• 한국의류산업학회지
• /
• 제23권2호
• /
• pp.273-289
• /
• 2021

This study aimed to examine the appearance of heated clothing in relation to fashion trends by analyzing constructive components of clothing using product images and actual products. A total of 91 images of domestic and foreign heated clothing products were collected, and a product analysis conducted with six parameters of item classification, namely, concept and image, silhouette, color, number of heating elements, and heating parts. In addition, an in-depth analysis was carried out with 11 products among them, while focusing on further detailed components of the design and heating system. As a result, the overall exterior design of domestic products has been changed from outdoor clothing to daily clothing reflecting the current design trend. Compared with domestic products, foreign products showed a diverse assortment and a greater number of heating regions per individual item of clothing. The current heating system commonly consists of a heating element, power source, controller board, and wires, although the existence and type of switches differed from product to product. To develop a more efficiently heated clothing to expand the market, the design, ease of use, safety, consumer preference, heating functionality, and durability should be considered. Along with design recommendations for future heated clothing, this study also provides a practical guide to the technical aspects of the design of the components of heated clothing.

• Smart Structures and Systems
• /
• 제30권1호
• /
• pp.75-88
• /
• 2022

Engineering structures in operation essentially belong to time-varying or nonlinear structures and the resultant response signals are usually non-stationary. For such time-varying structures, it is of great importance to extract time-dependent dynamic parameters from non-stationary response signals, which benefits structural health monitoring, safety assessment and vibration control. However, various traditional signal processing methods are unable to extract the embedded meaningful information. As a newly developed technique, variational mode decomposition (VMD) shows its superiority on signal decomposition, however, it still suffers two main problems. The foremost problem is that the number of modal components is required to be defined in advance. Another problem needs to be addressed is that VMD cannot effectively separate non-stationary signals composed of closely spaced or overlapped modes. As such, a new method named generalized adaptive variational modal decomposition (GAVMD) is proposed. In this new method, the number of component signals is adaptively estimated by an index of mean frequency, while the generalized demodulation algorithm is introduced to yield a generalized VMD that can decompose mode overlapped signals successfully. After that, synchrosqueezing wavelet transform (SWT) is applied to extract instantaneous frequencies (IFs) of the decomposed mono-component signals. To verify the validity and accuracy of the proposed method, three numerical examples and a steel cable with time-varying tension force are investigated. The results demonstrate that the proposed GAVMD method can decompose the multi-component signal with overlapped modes well and its combination with SWT enables a successful IF extraction of each individual component.

• 정보보호학회논문지
• /
• 제32권2호
• /
• pp.447-463
• /
• 2022

인공 지능(AI) 기술은 해양 산업에서 스마트 선박을 자율 운항 선박으로 발전시키는 주요 기술이다. 자율 운항 선박은 사람의 의사 판단 없이 수집된 정보로 상황을 인식하며 스스로 판단하여 운항한다. 기존의 선박 시스템은 육상에서의 제어 시스템과 마찬가지로 사이버 공격에 대한 보안성을 고려하여 설계되지 않았다. 이로 인해 선박 내·외부에서 수집되는 수많은 데이터에 대한 침해와 선박에 적용될 인공지능 기술에 대한 잠재적 사이버 위협이 존재한다. 자율 운항 선박의 안전성을 위해서는 선박 시스템의 사이버 보안뿐만 아니라, 인공지능 기술에 대한 사이버 보안에도 초점을 맞춰야 한다. 본 논문에서는 기존 선박 시스템과 자율 운항 선박에 적용될 인공지능 기술에 발생할 수 있는 잠재적인 사이버 위협을 분석하고, 자율 운항 선박 보안 위험과 보안이 필요한 범주를 도출했다. 도출한 결과를 바탕으로 향후 자율 운항 선박 사이버 보안 연구 방향을 제시하고 사이버 보안 향상에 기여한다.

• 한국컴퓨터정보학회논문지
• /
• 제28권1호
• /
• pp.65-70
• /
• 2023

본 논문에서는 YOLO v3를 이용한 CCTV 저장공간 확보 모델을 제안한다. CCTV는 방범, 화재예방, 감시 등 재난·재해 및 안전을 위해 사회 곳곳에 설치·운영되며, 개수의 증가와 화질의 개선이 함께 이뤄지고 있다. 이로 인해 영상파일의 개수와 크기가 증가하면서 기존의 저장공간으로는 이를 감당하기 어려움을 느끼고 있다. 이를 해소하기 위해 CCTV 영상 속의 특정 객체를 YOLO v3를 이용하여 탐지하여 해당 프레임만을 저장하여 불필요한 프레임을 삭제하는 모델을 제안하여 영상파일의 크기를 줄임으로써 저장공간을 확보하고, 그로 인해 더 오랜 기간 영상을 저장·관리할 수 있도록 하였다. 제안 모델 적용 후 평균 94.9% 영상파일의 크기가 절감됨을 확인하였으며, 제안 모델을 적용하기 전보다 약 20배의 보관 기간이 증가했음을 확인할 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제27권2호
• /
• pp.61-69
• /
• 2022

배달산업이 COVID-19 상황과 함께 요식업을 중심으로 크게 성장함에 따라 배달업 종사자가 크게 증가했다. 그와 함께 개인형 모빌리티(Personal Mobility: PM)를 활용한 새로운 배달 형태가 등장했으며, 이륜차 혹은 PM 관련 사고는 꾸준히 증가하고 있다. 본 연구는 안전 배달 모니터링 환경을 구축하기 위해 PM의 주행 분석 장치의 제작한다. 이를 위해 주행 분석 장치와 장치에서 수집된 데이터를 클라우드 서버를 통해 처리하는 시스템을 구성했으며, 이 시스템을 통해 PM의 운전상황에서 운전 중 발생할 수 있는 특수한 상황(가/감속, 과속방지턱 통과)을 인식하고 기록하고자 한다. 그 결과 장치 내 측정 센서(IMU)에서 수집한 각속도, 가속도, 지자기 값을 통해 운행 여부 및 인도 주행 여부, 경사로 주행 여부를 판단해 낼 수 있었다. 이 기술은 기존의 영상기반 기록장치보다 약 1600배 이상의 주행 정보 저장 효율을 달성할 수 있었다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.181-193
• /
• 2022

Data-driven structural health monitoring (SHM) of civil infrastructure can be used to continuously assess the state of a structure, allowing preemptive safety measures to be carried out. Long-term monitoring of large-scale civil infrastructure often involves data-collection using a network of numerous sensors of various types. Malfunctioning sensors in the network are common, which can disrupt the condition assessment and even lead to false-negative indications of damage. The overwhelming size of the data collected renders manual approaches to ensure data quality intractable. The task of detecting and classifying an anomaly in the raw data is non-trivial. We propose an approach to automate this task, improving upon the previously developed technique of image-based pre-processing on one-dimensional (1D) data by enriching the features of the neural network input data with multiple channels. In particular, feature engineering is employed to convert the measured time histories into a 3-channel image comprised of (i) the time history, (ii) the spectrogram, and (iii) the probability density function representation of the signal. To demonstrate this approach, a CNN model is designed and trained on a dataset consisting of acceleration records of sensors installed on a long-span bridge, with the goal of fault detection and classification. The effect of imbalance in anomaly patterns observed is studied to better account for unseen test cases. The proposed framework achieves high overall accuracy and recall even when tested on an unseen dataset that is much larger than the samples used for training, offering a viable solution for implementation on full-scale structures where limited labeled-training data is available.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.251-266
• /
• 2022

Structural Health Monitoring (SHM) of critical infrastructure comprises a major pillar of maintenance management, shielding public safety and economic sustainability. Although SHM is usually associated with data-driven metrics and thresholds, expert judgement is essential, especially in cases where erroneous predictions can bear casualties or substantial economic loss. Considering that visual inspections are time consuming and potentially subjective, artificial-intelligence tools may be leveraged in order to minimize the inspection effort and provide objective outcomes. In this context, timely detection of sensor malfunctioning is crucial in preventing inaccurate assessment and false alarms. The present work introduces a sensor-fault detection and interpretation framework, based on the well-established support-vector machine scheme for anomaly detection, combined with a coalitional game-theory approach. The proposed framework is implemented in two datasets, provided along the 1st International Project Competition for Structural Health Monitoring (IPC-SHM 2020), comprising acceleration and cable-load measurements from two real cable-stayed bridges. The results demonstrate good predictive performance and highlight the potential for seamless adaption of the algorithm to intrinsically different data domains. For the first time, the term "decision trajectories", originating from the field of cognitive sciences, is introduced and applied in the context of SHM. This provides an intuitive and comprehensive illustration of the impact of individual features, along with an elaboration on feature dependencies that drive individual model predictions. Overall, the proposed framework provides an easy-to-train, application-agnostic and interpretable anomaly detector, which can be integrated into the preprocessing part of various SHM and condition-monitoring applications, offering a first screening of the sensor health prior to further analysis.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.237-250
• /
• 2022

Structural health monitoring (SHM) plays an important role in ensuring the safety and functionality of critical civil infrastructure. In recent years, numerous researchers have conducted studies to develop computer vision and machine learning techniques for SHM purposes, offering the potential to reduce the laborious nature and improve the effectiveness of field inspections. However, high-quality vision data from various types of damaged structures is relatively difficult to obtain, because of the rare occurrence of damaged structures. The lack of data is particularly acute for fatigue crack in steel bridge girder. As a result, the lack of data for training purposes is one of the main issues that hinders wider application of these powerful techniques for SHM. To address this problem, the use of synthetic data is proposed in this article to augment real-world datasets used for training neural networks that can identify fatigue cracks in steel structures. First, random textures representing the surface of steel structures with fatigue cracks are created and mapped onto a 3D graphics model. Subsequently, this model is used to generate synthetic images for various lighting conditions and camera angles. A fully convolutional network is then trained for two cases: (1) using only real-word data, and (2) using both synthetic and real-word data. By employing synthetic data augmentation in the training process, the crack identification performance of the neural network for the test dataset is seen to improve from 35% to 40% and 49% to 62% for intersection over union (IoU) and precision, respectively, demonstrating the efficacy of the proposed approach.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.77-91
• /
• 2022

Various monitoring systems have been implemented in civil infrastructure to ensure structural safety and integrity. In long-term monitoring, these systems generate a large amount of data, where anomalies are not unusual and can pose unique challenges for structural health monitoring applications, such as system identification and damage detection. Therefore, developing efficient techniques is quite essential to recognize the anomalies in monitoring data. In this study, several machine learning techniques are explored and implemented to detect and classify various types of data anomalies. A field dataset, which consists of one month long acceleration data obtained from a long-span cable-stayed bridge in China, is employed to examine the machine learning techniques for automated data anomaly detection. These techniques include the statistic-based pattern recognition network, spectrogram-based convolutional neural network, image-based time history convolutional neural network, image-based time-frequency hybrid convolution neural network (GoogLeNet), and proposed ensemble neural network model. The ensemble model deliberately combines different machine learning models to enhance anomaly classification performance. The results show that all these techniques can successfully detect and classify six types of data anomalies (i.e., missing, minor, outlier, square, trend, drift). Moreover, both image-based time history convolutional neural network and GoogLeNet are further investigated for the capability of autonomous online anomaly classification and found to effectively classify anomalies with decent performance. As seen in comparison with accuracy, the proposed ensemble neural network model outperforms the other three machine learning techniques. This study also evaluates the proposed ensemble neural network model to a blind test dataset. As found in the results, this ensemble model is effective for data anomaly detection and applicable for the signal characteristics changing over time.

• Geomechanics and Engineering
• /
• 제28권6호
• /
• pp.599-611
• /
• 2022

Tendon reinforced cemented soil is applied extensively in foundation stabilisation and improvement, especially in areas with soft clay. To solve the deterioration problem led by steel corrosion, the glass fiber-reinforced polymer (GFRP) tendon is introduced to substitute the traditional steel tendon. The interface bond strength between the cemented soil matrix and GFRP tendon demonstrates the outstanding mechanical property of this composite. However, the lack of research between the influence factors and bond strength hinders the application. To evaluate these factors, back propagation neural network (BPNN) is applied to predict the relationship between them and bond strength. Since adjusting BPNN parameters is time-consuming and laborious, the particle swarm optimisation (PSO) algorithm is proposed. This study evaluated the influence of water content, cement content, curing time, and slip distance on the bond performance of GFRP tendon-reinforced cemented soils (GTRCS). The results showed that the ultimate and residual bond strengths were both in positive proportion to cement content and negative to water content. The sample cured for 28 days with 30% water content and 50% cement content had the largest ultimate strength (3879.40 kPa). The PSO-BPNN model was tuned with 3 neurons in the input layer, 10 in the hidden layer, and 1 in the output layer. It showed outstanding performance on a large database comprising 405 testing results. Its higher correlation coefficient (0.908) and lower root-mean-square error (239.11 kPa) were obtained compared to multiple linear regression (MLR) and logistic regression (LR). In addition, a sensitivity analysis was applied to acquire the ranking of the input variables. The results illustrated that the cement content performed the strongest influence on bond strength, followed by the water content and slip displacement.