• Journal of the Korean Society of Laryngology, Phoniatrics and Logopedics
• /
• v.27 no.1
• /
• pp.21-24
• /
• 2016

An irritable larynx syndrome is characterized by a sudden episodic dyspnea and dysphonia that is difficult to diagnose, and patients are often treated unnecessarily and/or too much. A correct diagnosis can be made by monitoring the larynx closing in the reversed direction during inhalation and posterior chink with videolaryngoscopy and by measuring a decrease in air flow volume during inhalation with a lung function test. Patients can be effectively treated with thorough differential diagnosis. Medications targeting precipitating factors, physical therapy sessions to improve abnormal larynx movement, counseling to reduce patients'anxiety rising from dyspnea, and etc. can effectively alleviate symptoms.

• Journal of Power System Engineering
• /
• v.2 no.2
• /
• pp.73-80
• /
• 1998

The identification of drilling joint dynamics which consists of drilling and structural dynamics and the on-line time series detection of malfunction process is substantial not only for the investigation of the static and dynamic characteristics but also for the analytic realization of diagnostic and control systems in drilling. Therefore, We have discussed on the comparative assessment of two recursive time series modeling algorithms that can represent the drilling operation and detect the abnormal geometric behaviors in precision roundshape machining such as turning, drilling and boring in precision diemaking. For this purpose, simulation and experimental work were performed to show the malfunctional behaviors for drilling operation. For this purpose, a new two recursive approach (Recursive Extended Instrument Variable Method : REIVM, Recursive Least Square Method : RLSM) may be adopted for the on-line system identification and monitoring of a malfunction behavior of drilling process, such as chipping, wear, chatter and hole lobe waviness.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.2
• /
• pp.25-32
• /
• 2022

In this paper, we propose a pet monitoring system based on deep learning using an activity recognition device. The system consists of a pet's activity recognition device, a pet owner's smart device, and a server. Accelerometer and gyroscope data were collected from an Arduino-based activity recognition device, and the number of steps was calculated. The collected data is pre-processed and the amount of activity is measured by recognizing the activity in five types (sitting, standing, lying, walking, running) through a deep learning model that hybridizes CNN and LSTM. Finally, monitoring of changes in the activity, such as daily and weekly briefing charts, is provided on the pet owner's smart device. As a result of the performance evaluation, it was confirmed that specific activity recognition and activity measurement of pets were possible. Abnormal behavior detection of pets and expansion of health care services can be expected through data accumulation in the future.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.4
• /
• pp.9-18
• /
• 2015

In recent years, the number of applications embedded in the various devices such as a smart phone is getting larger. Due to the frequent changes of states in the execution environment, various malfunctions may occur. In order to handle the issue, this paper suggests an approach to detecting method-level failures in the legacy software systems. We can determine if the software executes the abnormal behavior based on the behavior model. However, when we apply the context-sensitive behavior model to the method-level, several problems happen such as false alarms and monitoring overhead. To tackle those issues, we propose CIBFD (Context-Insensitive Behavior Model-based Failure Detection) method. Through the case studies, we compare CIBFD method with the existing method. In addition, we analyze the effectiveness of the method for each application domains.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.3
• /
• pp.47-55
• /
• 2018

Recently, increasing number of urban ground subsidence occurrences has been identified. This situation is mainly due to the increased number of underground cavities. This study is intended to develop the method that prevents ground settlement caused by deteriorated or damaged sewers, which are the main cause of land subsidence. To that end, GPR exploration was conducted using CCTV monitoring of deteriorated sewer at the location with high settlement potential. Through such CCTV monitoring and GPR investigation, abnormal ground behavior was monitored at the site where sewer was damaged, joint was cracked and soil was deposited. According to site investigation in this study, evaluation method using correlation analysis of CCTV monitoring and GPR investigation results is expected to prevent ground settlement attributable to damaged sewer.

• Journal of the Korea Convergence Society
• /
• v.13 no.1
• /
• pp.387-398
• /
• 2022

This paper presents a system that remotely monitors lone seniors at home and promptly alarms caregivers to recommend appropriate medical care services upon detecting abnormal behavior and critical conditions such as collapsing, excessive coughing, degradation of sleep quality, fever, and unusual indoor moving lines. Our system offers contactless monitoring techniques based on heterogeneous IoT sensors and deep learning to minimize the disruption to lone senior's daily life. In addition to the design and implementation of the sensor data collection and analysis system, we share our experience in installation, deployment, configuration, maintenance of the system through the case study conducted on the actual lone seniors living in Seoul Metropolitan. Based on our research, we recommend further development directions to prepare for the nationwide expansion of our system.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.2
• /
• pp.161-168
• /
• 2019

Recently, video equipments such as CCTV, which is spreading rapidly, is being used as a means to monitor and cope with abnormal situations in almost governments, companies, and households. However, in most cases, since recognizing the abnormal situation is carried out by the monitoring person, the immediate response is difficult and is used only for post-analysis. In this paper, we present the results of the development of video surveillance system that automatically recognizing the abnormal situations and sending such events to the smartphone immediately using the latest deep learning technology. The proposed system extracts skeletons from the human objects in real time using Openpose library and then recognizes the human behaviors automatically using deep learning technology. To this end, we reconstruct Openpose library, which developed in the Caffe framework, on Darknet framework to improve real-time processing. We also verified the performance improvement through experiments. The system to be introduced in this paper has accurate and fast behavioral recognition performance and scalability, so it is expected that it can be used for video surveillance systems for various applications.

• Journal of Internet Computing and Services
• /
• v.24 no.6
• /
• pp.73-80
• /
• 2023

The recent steep increase in the minimum hourly wage has increased the burden of labor costs, and the share of unmanned stores is increasing in the aftermath of COVID-19. As a result, theft crimes targeting unmanned stores are also increasing, and the "Just Walk Out" system is introduced to prevent such thefts, and LiDAR sensors, weight sensors, etc. are used or manually checked through continuous CCTV monitoring. However, the more expensive sensors are used, the higher the initial cost of operating the store and the higher the cost in many ways, and CCTV verification is difficult for managers to monitor around the clock and is limited in use. In this paper, we would like to propose an AI image processing fusion algorithm that can solve these sensors or human-dependent parts and detect customers who perform abnormal behaviors such as theft at low costs that can be used in unmanned stores and provide cloud-based notifications. In addition, this paper verifies the accuracy of each algorithm based on behavior pattern data collected from unmanned stores through motion capture using mediapipe, object detection using YOLO, and fusion algorithm and proves the performance of the convergence algorithm through various scenario designs.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.27 no.5
• /
• pp.40-48
• /
• 2023

In this paper, a sensor-based monitoring system was established to analyze the long-term behavioral characteristics of the caisson quay wall, a representative structural type in port facilities. Data was collected over a period of approximately 10 months. Based on existing literature, anomalous behaviors of port facilities were classified, and a measurement system was selected to detect them. Monitoring systems were installed on-site to periodically collect data. The collected data was transmitted and stored on a server through LTE network. Considering the site conditions, inclinometers for measuring slope and crack meters for measuring spacing and settlement were installed. They were attached to two caissons for comparison between different caissons. The correlation among measured data, temperature, and tidal level was examined. The temperature dominated the spacing and settlement data. When the temperature changed by approximately 50 degrees, the spacing changed by 10 mm, the settlement by 2 mm, and the slope by 0.1 degrees. On the other hand, there was no clear relationship with tidal level, indicating a need for more in-depth analysis in the future. Based on the characteristics of these collected database, it will be possible to develop algorithms for detecting abnormal states in gravity-type quay walls. The acquisition and analysis of long-term data enable to evaluate the safety and usability of structures in the event of disasters and emergencies.

• Environmental Analysis Health and Toxicology
• /
• v.18 no.2
• /
• pp.145-153
• /
• 2003

The goal of this study is to develop a biomarker used in monitoring abnormal behaviors of Japanese medaka (Oryzias latipes) as a model organism caused by hazardous chemicals. Japanese medaka was treated by copper of appropriate sublethal concentrations after starvation for 48 hr. The untreated individuals showed common behavioral characteristics (i.e. , smooth and linear movements). Locomotive activity of the fish was monitored using an image processing and automatic data acquisition system. When treated with copper (100 ppb), the fish showed shaking patterns more frequently. As the concentration of copper increased to 1,000 ppb, activity decreated, and the fish showed an erratic movement. Fish were exposed to copper at various concentrations (0,100 and 1,000 ppb) for 24 hrs, and acetylcholine esterase (AChE) activity was observed. When fish were exposed to 1,000 ppb of copper, the body AChE activities appeared to decrease but the head AChE activities showed little change. Expressions of tyrosine hydroxylase (TH) protein in the different organs from both head (brain) and body (kidney) portions affected by the copper treatment were analyzed using immunohistochemical technique compared with control. Five organs of the fish (olfactory bulb, hyothalamus, optic lobe, pons and myelencephalon regions) showed a relatively strong TH protein expression in the control experiment. A differential expression of TH, however, was observed in the treatment (100 ppb and 1,000 ppb). The treatment (1,000 ppb) significantly suppressed TH protein production in the brain regions. In kidney, however, the same treatment caused little suppression compared with the control. Copper appeared to be less effective in suppression of TH than diazinon, a known TH suppressor. It was concluded that TH could be used at a potential biomarker to monitor the acute copper toxicity in Japanese medaka.