• Journal of Korea Multimedia Society
• /
• v.23 no.12
• /
• pp.1464-1475
• /
• 2020

Due to the spread of COVID-19, the online lecture has become more prevalent. However, it was found that a lot of students and professors are experiencing lack of communication. This study is therefore designed to improve interactive communication between professors and students in real-time online lectures. To do so, we explore deep learning approaches for automatic recognition of students' facial expressions and classification of their understanding into 3 classes (Understand / Neutral / Not Understand). We use 'BlazeFace' model for face detection and 'ResNet-GRU' model for facial expression recognition (FER). We name this entire process 'Degree of Understanding (DoU)' algorithm. DoU algorithm can analyze a multitude of students collectively and present the result in visualized statistics. To our knowledge, this study has great significance in that this is the first study offers the statistics of understanding in lectures using FER. As a result, the algorithm achieved rapid speed of 0.098sec/frame with high accuracy of 94.3% in CPU environment, demonstrating the potential to be applied to real-time online lectures. DoU Algorithm can be extended to various fields where facial expressions play important roles in communications such as interactions with hearing impaired people.

• Fisheries and Aquatic Sciences
• /
• v.25 no.3
• /
• pp.151-157
• /
• 2022

Various approaches have been applied to transform aquaculture from a manual, labour-intensive industry to one dependent on automation technologies in the era of the fourth industrial revolution. Technologies associated with the monitoring of physical condition have successfully been applied in most aquafarm facilities; however, real-time biological monitoring systems that can observe fish condition and behaviour are still required. In this study, we used a video recorder placed on top of a fish tank to observe the swimming patterns of rock bream (Oplegnathus fasciatus), first one fish alone and then a group of five fish. Rock bream in the video samples were successfully identified using the you-only-look-once v3 algorithm, which is based on the Darknet-53 convolutional neural network. In addition to recordings of swimming behaviour under normal conditions, the swimming patterns of fish under abnormal conditions were recorded on adding an anaesthetic or lowering the salinity. The abnormal conditions led to changes in the velocity of movement (3.8 ± 0.6 cm/s) involving an initial rapid increase in speed (up to 16.5 ± 3.0 cm/s, upon 2-phenoxyethanol treatment) before the fish stopped moving, as well as changing from swimming upright to dying lying on their sides. Machine learning was applied to datasets consisting of normal or abnormal behaviour patterns, to evaluate the fish behaviour. The proposed algorithm showed a high accuracy (98.1%) in discriminating normal and abnormal rock bream behaviour. We conclude that artificial intelligence-based detection of abnormal behaviour can be applied to develop an automatic bio-management system for use in the aquaculture industry.

• Smart Structures and Systems
• /
• v.31 no.4
• /
• pp.365-381
• /
• 2023

The existing vision-based techniques for inspection and condition assessment of civil infrastructure are mostly manual and consequently time-consuming, expensive, subjective, and risky. As a viable alternative, researchers in the past resorted to deep learning-based autonomous damage detection algorithms for expedited post-disaster reconnaissance of structures. Although a number of automatic damage detection algorithms have been proposed, the scarcity of labeled training data remains a major concern. To address this issue, this study proposed a semi-supervised learning (SSL) framework based on consistency regularization and cross-supervision. Image data from post-earthquake reconnaissance, that contains cracks, spalling, and exposed rebars are used to evaluate the proposed solution. Experiments are carried out under different data partition protocols, and it is shown that the proposed SSL method can make use of unlabeled images to enhance the segmentation performance when limited amount of ground truth labels are provided. This study also proposes DeepLab-AASPP and modified versions of U-Net++ based on channel-wise attention mechanism to better segment the components and damage areas from images of reinforced concrete buildings. The channel-wise attention mechanism can effectively improve the performance of the network by dynamically scaling the feature maps so that the networks can focus on more informative feature maps in the concatenation layer. The proposed DeepLab-AASPP achieves the best performance on component segmentation and damage state segmentation tasks with mIoU scores of 0.9850 and 0.7032, respectively. For crack, spalling, and rebar segmentation tasks, modified U-Net++ obtains the best performance with Igou scores (excluding the background pixels) of 0.5449, 0.9375, and 0.5018, respectively. The proposed architectures win the second place in IC-SHM2021 competition in all five tasks of Project 2.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.62-69
• /
• 2022

An electrocardiogram (ECG) is one of the most important biosignals, and in particular, continuous ECG monitoring is very important in patients with arrhythmia. There are many different types of arrhythmia (sinus node, sinus tachycardia, atrial premature beat (APB), and ventricular fibrillation) depending on the cause, and continuous ECG monitoring during daily life is very important for early diagnosis of arrhythmias and setting treatment directions. The ECG signal of arrhythmia patients is very unstable, and it is difficult to detect the R-peak point, which is a key feature for automatic arrhythmias detection. In this study, we develped a continuous measuring Holter ECG monitoring device and software for analysis and confirmed the utility of R-peak of the ECG signal with MIT-BIH arrhythmia database. In future studies, it needs the validation of algorithms and clinical data for morphological classification and prediction of arrhythmias due to various etiologies.

• Journal of Korean Society for Quality Management
• /
• v.51 no.2
• /
• pp.283-296
• /
• 2023

Purpose: The purpose of this study is to actually implement and verify whether welding defects can be detected in real time by utilizing deep learning AI solutions in the welding process of electric vehicle hairpin winding motors. Methods: AI's function and technological elements using synthetic neural network were applied to existing electric vehicle hairpin winding motor laser welding process by making special hardware for detecting electric vehicle hairpin motor laser welding defect. Results: As a result of the test applied to the welding process of the electric vehicle hairpin winding motor, it was confirmed that defects in the welding part were detected in real time. The accuracy of detection of welds was achieved at 0.99 based on mAP@95, and the accuracy of detection of defective parts was 1.18 based on FB-Score 1.5, which fell short of the target, so it will be supplemented by introducing additional lighting and camera settings and enhancement techniques in the future. Conclusion: This study is significant in that it improves the welding quality of hairpin winding motors of electric vehicles by applying domestic artificial intelligence solutions to laser welding operations of hairpin winding motors of electric vehicles. Defects of a manufacturing line can be corrected immediately through automatic welding inspection after laser welding of an electric vehicle hairpin winding motor, thus reducing waste throughput caused by welding failure in the final stage, reducing input costs and increasing product production.

• Journal of The Geomorphological Association of Korea
• /
• v.26 no.2
• /
• pp.69-84
• /
• 2019

The purpose of this study is to extract lineaments in the southeastern part of the Gaeum Fault System, and to understand their characteristics and a relationship between them and fault activation. The lineaments were extracted using a multi-layered analysis based on a digital elevation model (5 m resolution), aerial photos, and satellite images. First-grade lineaments inferred as an high-activity along them were classified based on the displacement of the Quaternary deposits and the distribution of fault-related landforms. The results of classifying the first-grade lineaments were verified by fieldwork and electrical resistivity survey. In the study area of 510 km², a total of 222 lineaments was identified, and their total length was 333.4 km. Six grade lineaments were identified, and their total length was 11.2 km. The lineaments showed high-density distribution in the region along the Geumcheon, Gaeum, Ubo fault, and a boundary of the Hwasan cauldron consisting the Gaeum Fault System. They generally have WNW-ESE trend, which is the same direction with the strike of Gaeum Fault System. Electrical resistivity survey was conducted on eight survey lines crossing the first-grade lineament. A low-resistivity zone, which is assumed to be a fault damage zone, has been identified across almost all survey lines (except for only one survey line). The visual (naked eyes) detecting of the lineament was evaluated to be less objectivity than the automatic extraction using the algorithm. However, the results of electrical resistivity survey showed that first-grade lineament extracted by visual detecting was 83% reliable for inferred fault detection. These results showed that objective visual detection results can be derived from multi-layered analysis based on tectonic geomorphology.

• Journal of Biomedical Engineering Research
• /
• v.44 no.5
• /
• pp.346-353
• /
• 2023

In this paper, we propose an innovative approach that leverages deep learning to find optimal reference points for achieving precise tooth segmentation in three-dimensional tooth point cloud data. A dataset consisting of 350 aligned maxillary and mandibular cloud data was used as input, and both end coordinates of individual teeth were used as correct answers. A two-dimensional image was created by projecting the rendered point cloud data along the Z-axis, where an image of individual teeth was created using an object detection algorithm. The proposed algorithm is designed by adding various modules to the Unet model that allow effective learning of a narrow range, and detects both end points of the tooth using the generated tooth image. In the evaluation using DSC, Euclid distance, and MAE as indicators, we achieved superior performance compared to other Unet-based models. In future research, we will develop an algorithm to find the reference point of the point cloud by back-projecting the reference point detected in the image in three dimensions, and based on this, we will develop an algorithm to divide the teeth individually in the point cloud through image processing techniques.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.637-654
• /
• 2023

In recent years, the number of users has been increasing with the rapid development of earth observation satellites. In response, the Committee on Earth Observation Satellites (CEOS) has been striving to provide user-friendly satellite images by introducing the concept of Analysis Ready Data (ARD) and defining its requirements as CEOS ARD for Land (CARD4L). In ARD, a mask called an Unusable Data Mask (UDM), identifying unnecessary pixels for land analysis, should be provided with a satellite image. UDMs include clouds, cloud shadows, terrain shadows, etc. Terrain shadows are generated in mountainous terrain with large terrain relief, and these areas cause errors in analysis due to their low radiation intensity. previous research on terrain shadow detection focused on detecting terrain shadow pixels to correct terrain shadows. However, this should be replaced by the terrain correction method. Therefore, there is a need to expand the purpose of terrain shadow detection. In this study, to utilize CAS500-4 for forest and agriculture analysis, we extended the scope of the terrain shadow detection to shaded areas. This paper aims to analyze the potential for terrain shadow detection to make a terrain shadow mask for South and North Korea. To detect terrain shadows, we used a Hill-shade algorithm that utilizes the position of the sun and a surface's derivatives, such as slope and aspect. Using RapidEye images with a spatial resolution of 5 meters and Sentinel-2 images with a spatial resolution of 10 meters over the Korean Peninsula, the optimal threshold for shadow determination was confirmed by comparing them with the ground truth. The optimal threshold was used to perform terrain shadow detection, and the results were analyzed. As a qualitative result, it was confirmed that the shape was similar to the ground truth as a whole. In addition, it was confirmed that most of the F1 scores were between 0.8 and 0.94 for all images tested. Based on the results of this study, it was confirmed that automatic terrain shadow detection was well performed throughout the Korean Peninsula.

• Journal of the Institute of Convergence Signal Processing
• /
• v.7 no.3
• /
• pp.116-121
• /
• 2006

In this paper, we propose the dimension reduction method of multi-dimension speech feature vector for real-time adaptation procedure in various noisy environments. This method which reduces dimensions non-linearly to map the likelihood of speech feature vector and noise feature vector. The LRT(Likelihood Ratio Test) is used for classifying speech and non-speech. The results of implementation are similar to multi-dimensional speech feature vector. The results of speech recognition implementation of detected speech data are also similar to multi-dimensional(10-order dimensional MFCC(Mel-Frequency Cepstral Coefficient)) speech feature vector.

• Proceedings of the KSR Conference
• /
• 2011.05a
• /
• pp.1009-1013
• /
• 2011

Seoul Metro Line 1 to 4 guests per day to 4.5 million people have been using the subway. This is close to the city population, 57 percent of people use the subway and found that 57 percent of people use the subway and found that this is close to the city population. Motor vehicle indoor air quality, especially of the major factors affecting is passenger's clothing, cosmetics, adhesives and formaldehyde by the action and so are able to keep. Enclosure 30ppm formaldehyde during prolonged exposure at concentrations above the nose, bronchial cough and a burning can cause symptoms. It is necessary to introduce an appropriate ventilation system. 1-4 Line Press in 2008, leaving the subway, and normally the train measured in room air quality. Measurements in 2005, $19.3{\sim}83{\mu}g/m^3$, 2008 Year ND ~ $61.7{\mu}g/m^3$ is. When congestion(rush hour) to temporarily increase the formaldehyde can result in a higher number. Automatic detection of formaldehyde and improve ventilation to a practical system, and it is necessary to chatneun. In research since 2006, Removal of formaldehyde were analyzed for the study. the passengers on the effects of formaldehyde in rush hour, the plan for increasing the ventilation through the analysis of various factors, such as electric vehicle practical ways to improve air quality have been studied.