• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.07a
• /
• pp.57-58
• /
• 2022

Sleep apnea (SA) is a common chronic sleep disorder that disrupts breathing during sleep. Clinically, the standard for diagnosing SA involves nocturnal polysomnography (PSG). However, this requires expert human intervention and considerable time, which limits the availability of SA diagnoses in public health sectors. Therefore, ECG-based methods for SA detection have been proposed to automate the PSG procedure and reduce its discomfort. We propose a preprocessing method to convert the one-dimensional time series of ECG into two-dimensional images using the Gramian Angular Field (GAF) algorithm, extract temporal features, and use a two-dimensional convolutional neural network for classification. The results of this study demonstrated that the proposed method can perform SA detection with specificity, sensitivity, accuracy, and area under the curve (AUC) of 88.89%, 81.50%, 86.11%, and 0.85, respectively. Our experimental results show that SA is successfully classified by extracting preprocessing transforms with temporal features.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.387-396
• /
• 2020

Wearable biosensors have the potential to non-invasively and continuously monitor seniors' stress in their daily interaction with the urban environment, thereby enabling to address the stress and ultimately advance their outdoor mobility. However, current wearable biosensor-based stress detection methods have several drawbacks in field application due to their dependence on batch-learning algorithms. First, these methods train a single classifier, which might not account for multiple subjects' different physiological reactivity to stress. Second, they require a great deal of computational power to store and reuse all previous data for updating the signle classifier. To address this issue, we tested the feasibility of online multi-task learning (OMTL) algorithms to identify multiple seniors' stress from electrodermal activity (EDA) collected by a wristband-type biosensor in a daily trip setting. As a result, OMTL algorithms showed the higher test accuracy (75.7%, 76.2%, and 71.2%) than a batch-learning algorithm (64.8%). This finding demonstrates that the OMTL algorithms can strengthen the field applicability of the wearable biosensor-based stress detection, thereby contributing to better understanding the seniors' stress in the urban environment and ultimately advancing their mobility.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.791-802
• /
• 2023

The manual inspection of photovoltaic (PV) panels to meet the requirements of inspection work for large-scale PV power plants is challenging. We present a hot spot detection and positioning method to detect hot spots in batches and locate their latitudes and longitudes. First, a network based on the YOLOv3 architecture was utilized to identify hot spots. The innovation is to modify the RU_1 unit in the YOLOv3 model for hot spot detection in the far field of view and add a neural network residual unit for fusion. In addition, because of the misidentification problem in the infrared images of the solar PV panels, the DeepLab v3+ model was adopted to segment the PV panels to filter out the misidentification caused by bright spots on the ground. Finally, the latitude and longitude of the hot spot are calculated according to the geometric positioning method utilizing known information such as the drone's yaw angle, shooting height, and lens field-of-view. The experimental results indicate that the hot spot recognition rate accuracy is above 98%. When keeping the drone 25 m off the ground, the hot spot positioning error is at the decimeter level.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1714-1729
• /
• 2018

Change detection of remote sensing images is a profound challenge in the field of remote sensing image analysis. This paper proposes a novel change detection method for bitemporal remote sensing images based on feature fusion and fuzzy c-means (FCM). Different from the state-of-the-art methods that mainly utilize a single image feature for difference image construction, the proposed method investigates the fusion of multiple image features for the task. The subsequent problem is regarded as the difference image classification problem, where a modified fuzzy c-means approach is proposed to analyze the difference image. The proposed method has been validated on real bitemporal remote sensing data sets. Experimental results confirmed the effectiveness of the proposed method.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.6
• /
• pp.524-530
• /
• 2008

The spin valve tunneling magnetoresistance (SV-TMR) sensor performance is analyzed using Stoner-Wohlfarth model for the detection of eddy current signals in nondestructive testing applications. The SV-TMR response in terms of the applied AC magnetic field dominantly generates the second harmonic amplitude in hard axis direction. The second harmonic eddy current signal detection using SV-TMR sensor shows higher performance than that of the coil sensor at lower frequencies. The SV-TMR sensor with high sensitivity gives a good solution to improve the low frequency performance in comparison with the inductive coil sensors. Therefore, the low frequency eddy current techniques based on SV-TMR sensors are specially useful in the detection of hidden defects, and it can be applied to detect the deeply embedded flaws or discontinuities in the conductive materials.

• Journal of Korean Society of Water and Wastewater
• /
• v.19 no.1
• /
• pp.8-15
• /
• 2005

Field measurement data on water leakage are not readily available and it causes inaccurate assessment of water demand and poor supply planning. In this study, the procedure for leakage detection and unaccounted water calculation is proposed and applied to a city. The city has suffered from the significant amount of leak water and the financial loss as a result. Measurements were made for pressure and flow at 18 locations before and after the repair. Repair of the leakage increased pressure up to $2.0kgf/cm^2$ and saved 17.1% of water supply from distribution reservoirs. Monetary value of annual water savings for the entire city amounts to 1 billion won. It is believed that leakage detection and data analysis conducted in this study will contribute to the change of current practice and to the establishment of better water supply management system.

• 한국HCI학회:학술대회논문집
• /
• 2009.02a
• /
• pp.146-149
• /
• 2009

Face detection and recognition in real-time video constitutes one of the recent topics in the field of computer vision. In this paper, we propose face detection and tracking algorithm using the skin color and haar-like feature in real-time video sequence. The proposed algorithm further includes color space to enhance the result using haar-like feature and skin color. Experiment results reveal the real-time video processing speed and improvement in the rate of tracking.

• Proceedings of KOSOMES biannual meeting
• /
• 2006.05a
• /
• pp.41-45
• /
• 2006

From the 1978 Seasat synthetic aperture radar(SAR) to present systems, spaceborne SAR has demonstrated the capability to image the Earth's ocean and land features over broad areas, day and night, and under most weather conditions. The application of SAR for surveillance of commercial fishing grounds can did in the detection of illegal fishing activities and provides more efficient use cf limited aircraft or patron craft resources. In the area of vessel traffic monitoring for commercial vessels, Vessel Traffic Service (VTS) which uses the ground-based radar system has some difficulties in detecting moving ships due to the limited detection range cf about 10 miles. This paper introduces the field testing results of ship detection by RADARSAT SAR imagery, and proposes a new approach for a Vessel Monitoring System(VMS), including VTS, and SAR combination service.

• Journal of the Korean Society for Railway
• /
• v.7 no.2
• /
• pp.71-76
• /
• 2004

In this paper, we propose a pilot study to deploy the Railway Conflict Detection and Resolution System(RCDRS) in the context of Korean Railway(KORAIL). KORAIL plans to deploy in near future RCDRS, which is a decision support module placed on the top level of the Railway Traffic Management System(RTMS). This study entails the review of the state-of-art researches and projects in the field of the railway traffic management, as well as the analysis of the traffic characteristics of the major railroad lines in KORAIL. The analysis provides a basis to choose a solution approach for the railway conflict detection and resolution problem that each individual line faces. This study plays a role as a pilot study for a full systematic approach, in which interactions between lines require further advanced analysis to take the entire KORAIL lines into consideration rather than a myopic approach.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.32 no.3
• /
• pp.291-295
• /
• 2012

In the industrial field, real-time monitoring system like a fault early detection is very important. For this, the infrared thermography technique as a new diagnosis method is proposed. This study is focused on the damage detection and temperature characteristic analysis of ball bearing using the non-destructive infrared thermography method. In this paper, thermal image and temperature data were measured by a Cedip Silver 450 M infrared camera. Based on the results, the temperature characteristics under the conditions of normal, loss lubrication, damage, dynamic loading, and damage under loading were analyzed. It was confirmed that the infrared technique is very useful for the detection of the bearing damage.