• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.39 no.3
• /
• pp.347-352
• /
• 2015

Time domain reflectometry (TDR) is widely used for wire failure detection. It transmits a pulse that is reflected at the boundaries of different characteristic impedances. By analyzing the reflected signal, TDR makes it possible to locate the failure. In this study, TDR was used to detect the water leakage at a pipe joint. A wire attached to the pipe surface was soaked by water when a leak occurred, which affected the characteristic impedance of the wet part, resulting in a change in the reflected signal. To infer the leakage from the TDR signal, we first developed a finite difference time domain-based forward model that provided the output of the TDR signal given the configuration of the transmission line. Then, by solving the inverse problem, the locations of the leaks were found.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.10
• /
• pp.3729-3749
• /
• 2021

At present, deep convolution network-based salient object detection (SOD) has achieved impressive performance. However, it is still a challenging problem to make full use of the multi-scale information of the extracted features and which appropriate feature fusion method is adopted to process feature mapping. In this paper, we propose a new adjacency auxiliary network (AANet) based on multi-scale feature fusion for SOD. Firstly, we design the parallel connection feature enhancement module (PFEM) for each layer of feature extraction, which improves the feature density by connecting different dilated convolution branches in parallel, and add channel attention flow to fully extract the context information of features. Then the adjacent layer features with close degree of abstraction but different characteristic properties are fused through the adjacent auxiliary module (AAM) to eliminate the ambiguity and noise of the features. Besides, in order to refine the features effectively to get more accurate object boundaries, we design adjacency decoder (AAM_D) based on adjacency auxiliary module (AAM), which concatenates the features of adjacent layers, extracts their spatial attention, and then combines them with the output of AAM. The outputs of AAM_D features with semantic information and spatial detail obtained from each feature are used as salient prediction maps for multi-level feature joint supervising. Experiment results on six benchmark SOD datasets demonstrate that the proposed method outperforms similar previous methods.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.10
• /
• pp.1-9
• /
• 2022

In this paper, we propose the Deep Learning-Based Companion Animal Abnormal Behavior Detection Service, which using video and sensor data. Due to the recent increase in households with companion animals, the pet tech industry with artificial intelligence is growing in the existing food and medical-oriented companion animal market. In this study, companion animal behavior was classified and abnormal behavior was detected based on a deep learning model using various data for health management of companion animals through artificial intelligence. Video data and sensor data of companion animals are collected using CCTV and the manufactured pet wearable device, and used as input data for the model. Image data was processed by combining the YOLO(You Only Look Once) model and DeepLabCut for extracting joint coordinates to detect companion animal objects for behavior classification. Also, in order to process sensor data, GAT(Graph Attention Network), which can identify the correlation and characteristics of each sensor, was used.

• Journal of The Korean Society of Grassland and Forage Science
• /
• v.3 no.2
• /
• pp.100-111
• /
• 1983

The research results reported herein had the objectives to understand and analyze the present problems of saemaeul woodland joint cattle grazing system in Kang Won Do and to take steps of improvement. The study results on actual management conditions, problems analyzed and improvement plan of total 208 joint cattle grazing area which was established 105 area in 1981 and 103 area in 1982 were summarized as follows: 1. the effectiveness of joint cattle grazing projects 1) Average daily weight gain of cattle during joint cattle grazing period was 0.4kg, showing higher daily than the conventional feeding of 0.33kg. 2) Increase of total farm income over the conventional feeding system were \1,031,357,320 during the grazing period from May to October in 1982 by adapting the 208 joint cattle grazing system, of which effectiveness of weight gain was \293,075,300 and labor saving was \543,838,750. 3) According to the results of questionaire investigation from 208 joint cattle grazing area, effectiveness of joint cattle grazing system over the conventional system were (1) labor saving, (2) feed cost saving, (3) reduced diseases, (4) increase of number of feeding, (5) inspiration of joint endeavor, (6) effect of more gain, (7) easiness of feeding and feed cost savings. 2. Problems of joint cattle grazing system. 1) Shortages of grass were a problem at second year of joint cattle grazing period due to the low regrowth rate of wild grass. 2) Proper land for woodland joint cattle grazing is belonging to land of Government ownership and it is very hard to get the permission from office of forestry for cattle grazing purpose. 3) It is also difficult to find a proper time of breeding in grazing area by the difficulty of estrus detection. 4) There are a difficulty to give a proper vaccination and medical examination for the grazing cattle. 3. Improvement plans for woodland joint cattle grazing projects. 1) Obtain sufficient roughages by hoof cultivation and oversowing pasture from the second year of joint cattle grazing period. 2) In order to increase the beef production and to use for a calf production area, Government should arrange that all proper grazing land of Government owned in Kang Won Do convert into woodland joint cattle grazing area. 3) Make a good reproductive record by mixed grazing with a excellent breeding cow in a remote area. And carry out the collective artificial insemination with synchronous puberty induced by injection of puberty stimulation hormone. 4) Make a preventive injection for blackleg, twice medication of fasciola hepatica in a year, and spray and medication of tick insecticide. 4. A policy towards upbringing of woodland joint cattle grazing area. 1) Government should thoroughly investigate about a proper land for woodland joint cattle grazing from all forests. 2) When the area is suitable for the woodland joint cattle grazing, though it is national forest or restricted area, government should make it possible to establish a grazing area. 3) On the proper land foe joint cattle grazing in the remote place, Government should support for the road construction and electric fence equipments by using of national funds. 4) There should be an administrative consideration for well promotion of the project that make woodland joint cattle grazing suitable to the characteristics of Kang Won Do. 5) In order to improve the reproduction record, Government should reform the insufficiency of artificial insemination in the joint cattle grazing area. 6) In order to maintain a proper price of cow, Government should carry out the price plan. 7) When there is any request for grassland formation in the woodland joint cattle grazing area, Government should permit it with preference.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.387-392
• /
• 2019

A technique was researched to detect bolt looseness using a transfer impedance technique (the dual piezoelectric material technique) for monitoring the structural health of a bolt joint. In order to use the single piezoelectric material technique, an expensive impedance analyzer should be used. However, in the transfer impedance technique, low-cost fault detection can be performed using a general function generator and a digital multimeter. A steel plate frame test specimen composed of bolt joints was fabricated, and the tightening torques of the bolts were loosened step by step. By using the transfer impedance method, the damage index was obtained. It was found that the presence of faults could be reasonably estimated using the damage index, which increased with the degree of bolt looseness. An experiment was performed on the same specimen using the single piezoelectric material technique, and the results showed a similar tendency. It could be possible to estimate the damage of a bolt joint at low cost by eliminating the expensive impedance analyzer. This method could be used effectively for structural health monitoring after carrying out a study to estimate the fault location and severity.

• Ocean Systems Engineering
• /
• v.2 no.2
• /
• pp.137-145
• /
• 2012

Recent developments in underwater image recognition methods have received large attention by the ocean engineering researchers. In this paper, an improved bi-dimensional empirical mode decomposition (BEMD) approach is employed to decompose the given underwater image into intrinsic mode functions (IMFs) and residual. We developed a joint algorithm based on BEMD and Canny operator to extract multi-pixel edge features at multiple scales in IMFs sub-images. So the multiple pixel edge extraction is an advantage of our approach; the other contribution of this method is the realization of the bi-dimensional sifting process, which is realized utilizing regional-based operators to detect local extreme points and constructing radial basis function for curve surface interpolation. The performance of the multi-pixel edge extraction algorithm for processing underwater image is demonstrated in the contrast experiment with both the proposed method and the phase congruency edge detection.

• Structural Monitoring and Maintenance
• /
• v.3 no.4
• /
• pp.395-406
• /
• 2016

Modal parameter identification has received much attention recently for their usefulness in earthquake engineering, damage detection and structural health monitoring. The identification method based on Matrix Pencil technique is adopted in this paper to identify structural modal parameters, such as natural frequencies, damping ratios and modal shapes using impulse vibration responses. This method can also be applied to dynamic responses induced by stationary and white-noise inputs since the auto- and cross-correlation function of the two outputs has the same form as the impulse response dynamic functions. Matrix Pencil method is very robust to noise contained in the measurement data. It has a lower variance of estimates of the parameters of interest than the Polynomial Method, and is also computationally more efficient. The numerical simulation results show that this technique can identify modal parameters accurately even if the noise level is high.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.300-301
• /
• 2016

본 논문에서는 동영상에서 제한된 종류의 동적 객체를 자동적으로 검출하여 추적하는 기법을 제안한다. 제안하는 기법은 객체 검출 기법[1]과 객체 추적 기법[2]의 협업을 통해 이를 수행한다. 검출기는 매 장면마다 객체들을 검출하고 이 중 높은 신뢰도의 객체에 대해 추적을 시작한다. 추적기는 이전 장면에서 학습된 분류기에 기반하여 객체를 추적한다. 추적 결과와 겹치는 검출 결과를 분석하여 현재 장면에서 객체의 정확한 위치와 모양을 추정한다. 겹치는 검출 결과가 없을 때는 검출기로 부터 추적 결과의 신뢰도를 측정하고 문턱값에 따라 추적을 계속 진행하거나 종료한다. 실험 결과를 통해 제안하는 기법이 기존 검출 기법에 비해 우수한 검출 성능을 보임을 확인한다.

• Journal of Food Hygiene and Safety
• /
• v.12 no.2
• /
• pp.160-174
• /
• 1997

Progress in commercialization of the irradiation process, greater international trade in irradiated food, differing regulations relating to use of the technology in many countries, and consumer demand for clear labeling of irradiated food highlighted the need for tests that could be applied to the food itself. Scientists have had to focus on identifying and isolating the minute changes caused in the component food molecules by the process. A number of investigators have reviewed the changes occurring in food after irradiation, detecting and measuring the effects of irradiation. The Joint FAO/IAEA Division of Nuclear Techniques in Food and Agriculture organised a coordinated program on analytical detection methods in irradiation treatment of food (ADMIT) which promoted cooperation in this area and sponsored collaborative testing of some of the most promising methods.