Taehyoun Kim

Prof. Taehyoun Kim

Department of Mechanical and Information Engineering, University of Seoul - South Korea
orcid

Research Focus & Metrics

Academic Career Length

32Years (1995-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 June 2023 in IEEE Access
Verified
Journal Article
Open access
SLSeongjae Lee
Seongjae Lee
TKTaehyoun Kim
Taehyoun Kim
Deep learning has recently resulted in remarkable performance improvements in machine fault diagnosis using only raw input vibration signals with no signal preprocessing. However, research on machine fault diagnosis using deep learning has primarily focused on model architectures, even though optimizers and their hyperparameters used for training can have a significant impact on model performance. This paper presents extensive benchmarking results on the tuning of optimizer hyperparameters using various combinations of datasets, convolutional neural network (CNN) models, and optimizers with varying batch sizes. First, we set the hyperparameter search space and then trained the models using hyperparameters sampled from a quasi-random distribution. Subsequently, we refined the search space based on the results of the first step and finally evaluated model performances using noise-free and noisy data. The results showed that the learning rate and momentum factor, which determine training speed, substantially affected the model’s accuracy. We also discovered that the impacts of batch size and model training speed on model performance were highly correlated; large batch sizes led to higher performances at higher learning rates or momentum factors. Conversely, model performances tended to be high for small batch sizes at lower learning rates or momentum factors. In addition, regarding the growing attention to on-device artificial intelligence (AI) solutions, we assessed the accuracy and computational efficiency of candidate models. A CNN with training interference (TICNN) was the most efficient model in terms of computational efficiency and robustness against noise among the benchmarked candidate models.

1 August 2013 in International Journal of Computers Communications & Control
Verified
Journal Article
Open access
PDF file
MSMinyoung Sung
Minyoung Sung
IKIkhwan Kim
Ikhwan Kim
TKTaehyoun Kim
Taehyoun Kim
Toward a Holistic Delay Analysis of EtherCAT Synchronized Control Processes

14 September 2024 in Data in Brief
Verified
Journal Article
Open access
SLSeongjae Lee
Seongjae Lee
TKTaewan Kim
Taewan Kim
TKTaehyoun Kim
Taehyoun Kim
In modern complex mechanical systems, machine faults typically occur in multiple components simultaneously, and the domain of collected sensor data changes continuously due to variations in operating conditions. Deep learning-based fault diagnosis approaches have recently been enhanced to address these real-world industrial challenges. Comprehensive labeled data covering compound fault scenarios and multi-domain conditions are crucial for exploring these issues. However, existing multi-domain datasets focus on a limited range of operating conditions, such as motor rotating speeds and loads. This limits their applicability to real-world industrial scenarios. To bridge this gap, we present a novel multi-domain dataset that incorporates these basic conditions and extends to various bearing types and compound machine faults. The deep groove ball bearing, the cylindrical roller bearing, and the tapered roller bearing were utilized to provide data that reflect diverse mechanical interactions between the shaft and the bearing. Vibration data were collected using a USB digital accelerometer at two sampling rates and six rotating speeds, encompassing three single bearing faults, seven single rotating component faults, and 21 compound faults of the bearing and rotating component. Additionally, the dataset provides spectrograms of vibration data using short-time Fourier transform (STFT) for data-driven analysis with a 2-D input. This dataset encompasses more complex compound fault and domain shift problems than those presented in conventional public vibration datasets, thereby aiding researchers in studying intelligent fault diagnosis methods based on deep learning.

22 November 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
TYTaeyoung Yoo
Taeyoung Yoo
SLSeongjae Lee
Seongjae Lee
TKTaehyoun Kim
Taehyoun Kim
A reverse vending machine motivates citizens to bring recyclable waste by rewarding them, which is a viable solution to increase the recycling rate. Reverse vending machines generally use near-infrared sensors, barcode sensors, or cameras to classify recycling resources. However, sensor-based reverse vending machines suffer from a high configuration cost and the limited scope of target objects, and conventional single image-based reverse vending machines usually make erroneous predictions about intentional fraud objects. This paper proposes a dual image-based convolutional neural network ensemble model to address these problems. For this purpose, we first created a prototype reverse vending machine and constructed an image dataset containing two cross-sections of objects, top and front view. Then, we chose convolutional neural network models widely used in image classification as the candidates for building an accurate and lightweight ensemble model. Considering the size and classification performance of candidates, we constructed the best-fit ensemble combination and evaluated its classification performance. The final ensemble model showed a classification accuracy higher than 95% for all target classes, including fraud objects. This result proves that our approach achieves better robustness against intentional fraud objects than single image-based models and thus can broaden the scope for target resources. The measurement results on lightweight embedded platforms also demonstrated that our model provides a short inference time that is enough to facilitate the real-time execution of reverse vending machines based on low-cost edge artificial intelligence devices.

1 December 2009 in Journal of Mechanical Science and Technology
Verified
Journal Article
Closed access
PDF file
TKTaeseong Kim
Taeseong Kim
SSSangJoon Shin
SangJoon Shin
TKTaehyoun Kim
Taehyoun Kim

23 May 2008 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
KKKyungtae Kang
Kyungtae Kang
TKTaehyoun Kim
Taehyoun Kim
The broadcast and multicast services (BCMCS) protocol is designed for real-time applications such as MPEG-4 video streaming, which requires successive frames to arrive within a specific time interval. We analyze the execution time of Reed-Solomon (RS) decoding, which is the medium access control (MAC)-layer forward error-correction (FEC) scheme used in CDMA2000 1xEV-DO BCMCS, under various air channel conditions. The results show that the timing constraints of MPEG-4 cannot always be met by RS decoding when the packet loss rate (PLR) is high, due to the limited processing power of current hardware. We therefore propose three error control schemes: First, we have our static scheme, which bypasses RS decoding at the mobile node to satisfy the MPEG-4 timing constraint when the PLR exceeds a given level. Second, we have the dynamic scheme, which corrects as many errors as possible within the timing constraint, instead of giving up altogether when the PLR is high; this improves quality. Third, we have the video-aware dynamic scheme, which fixes errors in a similar way to the dynamic scheme but in a priority-driven manner, yielding a further increment in video quality at mobile terminals. Extensive simulation results show the effectiveness of our schemes compared with the original FEC scheme.