• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.4
• /
• pp.467-473
• /
• 2020

Recently, the number of traffic accidents has also increased with the increase in the penetration rate of cars in Korea. In particular, not only inter-vehicle accidents but also human accidents near crosswalks are increasing, so that more attention to traffic safety around crosswalks are required. In this paper, we propose a system for predicting the safety level around the crosswalk by recognizing an approaching vehicle and estimating the speed of the vehicle using NVIDIA Jetson Nano-class edge devices. To this end, various machine learning models are trained with the information obtained from deep learning-based vehicle detection to predict the degree of risk according to the speed of an approaching vehicle. Finally, based on experiments using actual driving images and web simulation, the performance and the feasibility of the proposed system are validated.

• Journal of Korea Water Resources Association
• /
• v.54 no.8
• /
• pp.607-616
• /
• 2021

The purpose of this study is to simulate the transport of nonuniform sediment considering the hiding-exposure effect numerically. In order to calculate the transport of multi-disperse suspended sediment mixtures, the set of advection-diffusion equations for each particle class is solved. The applicability of the numerical model is examined by comparing the simulation results with experimental data. In this study, we calculate the vertical distribution of total concentration of sediment particles using two approaches: (1) by considering the mixture as represented by a single size; and (2) by combining the concentration of the sediment corresponding to several particle size classes; From the simulation results, it is shown that both approaches calculate reasonable results due to the narrow range of size distribution. Under the condition of nonuniform sediment, the critical shear stress of the sediment particle is influenced by the size-selective entrainment, i.e., hiding-exposure effect. It is shown in this study that the effect of hiding-exposure effect on the erosion rates of fine sand is negligibly small.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1911-1923
• /
• 2022

The availability of high-resolution satellite images provides precise information without direct observation of the research target. Korea Multi-Purpose Satellite (KOMPSAT), also known as the Arirang satellite, has been developed and utilized for earth observation. The machine learning model was continuously proven as a good classifier in classifying remotely sensed images. This study aimed to compare the performance of the support vector machine (SVM) model in classifying the land cover of the Delaware River port area on high and medium-resolution images. Three optical images, which are KOMPSAT-2, KOMPSAT-3A, and Sentinel-2B, were classified into six land cover classes, including water, road, vegetation, building, vacant, and shadow. The KOMPSAT images are provided by Korea Aerospace Research Institute (KARI), and the Sentinel-2B image was provided by the European Space Agency (ESA). The training samples were manually digitized for each land cover class and considered the reference image. The predicted images were compared to the actual data to obtain the accuracy assessment using a confusion matrix analysis. In addition, the time-consuming training and classifying were recorded to evaluate the model performance. The results showed that the KOMPSAT-3A image has the highest overall accuracy and followed by KOMPSAT-2 and Sentinel-2B results. On the contrary, the model took a long time to classify the higher-resolution image compared to the lower resolution. For that reason, we can conclude that the SVM model performed better in the higher resolution image with the consequence of the longer time-consuming training and classifying data. Thus, this finding might provide consideration for related researchers when selecting satellite imagery for effective and accurate image classification.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.613-626
• /
• 2022

Guaranteeing the quality and integrity of structural health monitoring (SHM) data is very important for an effective assessment of structural condition. However, sensory system may malfunction due to sensor fault or harsh operational environment, resulting in multiple types of data anomaly existing in the measured data. Efficiently and automatically identifying anomalies from the vast amounts of measured data is significant for assessing the structural conditions and early warning for structural failure in SHM. The major challenges of current automated data anomaly detection methods are the imbalance of dataset categories. In terms of the feature of actual anomalous data, this paper proposes a data anomaly detection method based on data-level and deep learning technique for SHM of civil engineering structures. The proposed method consists of a data balancing phase to prepare a comprehensive training dataset based on data-level technique, and an anomaly detection phase based on a sophisticatedly designed network. The advanced densely connected convolutional network (DenseNet) and Transformer encoder are embedded in the specific network to facilitate extraction of both detail and global features of response data, and to establish the mapping between the highest level of abstractive features and data anomaly class. Numerical studies on a steel frame model are conducted to evaluate the performance and noise immunity of using the proposed network for data anomaly detection. The applicability of the proposed method for data anomaly classification is validated with the measured data of a practical supertall structure. The proposed method presents a remarkable performance on data anomaly detection, which reaches a 95.7% overall accuracy with practical engineering structural monitoring data, which demonstrates the effectiveness of data balancing and the robust classification capability of the proposed network.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.27 no.1
• /
• pp.8-14
• /
• 2023

The existing self-supervised learning-based CutPaste generated synthetic data by cutting and attaching specific patches from normal images and then performed anomaly detection. However, this method has a problem in that there is a clear difference in the boundary of the patch. NSA for solving these problems have achieved higher anomaly detection performance by generating natural synthetic data through Poisson Blending. However, NSA has the disadvantage of having many hyperparameters that need to be adjusted for each class. In this paper, synthetic data similar to normal were generated by a simple method of making the size of the synthetic patch very small. At this time, since the patches are so locally synthesized, models that learn local features can easily overfit synthetic data. Therefore, we performed anomaly detection using gMLP, which learns global features, and even with simple synthesis methods, we were able to achieve higher performance than conventional self-supervised learning techniques.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• 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.

• International Journal of Computer Science & Network Security
• /
• v.22 no.6
• /
• pp.57-62
• /
• 2022

The recent past has seen a tremendous amount of advancement in the field of Internet of Things (IoT), allowing the influx of a variety of devices into the market. IoT devices are present in almost every aspect of our daily lives. While this increase in usage has many advantages, it also comes with many problems, including and not limited to, the problem of security. There is a need for better measures to be put in place to ensure that the users' data is protected. In particular, fitness trackers used by a vast number of people, transmit important data regarding the health and location of the user. This data is transmitted from the fitness device to the phone and from the phone onto a cloud server. The transmission from device to phone is done over Bluetooth and the latest version of Bluetooth Light Energy (BLE) is fairly advanced in terms of security, it is susceptible to attacks such as Man-in-the-Middle attack and Denial of Service attack. Additionally, the data must be stored in an encrypted form on the cloud server; however, this proves to be a problem when the data must be decrypted to use for running computations. In order to ensure protection of data, measures such as end-to-end encryption may be used. Homomorphic encryption is a class of encryption schemes that allow computations on encrypted data. This paper explores the application of homomorphic encryption for fitness trackers.

• Journal of Korean Society of Rural Planning
• /
• v.28 no.4
• /
• pp.41-53
• /
• 2022

This study aims to identify perceptions on ESG management evaluation priorities based on public value in the agricultural and rural sector with the focus on the Korea Rural Community Corporation. We conduct Analytic Hierarchy Process (AHP) to analyze how ESG management evaluation priorities are perceived by distinctive groups across industrial fields. To this end, experts working in the agricultural and rural sector and the general public in non-agricultural sector were questioned to derive and compare the weights for each class of ESG management. Results show the followings: First, the weight for the environment (E) was derived as 0.51774 in the first layer, which was found to be the most important evaluation item among the environment (E), society (S), and governance (G). Second, "ecosystem restoration," "urban-rural exchange expansion and regional development," and "increasing transparency" were the most important items in the second layer. Third, priorities between the agricultural and non-agricultural respondents groups were different in environmental (E) and social (S) categories, which explained that perceptions on ESG management by workers and policy makers in the agricultural and rural sector are different from those by general public in the non-agricultural sector.

• Journal of Broadcast Engineering
• /
• v.27 no.1
• /
• pp.124-132
• /
• 2022

Recently, due to COVID-19, online remote classes and non-face-to-face exams have made it difficult to manage class attitudes and exam cheating. Therefore, there is a need for a system that automatically recognizes and detects the behavior of students online. Action recognition, which recognizes human action, is one of the most studied technologies in computer vision. In order to develop such a technology, data including human arm movement information and information about surrounding objects, which can be key information in online classes and exams, are needed. It is difficult to apply the existing dataset to this system because it is classified into various fields or consists of daily life action. In this paper, we propose a dataset that can classify attitudes in real-time online tests and classes. In addition, it shows whether the proposed dataset is correctly constructed through comparison with the existing action recognition dataset.

• The Journal of Bigdata
• /
• v.7 no.1
• /
• pp.37-47
• /
• 2022

Autonomous delivery operation data is the key to driving a paradigm shift for last-mile delivery in the Corona era. To bridge the technological gap between domestic autonomous delivery robots and overseas technology-leading countries, large-scale data collection and verification that can be used for artificial intelligence training is required as the top priority. Therefore, overseas technology-leading countries are contributing to verification and technological development by opening AI training data in public data that anyone can use. In this paper, 326 objects were collected to trainn autonomous delivery robots, and artificial intelligence models such as Mask r-CNN and Yolo v3 were trained and verified. In addition, the two models were compared based on comparison and the elements required for future autonomous delivery robot research were considered.