• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.991-1005
• /
• 2022

Satellite imaging is an effective supplementary data source for detecting and verifying nuclear activity. It is also highly beneficial in regions with limited access and information, such as nuclear installations. Time series analysis, in particular, can identify the process of preparing for the conduction of a nuclear experiment, such as relocating equipment or changing facilities. Differences in the semantic segmentation findings of time series photos were employed in this work to detect changes in meaningful items connected to nuclear activity. Building, road, and small object datasets made of KOMPSAT 3/3A photos given by AIHub were used to train deep learning models such as U-Net, PSPNet, and Attention U-Net. To pick relevant models for targets, many model parameters were adjusted. The final change detection was carried out by including object information into the first change detection, which was obtained as the difference in semantic segmentation findings. The experiment findings demonstrated that the suggested approach could effectively identify altered pixels. Although the suggested approach is dependent on the accuracy of semantic segmentation findings, it is envisaged that as the dataset for the region of interest grows in the future, so will the relevant scope of the proposed method.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_2
• /
• pp.1633-1641
• /
• 2022

Urban population concentration and indiscriminate development are causing various environmental problems such as air pollution and heat island phenomena, and causing human resources to deteriorate the damage caused by natural disasters. Urban trees have been proposed as a solution to these urban problems, and actually play an important role, such as providing environmental improvement functions. Accordingly, quantitative measurement and analysis of individual trees in urban trees are required to understand the effect of trees on the urban environment. However, the complexity and diversity of urban trees have a problem of lowering the accuracy of single tree detection. Therefore, we conducted a study to effectively detect trees in Dongjak-gu using high-resolution aerial images that enable effective detection of tree objects and You Only Look Once Version 5 (YOLOv5), which showed excellent performance in object detection. Labeling guidelines for the construction of tree AI learning datasets were generated, and box annotation was performed on Dongjak-gu trees based on this. We tested various scale YOLOv5 models from the constructed dataset and adopted the optimal model to perform more efficient urban tree detection, resulting in significant results of mean Average Precision (mAP) 0.663.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_4
• /
• pp.1925-1934
• /
• 2022

Monitoring nuclear activity for inaccessible areas using remote sensing technology is essential for nuclear non-proliferation. In recent years, deep learning has been actively used to detect nuclear-activity-related small objects. However, high-resolution satellite imagery containing small objects can result in class imbalance. As a result, there is a performance degradation problem in detecting small objects. Therefore, this study aims to improve detection accuracy by analyzing the effect of the ratio of small objects related to nuclear activity in the input data for the performance of the deep learning model. To this end, six case datasets with different ratios of small object pixels were generated and a U-Net model was trained for each case. Following that, each trained model was evaluated quantitatively and qualitatively using a test dataset containing various types of small object classes. The results of this study confirm that when the ratio of object pixels in the input image is adjusted, small objects related to nuclear activity can be detected efficiently. This study suggests that the performance of deep learning can be improved by adjusting the object pixel ratio of input data in the training dataset.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.1-9
• /
• 2022

Localization systems can be used with various circumstances like measuring population movement and rescue technology, even in security technology (like infiltration detection system). Vision sensors such as camera often used for localization is susceptible with light and temperature, and can cause invasion of privacy. In this paper, we used ultra-wideband radar technology (which is not limited by aforementioned problems) and machine learning techniques to measure the number and location of occupants in other indoor spaces behind the wall. We used four different algorithms and compared their results, including extremely randomized tree for four different situations; detect the number of occupants in a classroom, split the classroom into 28 locations and check the position of occupant, select one out of the 28 locations, divide it into 16 fine-grained locations, and check the position of occupant, and checking the positions of two occupants (existing in different locations). Overall, four algorithms showed good results and we verified that detecting the number and location of occupants are possible with high accuracy using machine learning. Also we have considered the possibility of service expansion using the oneM2M standard platform and expect to develop more service and products if this technology is used in various fields.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.32 no.1
• /
• pp.21-30
• /
• 2022

Objectives: The purpose of this study is to suggest an optimal method by comparing the analysis methods of work environment measurement datasets including left-censored data where one or more measurements are below the limit of detection (LOD). Methods: A computer program was used to generate left-censored datasets for various combinations of censoring rate (1% to 90%) and sample size (30 to 300). For the analysis of the censored data, the simple substitution method (LOD/2), β-substitution method, maximum likelihood estimation (MLE) method, Bayesian method, and regression on order statistics (ROS)were all compared. Each method was used to estimate four parameters of the log-normal distribution: (1) geometric mean (GM), (2) geometric standard deviation (GSD), (3) 95th percentile (X95), and (4) arithmetic mean (AM) for the censored dataset. The performance of each method was evaluated using relative bias and relative root mean squared error (rMSE). Results: In the case of the largest sample size (n=300), when the censoring rate was less than 40%, the relative bias and rMSE were small for all five methods. When the censoring rate was large (70%, 90%), the simple substitution method was inappropriate because the relative bias was the largest, regardless of the sample size. When the sample size was small and the censoring rate was large, the Bayesian method, the β-substitution method, and the MLE method showed the smallest relative bias. Conclusions: The accuracy and precision of all methods tended to increase as the sample size was larger and the censoring rate was smaller. The simple substitution method was inappropriate when the censoring rate was high, and the β-substitution method, MLE method, and Bayesian method can be widely applied.

• Journal of Internet Computing and Services
• /
• v.22 no.6
• /
• pp.33-40
• /
• 2021

Automatic Speech Recognition(ASR) is a technology that analyzes human speech sound into speech signals and then automatically converts them into character strings that can be understandable by human. Speech recognition technology has evolved from the basic level of recognizing a single word to the advanced level of recognizing sentences consisting of multiple words. In real-time voice conversation, the high recognition rate improves the convenience of natural information delivery and expands the scope of voice-based applications. On the other hand, with the active application of speech recognition technology, concerns about related cyber attacks and threats are also increasing. According to the existing studies, researches on the technology development itself, such as the design of the Automatic Speaker Verification(ASV) technique and improvement of accuracy, are being actively conducted. However, there are not many analysis studies of attacks and threats in depth and variety. In this study, we propose a cyber attack model that bypasses voice authentication by simply manipulating voice frequency and voice speed for AI voice recognition service equipped with automated identification technology and analyze cyber threats by conducting extensive experiments on the automated identification system of commercial smartphones. Through this, we intend to inform the seriousness of the related cyber threats and raise interests in research on effective countermeasures.

• Journal of Korean Society of Rural Planning
• /
• v.27 no.4
• /
• pp.55-70
• /
• 2021

In this study, in the field of remote sensing, where the scope of application is rapidly expanding to fields such as land monitoring, disaster prediction, facility safety inspection, and maintenance of cultural properties, monitoring of rural space and surrounding environment using UAV is utilized. It was carried out to verify the possibility, and the following main results were derived. First, the aerial image taken with an unmanned aerial vehicle had a much higher image size and spatial resolution than the aerial image provided by the National Geographic Information Service. It was suitable for analysis due to its high accuracy. Second, the more the number of photographed photos and the more complex the terrain features, the more the point cloud included in the aerial image taken with the UAV was extracted. As the amount of point cloud increases, accurate 3D mapping is possible, For accurate 3D mapping, it is judged that a point cloud acquisition method for difficult-to-photograph parts in the air is required. Third, 3D mapping technology using point cloud is effective for monitoring rural space and rural resources because it enables observation and comparison of parts that cannot be read from general aerial images. Fourth, the digital elevation model(DEM) produced with aerial image taken with an UAV can visually express the altitude and shape of the topography of the study site, so it can be used as data to predict the effects of topographical changes due to changes in rural space. Therefore, it is possible to utilize various results using the data included in the aerial image taken by the UAV. In this study, the superiority of images acquired by UAV was verified by comparison with existing images, and the effect of 3D mapping on rural space monitoring was visually analyzed. If various types of spatial data such as GIS analysis and topographic map production are collected and utilized using data that can be acquired by unmanned aerial vehicles, it is expected to be used as basic data for rural planning to maintain and preserve the rural environment.

• Korean Journal of Remote Sensing
• /
• v.38 no.5_2
• /
• pp.781-791
• /
• 2022

It is crucial to provide forest fire risk forecast information to minimize forest fire-related losses. In this research, forecast models of forest fire risk at a mid-range (with lead times up to 7 days) scale were developed considering past, present and future conditions (i.e., forest fire risk, drought, and weather) through random forest machine learning over South Korea. The models were developed using weather forecast data from the Global Data Assessment and Prediction System, historical and current Fire Risk Index (FRI) information, and environmental factors (i.e., elevation, forest fire hazard index, and drought index). Three schemes were examined: scheme 1 using historical values of FRI and drought index, scheme 2 using historical values of FRI only, and scheme 3 using the temporal patterns of FRI and drought index. The models showed high accuracy (Pearson correlation coefficient >0.8, relative root mean square error <10%), regardless of the lead times, resulting in a good agreement with actual forest fire events. The use of the historical FRI itself as an input variable rather than the trend of the historical FRI produced more accurate results, regardless of the drought index used.

• Journal of the Korea institute for structural maintenance and inspection
• /
• v.26 no.4
• /
• pp.20-29
• /
• 2022

The operational modal analysis (OMA) technique, which extracts the modal parameters of a structural system using ambient vibrations, has been actively developed as a field of structural health monitoring of cable-supported bridges. In this paper, the short and long-term modal parameters of a cable-stayed bridge were evaluated using the acceleration data obtained from the two ambient vibration tests (AVTs) and three years of continuous measurements. A total of 27 vertical modes and 1 lateral mode in the range 0.1 ~ 2.5 Hz were extracted from the high-resolution AVTs which were conducted in the 6th and 19th years after its completion. Existing OMA methods such as Peak-Picking (PP), Eigensystem Realization Algorithm with Data Correlation (ERADC), Frequency Domain Decomposition (FDD) and Time Domain Decomposition (TDD) were applied for modal parameters extraction, and it was confirmed that there was no significant difference between the applied methods. From the correlation analysis between long-term natural frequencies and environmental factors, it was confirmed that temperature change is the dominant factor influencing natural frequency fluctuations. It was revealed that the decreased natural frequencies of the bridge were not due to changes in structural performance and integrity, but to the environmental effects caused by the temperature difference between the two AVTs. In addition, when the TDD technique is applied, the accuracy of extracted mode shapes is improved by adding a proposed algorithm that normalizes the sequence so that the autocorrelations at zero lag equal 1.

• Journal of Advanced Navigation Technology
• /
• v.26 no.5
• /
• pp.365-372
• /
• 2022

Compared to sensors mainly used in human activity recognition (HAR) systems, inertial measurement unit (IMU) sensors are small and light, so can achieve lightweight system at low cost. Therefore, in this paper, we propose a binary neural network (BNN) based gait pattern analysis system using IMU sensor, and present the design and implementation results of an FPGA-based accelerator for computational acceleration. Six signals for gait are measured through IMU sensor, and a spectrogram is extracted using a short-time Fourier transform. In order to have a lightweight system with high accuracy, a BNN-based structure was used for gait pattern classification. It is designed as a hardware accelerator structure using FPGA for computation acceleration of binary neural network. The proposed gait pattern analysis system was implemented using 24,158 logics, 14,669 registers, and 13.687 KB of block memory, and it was confirmed that the operation was completed within 1.5 ms at the maximum operating frequency of 62.35 MHz and real-time operation was possible.