• Journal of Korean Tunnelling and Underground Space Association
• /
• v.26 no.2
• /
• pp.129-152
• /
• 2024

In the application of deep learning object detection via CCTV in tunnels, a large number of false positive detections occur due to the poor environmental conditions of tunnels, such as low illumination and severe perspective effect. This problem directly impacts the reliability of the tunnel CCTV-based accident detection system reliant on object detection performance. Hence, it is necessary to reduce the number of false positive detections while also enhancing the number of true positive detections. Based on a deep learning object detection model, this paper proposes a false positive data training method that not only reduces false positives but also improves true positive detection performance through retraining of false positive data. This paper's false positive data training method is based on the following steps: initial training of a training dataset - inference of a validation dataset - correction of false positive data and dataset composition - addition to the training dataset and retraining. In this paper, experiments were conducted to verify the performance of this method. First, the optimal hyperparameters of the deep learning object detection model to be applied in this experiment were determined through previous experiments. Then, in this experiment, training image format was determined, and experiments were conducted sequentially to check the long-term performance improvement through retraining of repeated false detection datasets. As a result, in the first experiment, it was found that the inclusion of the background in the inferred image was more advantageous for object detection performance than the removal of the background excluding the object. In the second experiment, it was found that retraining by accumulating false positives from each level of retraining was more advantageous than retraining independently for each level of retraining in terms of continuous improvement of object detection performance. After retraining the false positive data with the method determined in the two experiments, the car object class showed excellent inference performance with an AP value of 0.95 or higher after the first retraining, and by the fifth retraining, the inference performance was improved by about 1.06 times compared to the initial inference. And the person object class continued to improve its inference performance as retraining progressed, and by the 18th retraining, it showed that it could self-improve its inference performance by more than 2.3 times compared to the initial inference.

• 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.

• Nuclear Engineering and Technology
• /
• v.48 no.3
• /
• pp.820-830
• /
• 2016

Pipe wall thinning by flow-accelerated corrosion and various types of erosion is a significant and costly damage phenomenon in secondary piping systems of nuclear power plants (NPPs). Most NPPs have management programs to ensure pipe integrity due to wall thinning that includes periodic measurements for pipe wall thicknesses using nondestructive evaluation techniques. Numerous measurements using ultrasonic tests (UTs; one of the nondestructive evaluation technologies) have been performed during scheduled outages in NPPs. Using the thickness measurement data, wall thinning rates of each component are determined conservatively according to several evaluation methods developed by the United States Electric Power Research Institute. However, little is known about the conservativeness or reliability of the evaluation methods because of a lack of understanding of the measurement error. In this study, quantitative models for UT thickness measurement deviations of nuclear pipes and fittings were developed as the first step for establishing an optimized thinning evaluation procedure considering measurement error. In order to understand the characteristics of UT thickness measurement errors of nuclear pipes and fittings, round robin test results, which were obtained by previous researchers under laboratory conditions, were analyzed. Then, based on a large dataset of actual plant data from four NPPs, a quantitative model for UT thickness measurement deviation is proposed for plant conditions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.4043-4060
• /
• 2017

Network Intrusion Detection (NID), an important topic in the field of information security, can be viewed as a pattern recognition problem. The existing pattern recognition methods can achieve a good performance when the number of training samples is large enough. However, modern network attacks are diverse and constantly updated, and the training samples have much smaller size. Furthermore, to improve the learning ability of SVM, the research of kernel functions mainly focus on the selection, construction and improvement of kernel functions. Nonetheless, in practice, there are no theories to solve the problem of the construction of kernel functions perfectly. In this paper, we effectively integrate the advantages of the radial basis function kernel and the polynomial kernel on the notion of the game theory and propose a novel kernel SVM algorithm with game theory for NID, called GTNID-SVM. The basic idea is to exploit the game theory in NID to get a SVM classifier with better learning ability and generalization performance. To the best of our knowledge, GTNID-SVM is the first algorithm that studies ensemble kernel function with game theory in NID. We conduct empirical studies on the DARPA dataset, and the results demonstrate that the proposed approach is feasible and more effective.

• Journal of the Korean Society of Radiology
• /
• v.82 no.5
• /
• pp.1196-1206
• /
• 2021

Purpose To construct a standard dataset of contrast-enhanced CT images of liver tumors to test the performance and safety of artificial intelligence (AI)-based algorithms for clinical decision support systems (CDSSs). Materials and Methods A consensus group of medical experts in gastrointestinal radiology from four national tertiary institutions discussed the conditions to be included in a standard dataset. Seventy-five cases of hepatocellular carcinoma, 75 cases of metastasis, and 30-50 cases of benign lesions were retrieved from each institution, and the final dataset consisted of 300 cases of hepatocellular carcinoma, 300 cases of metastasis, and 183 cases of benign lesions. Only pathologically confirmed cases of hepatocellular carcinomas and metastases were enrolled. The medical experts retrieved the medical records of the patients and manually labeled the CT images. The CT images were saved as Digital Imaging and Communications in Medicine (DICOM) files. Results The medical experts in gastrointestinal radiology constructed the standard dataset of contrast-enhanced CT images for 783 cases of liver tumors. The performance and safety of the AI algorithm can be evaluated by calculating the sensitivity and specificity for detecting and characterizing the lesions. Conclusion The constructed standard dataset can be utilized for evaluating the machine-learning-based AI algorithm for CDSS.

• Proceedings of the KSRS Conference
• /
• 2002.10a
• /
• pp.66-69
• /
• 2002

This article outlines the capabilities of a viewer component called GridViewer, and proves its reusability. GridViewer was designed for the construction of the image display part of GIS or remote sensing application software, and consequently it is particularly straightforward to closely couple GridViewer with access to very large images. Displaying is performed through pyramid structure, which enables to treat very large dataset up to several gigabytes in size under the limited capability of PC. GridViewer is free from responsibility to handle various formats of raster data files by taking grid coverage, which is designed by OGC to promote interoperability between implementations done by data vendors and software vendors providing analysis and grid processing implementations. GridViewer differs from other such viewer by allowing for clients to extend its function and capability by using small set of methods originally implemented in it. We show its reusability and expandability by applying it in developing application programs performing various functions not supported originally by the GridViewer COM component.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.343-345
• /
• 2017

통신 기술이 발달하고, 네트워크 환경 또한 다양해짐에 따라 통신 사용자들에 대한 사이버 위협 또한 다양해졌다. 패턴인식 기술과 기계학습에 기반한 침입탐지 기술은 새롭게 보고되는 수많은 사이버 공격들에 대응하기 위해 등장하였다. 기계학습 기반의 IDS는 낮은 오탐률과 높은 효율성을 요구하며, 이러한 특징은 데이터셋을 구성하는 방법론에 큰 영향을 받는다. 본 논문에서는 패턴인식 기반 트래픽 분석을 수행하기 위한 데이터셋을 구성할 때 고려해야할 주안점에 대해 논하며, 현실의 사이버 위협 상황을 잘 반영할 수 있는 데이터셋을 도출하는 방법을 모색한다.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2015.07a
• /
• pp.516-517
• /
• 2015

The automatic traffic sign detection and recognition has been one of the highly researched and an important component of advanced driver assistance systems (ADAS). They are designed especially to warn the drivers of imminent dangers such as sharp curves, under construction zone, etc. This paper presents a traffic sign recognition (TSR) system using morphological operations and multiple descriptors. The TSR system is realized in three stages: segmentation, shape classification and recognition stage. The system is designed to attain maximum accuracy at the segmentation stage with the inclusion of morphological operations and boost the computation time at the shape classification stage using MB-LBP descriptor. The proposed system is tested on the German traffic sign recognition benchmark (GTSRB) and on Korean traffic sign dataset.

• Journal of Computing Science and Engineering
• /
• v.8 no.2
• /
• pp.65-77
• /
• 2014

To address the problem of multi-target retrieval (MTR) of remote sensing images, this study proposes a new object-level feature representation model. The model provides an enhanced application image representation that improves the efficiency of MTR. Generating the model in our scheme includes processes, such as object-oriented image segmentation, feature parameter calculation, and symbolic image database construction. The proposed model uses the spatial representation method of the extended nine-direction lower-triangular (9DLT) matrix to combine spatial relationships among objects, and organizes the image features according to MPEG-7 standards. A similarity metric method is proposed that improves the precision of similarity retrieval. Our method provides a trade-off strategy that supports flexible matching on the target features, or the spatial relationship between the query target and the image database. We implement this retrieval framework on a dataset of remote sensing images. Experimental results show that the proposed model achieves competitive and high-retrieval precision.

• Proceedings of the Korean Information Science Society Conference
• /
• 2005.07a
• /
• pp.550-552
• /
• 2005

국내에는 많은 수의 네트워크 망 제공 업체로부터 고속 네트워크가 제공되고 있다. 이러한 네트워크 망에서 또한 많은 침입 탐지 시스템을 필요로 하고 있고 또한 많은 새로운 웜 바이러스의 출현에 따른 연구도 필요로 하고 있다. 그러나 현재 실정에 맞는 네트워크 데이터 셋이 구성되어 있지 않고 이러한 문제점으로 하여 정확한 침입 탐지 혹은 웜 바이러스의 효과적인 탐지와 차단에서 어려움이 있다. 이러한 문제를 해결하기 위해 본 논문에서는 실제 환경과 흡사한 데이터 셋 구성을 위한 방안에 대해서 제안 한다.