Jaepil Ko

Prof. Jaepil Ko


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
21 June 2021 in Plants
Verified
Journal Article
Open access
PDF file
MYMilkisa Yebasse
Milkisa Yebasse
BGBirhanu Shimelis Girma
Birhanu Shimelis Girma
HWHenok Tegegn Warku
Henok Tegegn Warku
JKJaepil Ko
Jaepil Ko
KCKyung Joo Cheoi
Kyung Joo Cheoi
Deep learning architectures are widely used in state-of-the-art image classification tasks. Deep learning has enhanced the ability to automatically detect and classify plant diseases. However, in practice, disease classification problems are treated as black-box methods. Thus, it is difficult to trust the model that it truly identifies the region of the disease in the image; it may simply use unrelated surroundings for classification. Visualization techniques can help determine important areas for the model by highlighting the region responsible for the classification. In this study, we present a methodology for visualizing coffee diseases using different visualization approaches. Our goal is to visualize aspects of a coffee disease to obtain insight into what the model “sees” as it learns to classify healthy and non-healthy images. In addition, visualization helped us identify misclassifications and led us to propose a guided approach for coffee disease classification. The guided approach achieved a classification accuracy of 98% compared to the 77% of naïve approach on the Robusta coffee leaf image dataset. The visualization methods considered in this study were Grad-CAM, Grad-CAM++, and Score-CAM. We also provided a visual comparison of the visualization methods.

14 February 2023 in IEEE Access
Verified
Journal Article
Open access
MYMilkisa Yebasse
Milkisa Yebasse
KCKyung Joo Cheoi
Kyung Joo Cheoi
JKJaepil Ko
Jaepil Ko
Deep learning-based methods have become an active research area in medical imaging. Malaria is diagnosed by testing red blood cells. Deep learning methods can be used to distinguish malaria infected cell images from non-infected cell images. The small number of malaria dataset may limit the application of deep learning. Moreover, the infected area in the cell images is generally vague and small, requiring more complex models and a larger dataset to train on. Motivated by the tendency of humans to highlight important words when reading, we propose a simple neural network training strategy for highlighting the infected pixel regions that are mainly responsible for malaria cell classification. In our experiments on the NIH(National Institutes of Health) malaria dataset available in public domain, the proposed method significantly improved classification accuracy for our four different sized models, ranging from simple to complex including Resnet and Mobilenet. Our proposed method significantly improved classification accuracy. The result indicate that approach achieves a classification accuracy of 97.2%, compared to 94.49% for a baseline model. In addition, we demonstrate the superiority of the proposed strategy by providing an analysis on the magnitude of weight parameters in terms of regularization.

21 November 2023 in Materials
Verified
Journal Article
Open access
PDF file
BSBishal Ranjan Swain
Bishal Ranjan Swain
DCDahee Cho
Dahee Cho
JPJoongcheul Park
Joongcheul Park
JRJae-Seung Roh
Jae-Seung Roh
JKJaepil Ko
Jaepil Ko
The quantification of the phase fraction is critical in materials science, bridging the gap between material composition, processing techniques, microstructure, and resultant properties. Traditional methods involving manual annotation are precise but labor-intensive and prone to human inaccuracies. We propose an automated segmentation technique for high-tensile strength alloy steel, where the complexity of microstructures presents considerable challenges. Our method leverages the UNet architecture, originally developed for biomedical image segmentation, and optimizes its performance via careful hyper-parameter selection and data augmentation. We employ Electron Backscatter Diffraction (EBSD) imagery for complex-phase segmentation and utilize a combined loss function to capture both textural and structural characteristics of the microstructures. Additionally, this work is the first to examine the scalability of the model across varying magnifications and types of steel and achieves high accuracy in terms of dice scores demonstrating the adaptability and robustness of the model.

26 December 2022 in Sensors
Verified
Journal Article
Open access
PDF file
TKTaeho Kim
Taeho Kim
YKYoujin Kim
Youjin Kim
SKSehan Kim
Sehan Kim
JKJaepil Ko
Jaepil Ko
Pork production is hugely impacted by the health and breeding of pigs. Analyzing the eating pattern of pigs helps in optimizing the supply chain management with a healthy breeding environment. Monitoring the feed intake of pigs in a barn provides information about their eating habits, behavioral patterns, and surrounding environment, which can be used for further analysis to monitor growth in pigs and eventually contribute to the quality and quantity of meat production. In this paper, we present a novel method to estimate the number of pigs taking in feed by considering the pig’s posture. In order to solve problems arising from using the pig’s posture, we propose an algorithm to match the pig’s head and the corresponding pig’s body using the major-and-minor axis of the pig detection box. In our experiment, we present the detection performance of the YOLOv5 model according to the anchor box, and then we demonstrate that the proposed method outperforms previous methods. We therefore measure the number of pigs taking in feed over a period of 24 h and the number of times pigs consume feed in a day over a period of 30 days, and observe the pig’s feed intake pattern.

3 January 2024 in Sensors
Verified
Journal Article
Open access
PDF file
MJMinSeong Jeon
MinSeong Jeon
JKJaepil Ko
Jaepil Ko
KCKyung Joo Cheoi
Kyung Joo Cheoi
This paper presents a novel approach to risk assessment by incorporating image captioning as a fundamental component to enhance the effectiveness of surveillance systems. The proposed surveillance system utilizes image captioning to generate descriptive captions that portray the relationship between objects, actions, and space elements within the observed scene. Subsequently, it evaluates the risk level based on the content of these captions. After defining the risk levels to be detected in the surveillance system, we constructed a dataset consisting of [Image-Caption-Danger Score]. Our dataset offers caption data presented in a unique sentence format, departing from conventional caption styles. This unique format enables a comprehensive interpretation of surveillance scenes by considering various elements, such as objects, actions, and spatial context. We fine-tuned the BLIP-2 model using our dataset to generate captions, and captions were then interpreted with BERT to evaluate the risk level of each scene, categorizing them into stages ranging from 1 to 7. Multiple experiments provided empirical support for the effectiveness of the proposed system, demonstrating significant accuracy rates of 92.3%, 89.8%, and 94.3% for three distinct risk levels: safety, hazard, and danger, respectively.

Verified
Journal Article
Open access
PDF file
GNGwang-Ho Na
Gwang-Ho Na
JKJaepil Ko
Jaepil Ko
KCKyung Joo Cheoi
Kyung Joo Cheoi
In this paper, we present a novel model that enhances performance by extending the dual-modality TEVAD model—originally leveraging visual and textual information—into a multi-modal framework that integrates visual, audio, and textual data. Additionally, we refine the multi-scale temporal network (MTN) to improve feature extraction across multiple temporal scales between video snippets. Using the XD-Violence dataset, which includes audio data for violence detection, we conduct experiments to evaluate various feature fusion methods. The proposed model achieves an average precision (AP) of 83.9%, surpassing the performance of single-modality approaches (visual: 73.9%, audio: 67.1%, textual: 29.9%) and dual-modality approaches (visual + audio: 78.8%, visual + textual: 78.5%). These findings demonstrate that the proposed model outperforms models based on the original MTN and reaffirm the efficacy of multi-modal approaches in enhancing violence detection compared to single- or dual-modality methods.