• Journal of the Korea Society of Computer and Information
• /
• v.25 no.10
• /
• pp.35-42
• /
• 2020

In this study, we propose a crack detection method using limited data with a U-Net based image inpainting technique that is a modified unsupervised anomaly detection method. Concrete cracking occurs due to a variety of causes and is a factor that can cause serious damage to the structure in the long term. In general, crack investigation uses an inspector's visual inspection on the concrete surfaces, which is less objective in judgment and has a high possibility of human error. Therefore, a method with objective and accurate image analysis processing is required. In recent years, the methods using deep learning have been studied to detect cracks quickly and accurately. However, when the amount of crack data on the building or infrastructure to be inspected is small, existing crack detection models using it often show a limited performance. Therefore, in this study, an unsupervised anomaly detection method was used to augment the data on the object to be inspected, and as a result of learning using the data, we confirmed the performance of 98.78% of accuracy and 82.67% of harmonic average (F1_Score).

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.1
• /
• pp.21-29
• /
• 2001

In order to detect the precise port/starboard direction of arrival of target signal in real noisy ocean environments, Inverse beamforming (IBF) algorithm is surveyed theoretically and the detection performances of IBF are analyzed with simulations. Cardioid Inverse beamforming algorithm was proposed for port/starboard discrimination and the performance was studied with simulations. It is shown that IBF has a 3dB array gain advantage over Conventional beamforming (CBF) under ideal conditions. This 3 dB advantage is proven theoretically and illustrated with simulations. The fact that the IBF beamwidth is narrower than the CBF beamwidth by a factor of 0.68 proves the performance of defection and spatial resolution improvement. Comparing the simulation results of Cardioid Inverse beamforming and Conventional Cardioid beamforming, it is shown that Cardioid Inverse beamformer has enhanced performance in minimum detection level, detection accuracy and resolution. Due to the results of moving target bearing detection test in endfire, it is shown that Cardioid Inverse beamformer has better performance, comparing the Conventional Cardioid beamformer.

• Journal of the Korea Society for Simulation
• /
• v.29 no.4
• /
• pp.73-84
• /
• 2020

As the Internet began to become popular, there have been hacking and attacks on networks including systems, and as the techniques evolved day by day, it put risks and burdens on companies and society. In order to alleviate that risk and burden, it is necessary to detect hacking and attacks early and respond appropriately. Prior to that, it is necessary to increase the reliability in detecting network intrusion. This study was conducted on applying weight initialization and weight optimization to the KDD'99 dataset to improve the accuracy of detecting network intrusion. As for the weight initialization, it was found through experiments that the initialization method related to the weight learning structure, like Xavier and He method, affects the accuracy. In addition, the weight optimization was confirmed through the experiment of the network intrusion detection dataset that the Adam algorithm, which combines the advantages of the Momentum reflecting the previous change and RMSProp, which allows the current weight to be reflected in the learning rate, stands out in terms of accuracy.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.6
• /
• pp.381-392
• /
• 2021

In this study, we perform deep learning-based object detection analysis on eight types of buildings defined by the digital map topography standard code, leveraging images taken with UAV (Unmanned Aerial Vehicle). Image labeling was done for 509 images taken by UAVs and the YOLO (You Only Look Once) v5 model was applied to proceed with learning and inference. For experiments and analysis, data were analyzed by applying an open source-based analysis platform and algorithm, and as a result of the analysis, building objects were detected with a prediction probability of 88% to 98%. In addition, the learning method and model construction method necessary for the high accuracy of building object detection in the process of constructing and repetitive learning of training data were analyzed, and a method of applying the learned model to other images was sought. Through this study, a model in which high-efficiency deep neural networks and spatial information data are fused will be proposed, and the fusion of spatial information data and deep learning technology will provide a lot of help in improving the efficiency, analysis and prediction of spatial information data construction in the future.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.1
• /
• pp.25-38
• /
• 2022

With the diversification of payment methods and games, related financial accidents are causing serious problems for users and game companies. Recently, game companies have introduced an Fraud Detection System (FDS) for game payment systems to prevent financial incident. However, FDS is ineffective and cannot provide major evidence based on judgment results, as it requires constant change of detection patterns. In this paper, we analyze abnormal transactions among payment log data of real game companies to generate related features. One of the unsupervised learning models, Autoencoder, was used to build a model to detect abnormal transactions, which resulted in over 85% accuracy. Using X-FDS (Explainable FDS) with XAI-SHAP, we could understand that the variables with the highest explanation for anomaly detection were the amount of transaction, transaction medium, and the age of users. Based on X-FDS, we derive an improved detection model with an accuracy of 94% was finally derived by fine-tuning the importance of features that adversely affect the proposed model.

• KNOM Review
• /
• v.24 no.2
• /
• pp.24-34
• /
• 2021

Service providers using edge computing provide a high level of service. As a result, devices store important information in inner storage and have become a target of the latest cyberattacks, which are more difficult to detect. Although experts use a security system such as intrusion detection systems, the existing intrusion systems have low detection accuracy. Therefore, in this paper, we proposed a machine learning model for more accurate intrusion detections of devices in edge computing. The proposed model is a hybrid model that combines a stacked sparse autoencoder (SSAE) and a convolutional neural network (CNN) to extract important feature vectors from the input data using sparsity constraints. To find the optimal model, we compared and analyzed the performance as adjusting the sparsity coefficient of SSAE. As a result, the model showed the highest accuracy as a 96.9% using the sparsity constraints. Therefore, the model showed the highest performance when model trains only important features.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.15-17
• /
• 2021

This paper proposes a drone flight trajectory method for accurate air pollutant emission designation detection. In areas with many factories, such as industrial complexes, there are workplaces that illegally emit air pollutants in a situation where monitoring is neglected. In the past, studies have been actively conducted to measure air pollutants in these areas using drones. The measurement method using a drone uses a method of detecting pollution by stopping around the chimney of a factory, but it has a problem in that the detection of air pollutants is inaccurate depending on environmental factors such as air pressure and wind. Therefore, this paper proposes a drone flight trajectory method for accurate air pollutant emission designation detection. This paper devises a screw orbit flight method in which a drone flies upward while rotating the chimney, and the total area of the chimney is detected and measured considering environmental factors. In the experiment, our proposal shows a higher performance than the existing method.

• Review of KIISC
• /
• v.24 no.1
• /
• pp.39-44
• /
• 2014

악성코드는 다양해진 감염 경로를 통해 쉽게 노출될 수 있으며, 개인정보의 유출뿐만 아니라 봇넷을 이용한 DDoS 공격과 지능화된 APT 공격 등을 통해 심각한 보안 위협을 발생시키고 있다. 최근 악성코드들은 실행 후에는 메모리에서만 동작하는 방식으로 파일로 존재하지 않기 때문에 기존의 악성코드 탐지 기법으로 이를 찾기가 쉽지 않다. 이를 극복하고자 최근에는 물리 메모리 덤프를 포함하여 악성코드 분석 및 탐지 연구가 활발하게 진행되고 있다. 본 논문에서는 윈도우 시스템의 물리 메인 메모리에서 악성코드 탐지 기술에 대해 설명하고, 기존 개발된 물리 메모리 악성코드 탐지 도구에 대한 분석을 수행하여 도구별 악성코드 탐지 기능에 대한 특징을 설명한다. 물리 메모리 악성코드 탐지 도구의 분석 결과를 통해 기존 물리 메모리 악성코드 탐지 기술의 한계점을 제시하고, 향후 정확하고 효율적인 물리 메모리 악성코드 탐지의 기반 연구로 활용하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.11c
• /
• pp.1843-1846
• /
• 2003

네트워크 기반의 공격 및 비정상 행위를 정확히 탐지하고 판단하기 위한 기존의 탐지 모델은 공격 룰셋의 패턴매칭 기반인 Misuse Detection System을 사용하고 있다. 그러나 이 시스템의 특성상 새로운 공격의 미탐지 및 공격 오인등으로 False Positive 가 높다는 단점이 있다. 본 논문은 전체 시스템의 성능을 판정하는 False Positve 에러율을 줄여 성능을 향상하기 위해 Meachine Learning기반의 Anomaly Detection System 을 결합한 새로운 탐지 모델을 제안하고자 한다. Anomaly Detection System 은 정상행위에 대한 비교적 높은 탐지율과 새로운 공격에 대한 탐지가 용이하다. 본 논문에서는 각 시스템의 탐지모델로 Snort 와 인스턴스 기반의 알고리즘인 IBL 을 사용했으며, 결합모델의 타당성을 검증하기 위해서 각 탐지 모델의 False Positive와 False Negative 에러율을 측정하였다.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.4
• /
• pp.359-364
• /
• 2022

The change detection in remote sensing results in errors due to the camera's optical factors, seasonal factors, and land cover characteristics. The inclination of the building in the image was simulated according to the camera angle using the Cycle Generative Adversarial Network method, and the simulated image was used to contribute to the improvement of change detection accuracy. Based on CycleGAN, the inclination of the building was similarly simulated to the building in the other image based on the image of one of the two periods, and the error of the original image and the inclination of the building was compared and analyzed. The experimental data were taken at different times at different angles, and Kompsat-3A high-resolution satellite images including urban areas with dense buildings were used. As a result of the experiment, the number of incorrect detection pixels per building in the two images for the building area in the image was shown to be reduced by approximately 7 times from 12,632 in the original image and 1,730 in the CycleGAN-based simulation image. Therefore, it was confirmed that the proposed method can reduce detection errors due to the inclination of the building.