• Geomechanics and Engineering
• /
• 제38권1호
• /
• pp.29-44
• /
• 2024

This research investigates the effectiveness of data augmentation techniques in the automated analysis of B-scan images from ground-penetrating radar (GPR) using deep learning. In spite of the growing interest in automating GPR data analysis and advancements in deep learning for image classification and object detection, many deep learning-based GPR data analysis studies have been limited by the availability of large, diverse GPR datasets. Data augmentation techniques are widely used in deep learning to improve model performance. In this study, we applied four data augmentation techniques (geometric transformation, color-space transformation, noise injection, and applying kernel filter) to the GPR datasets obtained from a testbed. A deep learning model for GPR data analysis was developed using three models (Faster R-CNN ResNet, SSD ResNet, and EfficientDet) based on transfer learning. It was found that data augmentation significantly enhances model performance across all cases, with the mAP and AR for the Faster R-CNN ResNet model increasing by approximately 4%, achieving a maximum mAP (Intersection over Union = 0.5:1.0) of 87.5% and maximum AR of 90.5%. These results highlight the importance of data augmentation in improving the robustness and accuracy of deep learning models for GPR B-scan analysis. The enhanced detection capabilities achieved through these techniques contribute to more reliable subsurface investigations in geotechnical engineering.

• Journal of Multimedia Information System
• /
• 제6권4호
• /
• pp.165-172
• /
• 2019

Machine-learning techniques have been actively employed to information security in recent years. Traditional rule-based security solutions are vulnerable to advanced attacks due to unpredictable behaviors and unknown vulnerabilities. By employing ML techniques, we are able to develop intrusion detection systems (IDS) based on anomaly detection instead of misuse detection. Moreover, threshold issues in anomaly detection can also be resolved through machine-learning. There are very few datasets for network intrusion detection compared to datasets for malicious code. KDD CUP 99 (KDD) is the most widely used dataset for the evaluation of IDS. Numerous studies on ML-based IDS have been using KDD or the upgraded versions of KDD. In this work, we develop an IDS model using CSE-CIC-IDS 2018, a dataset containing the most up-to-date common network attacks. We employ deep-learning techniques and develop a convolutional neural network (CNN) model for CSE-CIC-IDS 2018. We then evaluate its performance comparing with a recurrent neural network (RNN) model. Our experimental results show that the performance of our CNN model is higher than that of the RNN model when applied to CSE-CIC-IDS 2018 dataset. Furthermore, we suggest a way of improving the performance of our model.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권2호
• /
• pp.110-114
• /
• 2015

This paper reports a novel object-detection technique in video sequences. The proposed algorithm consists of detection of objects in illuminated and occluded videos by using object features and a neural network technique. It consists of two functional modules: region-based object feature extraction and continuous detection of objects in video sequences with region features. This scheme is proposed as an enhancement of the Lowe's scale-invariant feature transform (SIFT) object detection method. This technique solved the high computation time problem of feature generation in the SIFT method. The improvement is achieved by region-based feature classification in the objects to be detected; optimal neural network-based feature reduction is presented in order to reduce the object region feature dataset with winner pixel estimation between the video frames of the video sequence. Simulation results show that the proposed scheme achieves better overall performance than other object detection techniques, and region-based feature detection is faster in comparison to other recent techniques.

• 한국산학기술학회논문지
• /
• 제21권5호
• /
• pp.630-636
• /
• 2020

본 논문에서는 군용 항공기의 시각 탐지(visual detection)를 지연시키는 위장기술에 대하여 조사하였다. 위장(camouflage)이란 관찰자에게 드러나 보이지 않도록 어떤 물체를 거짓으로 꾸미는 것으로 정의할 수 있다. 그러나 군사적 관점에서의 위장은 완전히 사라지게 하는 것이라기보다는 관찰자의 탐지시간을 연장하거나 탐지가능성(detectability)을 낮추는데 목적이 있다. 기본적으로 항공기 위장은 항공기 위치 탐지를 지연시킬 뿐만 아니라, 관측자에게 항공기의 속도와 고도, 진행방향에 대한 혼란을 유발하여야 한다. 따라서 저(低)탐지기술 또는 위장기술은 군용 항공기의 생존성 향상에 많은 영향을 미치므로 많은 연구가 지속적으로 진행되었다. 근접 지원 항공기 및 제공 전투기의 경우는 다색(multi-tone) 위장패턴과 반음영(counter-shaded) 위장패턴이 일반적으로 적용되고 있다. 아울러, 단색(mono-tone) 위장패턴 역시 색상(hue)과 명도(brightness)가 적절히 조절 및 조합되었을 때 위장효과가 큰 것으로 나타났다. 항공기의 위장 성능 향상을 위한 능동 시각 위장 기술(active camouflage techniques)에 관한 연구도 진행되었다. 특히, 발광 반사율이 높은 발광 장치를 사용하는 Counter-illumination 기술은 항공기 표면과 배경 하늘의 명도차를 최소화하여 위장 효과를 향상시켰다. 이와 같은 능동 시각 위장 기술은 시각 탐지에 비교적 취약한 저고도 무인기의 생존성 향상에 기여할 것으로 기대된다.

• 한국정보과학회논문지:정보통신
• /
• 제31권2호
• /
• pp.171-178
• /
• 2004

포트 스캐닝 탐지 시스템은 “False Positive”(실제 공격이 아닌데 공격이라고 탐지, 오탐지)와 “False Negative”(실제 공격인데 공격이 아니라고 탐지, 미탐지)가 낮아야 하는 등의 시스템 성능에 관한 요구사항과, 해당 탐지 시스템을 활용한 보안관리가 용이해야 하는 등의 사용자 친화적인 요구사항을 만족할 필요가 있다. 그러나 공개되어 있는 실시간 스캔 탐지 시스템은 False Positive가 높고 다양한 스캔 기법에 대한 탐지가 잘 이루어지지 않고 있다. 또한 실시간 스캔 탐지 시스템의 대부분이 명령어 기반으로 이루어져 있기 때문에 이률 활용하여 시스템 보안 관리를 수행하는데 많은 어려움이 있다. 따라서 본 논문에서는 새로운 필터 룰 집합의 적용에 의해 포트 스캐닝 기법 기반의 다양한 공격을 탐지 할 수 있고, 공격자의 행동 패턴으로부터 유도된 ABP-Rule의 적용에 의해 False Positive를 최소화할 수 있는 실시간 스캔 탐지 시스템(TkRTSD)을 제안한다. 또한 Tcl/Tk를 이용하여 GUI환경을 구축함으로써 사용자가 쉽게 보안관리를 할 수 있는 사용자 친화적인 탐지 시스템을 제안한다.

• 정보과학회 컴퓨팅의 실제 논문지
• /
• 제23권2호
• /
• pp.128-133
• /
• 2017

최근 대용량 데이터 분석을 위해 다수의 서버를 사용하는 시스템이 증가하고 있다. 대표적인 빅데이터 기술인 하둡은 대용량 데이터를 다수의 서버로 구성된 분산 환경에 저장하여 처리한다. 이러한 분산 시스템에서는 각 서버의 시스템 자원 관리가 매우 중요하다. 본 논문은 다수의 서버에서 수집된 로그 데이터를 토대로 간단하면서 효율적인 이상 탐지 기법을 사용하여 로그 데이터의 변화가 급증하는 이상치를 탐지하고자 한다. 이를 위해, 각 서버로부터 로그 데이터를 수집하여 하둡 에코시스템에 저장할 수 있도록 Apache Hive의 저장 구조를 설계하고, 이동 평균 및 3-시그마를 사용한 세 가지 이상 탐지 기법을 설계한다. 마지막으로 실험을 통해 세 가지 기법이 모두 올바로 이상 구간을 탐지하며, 또한 가중치가 적용된 이상 탐지 기법이 중복을 제거한 더 정확한 탐지 기법임을 확인한다. 본 논문은 하둡 에코시스템을 사용하여 간단한 방법으로 로그 데이터의 이상을 탐지하는 우수한 결과라 사료된다.

• 한국측량학회:학술대회논문집
• /
• 한국측량학회 2006년도 춘계학술발표회 논문집
• /
• pp.243-248
• /
• 2006

In this paper, we propose the unsupervised change detection algorithm that apply the similarity measure techniques to the hyperspectral image. The general similarity measures including euclidean distance and spectral angle were compared. The spectral similarity scale algorithm for reducing the problems of those techniques was studied and tested with Hyperion data. The thresholds for detecting the change area were estimated through EM(Expectation-Maximization) algorithm. The experimental result shows that the similarity measure techniques and EM algorithm can be applied effectively for the unsupervised change detection of the hyperspectral data.

• Structural Engineering and Mechanics
• /
• 제32권4호
• /
• pp.489-500
• /
• 2009

The aim of this paper is to compare wavelet, kurtosis and pseudofractal based techniques for structural health monitoring in the presence of measurement noise. A detailed comparison and assessment of these techniques have been carried out in this paper through numerical experiments for the calibration of damage extent of a simply supported beam with an open crack serving as an illustrative example. The numerical experiments are deemed critical due to limited amount of experimental data available in the field of singularity based detection of damage. A continuous detectibility map has been proposed for comparing various techniques qualitatively. Efficiency surfaces have been constructed for wavelet, kurtosis and pseudofractal based calibration of damage extent as a function of damage location and measurement noise level. Levels of noise have been identified for each technique where a sudden drop of calibration efficiency is observed marking the onset of damage masking regime by measurement noise.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2013년도 추계학술대회 논문집
• /
• pp.757-762
• /
• 2013

A technique is presented that uses a new guided wave technique for sludge and blockages detection in long-range pipelines. Existing techniques have the limitations that the sludge position needs to be known a priori and the area to be inspected needs to be accessible. Two guided wave techniques have been developed which allow the sludge or blockages to be detected remotely without the need to access the specific location where the pipe is blocked, nor to open the pipe. The first technique measures the reflection of guided waves by sludge which can be used to accurately locate the blocked region; the second technique detects sludge by revealing the changes to the transmitted guided waves propagating in the blocked region or after it. The two techniques complement each other and their combination leads to a reliable sludge or blockage detection. Various types of realistic sludge have been considered in the study and the practical capabilities of the two techniques have been demonstrated.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2007년도 춘계학술대회B
• /
• pp.2781-2784
• /
• 2007

Early detection of a disease is important to tackle treatment issues in a better manner. Several diagnostic techniques are in use, these days; for such purpose and tremendous research is going on to develop newer and newer methods. However, more work is required to be done to develop cheap and reliable early detection techniques. Micro-fluidic chips are also playing key role to deliver new devices for better health care. The present study focuses on a review of recent developments in the interrogation of different techniques and present state-of-the-art of microfluidic sensor for better, quick, easy, rapid, early, inexpensive and portable POCT (Point of Care testing device) device for a particular study, in this case, bone disease called osteoporosis. Some simulations of the microchip are also made to enable feasibility of the development of a blood-chip-based system. The proposed device will assist in early detection of diseases in an effective and successful manner.