• Geomechanics and Engineering
• /
• v.33 no.2
• /
• pp.203-209
• /
• 2023

One major advantage of ground penetrating radar (GPR) over other field test methods is its ability to obtain subsurface images of roads in an efficient and non-intrusive manner. Not only can the strata of pavement structure be retrieved from the GPR scan images, but also various irregularities, such as cracks and internal cavities. This article introduces a deep learning-based approach, focusing on detecting subsurface cracks by recognizing their distinctive hyperbolic signatures in the GPR scan images. Given the limited road sections that contain target features, two data augmentation methods, i.e., feature insertion and generation, are implemented, resulting in 9,174 GPR scan images. One of the most popular real-time object detection models, You Only Learn One Representation (YOLOR), is trained for detecting the target features for two types of subsurface cracks: bottom cracks and full cracks from the GPR scan images. The former represents partial cracks initiated from the bottom of the asphalt layer or base layers, while the latter includes extended cracks that penetrate these layers. Our experiments show the test average precisions of 0.769, 0.803 and 0.735 for all cracks, bottom cracks, and full cracks, respectively. This demonstrates the practicality of deep learning-based methods in detecting subsurface cracks from GPR scan images.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.18 no.4
• /
• pp.112-117
• /
• 2004

This paper describes the analysis of the UHF signal characteristics due to the partial discharge sources which can exist in a GIS. For the experiment, a model GIS was made and 5 types of discharge source were created as follows; corona discharge, surface discharge, void discharge, discharge due to free particle, discharge from floating electrode. The frequency spectra and the phase characteristics of UHF signals were induced by UHF signal analysis. The results were quantified to systematically adapt to analyze the PD sources in the GIS and utilized as algorithm data based on the neural network for Back-Propagation Algorithm with a multi-layer structure. The perception rate of the constructed algorithm showed approximately 94[%] and 82[%] in learning and testing data, respectively.

• Proceedings of the KIEE Conference
• /
• 1998.11c
• /
• pp.910-912
• /
• 1998

In this paper, we purpose automatic diagnosis in online, as the fundamental study to diagnose the partial discharge mechanism and to predict the lifetime, by introduction a neural network. In the proposed method, Ire use acoustic emission sensing system and calculate a fixed quantity statistic operator by pulse number and amplitude. Using statically operators such as the center of gravity(G) and the gradient of the discharge distribute(C), we analyzed the early stage and the middle stage. the fixed quantity statistic operators are learned by a neural network. The diagnosis of insulation degradation and a lifetime prediction by the early stage time are achieved. On the basis of revealed excellent diagnosis ability through the neural network learning for the patterns during degradation, it was proved that the neural network is appropriate for degradation diagnosis and lifetime prediction in partial discharge.

• Journal of the Korea Society of Computer and Information
• /
• v.21 no.5
• /
• pp.91-98
• /
• 2016

We propose a method to train a model that can predict the probability of a crime being committed. CCTV data by matching criminal events are required to train the crime prediction model. However, collecting CCTV data appropriate for training is difficult. Thus, we collected actual criminal records and converted them to an appropriate format using variables by considering a crime prediction environment and the availability of real-time data collection from CCTV. In addition, we identified new specific crime types according to the characteristics of criminal events and trained and tested the prediction model by applying neural network partial least squares for each crime type. Results show a level of predictive accuracy sufficiently significant to demonstrate the applicability of CCTV to real-time crime prediction.

• Proceedings of the KIEE Conference
• /
• 1999.07b
• /
• pp.942-944
• /
• 1999

This paper presents a genetic learning algorithm with partial update technique in application to active control system. Proposed algorithm divides active control system into two parts, real time control part and control parameter update part. This genetic algorithm has global convergent advantage and is expected to be applied easily to real time active noise and vibration control systems. Computer simulation was performed.

• The Korean Journal of Emergency Medical Services
• /
• v.9 no.2
• /
• pp.21-28
• /
• 2005

This study examines and analyzes EMTs works in hospital with 48 subjects working for hospitals at partial areas. It aims to provide basic materials for practice-centered learning to students at Dept. of Emergency Care and information of roles of EMTs. As a result of study, it was found that EMTs works included classification of severity of patients when they came to hosptial, supervision and move of serious case, move of patients and a member of cardiopulmonary resuscitation team as well as filling empty of medical staff and playing medical assistant under direct control of doctors and they played important roles in medical examination. These results showed that EMTs could extend their areas of service within hospital and they could have a positive influence on their seniors' employment.

• Proceedings of the KSPS conference
• /
• 2000.07a
• /
• pp.301-311
• /
• 2000

The purpose of this paper is to explore the use of reaction signals by Japanese and English speakers. After collecting data from Japanese and English speakers, American and British, I checked them and decided to be concerned with five of them: ah, eh, oh, m, and ${\partial}:m$. At first I thought that the first three of them resembled in form and in their tones and meanings, while the others occur frequently only in English. But as I was reading the data more in detail I found the reason for too frequent use of the signal eh by Japanese. It is also found that the signal eh is a kind of substitute for a real word, the similar linguistic phenomenon is seen in the use of m, and m seems to be different from ${\partial}:m$ in its function, according to whether the speaker is talkative or not. And American students learning Japanese started their Japanese with an English reaction signal and the reverse phenomenon was found with Japanese students speaking in English, so much so that reaction signals are used spontaneously, though they have various tones and meanings.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 1996.11a
• /
• pp.361-364
• /
• 1996

Aging diagnosis system using partial discharge(PD) is being highlighted as a research area. But the application of PD requires complicated analysis method because the PD has complex progressing forms. In this paper, It has been developed to the PD diagnosis system using neural network(NN). As a result after NN learning, the recognized rate was represented about 85%. The safety area is possible to express the second output of NN in this experiments.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.5C no.3
• /
• pp.138-142
• /
• 2005

In this paper, we compared recognition rates between NN(neural networks) and clustering method as a scheme of off-line PD(partial discharge) diagnosis which occurs at the stator coil of traction motor. To acquire PD data, three defective models are made. PD data for classification were acquired from PD detector. And then statistical distributions are calculated to classify model discharge sources. These statistical distributions were applied as input data of two classification tools, BP(Back propagation algorithm) and ANFIS(adaptive network based fuzzy inference system) pre-processed FCM(fuzzy c-means) clustering method. So, classification rate of BP were somewhat higher than ANFIS. But other items of ANFIS were better than BP; learning time, parameter number, simplicity of algorithm.

• KIEE International Transactions on Electrophysics and Applications
• /
• v.3C no.1
• /
• pp.5-9
• /
• 2003

The waveforms of partial discharges (PDs) imply physical and structural properties of PD sources, so analyzing them give us information on the kind of PD sources and the location. Waveforms of PD as a time series function have variable amplitudes but sustain a certain uniform shape, which shows well the characteristics of the waveforms and frequency region. They can also be used as parameters having time and frequency information of PD signals and applied to classification of multiple PDs sources via Artificial Neural Network with back propagation (BP) learning.