About me

I am currently working as a research scientist at Nokia Bell Labs in Cambridge, United Kingdom. My research interests encompass a broad spectrum of research areas, including edge AI, on-device AI, tinyML, mobile systems, and networking technologies. I am enthusiastic about engaging in interdisciplinary research that bridges the gap between various domains, aiming to design and develop comprehensive, real-world systems and applications.

News

  • [May 1] Paper accepted at ACM BodySys 2024

    Our paper about thermal characteristics of AI accelerator-equipped microcontrollers was accepted to ACM BodySys 2024.

  • [Feb 24] Co-chairing NetAISys workshop at MobiSys 2024

    I am co-chairing Network AI system (NetAISys) workshop at Mobisys 2024, Tokyo. Please consider submitting your work!

  • [Dec 23] (Closed) Hiring interns for 2024 summer! 📣

    Come work with us in our Cambridge office! We have multiple internship positions available for 2024 summer! Check our leaflet for more infromation! [PDF] [LinkedIn]

Research Projects

AI/ML on distributed ultra low-power (ULP) AI acclerators

AI accelerators on ultra-low-power (ULP) devices serve as specialized hardware optimized to execute AI/ML algorithms faster and energy-efficiently, outperforming general-purpose MCUs and meeting the demands of wearables, IoT devices, and embedded systems. In our pursuit of facilitating real-time intelligence directly on the device, we aim to address challenges posed by the highly constrained environment and devising effective solutions within and across ULP devices.

Camera as a service (CaaS)

Intelligent cameras have become a common presence in our modern society, but they often come with drawbacks like restricted functionality, potential breaches of privacy, and the need for high-bandwidth video streaming. To address these issues, our team has built a software-defined camera system that revolutionizes the use of smart cameras by serving different vision-based models optimally and providing AI services such as real time face recognition, asset tracking, safety monitoring on-device. Our research has been showcased in U23 athletic championship in Espoo, Finland.

Application aware edge IoT virtualization for video analytics

Edge computing environments consist of various devices, compute resources, and networks, which come together to form a constantly changing environment. To maintain quality of service (QoS) amidst these changes, it is important to understand the needs of user applications requirements and adjust the user’s service components responsively. This research introduces a systematic approach for interpreting user’s service requirements, evaluating impact of context changes on the performance, and reconfiguring containerized service pipelines on the edge.

Publication

  • SiYoung Jang, Fahim, Kawsar, Chulhong Min, "Thermal Characterization of AI Applications on AI Accelerators-equipped Microcontrollers", In Proc. International Workshop on Body-Centric Computing Systems (BodySys 2024) in conjuction with ACM MobiSys 2024, Tokyo, Japan, June 2024.
  • Chulhong Min, Utku Günay Acer, SiYoung Jang, Sangwon Choi, Diana A. Vasile, Taesik Gong, Juheon Yi, Fahim Kawsar, "An AI-Native Runtime for Multi-Wearable Environments", arXiv preprint arXiv:2403.17863 (2024)
  • Taesik Gong, SiYoung Jang, Utku Gunay Acer, Fahim Kawsar, Chulhong Min, "Collaborative Inference via Dynamic Composition of Tiny AI Accelerators on MCUs", arXiv preprint arXiv:2401.08637 (2024)
  • Nguyen Thanh-Tung, SiYoung Jang, Boyan Kostadinov and Dongman Lee. "PreActo: Efficient Cross-Camera Object Tracking System in Video Analytics Edge Computing." 2023 IEEE International Conference on Pervasive Computing and Communications (PerCom). IEEE. 2023.
  • Bhawana Chhaglani, Utku Acer, SiYoung Jang, Fahim Kawsar and Chulhong Min. "Cocoon: On-body microphone collaboration for spatial awareness." Proceedings of the 24th International Workshop on Mobile Computing Systems and Applications (HotMobile). 2023.
  • SiYoung Jang, SungKyu Park, Jin Hee Cho, and Dongman Lee. "CARES: Context-aware trust estimation for realtime crowdsensing services in vehicular edge networks." ACM Transactions on Internet Technology 22.4 (2022): 1-24.
  • Seungho Lee, SiYoung Jang, Soon J. Hyun, Dongman Lee. "DQN-based Coverage Maximization for Mobile Video Camera Networks." 2021 IEEE 18th Annual Consumer Communications & Networking Conference (CCNC). IEEE, 2021.
  • SiYoung Jang, Boyan Kostadinov, and Dongman Lee. "Microservice-based edge device architecture for video analytics." 2021 IEEE/ACM Symposium on Edge Computing (SEC). IEEE Computer Society, 2021.
  • SiYoung Jang, Utku Acer, Chulhong Min, and Fahim Kawsar. "Deploying Collaborative Machine Learning Systems in Edge with Multiple Cameras." 2021 Thirteenth International Conference on Mobile Computing and Ubiquitous Network (ICMU). IEEE, 2021. 🏆
  • Dongman Lee, SiYoung Jang, Byoungheon Shin and Yoonhyung Lee. "Towards dynamically reconfigurable IoT camera virtualization for video analytics edge cloud services." IEEE Internet Computing 23.4 (2019): 10-17.
  • SiYoung Jang, Byoungheon Shin, Yoonhyung Lee and Dongman Lee. "Towards application-aware virtualization for edge iot clouds." Proceedings of the 13th International Conference on Future Internet Technologies. 2018.
  • SiYoung Jang, Yoonhyung Lee, Byoungheon Shin and Dongman Lee. "Application-aware IoT camera virtualization for video analytics edge computing." 2018 IEEE/ACM Symposium on Edge Computing (SEC). IEEE, 2018.
  • SiYoung Jang, Hayoung Choi, Yoonhyung Lee, Byoungheon Shin and Dongman Lee. "Semantic virtualization for edge-IoT cloud: Issues and challenges." Proceedings of the 2nd Workshop on Cloud-Assisted Networking. 2017.
  • SiYoung Jang, Byoungheon Shin, and Dongman Lee. "Implementing a Dynamically Reconfigurable Wireless Mesh Network Testbed for Multi-Faceted QoS Support." Proceedings of the 11th International Conference on Future Internet Technologies. 2016.
  • SiYoung Jang, Byoungheon Shin, and Dongman Lee. "An adaptive tail time adjustment scheme based on inter-packet arrival time for IEEE 802.11 WLAN." 2016 IEEE International Conference on Communications (ICC). IEEE, 2016.
  • Yuepeng Qi, Chansu Yu, Youngju Suh and SiYoung Jang. "Gps tethering for energy conservation." 2015 IEEE Wireless Communications and Networking Conference (WCNC). IEEE, 2015.

Work Experience

Research scientist at Nokia Bell Labs (Cambridge, UK)

2022.07 ~ Present

Postdoc at KAIST (Daejeon, South Korea)

2022.03 ~ 2022.06 (3 month)

Research intern at Nokia Bell Labs (Cambridge, UK)

2021.06 ~ 2021.09 (3 month)

Teaching Assitant at KAIST (Daejeon, South Korea)

Computer Networks CS341, Distributed systems CS543
2017.03 ~ 2019.02

Talks

  • Double edged sword: big data and data science (Korean), Seoul Metropolitan Office of Education 2022 (link1, link2)
  • Deploying collaborative machine learning systems in edge with multiple cameras, ICMU 2021
  • Microservice-based edge device architecture for video analytics, IEEE/ACM SEC 2021
  • Application-aware IoT camera virtualization for video analytics edge computing, IEEE/ACM SEC 2018
  • Semantic virtualization for edge-IoT cloud: Issues and challenges, Cloud-Assisted Networking (CoNext Workshop) 2017
  • An adaptive tail time adjustment scheme based on inter-packet arrival time for IEEE 802.11 WLAN, IEEE ICC 2016

Mentorship

  • Exploring Distributed Inference on Tiny AI Accelerators

    Arthur Moss from Newcastle University (2023)

  • Exploring Model Inference over Distributed Ultra-low Power DNN Accelerators

    Prerna Khanna from Stony Brook University (2022)

  • Ultra-low Power DNN Accelerators for IoT: Resource Characterisation of the MAX78000

    Hyunjong Lee from KAIST (2022)

  • Cocoon: On-body Microphone Collaboration for Spatial Awareness

    Bhawana Chhaglani from University of Massachusetts Amherst (2022)

  • DNN Partitioning and Retraining Scheduling for the Edge

    Sangwoo Kim from KAIST (2022)

  • Exploring Microservice Design for Edge Devices

    Boyan Kostadinov from KAIST (2021)

  • IoT Service Provisioning for Edge

    Younhyung Lee from KAIST (2018)