• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.225-238
• /
• 2018

In this paper, to investigate the influence of installation damage, a variety of full-scale field installation tests with 15 geosynthetics reinforcements and fill materials of various grain size distribution have been performed. The full-scale field installation test was conducted with reference to the FHWA (2009) guidelines. The tensile strength tests were performed by sampling up to 20 specimens randomly from the excavated geosynthetics reinforcements after compaction of fill material, and the degree of decrease in tensile strength of reinforcements due to compaction was analyzed based on the experiment results. It was found that the degree of tensile strength reduction of geosynthetics reinforcements due to the compaction of fill material is greatly influenced by the type of reinforcement and the maximum diameter of fill material. In addition, it was found that the strength reduction ratio of PET geogrid (PVC coating) with relatively small stiffness was greatest, and that the larger the maximum grain size of the fill material, the greater the strength reduction ratio. And also, a more reasonable evaluation method for the installation damage reduction factor of geosynthetics reinforcements is proposed based on the results of full-scale field installation tests in present study and the existing test results.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1012-1018
• /
• 2018

In this paper, CMOS SAR (Successive Approximation Register) A/D converter with 1.8V supply voltage is designed for IoT sensor processing. This paper proposes design of a 12-bit SAR A/D converter with two A / D converters in parallel to improve the sampling rate. A/D converter1 of the two A/D converters determines all the 12-bit bits, and another A/D converter2 uses the upper six bits of the other A/D converters to minimize power consumption and switching energy. Since the second A/D converter2 does not determine the upper 6 bits, the control circuits and SAR Logic are not needed and the area is minimized. In addition, the switching energy increases as the large capacitor capacity and the large voltage change in the C-DAC, and the second A/D converter does not determine the upper 6 bits, thereby reducing the switching energy. It is also possible to reduce the process variation in the C-DAC by proposed structure by the split capacitor capacity in the C-DAC equals the unit capacitor capacity. The proposed SAR A/D converter was designed using 0.18um CMOS process, and the supply voltage of 1.8V, the conversion speed of 10MS/s, and the Effective Number of Bit (ENOB) of 10.2 bits were measured. The area of core block is $600{\times}900um^2$, the total power consumption is $79.58{\mu}W$, and the FOM (Figure of Merit) is 6.716fJ / step.

• Tunnel and Underground Space
• /
• v.29 no.4
• /
• pp.230-242
• /
• 2019

While various automatic rock fracture survey methods have been researched, the evaluation of the accuracy of these methods raises issues due to the absence of a metric which fully expresses the similarity between automatic and manual fracture maps. Therefore, this paper proposes a geometry similarity metric which is especially designed to determine the overall similarity of fracture maps and to evaluate the accuracy of rock fracture survey methods by a single number. The proposed metric, Scanline Intersection Similarity (SIS), is derived by conducting a large number of scanline surveys upon two fracture maps using Python code. By comparing the frequency of intersections over a large number of scanlines, SIS is able to express the overall similarity between two fracture maps. The proposed metric was compared with Intersection Over Union (IoU) which is a widely used evaluation metric in computer vision. Results showed that IoU is inappropriate for evaluating the geometry similarity of fracture maps because it is overly sensitive to minor geometry differences of thin elongated objects. The proposed metric, on the other hand, reflected macro-geometry differences rather than micro-geometry differences, showing good agreement with human perception. The metric was further applied to evaluate the accuracy of a deep learning-based automatic fracture surveying method which resulted as 0.674 (SIS). However, the proposed metric is currently limited to 2D fracture maps and requires comparison with rock joint parameters such as RQD.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.39 no.3
• /
• pp.141-148
• /
• 2021

This paper presents a method to detect zebra-crossing using deep learning which combines SegNet and ResNet. For the blind, a safe crossing system is important to know exactly where the zebra-crossings are. Zebra-crossing detection by deep learning can be a good solution to this problem and robotic vision-based assistive technologies sprung up over the past few years, which focused on specific scene objects using monocular detectors. These traditional methods have achieved significant results with relatively long processing times, and enhanced the zebra-crossing perception to a large extent. However, running all detectors jointly incurs a long latency and becomes computationally prohibitive on wearable embedded systems. In this paper, we propose a model for fast and stable segmentation of zebra-crossing from captured images. The model is improved based on a combination of SegNet and ResNet and consists of three steps. First, the input image is subsampled to extract image features and the convolutional neural network of ResNet is modified to make it the new encoder. Second, through the SegNet original up-sampling network, the abstract features are restored to the original image size. Finally, the method classifies all pixels and calculates the accuracy of each pixel. The experimental results prove the efficiency of the modified semantic segmentation algorithm with a relatively high computing speed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.2
• /
• pp.276-284
• /
• 2020

This paper proposes a new convolutional neural network (CNN) based spectrum sensing technique for cognitive radio communications. The proposed technique determines the existence of the primary user (PU) by using energy detection without any prior knowledge of the PU's signal. In the proposed method, the received signal is high-rate sampled to sense the entire spectrum bands of interest. After that, fast Fourier transform (FFT) of the signal converts the time domain signal to frequency domain spectrum and by stacking those consecutive spectrums, a 2 dimensional signal is made. The 2 dimensional signal is cut by the sensing channel bandwidth and inputted to the CNN. The CNN determines the existence of the primary user. Since there are only two states (existence or non-existence), binary classification CNN is used. The performance of the proposed method is examined through computer simulation and indoor experiment. According to the results, the proposed method outperforms the conventional threshold-based method by over 2 dB.

• Journal of Korea Entertainment Industry Association
• /
• v.15 no.2
• /
• pp.159-167
• /
• 2021

The main purpose of this study is to closely investigate the constructive relationship between leisure satisfaction, leisure ability, exercise satisfaction, and consistent motor behavior patterns of the elderly's participation in leisure life sports. In order to achieve this, we surveyed and utilized the sampling of conveniences that selected Yongin and Seongnam city in Gyeonggi-do sports clubs, and accumulated samples of the elderly in living sports. The sample size was 239 elderly people. Based on this, according to the purpose of the study, statistical techniques, spss 23.0, and amos programs were used for analysis. The satisfaction analysis used in the research for a data analysis includes frequency analysis, exploatory factor analysis, confirmatory facor analysis, reliability analysis, correnlation analysis and structure equation model analysis. The research has drawn the following conclusions, based on the above mentioned research method and its procedures: First, it affects the satisfaction of the leisure satisfaction movement. Second, leisure ability affects exercise satisfaction. Third, exercise satisfaction affects the consistent exercise persistence and immersion satisfaction of exercise. As a result, it can be seen that the leisure immersion according to the experience of leisure competence has an effect on the satisfaction of the exercise. As a result, and the continuation of the exercise.

• Journal of Korean Society for Geospatial Information Science
• /
• v.14 no.2 s.36
• /
• pp.89-94
• /
• 2006

Forest damage is a worldwide issue and specially, a forest fire involves damage to itself and causes secondary damage such as a flood etc. However, actually, clear analysis on forest fire damage can be hardly conducted due to difficulty in approaching a forest fire and quite a long period of time for analysis. To overcome such difficulty, recently, forest fire damage has been actively investigated with satellite image data, but it is also difficult to obtain satellite image data fitted to the time a forest fire occurred. In addition, it is burdensome to verify accuracy of the obtained image. Therefore, this study was attempted to look into the damaged districts from forest fires by reference to spectroradiometric characteristics of the obtained vegetation with a spectroradiometer as preliminary work to use satellite image data. To begin with, the researcher analyzed the field survey data each measured 3 months and 6 months after occurrence of a forest fire by judging the extent of the damage through visual observation and using a spectroradiometer in order to investigate any potential errors arising out of one-time visual observation. Besides, in this study, groups showing possibilities that trees might be restored to life and wither to death could be classified on the sampling points where forest fire damage is minor.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.6
• /
• pp.259-266
• /
• 2023

It is very difficult to measure the performance of the machine learning model in the business service stage. Therefore, managing the performance of the model through the operational department is not done effectively. Academically, various studies have been conducted on the concept drift detection method to determine whether the model status is appropriate. The operational department wants to know quantitatively the performance of the operating model, but concept drift can only detect the state of the model in relation to the data, it cannot estimate the quantitative performance of the model. In this study, we propose a performance prediction model (PPM) that quantitatively estimates precision through the statistics of concept drift. The proposed model induces artificial drift in the sampling data extracted from the training data, measures the precision of the sampling data, creates a dataset of drift and precision, and learns it. Then, the difference between the actual precision and the predicted precision is compared through the test data to correct the error of the performance prediction model. The proposed PPM was applied to two models, a loan underwriting model and a credit card fraud detection model that can be used in real business. It was confirmed that the precision was effectively predicted.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.40 no.1
• /
• pp.51-66
• /
• 2022

SST (Sea Surface Temperature) is based on the atmosphere-ocean interaction, one of the most important mechanisms for the Earth system. Because it is a crucial oceanic and meteorological factor for understanding climate change, gap-free grid data at a specific spatial and temporal resolution is beneficial in SST studies. This paper examined the production of daily SST grid maps from 137 stations in 2020 through the ordinary kriging with variogram optimization and their accuracy assessment. The variogram optimization was achieved by WLS (Weighted Least Squares) method, and the blind tests for the interpolation accuracy assessment were conducted by an objective and spatially unbiased sampling scheme. The four-round blind tests showed a pretty high accuracy: a root mean square error between 0.995 and 1.035℃ and a correlation coefficient between 0.981 and 0.982. In terms of season, the accuracy in summer was a bit lower, presumably because of the abrupt change in SST affected by the typhoon. The accuracy was better in the far seas than in the near seas. West Sea showed better accuracy than East or South Sea. It is because the semi-enclosed sea in the near seas can have different physical characteristics. The seasonal and regional factors should be considered for accuracy improvement in future work, and the improved SST can be a member of the SST ensemble around South Korea.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.6
• /
• pp.255-266
• /
• 2022

The quality control of coarse aggregate among aggregates, which are the main ingredients of concrete, is currently carried out by SPC(Statistical Process Control) method through sampling. We construct a smart factory for manufacturing innovation by changing the quality control of coarse aggregates to inspect the coarse aggregates based on this image by acquired images through the camera instead of the current sieve analysis. First, obtained images were preprocessed, and HED(Hollistically-nested Edge Detection) which is the filter learned by deep learning segment each object. After analyzing each aggregate by image processing the segmentation result, fineness modulus and the aggregate shape rate are determined by analyzing result. The quality of aggregate obtained through the video was examined by calculate fineness modulus and aggregate shape rate and the accuracy of the algorithm was more than 90% accurate compared to that of aggregates through the sieve analysis. Furthermore, the aggregate shape rate could not be examined by conventional methods, but the content of this paper also allowed the measurement of the aggregate shape rate. For the aggregate shape rate, it was verified with the length of models, which showed a difference of ±4.5%. In the case of measuring the length of the aggregate, the algorithm result and actual length of the aggregate showed a ±6% difference. Analyzing the actual three-dimensional data in a two-dimensional video made a difference from the actual data, which requires further research.