Sung-Jae Lee
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sung-Jae Lee has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
- Jun-Eun Park
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea
3 shared publications - Kang-Yoon Lee
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea
3 shared publications - Jong Wan Jo
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon, South Korea
2 shared publications - Ju-Won Oh
Sungkyunkwan University
2 shared publications - Yeonjae Jung
Department of Electrical and Computer Engineering, Sungkyunkwan University, Suwon-si, South Korea
2 shared publications Young-Gun Pu
SKAIChips Company Ltd
2 shared publications
Latest Publications
- Open Access
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 90741-90752
A Low Power Memory-Integrated Hardware BNN-MLP Model on an FPGA for Current Signals in a Biosensor
This paper presents a method for processing and digitizing the current signal information output from biosensors and a hardware Artificial Intelligence (AI) model design that classifies data using low-power and compact AI algorithms to minimize the high-power consumption and on chip area of the Convolution Neural Network (CNN) models used in biosensors. The dataset was built using a data sampling method that digitizes the current signal values from the biosensor by sampling them 16 times with a 16-bit Analog-to-Digital Converter (ADC), enabling feature extraction in advance. To reduce power consumption and area, a BNN-MLP model without an extraction layer was designed, and to improve accuracy, a dense layer was added to the final layer. This approach enhances accuracy while using binary weights. BNN-MLP model was designed using TensorFlow for the software model and implemented in hardware at the Register Transfer Level (RTL). To verify the similarity between the hardware-implemented BNN-MLP model and the software BNN-MLP model, classification was performed on a test dataset of 1,000 samples using a Field Programmable Gate Array (FPGA), and the classification accuracy for each class was compared. When the When the BNN-MLP model is implemented on an FPGA, it utilizes 7,994 LUTs and 9,780 FFs, occupying fewer resources compared to previous studies. Additionally, it operates at a lower power consumption of 0.157 W, demonstrating the highest power efficiency performance of 407.6 GOPS/W. Finally, the inference time for a single data point was 0.018 ms, which is much faster that in previous studies, confirming its potential for low-power and compact applications in biosensors.
- 21 May 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 90741-90752
Open AccessA Low Power Memory-Integrated Hardware BNN-MLP Model on an FPGA for Current Signals in a Biosensor
This paper presents a method for processing and digitizing the current signal information output from biosensors and a hardware Artificial Intelligence (AI) model design that classifies data using low-power and compact AI algorithms to minimize the high-power consumption and on chip area of the Convolution Neural Network (CNN) models used in biosensors. The dataset was built using a data sampling method that digitizes the current signal values from the biosensor by sampling them 16 times with a 16-bit Analog-to-Digital Converter (ADC), enabling feature extraction in advance. To reduce power consumption and area, a BNN-MLP model without an extraction layer was designed, and to improve accuracy, a dense layer was added to the final layer. This approach enhances accuracy while using binary weights. BNN-MLP model was designed using TensorFlow for the software model and implemented in hardware at the Register Transfer Level (RTL). To verify the similarity between the hardware-implemented BNN-MLP model and the software BNN-MLP model, classification was performed on a test dataset of 1,000 samples using a Field Programmable Gate Array (FPGA), and the classification accuracy for each class was compared. When the When the BNN-MLP model is implemented on an FPGA, it utilizes 7,994 LUTs and 9,780 FFs, occupying fewer resources compared to previous studies. Additionally, it operates at a lower power consumption of 0.157 W, demonstrating the highest power efficiency performance of 407.6 GOPS/W. Finally, the inference time for a single data point was 0.018 ms, which is much faster that in previous studies, confirming its potential for low-power and compact applications in biosensors.
- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (9) , 5270-5283
A 92.7% Peak Efficiency Self-Starting Boost Converter With MPPT and Phase Frequency Detector Based Multi Current Detector for Energy Harvesting Systems With a Minimum Input Source Impedance of 1 Ω
This article presents a boost converter based on a maximum power point tracking (MPPT) circuit, and a multicurrent detector (MCD), an offset cancellation circuit to achieve high efficiency over a wide range of input power. The proposed boost converter employs an MPPT design for adaptive on-time operation, which adjusts the on-time width to achieve maximum efficiency depending on the input voltage. In addition, a phase frequency detector-based offset cancellation method is proposed to minimize power loss by accurately sensing the current detector, thereby transferring power. Therefore, the proposed method achieves a significant efficiency improvement of up to 10 % by implementing high-precision offset cancellation with an offset level of approximately$5~\mu $ A, which is significantly lower than the conventional MCD offset of over 60 mA of maximum offset current level. The proposed boost converter fabricated in a 130 nm Bipolar-CMOS-DMOS (BCD) process occupies an active area of 0.806 mm2 and can self-start with a minimum input voltage of 450 mV ($40~\mu $ W) and achieve maximum efficiency of 92.7 %.- 17 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems I: Regular Papers
- Vol. 72 (9) , 5270-5283
A 92.7% Peak Efficiency Self-Starting Boost Converter With MPPT and Phase Frequency Detector Based Multi Current Detector for Energy Harvesting Systems With a Minimum Input Source Impedance of 1 Ω
This article presents a boost converter based on a maximum power point tracking (MPPT) circuit, and a multicurrent detector (MCD), an offset cancellation circuit to achieve high efficiency over a wide range of input power. The proposed boost converter employs an MPPT design for adaptive on-time operation, which adjusts the on-time width to achieve maximum efficiency depending on the input voltage. In addition, a phase frequency detector-based offset cancellation method is proposed to minimize power loss by accurately sensing the current detector, thereby transferring power. Therefore, the proposed method achieves a significant efficiency improvement of up to 10 % by implementing high-precision offset cancellation with an offset level of approximately$5~\mu $ A, which is significantly lower than the conventional MCD offset of over 60 mA of maximum offset current level. The proposed boost converter fabricated in a 130 nm Bipolar-CMOS-DMOS (BCD) process occupies an active area of 0.806 mm2 and can self-start with a minimum input voltage of 450 mV ($40~\mu $ W) and achieve maximum efficiency of 92.7 %.