• The Journal of the Korea institute of electronic communication sciences
• /
• v.17 no.4
• /
• pp.577-586
• /
• 2022

Detection and classification of steel surface defects are critical for product quality control in the steel industry. However, due to its low accuracy and slow speed, the traditional approach cannot be effectively used in a production line. The current, widely used algorithm (based on deep learning) has an accuracy problem, and there are still rooms for development. This paper proposes a method of steel surface defect detection combining EfficientNetV2 for image classification and YOLOv5 as an object detector. Shorter training time and high accuracy are advantages of this model. Firstly, the image input into EfficientNetV2 model classifies defect classes and predicts probability of having defects. If the probability of having a defect is less than 0.25, the algorithm directly recognizes that the sample has no defects. Otherwise, the samples are further input into YOLOv5 to accomplish the defect detection process on the metal surface. Experiments show that proposed model has good performance on the NEU dataset with an accuracy of 98.3%. Simultaneously, the average training speed is shorter than other models.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.19 no.1
• /
• pp.309-316
• /
• 2024

Facial recognition technology is widely used in various fields but faces challenges due to its vulnerability to fraudulent activities such as photo spoofing. Extensive research has been conducted to overcome this challenge. Most of them, however, require the use of specialized equipment like multi-modal cameras or operation in high-performance environments. In this paper, we introduce LH-FAS v2 (: Lightweight Head-pose-based Face Anti-Spoofing v2), a system designed to operate on a commercial webcam without any specialized equipment, to address the issue of facial recognition spoofing. LH-FAS v2 utilizes FSA-Net for head pose estimation and ArcFace for facial recognition, effectively assessing changes in head pose and verifying facial identity. We developed the VD4PS dataset, incorporating photo spoofing scenarios to evaluate the model's performance. The experimental results show the model's balanced accuracy and speed, indicating that head pose estimation-based facial anti-spoofing technology can be effectively used to counteract photo spoofing.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.353-361
• /
• 2020

Due to the rapid urbanization, various traffic problems such as traffic jams during commute and regular traffic jams are occurring. In order to solve these traffic problems, it is necessary to quickly and accurately estimate and analyze traffic volume. ITS (Intelligent Transportation System) is a system that performs optimal traffic management by utilizing the latest ICT (Information and Communications Technology) technologies, and research has been conducted to analyze fast and accurate traffic volume through various techniques. In this study, we proposed a deep learning-based vehicle detection method using UAV (Unmanned Aerial Vehicle) video for real-time traffic analysis with high accuracy. The UAV was used to photograph orthogonal videos necessary for training and verification at intersections where various vehicles pass and trained vehicles by classifying them into sedan, truck, and bus. The experiment on UAV dataset was carried out using YOLOv3 (You Only Look Once V3), a deep learning-based object detection technique, and the experiments achieved the overall object detection rate of 90.21%, precision of 95.10% and the recall of 85.79%.

• Journal of Convergence for Information Technology
• /
• v.11 no.11
• /
• pp.57-65
• /
• 2021

We propose a novel method to detect abnormal data of specific symptoms using deep learning in air pollution measurement system. Existing methods generally detect abnomal data by classifying data showing unusual patterns different from the existing time series data. However, these approaches have limitations in detecting specific symptoms. In this paper, we use DeepLab V3+ model mainly used for foreground segmentation of images, whose structure has been changed to handle one-dimensional data. Instead of images, the model receives time-series data from multiple sensors and can detect data showing specific symptoms. In addition, we improve model's performance by reducing the complexity of noisy form time series data by using 'piecewise aggregation approximation'. Through the experimental results, it can be confirmed that anomaly data detection can be performed successfully.

• Journal of Korea Society of Industrial Information Systems
• /
• v.27 no.2
• /
• pp.71-82
• /
• 2022

In order to replace the sampling tensile test of products produced in the tab welding process, which is one of the automotive battery manufacturing processes, vision inspectors are currently being developed and used. However, the vision inspection has the problem of inspection position error and the cost of improving it. In order to solve these problems, there are recent cases of applying deep learning technology. As one such case, this paper tries to examine the usefulness of applying Faster R-CNN, one of the deep learning technologies, to existing product inspection. The images acquired through the existing vision inspection machine are used as training data and trained using the Faster R-CNN ResNet101 V1 1024x1024 model. The results of the conventional vision test and Faster R-CNN test are compared and analyzed based on the test standards of 0% non-detection and 10% over-detection. The non-detection rate is 34.5% in the conventional vision test and 0% in the Faster R-CNN test. The over-detection rate is 100% in the conventional vision test and 6.9% in Faster R-CNN. From these results, it is confirmed that deep learning technology is very useful for detecting welding error of lead tabs in automobile batteries.

• Therapeutic Science for Rehabilitation
• /
• v.13 no.2
• /
• pp.69-84
• /
• 2024

Objective : This study aimed to categorize the lifestyles of older adults into two types - healthy and unhealthy, and use machine learning to identify the personal values that influence these lifestyles. Methods : This cross-sectional study targeting middle-aged and older adults (55 years and above) living in local communities in South Korea. Data were collected from 300 participants through online surveys. Lifestyle types were dichotomized by the Yonsei Lifestyle Profile (YLP)-Active, Balanced, Connected, and Diverse (ABCD) responses using latent profile analysis. Personal value information was collected using YLP-Values (YLP-V) and analyzed using machine learning to identify the relative importance of personal values on lifestyle types. Results : The lifestyle of older adults was categorized into healthy (48.87%) and unhealthy (51.13%). These two types showed the most significant difference in social relationship characteristics. Among the machine learning models used in this study, the support vector machine showed the highest classification performance, achieving 96% accuracy and 95% area under the receiver operating characteristic (ROC) curve. The model indicated that individuals who prioritized a healthy diet, sought health information, and engaged in hobbies or cultural activities were more likely to have a healthy lifestyle. Conclusion : This study suggests the need to encourage the expansion of social networks among older adults. Furthermore, it highlights the necessity to comprehensively intervene in individuals' perceptions and values that primarily influence lifestyle adherence.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.6
• /
• pp.95-105
• /
• 2004

It is important to understand how pre-service teachers perceive e-learning because their prior-experience with e-learning will have a great impact on their teaching after the graduation. Pre-service teachers (401 students) with cyber learning experience, which is a form of e-learning, were selected in 2004 in May and June. Survey was conducted regarding the instructional experience (working hours, tasks and evaluation, satisfaction about cyber learning and its academic achievement, difficulties and suggestions) and instructional methods (instructional activities, frequencies of interaction, strategies of interaction, collaborative activities, behaviors in the group instructional activities for knowledge development). The results are pre-service teachers tent to spend similar v slightly less working hours for cyber learning, similar or slightly less satisfaction level for the instruction and the academic achievement. It was interesting that female students were more negative than males students, considering female students have been more active in online discussion traditionally. Logical presentation of contents and instructional strategies for the cyber learning were the most wanting suggestions. E-mails and BBS for reference materials were the two most used functions in the online learning. The amount and types of tasks were satisfactory. Students did not interact freely during the group activities, they reported they did not learn much through the group activity. During the group work, they consider they do their roles with responsibility while they have slightly negative responses toward other members' contribution in the group activity. Off line meeting is strongly suggested.

• Journal of Biomedical Engineering Research
• /
• v.43 no.5
• /
• pp.341-352
• /
• 2022

Medical image segmentation is the most important task in radiation therapy. Especially, when segmenting medical images, the liver is one of the most difficult organs to segment because it has various shapes and is close to other organs. Therefore, automatic segmentation of the liver in computed tomography (CT) images is a difficult task. Since tumors also have low contrast in surrounding tissues, and the shape, location, size, and number of tumors vary from patient to patient, accurate tumor segmentation takes a long time. In this study, we propose a method algorithm for automatically segmenting the liver and tumor for this purpose. As an advantage of setting the boundaries of the tumor, the liver and tumor were automatically segmented from the CT image using the 2D CoordConv DeepLab V3+ model using the CoordConv layer. For tumors, only cropped liver images were used to improve accuracy. Additionally, to increase the segmentation accuracy, augmentation, preprocess, loss function, and hyperparameter were used to find optimal values. We compared the CoordConv DeepLab v3+ model using the CoordConv layer and the DeepLab V3+ model without the CoordConv layer to determine whether they affected the segmentation accuracy. The data sets used included 131 hepatic tumor segmentation (LiTS) challenge data sets (100 train sets, 16 validation sets, and 15 test sets). Additional learned data were tested using 15 clinical data from Seoul St. Mary's Hospital. The evaluation was compared with the study results learned with a two-dimensional deep learning-based model. Dice values without the CoordConv layer achieved 0.965 ± 0.01 for liver segmentation and 0.925 ± 0.04 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.927 ± 0.02 for liver division and 0.903 ± 0.05 for tumor division. The dice values using the CoordConv layer achieved 0.989 ± 0.02 for liver segmentation and 0.937 ± 0.07 for tumor segmentation using the LiTS data set. Results from the clinical data set achieved 0.944 ± 0.02 for liver division and 0.916 ± 0.18 for tumor division. The use of CoordConv layers improves the segmentation accuracy. The highest of the most recently published values were 0.960 and 0.749 for liver and tumor division, respectively. However, better performance was achieved with 0.989 and 0.937 results for liver and tumor, which would have been used with the algorithm proposed in this study. The algorithm proposed in this study can play a useful role in treatment planning by improving contouring accuracy and reducing time when segmentation evaluation of liver and tumor is performed. And accurate identification of liver anatomy in medical imaging applications, such as surgical planning, as well as radiotherapy, which can leverage the findings of this study, can help clinical evaluation of the risks and benefits of liver intervention.

• Journal of Broadcast Engineering
• /
• v.25 no.5
• /
• pp.776-788
• /
• 2020

In this paper, a vehicle type recognition system using deep learning and a license plate recognition system are proposed. In the existing system, the number plate area extraction through image processing and the character recognition method using DNN were used. These systems have the problem of declining recognition rates as the environment changes. Therefore, the proposed system used the one-stage object detection method YOLO v3, focusing on real-time detection and decreasing accuracy due to environmental changes, enabling real-time vehicle type and license plate character recognition with one RGB camera. Training data consists of actual data for vehicle type recognition and license plate area detection, and synthetic data for license plate character recognition. The accuracy of each module was 96.39% for detection of car model, 99.94% for detection of license plates, and 79.06% for recognition of license plates. In addition, accuracy was measured using YOLO v3 tiny, a lightweight network of YOLO v3.

• Journal of Internet Computing and Services
• /
• v.18 no.5
• /
• pp.61-67
• /
• 2017

In this paper we introduce two experimental results from classification of Instagram images and some valuable lessons from them. We have tried some experiments for evaluating the competitive power of Convolutional Neural Network(CNN) in classification of real social network images such as Instagram images. We used AlexNet and ResNet, which showed the most outstanding capabilities in ImageNet Large Scale Visual Recognition Challenge(ILSVRC) 2012 and 2015, respectively. And we used 240 Instagram images and 12 pre-defined categories for classifying social network images. Also, we performed fine-tuning using Inception V3 model, and compared those results. In the results of four cases of AlexNet, ResNet, Inception V3 and fine-tuned Inception V3, the Top-1 error rates were 49.58%, 40.42%, 30.42%, and 5.00%. And the Top-5 error rates were 35.42%, 25.00%, 20.83%, and 0.00% respectively.