "CoReD: Generalizing Fake Media Detection with Continual Representation using Distillation", Minha Kim, Shahroz Tariq and Simon S. Woo*, ACMMM, 2021

    "One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework", Shahroz Tariq, Sangyup Lee, and Simon S. Woo, The 30th Web Conference (WWW), 2021


  • LamdaLab - Prof. HAYOUNG OH

    Major research interests

    Artificial Intelligence, Machine Learning and Deep Learning

    Multi-modal dataset(i.e., Natural Language Processing, Image, Time series dataset) analysis

    Chatbot implementation

    Digital Cure implementation


    Major research achievements


    International Journal (2020~present)

    Suhyun Cho and Hayoung Oh,"Generalized Image Captioning For Multilingual Support", Appl. Sci. (Applied Sciences), 13(4), 2446, Feb. 2023 (SCIE)

    Hayoung Oh,"A YouTube Spam Comments Detection Scheme Using Cascaded Ensemble Machine Learning Model", IEEE Access, v.9, pp.144121 – 144128, Oct. 2021 (SCIE)

    Rong Ran and Hayoung Oh,"Low‑complexity sparse‑aware multiuser detection for large‑scale MIMO systems", EURASIP Journal on Wireless Communications and Networking volume 2021 (SCIE)

    Hayoung Oh," Security-aware fair transmission scheme for 802.11 based cognitive IoT ", International Journal of Electrical and Computer Engineering (IJECE), Vol.10, No.3, June2020, pp. 2589~2599 (Scopous)

       Book (2019~present)

    Hayoung Oh, ‘Basics of data analysis using Jupyter notebook’ (Feb, 2020)

    Hayoung Oh, ‘Non-major class case-based data analysis’ (Feb, 2020)

    Shin Seung-hun, Lee Taek-gyun, Seo Ju-young, Hayoung Oh, Kang Kyung-ran, Koo Eun-hee, ‘Computational Thinking Workbook’ (Oct, 2019)

    Hayoung Oh, ‘Python application to improve computational thinking for non-major students’ (Feb, 2019)

    Hayoung Oh, ‘Application of R to Improve Discrete Computational Thinking Skills for Non-Majors’ (Feb, 2019)


    Patent and Technology Transfer (2018~present)

    [Patent application] Non-face-to-face medical chatbot app service method using artificial intelligence, April 05, 2022

    [Patent application] Modern people’s emotional analysis method through online medical consultation data analysis, April 05, 2022

    [Patent registration] Apparatus and method for detecting Sybil account, 2020.06.26

    [Patent registration] Method and device for providing recommended apps, 2020.04.21

    [Technology Transfer] Spam detection device and method, 2021.02.03

    [Technology Transfer] Spam character identification system and method, recording medium for this, 2018.10.31


  • Distributed Computing Lab - Prof. YOUNG IK EOM

    Major research interests

    Operating Systems

    Platform Virtualization and Operating System Virtualization Technologies

    File Systems and Storage Systems for Next Generation Storage Technologies

    Distributed Computing and Cloud Computing


    Major research achievements (2021~present)

    "SWAM: Revisiting Swap and OOMK for Improving Application Responsiveness on Mobile Devices", ACM International Conference On Mobile Computing And Networking (MobiCom), Oct. 2023.

    "PRISM: Optimizing Key-Value Store for Modern Heterogeneous Storage Devices", ACM International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS), pp. 588-602, Mar. 2023.

    "Weight-Aware Cache for Application-Level Proportional I/O Sharing", IEEE Transactions on Computers (TC), Vol. 71, No. 10, pp. 2395-2407, Oct. 2022.

    "File Fragmentation from the Perspective of I/O Control", ACM Workshop on Hot Topics in Storage and File Systems (HotStorage), pp. 126-132, June 2022.

    "When F2FS Meets Address Remapping", ACM Workshop on Hot Topics in Storage and File Systems (HotStorage), pp. 31-36, June 2022.

    "FragPicker: A New Defragmentation Tool for Modern Storage Devices", ACM Symposium on Operating Systems Principles (SOSP), pp. 280-294, Oct. 2021.

    "SFM: Mitigating Read/Write Amplification Problem of LSM-tree-based Key-value Stores", IEEE ACCESS, Vol. 9, pp. 103153-103166, July 2021.

    "Alleviating I/O Interference in Virtualized Systems with VM-aware Persistency Control", IEEE ACCESS, Vol. 9, pp. 89263-89275, June 2021.

    "Efficient Single-pair All-shortest-path Query Processing for Massive Dynamic Networks", Information Sciences, Vol. 546, pp. 1306-1327, Feb. 2021.


  • Intelligent Embedded Systems Lab - Prof. DONGKUN SHIN

    Major research interests

    Embedded Storage (Flash Memory Software, File Systems)

    Computer Architecture, Neural Processing Unit (NPU), Compiler

    On-device Machine Learning, Processing-In-Memory, Near-Data-Processing


    Major research achievements (2020~present)

    Stackable Transactional File System Using Kernel-Level WAL, IEEE Access, 2022  

    Remap-based Inter-Partition Copy for Arrayed Solid-State Drives, IEEE Transactions On Computers, 2022

    Lifetime-Leveling LSM-Tree Compaction for ZNS SSD, (HotStorage ’22)

    When F2FS Meets Address Remapping, (HotStorage ’22)

    Structural Pruning for Deep Convolutional Neural Networks via Adaptive Sparsity Regularization, IEEE COMPSAC, 2022

    SCJ: Segment Cleaning Journaling for Log-Structured File Systems, IEEE Access, 2021

    ZNS+: Advanced Zoned Namespace Interface for Supporting In-Storage Zone Compaction, USENIX Symp. on Operating Systems Design and Implementation (OSDI’21)

    mStream: Stream Management for Mobile File System Using Android File Contexts, The 36th ACM/SIGAPP Symposium on Applied Computing (SAC’21)

    Filter-Wise Quantization of Deep Neural Networks for IoT Devices, IEEE International Conference on Consumer Electronics (ICCE’21)

    Reinforcement Learning-Based SLC Cache Technique for Enhancing SSD Write Performance, (HotStorage ’20)

    Flexible Group-Level Pruning of Deep Neural Networks for On-Device Machine Learning, Design Automation and Test in Europe (DATE’20)

    Virtual Connection: Selective Connection System for Energy-Efficient Wearable Consumer Electronics, IEEE Transactions on Consumer Electronics, 2020

    Command Queue-Aware Host I/O Stack for Mobile Flash Storage, Journal of Systems Architecture, 2020

    WAL-SSD: Address Remapping-Based Write-Ahead-Logging Solid-State Disks, IEEE Transactions on Computers, 2020


  • Human-AI Interaction Lab - Prof. HAYEON SONG

    Major research interests

    Human-AI Interaction and Human-computer interaction

    Media psychology

    Using technology for health promotion


    Major research achievements (2022~present)

    Kim, T., Song, H. (2023). “I believe AI can learn from the error. Or can it not?”: The effects of implicit theories on trust repair of the intelligent agent. International Journal of Social Robotics,15(1), 115-128. https://doi.org/10.1007/s12369-022-00951-5

    Song, H., So, J., Shim, M., Kim, J., Kim, E., & Lee, K. (2023). What message features influence the intention to share misinformation about COVID-19 on social media? The role of efficacy and novelty. Computers in Human Behavior, 138, 107439.

    Kim, T. & Song, H. (2023). Communicating the limitations of AI: The effect of message framing and ownership on trust in artificial intelligence, International Journal of Human-Computer Interaction, 39(4), 790-800. https://doi.org/10.1080/10447318.2022.2049134

    Yang, M., Lee, K., Kim, E., Song, Y., Lee, S., Kang, J., Han, J., Song, H., & Taeeun Kim (2022) Magic Brush: An AI-based Service for Dementia Prevention focused on Intrinsic Motivation, Proceedings of the ACM on Human-Computer Interaction, Computer-Supported Cooperative Work and Social Computing (CSCW), Volume 6, Issue CSCW2, Article No.: 448pp 1–21, https://doi.org/10.1145/3555549

    Kang, J., Kim, J., Kim, T., Song, H, & Han, J. (2022). Experiencing stress during COVID-19: A computational analysis of stressors and emotional responses to stress, Cyberpsychology, Behavior, and Social Networking, 25(9), 561-570. (SSCI, JCR 2021 IF = 6.135)

    Adachi, R., Cramer, E, & Song, H. (2022). Using virtual reality for tourism marketing: A mediating role of self-presence. The Social Science Journal, 59(4), 657-670. https://doi.org/10.1080/03623319.2020.1727245

    Kim, D., Park, C., Kim, E., Han, J. & Song, H. (2022). Social sharing of emotion during the COVID-19 pandemic. Cyberpsychology, Behavior, and Social Networking, 25(6), 369-376. https://doi.org/10.1089/cyber.2021.0270


  • Computer Systems Lab - Prof. EUISEONG SEO

    Major research interests

    System Software

    Operating Systems

    Cloud Platform

    System Support for Machine Learning


    Major research achievements (2021~present)

     A Close Look At Shared Resource Consumption in NoSQL Databases for Accurate Accounting, IEEE/IFIP Network Operations and Management Symposium (NOMS), 2023

     Know Your Enemy To Save Cloud Energy: Energy-Performance Characterization of Machine Learning Serving, The 29th IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2023

     Analysis and Mitigation of Data Sanitization Overhead in DAX File Systems, The 40th IEEE International Conference on Computer Design (ICCD), 2022

     Dedup-for-Speed: Storing Duplications in Fast Flash Mode for Enhanced Read Performance, The 15th ACM International Systems and Storage Conference (SYSTOR), 2022

     NoSQL Database Performance Diagnosis through System Call-level Introspection, IEEE/IFIP Network Operations and Management Symposium (NOMS), 2022

     Z-Journal: Scalable Per-Core Journaling, USENIX Annual Technical Conference (ATC), 2021

     Analysis and Mitigation of Patterned Read Collisions in Flash SSDs, IEEE Access, 2022

     Scale-Train: A Scalable DNN Training Framework for a Heterogeneous GPU Cloud, IEEE Access, 2022

     Analysis and Optimization of Persistent Memory Index Structures’ Write Amplification, IEEE Access, 2022

     Block-Level Storage Caching for Hypervisor-Based Cloud Nodes, IEEE Access, 2021

     A Performance-Stable NUMA Management Scheme for Linux-based HPC Systems, IEEE Access, 2021

     Idempotence-Based Preemptive GPU Kernel Scheduling for Embedded Systems, IEEE Transactions on Computers, Vol. 70, No. 3, pp. 332-346, 2021


  • Data Mining Lab - Prof. HOGUN PARK

    Major research interests

    Graph Neural Networks

    Explainable AI

    Knowledge Graph Embedding and its Applications

    Commonsense Reasoning

    Computational Social Science

    ML Models for Multi-channel Sensor


    Major research achievements (2020~present)

    “Dual Policy Learning for Aggregation Optimization in Graph Neural Network-based Recommender Systems”, The Web Conference (WWW), 2023.

    “Laser-induced Carbonization for Anticounterfeiting Tags”, Advanced Functional Materials, 2023.

    “Providing Post-hoc Explanation for Node Representation Learning Models Through Inductive Conformal Predictions”, IEEE Access, 2023.

    “Stretchable Array sEMG Sensor with Graph Neural Network for Static and Dynamic Gestures Recognition System”, npj Flexible Electronics, 2023.

    Providing Node-level Local Explanation for node2vec through Reinforcement Learning, Proc. of the Machine Learning on Graphs (MLoG) Workshop at the 15th ACM Conference on Web Search and Data Mining (WSDM 2022), 2022.

    “Finding Client-side Business Flow Tampering Vulnerabilities”, the International Conference on Software Engineering (ICSE), 2020.

    “A framework for understanding online group behaviors during a catastrophic event“, International Journal of Information Management, Elsevier, 2020.

    “Exploiting Interaction Links for Node Classification with Deep Graph Neural Networks“, The International Joint Conference on Artificial Intelligence (IJCAI), 2020.