• Journal of the Society of Disaster Information
• /
• v.19 no.3
• /
• pp.498-509
• /
• 2023

Purpose: This paper proposes a method detecting the falling of a maintenance worker in the underground utility tunnel, by applying deep learning techniques using CCTV video, and evaluates the applicability of the proposed method to the worker monitoring of the utility tunnel. Method: Each rule was designed to detect the falling of a maintenance worker by using the inference results from pre-trained YOLOv5 and OpenPose models, respectively. The rules were then integrally applied to detect worker falls within the utility tunnel. Result: Although the worker presence and falling were detected by the proposed model, the inference results were dependent on both the distance between the worker and CCTV and the falling direction of the worker. Additionally, the falling detection system using YOLOv5 shows superior performance, due to its lower dependence on distance and fall direction, compared to the OpenPose-based. Consequently, results from the fall detection using the integrated dual deep learning model were dependent on the YOLOv5 detection performance. Conclusion: The proposed hybrid model shows detecting an abnormal worker in the utility tunnel but the improvement of the model was meaningless compared to the single model based YOLOv5 due to severe differences in detection performance between each deep learning model

• Journal of Korean Society of societal Security
• /
• v.1 no.4
• /
• pp.73-81
• /
• 2008

Electromagnetic induction surveys are one of the useful methods to detect the location and buried depth of underground utilities by measuring horizontal and vertical magnetic fields. It can effectively detects single buried utility with the accuracy of within 20 cm. However when another utility is buried near to target one, the accuracy of utility location considerably decreases due to the distortion of magnetic fields caused from adjacent utility. This study shows the ways to verify the location and buried depth of target utility when magnetic fields does not show symmetric distribution due to adjacent another utility. Using Bluetooth wireless communication tools, we developed the way to records measured magnetic fields to handheld PDA. We investigated the criteria for minimum distance of two adjacent utilities to separate the individual responses through field model test.

• Journal of Korean Society of societal Security
• /
• v.3 no.1
• /
• pp.25-32
• /
• 2010

Detecting rebars in side the concrete structures is one of the important steps in assessing condition of the structure. In order to determine the detection capability of locating rebars inside the concrete, two types of equipments, which use radar system and electromagnetic system each, were tested. Four concrete specimens which have the dimensions of $1,000mm(length){\times}300mm(width)$ with different thickness and diameter of steel bars were applied. A series of testing was achieved after drying in air for 90 days, immersed in water for 3, 24, 48 hour and 28 day. From the experimental outcome, it is shown that error is increased as the diameter of rebar enlarge in case of electromagnetic method. In case of radar method, the detection of embedded rebars in deep is good in the view of reliability. As moisture content increase from 3.6% to 5.5%, the relative permittivity of concrete test specimens show tendency to increase, too. Therefore, it is shown that moisture content is one of the major contributing factors to determine the relative permittivity. And the relative permittivity regression equation is suggested.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.6
• /
• pp.605-610
• /
• 2016

The ELCB(: Earth Leakage Circuit Breaker) is the only way being used to prevent accidents from happening caused by electrical disaster. However, the existing ELCB has a limit to prevent damages to life and property due to a electric fire and a human body electric shock caused by the resistive leakage current, because of detecting the total leakage current in the block range of 15mA~30mA. It also has problems such as reduced productivity and reliability due to malfunctions by capacitive leakage currents. In this study, we have implemented the algorithm for the resistive leakage current detection technique and developed the resistive leakage current detection module based on a MSP430 processor, 16bit signal processor and this module can be operated in a desired block threshold within 0.03 seconds as specified in KS C 4613.

• Journal of Korean Society on Water Environment
• /
• v.40 no.4
• /
• pp.168-178
• /
• 2024

Wastewater treatment plants are constantly exposed to influent wastewater that is constantly changing. This poses a major challenge to the operation of the plants. It is crucial to have a rapid and accurate measurement of the influent concentrations of wastewater in order to maintain and optimize treatment performance, as well as to develop energy-saving strategies. While laboratory measurements provide the highest accuracy in determining influent water quality, they are inevitably time-consuming procedures. In order to cope with the ongoing disturbances from wastewater influent, absorption-based optical measuring instruments have been developed. These instruments can detect the influent water quality in a short amount of time, improving their practicality and reliability. However, when these optical measuring instruments malfunction, the accuracy of the measured values decreases, leading to unreasonable operation of the treatment plant. This paper proposes a method for detecting anomalies in optical water quality measurement devices. The Harmony Search algorithm is used to validate the measured water quality values and detect abnormalities such as contamination or physical anomalies in the measurement apparatus. To assess the performance of the developed algorithm in detecting anomalies, validation was conducted by installing it in a field-scale wastewater treatment plant. The results consistently showed that the developed fault detection method for optical water quality measurements equipment provided acceptable results for normal, temporary abnormal, and long-term abnormal conditions.

• Journal of the Korean GEO-environmental Society
• /
• v.17 no.9
• /
• pp.47-52
• /
• 2016

Unusual extreme weather events, which exceed a safe design capacity of the infrastructure, increase the frequency of natural disasters and has also been enlarged damage scale. Aging buildings and rapid urban progress act as weighting factors for the new composite disasters. Technological advances support detecting pre-disaster risk, real-time data analysis, and rapid response to the disaster site, but it is insufficient that emergency relief for buried alive must take advantage of the proven technologies through field tests. This study aims to evaluate directional drilling performance through underground soils and the reinforced concrete structure for primary lifeline installation in order to quickly provide relief supplies for buried alive when urban structures collapse.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.87-95
• /
• 2020

Purpose: In this paper, we propose an algorithm for detecting respiratory rate and heart beat of a driver of car by exploiting Doppler radar, and verifying the feasibility of the study through experiments. Method: In this paper, we propose a weighted peak detection technique using peak frequency values. The tests are performed in stop-state and driving-state, and the experiment result is analyzed by two proposed algorithms. Result: The results showed more than 95% and 96% accuracy of respiratory and heart rate, respectively. It also showed more than 72% and 84% accuracy of those even for driving experiments. Conclusion: The proposed detection scheme for vital signs can be used for the safety of the driver as well as for prevention of a large size of car accidents.

• Journal of the Society of Disaster Information
• /
• v.16 no.1
• /
• pp.144-154
• /
• 2020

Purpose: This paper is a fundamental study on the applicability of the smart bolt developed for monitoring system to detect the leakage of water supply valve. Method: A leak detection experiments were conducted using the smart bolt having embedded strain sensors and accelerometer. The smart bolt used in study meets the allowable criteria of torque and tensile stress for water supply system, and it can be applied to a joint of the water supply valve by behaving well within the allowable limits. Result: As a result of the simulated leak tests, a leak signal at the valve leak point was detected in a band of 60Hz, and the main pipe leaking point was observed to produce a leak signal having much higher frequency than that of the valve leak point. This seems to result in a total coupled vibration under unconfined conditions of the pipes. Conclusion: The smart bolts appeared applicable to detecting a leaking signal from the water supply valve.

• Journal of the Society of Disaster Information
• /
• v.5 no.1
• /
• pp.48-62
• /
• 2009

Bodyguards always perform their duty with psychological burdens in their mind, not only because security situations are developed in various forms dependent on the surrounding environments or circumstances, but because bodyguards only take follow-up actions while the criminal decides time, place, and style of every attack. Thus, in the security situation, it is not uncommon for bodyguards to experience muscle rigidity, uncontrollable emotional elevation, difficulty in concentration, negative perception, frustration and enervation, which are caused by continuous physical/mental burdens, stimulations by various interpersonal behaviors or minute environmental stimulants. In conclusion, the result of performing security duties is related in the first place with the degree of the bodyguard's potential, in the second place with the degree of training and efficiency. And the result can also be changed by the way they control their negative psychological state of the moment when they carry out the skills they acquired. Maximizing the performance of the bodyguards by helping them overcome these psychological factors may be facilitated by detecting their psychological factors, understanding the causes, and training them in applying appropriate measures for overcoming these factors. When these measures are applied, the positive perception is indispensable that duties of protecting clients can be carried out successfully. No single measure can be declared to be more effective than the other because the effect of each measure is expressed differently by the individual characteristics of the bodyguards. However, it is important to select and apply the measures most appropriate to the bodyguard. Besides, they should devote themselves to the training with persistence because efficient implement of the measures for overcoming psychological factors takes a lot of time.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.364-373
• /
• 2022

Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.