Sungyong Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Sungyong Lee has a total of 22 co-authors. Here are the top co-authors by number of shared publications:
- Kyunghan Lee
Seoul National University, Seoul, Republic of Korea
3 shared publications - Jinsung Lee
Qualcomm Technologies Inc., San Jose, CA, USA
2 shared publications - Wooseung Nam
Department of Electrical and Computer Engineering, Seoul National University, Seoul, South Korea
2 shared publications - Choong Seon Hong
Kyung Hee University
1 shared publication - Claudia Villalonga
University of Granada
1 shared publication - Dong Woo Kang
Department of Chemical and Biomolecular Engineering, Korea Advanced Institute of Science and Technology (KAIST), Daejeon 34141, Republic of Korea
1 shared publication
Latest Publications
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (6) , 5386-5399
nCTX: A Neural Network-Powered Lossless Compressive Transmission Using Shared Information
In this work, we explore the possibility of a new delivery method for lossless data, namely compressive transmission. It aims at minimizing the transmission data volume at runtime by exploiting the tailored information shared between the sender and the receiver. There are two approaches to leverage shared information for compression: 1) using a DNN-based codec as a proxy for shared information and 2) applying redundancy elimination using deduplication. However, these approaches have not been studied in depth to utilize the trade-off between the compression rate and the amount of shared information. Compared to these approaches, compressive transmission is unique as it fully leverages the abundance of information available on both sides, which is chosen and placed purposely. To bring the concept to reality, we propose nCTX, a neural network-powered Compressive Transmission System that adaptively exploits a generative model and matching blocks. nCTX extracts the optimal semantic data from the input data, exploiting shared information to closely imitate the original and compensate it with the offset (i.e., difference). Extensive evaluations in mobile platforms confirm that nCTX reduces the transmission volume significantly by 25.8% and 23.3% compared to FLIF and RC, the state-of-the-art image codecs, respectively, in comparable or shorter computation times.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 24 (6) , 5386-5399
nCTX: A Neural Network-Powered Lossless Compressive Transmission Using Shared Information
In this work, we explore the possibility of a new delivery method for lossless data, namely compressive transmission. It aims at minimizing the transmission data volume at runtime by exploiting the tailored information shared between the sender and the receiver. There are two approaches to leverage shared information for compression: 1) using a DNN-based codec as a proxy for shared information and 2) applying redundancy elimination using deduplication. However, these approaches have not been studied in depth to utilize the trade-off between the compression rate and the amount of shared information. Compared to these approaches, compressive transmission is unique as it fully leverages the abundance of information available on both sides, which is chosen and placed purposely. To bring the concept to reality, we propose nCTX, a neural network-powered Compressive Transmission System that adaptively exploits a generative model and matching blocks. nCTX extracts the optimal semantic data from the input data, exploiting shared information to closely imitate the original and compensate it with the offset (i.e., difference). Extensive evaluations in mobile platforms confirm that nCTX reduces the transmission volume significantly by 25.8% and 23.3% compared to FLIF and RC, the state-of-the-art image codecs, respectively, in comparable or shorter computation times.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 33 (3) , 1041-1055
N-Epitomizer: A Semantic Offloading Framework Leveraging Essential Information for Timely Neural Network Inferences
Offloading neural network inferences from resource-constrained mobile devices to an edge server over wireless networks is becoming more crucial as the neural networks get heavier. To this end, recent studies have tried to make this offloading process more efficient. However, the most fundamental question on extracting and offloading the minimal amount of necessary information that does not degrade the inference accuracy has remained unanswered. We call such an ideal offloading semantic offloading and propose N-epitomizer, a new offloading framework that enables semantic offloading, thus achieving more reliable and timely inferences in highly-fluctuated or even low-bandwidth wireless networks. To realize N-epitomizer, we design an autoencoder-based scalable encoder trained to extract the most informative data and scale its output size to meet the latency and accuracy requirements of inferences over a network. We also accelerate N-epitomizer by exploiting light-weight knowledge distillation for the encoder design and decoder slimming for the decoder design, reducing its overall computation time significantly. Moreover, we extend our N-epitomizer to support multiple DNNs by extracting and offloading the union of the essential information required for each DNN. Our evaluation shows that N-epitomizer achieves exceptionally high compression for images without compromising inference accuracy, which is 21 $\times$ , 77 $\times$ , and 192 $\times$ higher than JPEG compression, and 20 $\times$ , 55 $\times$ , and 86 $\times$ higher than the state-of-the-art DNN-aware image compression GRACE for semantic segmentation, depth estimation, and classification, respectively. Our results show N-epitomizer’s strong potential as the first semantic offloading system to guarantee end-to-end latency even under highly varying cellular networks.
- 6 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Networking
- Vol. 33 (3) , 1041-1055
N-Epitomizer: A Semantic Offloading Framework Leveraging Essential Information for Timely Neural Network Inferences
Offloading neural network inferences from resource-constrained mobile devices to an edge server over wireless networks is becoming more crucial as the neural networks get heavier. To this end, recent studies have tried to make this offloading process more efficient. However, the most fundamental question on extracting and offloading the minimal amount of necessary information that does not degrade the inference accuracy has remained unanswered. We call such an ideal offloading semantic offloading and propose N-epitomizer, a new offloading framework that enables semantic offloading, thus achieving more reliable and timely inferences in highly-fluctuated or even low-bandwidth wireless networks. To realize N-epitomizer, we design an autoencoder-based scalable encoder trained to extract the most informative data and scale its output size to meet the latency and accuracy requirements of inferences over a network. We also accelerate N-epitomizer by exploiting light-weight knowledge distillation for the encoder design and decoder slimming for the decoder design, reducing its overall computation time significantly. Moreover, we extend our N-epitomizer to support multiple DNNs by extracting and offloading the union of the essential information required for each DNN. Our evaluation shows that N-epitomizer achieves exceptionally high compression for images without compromising inference accuracy, which is 21 $\times$ , 77 $\times$ , and 192 $\times$ higher than JPEG compression, and 20 $\times$ , 55 $\times$ , and 86 $\times$ higher than the state-of-the-art DNN-aware image compression GRACE for semantic segmentation, depth estimation, and classification, respectively. Our results show N-epitomizer’s strong potential as the first semantic offloading system to guarantee end-to-end latency even under highly varying cellular networks.
- 30 September 2023
- Published by Korean Society for Rehabilitation of Persons with Disabilities in Korean Society for Rehabilitation of Persons with Disabilities
- Vol. 27 (3) , 1-18
A Study on the Analysis of Factors Affecting Assistive Technology Device Need for People with Disabilities: Focused on Human, Activity, and Environmental Factors
It is important to consider the individual characteristics of Assistive Technology Device (ATD) for assisting people with disabilities in their daily activities. A representative method is to consider the four basic elements of Human, Activity, Assistive Technology Device, and Environment when providing assistive technology services (HAAT model, Cook & Hussey, 2002). In this study, the factors affecting the ATDs required by the people with disabilities in Korea were analyzed by applying to the HAAT model. The top five ATDs with high need were extracted, and the factors influencing the need for the top five ATDs among people, activities, and environmental factors were analyzed by conducting binomial logistic regression analysis. As a result of the analysis, the top 5 ATDs most needed by the people with disabilities in Korea are cane, safety handle, powered wheelchair, electric scooter, and home modification. These results indicate that they mostly require ATDs for activities of daily living related to mobility and movement. Age, disability grade, and whether or not to use public transportation were analyzed as factors that had a statistically significant effect on the need for ATDs. The limitation of this study is that there is a limitation in generalizing the analysis results of this study because there is a possibility that sufficient information on ATDs may not be provided when conducting a fact-finding survey of the people with disabilities. Nevertheless, the results of this study suggest that it is necessary to apply appropriate ATDs considering factors such as disability type, living environment, and age. The results of this study are expected to be used as basic data for the application of assistive devices suitable for the characteristics of the people with disabilities in Korea.
- 30 September 2023
- Published by Korean Society for Rehabilitation of Persons with Disabilities in Korean Society for Rehabilitation of Persons with Disabilities
- Vol. 27 (3) , 1-18
A Study on the Analysis of Factors Affecting Assistive Technology Device Need for People with Disabilities: Focused on Human, Activity, and Environmental Factors
It is important to consider the individual characteristics of Assistive Technology Device (ATD) for assisting people with disabilities in their daily activities. A representative method is to consider the four basic elements of Human, Activity, Assistive Technology Device, and Environment when providing assistive technology services (HAAT model, Cook & Hussey, 2002). In this study, the factors affecting the ATDs required by the people with disabilities in Korea were analyzed by applying to the HAAT model. The top five ATDs with high need were extracted, and the factors influencing the need for the top five ATDs among people, activities, and environmental factors were analyzed by conducting binomial logistic regression analysis. As a result of the analysis, the top 5 ATDs most needed by the people with disabilities in Korea are cane, safety handle, powered wheelchair, electric scooter, and home modification. These results indicate that they mostly require ATDs for activities of daily living related to mobility and movement. Age, disability grade, and whether or not to use public transportation were analyzed as factors that had a statistically significant effect on the need for ATDs. The limitation of this study is that there is a limitation in generalizing the analysis results of this study because there is a possibility that sufficient information on ATDs may not be provided when conducting a fact-finding survey of the people with disabilities. Nevertheless, the results of this study suggest that it is necessary to apply appropriate ATDs considering factors such as disability type, living environment, and age. The results of this study are expected to be used as basic data for the application of assistive devices suitable for the characteristics of the people with disabilities in Korea.
- 7 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 22 (6) , 3270-3286
DeepVehicleSense: An Energy-Efficient Transportation Mode Recognition Leveraging Staged Deep Learning Over Sound Samples
In this paper, we present a new transportation mode recognition system for smartphones called DeepVehicleSense, which is widely applicable to mobile context-aware services. DeepVehicleSense aims at achieving three performance objectives: high accuracy, low latency, and low power consumption at once by exploiting sound characteristics captured from the built-in microphone while being on candidate transportations. To attain high energy efficiency, DeepVehicleSense adopts hierarchical accelerometer-based triggers that minimize the activation of the microphone of smartphones. Further, to achieve high accuracy and low latency, DeepVehicleSense makes use of non-linear filters that can best extract the transportation sound samples. For recognition of five different transportation modes, we design a deep learning based sound classifier using a novel deep neural network architecture with multiple branches. Our staged inference technique can significantly reduce runtime and energy consumption while maintaining high accuracy for the majority of samples. Through 263-hour datasets collected by seven different Android phone models, we demonstrate that DeepVehicleSense achieves the recognition accuracy of 97.44% with only sound samples of 2 seconds at the power consumption of 35.08 mW on average for all-day monitoring.
- 7 January 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Mobile Computing
- Vol. 22 (6) , 3270-3286
DeepVehicleSense: An Energy-Efficient Transportation Mode Recognition Leveraging Staged Deep Learning Over Sound Samples
In this paper, we present a new transportation mode recognition system for smartphones called DeepVehicleSense, which is widely applicable to mobile context-aware services. DeepVehicleSense aims at achieving three performance objectives: high accuracy, low latency, and low power consumption at once by exploiting sound characteristics captured from the built-in microphone while being on candidate transportations. To attain high energy efficiency, DeepVehicleSense adopts hierarchical accelerometer-based triggers that minimize the activation of the microphone of smartphones. Further, to achieve high accuracy and low latency, DeepVehicleSense makes use of non-linear filters that can best extract the transportation sound samples. For recognition of five different transportation modes, we design a deep learning based sound classifier using a novel deep neural network architecture with multiple branches. Our staged inference technique can significantly reduce runtime and energy consumption while maintaining high accuracy for the majority of samples. Through 263-hour datasets collected by seven different Android phone models, we demonstrate that DeepVehicleSense achieves the recognition accuracy of 97.44% with only sound samples of 2 seconds at the power consumption of 35.08 mW on average for all-day monitoring.
- Open Access
- 1 January 2015
- Published by Association for Computing Machinery (ACM)
- p. 149-152
Facilitating trunk endurance assessment by means of mobile health technologies
Trunk endurance tests are widely used in physical medicine to assess the muscle status of people affected by low back pain. Nevertheless, traditional evaluation procedures suffer from practical limitations, which can lead to potential misdiagnoses. This work presents mDurance, a novel mobile health system aimed at supporting specialists in the functional assessment of trunk endurance by using wearable and mobile devices. The system makes use of a wearable inertial sensor to track the patient trunk posture, while portable electromyography sensors are employed to seamlessly measure the electrical activity produced by the trunk muscles. The information registered by the sensors is processed and managed by a mobile application that facilitates the expert normal routine, while reducing the impact of human errors and expediting the analysis of the test results. The reliability and usability of mDurance is proved through a case study, thus demonstrating its potential interest for regular physical therapy routines.
- 1 January 2015
- Published by Association for Computing Machinery (ACM)
- p. 149-152
Open AccessFacilitating trunk endurance assessment by means of mobile health technologies
Trunk endurance tests are widely used in physical medicine to assess the muscle status of people affected by low back pain. Nevertheless, traditional evaluation procedures suffer from practical limitations, which can lead to potential misdiagnoses. This work presents mDurance, a novel mobile health system aimed at supporting specialists in the functional assessment of trunk endurance by using wearable and mobile devices. The system makes use of a wearable inertial sensor to track the patient trunk posture, while portable electromyography sensors are employed to seamlessly measure the electrical activity produced by the trunk muscles. The information registered by the sensors is processed and managed by a mobile application that facilitates the expert normal routine, while reducing the impact of human errors and expediting the analysis of the test results. The reliability and usability of mDurance is proved through a case study, thus demonstrating its potential interest for regular physical therapy routines.