• Journal of IKEEE
• /
• v.24 no.4
• /
• pp.1011-1016
• /
• 2020

We propose a framework called Stacked Gated Recurrent Unit - Infrequent Residual Analysis (SG-IRA) that detects anomalies in time-series data that can be trained on streams of raw sensor data without any pre-labeled dataset. To enable such unsupervised learning, SG-IRA includes an estimation model that uses a stacked Gated Recurrent Unit (GRU) structure and an analysis method that detects anomalies based on the difference between the estimated value and the actual measurement (residual). SG-IRA's residual analysis method dynamically adapts the detection threshold from the population using frequency analysis, unlike the baseline model that relies on a constant threshold. In this paper, SG-IRA is evaluated using the industrial control systems (ICS) datasets. SG-IRA improves the detection performance (F1 score) by 5.9% compared to the baseline model.

• Structural Monitoring and Maintenance
• /
• v.9 no.3
• /
• pp.221-235
• /
• 2022

Among nondestructive damage detection methods, impedance-based methods have been recognized as an effective technique for damage identification in many kinds of structures. This paper proposes a method to detect cracks in metal structures by combining electro-mechanical impedance (EMI) responses and artificial neural networks (ANN). Firstly, the theories of EMI responses and impedance-based damage detection methods are described. Secondly, the reliability of numerical simulations for impedance responses is demonstrated by comparing to pre-published results for an aluminum beam. Thirdly, the proposed method is used to detect cracks in the beam. The RMSD (root mean square deviation) index is used to alarm the occurrence of the cracks, and the multi-layer perceptron (MLP) ANN is employed to identify the location and size of the cracks. The selection of the effective frequency range is also investigated. The analysis results reveal that the proposed method accurately detects the cracks' occurrence, location, and size in metal structures.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.7
• /
• pp.1098-1101
• /
• 2022

With the development of computer music notation programs, when drawing sheet music, it is often drawn using a computer. However, there are still many use of hand-written notations for educational purposes or to quickly draw sheet music such as listening and dictating. In previous studies, OMR focused on recognizing the printed music sheet made by music notation program. the result of handwritten OMR with camera is poor because different people have different writing methods, and lens distortion. In this study, as a pre-processing process for recognizing handwritten music sheet, we propose a method for recognizing a staff using linear regression and a method for recognizing a bar using CNN. F₁ scores of staff recognition and barline detection are 99.09% and 95.48%, respectively. This methodologies are expected to contribute to improving the accuracy of handwriting.

• Journal of Advanced Navigation Technology
• /
• v.27 no.5
• /
• pp.685-689
• /
• 2023

The proposed system in the study aims to detect forest fires in real-time stream data received from the drone-camera. Recently, the number of wildfires has been increasing, and also the large scaled wildfires are frequent more and more. In order to prevent forest fire damage, many experiments using the drone camera and vision analysis are actively conducted, however there were many challenges, such as network speed, pre-processing, and model performance, to detect forest fires from real-time streaming data of the flying drone. Therefore, this study applied image data processing works to capture five good image frames for vision analysis from whole streaming data and then developed the object detection model based on YOLO_v2. As the result, the classification model performance of forest fire images reached upto 93% of accuracy, and the field test for the model verification detected the forest fire with about 70% accuracy.

• Structural Engineering and Mechanics
• /
• v.91 no.2
• /
• pp.163-175
• /
• 2024

The objective of this research is to improve public safety in civil engineering by recognizing fractures in concrete structures quickly and correctly. The study offers a new crack detection method based on advanced image processing and machine learning techniques, specifically transfer learning with convolutional neural networks (CNNs). Four pre-trained models (VGG16, AlexNet, ResNet18, and DenseNet161) were fine-tuned to detect fractures in concrete surfaces. These models constantly produced accuracy rates greater than 80%, showing their ability to automate fracture identification and potentially reduce structural failure costs. Furthermore, the study expands its scope beyond crack detection to identify concrete health, using a dataset with a wide range of surface defects and anomalies including cracks. Notably, using VGG16, which was chosen as the most effective network architecture from the first phase, the study achieves excellent accuracy in classifying concrete health, demonstrating the model's satisfactorily performance even in more complex scenarios.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.19-21
• /
• 2022

Anomaly detection using self-supervised learning typically generates synthetic data to learn to classify normal and abnormal, and uses real abnormal data as test data to measure anomaly detection performance. In a study using this method to generate synthetic data similar to normal data, anomaly detection was carried out by generating synthetic data by cutting and pasting a specific patch from the original image. In this way, the degree of similarity to normal data depends on the number and size of patches, which affects anomaly detection performance. In this paper, synthetic data were generated by varying patch sizes and numbers, and then similarity and analysis with normal data were conducted using a pre-trained model, and anomaly detection performance was measured by learning the model.

• Smart Structures and Systems
• /
• v.3 no.4
• /
• pp.439-454
• /
• 2007

In this paper a damage imaging technique using pre-stack migration is developed using Lamb (guided) wave propagation in composite structures for imaging multi damages by both numerical simulations and experimental studies. In particular, the paper focuses on the experimental study using a finite number of sensors for future practical applications. A composite laminate with a surface-mounted linear piezoelectric ceramic (PZT) disk array is illustrated as an example. Two types of damages, one straight-crack damage and two simulated circular-shaped delamination damage, have been studied. First, Mindlin plate theory is used to model Lamb waves propagating in laminates. The group velocities of flexural waves in the composite laminate are also derived from dispersion relations and validated by experiments. Then the pre-stack migration technique is performed by using a two-dimensional explicit finite difference algorithm to back-propagate the scattered energy to the damages and damages are imaged together with the excitation-time imaging conditions. Stacking these images together deduces the resulting image of damages. Both simulations and experimental results show that the pre-stack migration method is a promising method for damage identification in composite structures.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.538-541
• /
• 2009

Increasing of number of people who suffered from long term chronic diseases which required frequent daily health monitoring and body check up in conjunction with the trendy uses of mobile phones and Personal Digital Assistants (PDAs) in various ubiquitous computing had make portable healthcare system a well known application today. A mobile phone based portable healthcare monitoring system with multiple vital signals monitoring ability at real time in WSN and CDMA network is developed. This system carries out real time monitoring and local data analysis process in the mobile phone. Any detection of abnormal health condition and diagnosis at earlier stage will reduce the risk of patient's life. As an extension to the existing model, a pre-diagnosis management system (PDMS) is designed to minimize the time consuming in pre-diagnosis process in the hospital or healthcare center. An alert is sent to the web server at the healthcare center when the patient detects his health is at critical state where the immediate diagnosis is needed. Preparation of diagnosis equipments and arrangement of doctor and nurses at the hospital side can be done earlier before the arrival of patient at the hospital with the help of PDMS. An efficient pre-diagnosis management increases the chances of diseases recovery rate as well.

• Journal of Sasang Constitutional Medicine
• /
• v.34 no.1
• /
• pp.37-45
• /
• 2022

Objectives The purpose of this study was to reveal that Sasang constitution(SC) was associated with hypertension and pre-hypertension and could be a risk factor. Methods We introduced this study to educational personnel in D university in Daejeon, and 275 subjects joined this study. The SC classification was conducted with KS 15 questionnaire. The subjected measured the blood pressure with Jawon medical device automatically after 10 minute rest. The hypertension and pre-hypertension was classified by the guide of the Seventh Report of the Joint National Committee on Prevention, Detection, Evaluation, and Treatment of High Blood Pressure. The frequency analysis and T-test was used in general characteristics, and chi-square test was also used between SC and pre-hypertension and hypertension. Logistic regression was used to calculate the odds ratios (ORs) and 95% confidence interval (95% CI) for pre-hypertension and hypertension. Results The number of Taeeumin(TE), Soeumin(SE), and Soyangin(SY) was 142, 71, and 61 respectively. There was significantly different in systolic and diastolic blood pressure among SC types(p<.001). The distribution of the normal group, pre-hypertension and hypertension group by SC types was significantly different (p<.001). The ORs of TE was significantly increased (ORs 4.039, 95% CI=2.019-8.082 in pre-hypertension and ORs 4.235, 95% CI=1.581-11.348 in hypertension) compared with SE(p<.001), and after adjusting gender and smoking habit, it was still significantly different(p<.001). Conclusions It is possible that SC, especially TE could be a risk factor both pre-hypertension and hypertension.

• The Journal of the Korea Contents Association
• /
• v.16 no.10
• /
• pp.467-476
• /
• 2016

With the development of information technology, Small office Home office(SOHO) is picking up. SOHO generally uses Wi-Fi. The wireless LAN environment using 802.11 protocol is easily affected by DoS attacks. To deal with these threats, there is Wireless Intrusion Detection System(WIDS). However, legacy products of WIDS cannot be easily used by SOHO because they are expensive and require management burden. In this paper, Smart WIDS for SOHO is proposed and implemented on Raspberry Pi2. And, it provides the interface for attack detection notice to android smart phone. Smart WIDS detects Masquerading DoS and Resource Depletion DoS based on IEEE 802.11 so that we notice the attempt of cracking Pre-shared Key(PSK), Man-In-The-Middle(MITM), and service failure.