Ji Hwan Park

Mr. Ji Hwan Park

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
9 August 2022 in Sensors
Verified
Journal Article
Open access
PDF file
KNKim Margarette Corpuz Nogoy
Kim Margarette Corpuz Nogoy
SCSun Il Chon
Sun Il Chon
JPJi Hwan Park
Ji Hwan Park
SSSaraswathi Sivamani
Saraswathi Sivamani
Dong-Hoon LeeDong-Hoon Lee
Dong-Hoon Lee
SCSeong Ho Choi
Seong Ho Choi
Cattle are less active than humans. Hence, it was hypothesized in this study that transmitting acceleration signals at a 1 min sampling interval to reduce storage load has the potential to improve the performance of motion sensors without affecting the precision of behavior classification. The behavior classification performance in terms of precision, sensitivity, and the F1-score of the 1 min serial datasets segmented in 3, 4, and 5 min window sizes based on nine algorithms were determined. The collar-fitted triaxial accelerometer sensor was attached on the right side of the neck of the two fattening Korean steers (age: 20 months) and the steers were observed for 6 h on day one, 10 h on day two, and 7 h on day three. The acceleration signals and visual observations were time synchronized and analyzed based on the objectives. The resting behavior was most correctly classified using the combination of a 4 min window size and the long short-term memory (LSTM) algorithm which resulted in 89% high precision, 81% high sensitivity, and 85% high F1-score. High classification performance (79% precision, 88% sensitivity, and 83% F1-score) was also obtained in classifying the eating behavior using the same classification method (4 min window size and an LSTM algorithm). The most poorly classified behavior was the active behavior. This study showed that the collar-fitted triaxial sensor measuring 1 min serial signals could be used as a tool for detecting the resting and eating behaviors of cattle in high precision by segmenting the acceleration signals in a 4 min window size and by using the LSTM classification algorithm.

17 December 2021 in Applied Sciences
Verified
Journal Article
Open access
PDF file
KNKim Margarette Corpuz Nogoy
Kim Margarette Corpuz Nogoy
JPJi Hwan Park
Ji Hwan Park
SCSun Il Chon
Sun Il Chon
SSSaraswathi Sivamani
Saraswathi Sivamani
MPMin-Jeong Park
Min-Jeong Park
SCSeong Ho Choi
Seong Ho Choi
One of the main challenges in the adoption of artificial intelligence-based tools, such as integrated decision support systems, is the complexities of their application. This study aimed to define the relevant parameters that can be used as indicators for real-time detection of heat stress and subclinical mastitis in dairy cows. Moreover, this study aimed to demonstrate the use of a developed data-mining hub as an artificial intelligence-based tool that integrates the defined relevant information (parameters or traits) in accurately identifying the condition of the cow. A comprehensive theoretical framework of the data-mining hub is demonstrated, the selection of the parameters that were used for the data-mining hub is listed, and the relevance of the traits is discussed. The practical application of the data-mining hub has shown that using 21 parameters instead of 13 and 8 parameters resulted in a high overall accuracy of detecting heat stress and subclinical mastitis in dairy cows with a high precision effect reflecting a low percentage of misclassifying the conditions of the dairy cows. This study has developed an innovative approach in which combined information from different independent data was used to accurately detect the health and wellness status of the dairy cows. It can also be implied that an artificial intelligence-based tool such as the proposed theoretical data-mining hub of dairy cows could maximize the use of continuously generated and underutilized data in farms, thus ultimately simplifying repetitive and difficult decision-making tasks in dairy farming.

1 January 2022 in Computers, Materials & Continua
Verified
Journal Article
Open access
PDF file
SSSaraswathi Sivamani
Saraswathi Sivamani
SCSun Il Chon
Sun Il Chon
DCDo Yeon Choi
Do Yeon Choi
DLDong Hoon Lee
Dong Hoon Lee
JPJi Hwan Park
Ji Hwan Park
Existing segmentation and augmentation techniques on convolutional neural network (CNN) has produced remarkable progress in object detection. However, the nominal accuracy and performance might be downturned with the photometric variation of images that are directly ignored in the training process, along with the context of the individual CNN algorithm. In this paper, we investigate the effect of a photometric variation like brightness and sharpness on different CNN. We observe that random augmentation of images weakens the performance unless the augmentation combines the weak limits of photometric variation. Our approach has been justified by the experimental result obtained from the PASCAL VOC 2007 dataset, with object detection CNN algorithms such as YOLOv3 (You Only Look Once), Faster R-CNN (Region-based CNN), and SSD (Single Shot Multibox Detector). Each CNN model shows performance loss for varying sharpness and brightness, ranging between −80% to 80%. It was further shown that compared to random augmentation, the augmented dataset with weak photometric changes delivered high performance, but the photometric augmentation range differs for each model. Concurrently, we discuss some research questions that benefit the direction of the study. The results prove the importance of adaptive augmentation for individual CNN model, subjecting towards the robustness of object detection.

18 September 2020 in IEEE Access
Verified
Journal Article
Open access
SSSaraswathi Sivamani
Saraswathi Sivamani
SCSun Il Chon
Sun Il Chon
DCDo Yeon Choi
Do Yeon Choi
JPJi Hwan Park
Ji Hwan Park
Image processing systems are widespread with the digital transformation of artificial intelligence. Many researchers developed and tested several image classification models using machine learning and statistical techniques. Nevertheless, the current research seldom focuses on the quality assurance of these models. The existing methods lack to verify the quality assurance, with the lack of test cases to prepare the evaluation dataset to test the model, which can cause critical drawbacks in the nuclear field and defense system. In this paper, we discuss and suggest the preparation of the evaluation dataset using improved test cases through Cause-Effect Graphing. The proposed method can generate the evaluation dataset with automated test cases through the quantification method, which consists of 1) image characteristic selection 2) creating the Cause-Effect graphing approach of the image with the feature, and 3) generate all possible test coverage. The testing is performed with the COCO dataset, which shows the declining prediction accuracy with the adjusted brightness and sharpness ranging between -75 to 75%, which indicates the negligence of the important characteristics in the existing test dataset. The experiment shows the prediction fails while sharpness is less than the 0%, and the brightness fails at -75% with less number of detection object between -50% and 75%. This indicates that characteristic changes affects the prediction accuracy and the number of detected objects in an image. Our approach proves the importance of the characteristic selection process for the overall image to generate a more efficient model and increase the accuracy of object detection.

2 August 2024 in IEEE Access
Verified
Journal Article
Open access
SSSaraswathi Sivamani
Saraswathi Sivamani
SCSun Il Chon
Sun Il Chon
JPJi Hwan Park
Ji Hwan Park
Dataset quality is an integral aspect of image object detection. Consequently, poor-quality datasets are often blamed for limiting model performance. Conventional convolutional neural network models attempt to address the model performance issue and have achieved high accuracy; however, these models fail to detect objects with photometric and geometric variations in similar images. To address this object detection issue, we adopt selective image augmentation by identifying potential weak points of photometric factors, such as brightness and sharpness. A stall-housed pig dataset and a food product dataset with complex and clear backgrounds, respectively, were selected to test our hypothesis. Images from both test datasets were investigated with photometric variations ranging between −60% ~ 60% with a step size of 20% to identify the weak points of the dataset. The test results demonstrate that a photometrically balanced dataset with selective augmentation significantly outperforms the original dataset in terms of high accuracy and robustness.