• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.6
• /
• pp.571-581
• /
• 2020

Vegetation affects water level change and flow resistance in rivers and impacts waterway ecosystems as a whole. Therefore, it is important to have accurate information about the species, shape, and size of any river vegetation. However, it is not easy to collect full vegetation data on-site, so recent studies have attempted to obtain large amounts of vegetation data using terrestrial laser scanning (TLS). Also, due to the complex shape of vegetation, it is not easy to obtain accurate information about the canopy area, and there are limitations due to a complex range of variables. Therefore, the physical structure of vegetation was analyzed in this study by reconfiguring high-resolution point cloud data collected through 3-dimensional terrestrial laser scanning (3D TLS) in a voxel. Each physical structure was analyzed under three different conditions: a simple vegetation formation without leaves, a complete formation with leaves, and a patch-scale vegetation formation. In the raw data, the outlier and unnecessary data were filtered and removed by Statistical Outlier Removal (SOR), resulting in 17%, 26%, and 25% of data being removed, respectively. Also, vegetation volume by voxel size was reconfigured from post-processed point clouds and compared with vegetation volume; the analysis showed that the margin of error was 8%, 25%, and 63% for each condition, respectively. The larger the size of the target sample, the larger the error. The vegetation surface looked visually similar when resizing the voxel; however, the volume of the entire vegetation was susceptible to error.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.211-220
• /
• 2022

Recently, research on smart factories triggered by the 4th industrial revolution is being actively conducted. Accordingly, the manufacturing industry is conducting various studies to improve productivity and quality based on deep learning technology with robust performance. This paper is a study on the method of detecting tire surface defects in the visual inspection stage of the tire manufacturing process, and introduces a tire surface defect detection method using a depth image acquired through a 3D camera. The tire surface depth image dealt with in this study has the problem of low contrast caused by the shallow depth of the tire surface and the difference in the reference depth value due to the data acquisition environment. And due to the nature of the manufacturing industry, algorithms with performance that can be processed in real time along with detection performance is required. Therefore, in this paper, we studied a method to normalize the depth image through relatively simple methods so that the tire surface defect detection algorithm does not consist of a complex algorithm pipeline. and conducted a comparative experiment between the general normalization method and the normalization method suggested in this paper using YOLO V3, which could satisfy both detection performance and speed. As a result of the experiment, it is confirmed that the normalization method proposed in this paper improved performance by about 7% based on mAP 0.5, and the method proposed in this paper is effective.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.562-565
• /
• 2022

Recently, the increasing number of overloaded vehicles on the road poses a risk to traffic safety, such as falling objects, road damage, and chain collisions due to the abnormal weight distribution, and can cause great damage once an accident occurs. However, this irregular weight distribution is not possible to be recognized with the current weight measurement system for vehicles on roads. To address this limitation, we propose to build an object detection-based AI model to identify overloaded vehicles that cause such social problems. In addition, we present a simple yet effective method to construct an object detection model for the large-scale vehicle images. In particular, we utilize the large-scale of vehicle image sets provided by open AI-Hub, which include the overloaded vehicles from the CCTV, black box, and hand-held camera point of view. We inspected the specific features of sizes of vehicles and types of image sources, and pre-processed these images to train a deep learning-based object detection model. Finally, we demonstrated that the detection performance of the overloaded vehicle was improved by about 23% compared to the one using raw data. From the result, we believe that public big data can be utilized more efficiently and applied to the development of an object detection-based overloaded vehicle detection model.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.6
• /
• pp.55-60
• /
• 2023

When performing the multiplication m×r=p of two binary numbers m and r on a computer, there is a shift-and-add(SA) method in which no time-consuming multiplication is performed, but only addition and shift-right(SR). SA is a very simple method in which when the value of the multiplier r_i is 0, the result p is only SR with m×0=0, and when r_i is 1, the result p=p+m is performed with m×1=m, and p is SR. In SA, the number of SRs can no longer be shortened, and the improvement part is whether the number of additions is shortened. This paper proposes an SA method to minimize addition based on the fact that setting a smaller number to r when converted to a binary number to be processed by a computer can significantly reduce the number of additions compared to the case of setting a smaller number to r based on the decimals that humans perform. The number of additions to the proposed algorithm was compared for four cases with signs (-,-), (-,+), (+,-), and (+,+) for some numbers in the range [-127,128]. The conclusion obtained from the experiment showed that when determining m and r, it should be determined as a binary number rather than a decimal number.

• Science of Emotion and Sensibility
• /
• v.26 no.3
• /
• pp.41-52
• /
• 2023

The purpose of this study was to determine the effects of resilience on information processing. Thirty-nine male high school students were randomly selected and assigned to one of the three experimental groups: (1) high group (n = 13), (2) middle group (n = 13) and low group (n = 13) according to their resilience scale (KRQ-53) scores. The tasks were simple reaction time, choice reaction time-1, and choice reaction time -2. Electroencephalogram (EEG) was measured at Fp1, Fp2, F3, F4, Fz, Cz and Pz. A 3 × 8 × 4 (groups × areas × times) ANOVA with repeated measures on the last factor was calculated to determine resilience effects on EEG. P300 was analyzed using a 3 × 3 × 8 (groups × tasks × areas) ANOVA. The results showed that the theta waves of the middle group were higher than those of the high and low groups. Second, as a result of analyzing alpha waves, the high group demonstrated higher alpha waves than the middle and low groups. Third, the mid-beta waves of the middle and low groups were higher than those of the high group. Lastly, the result of this study showed that the P300 amplitude of the middle group was higher than that of the high and low groups. These results indicated that the middle group processed cognitive information more efficiently than the other two groups. The findings of this study demonstrated that cognitive information processing ability varies depending on the degree of resilience.

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.7
• /
• pp.41-51
• /
• 2024

In this paper, we explore the enhancement of target detection accuracy in the guided weapon using deep learning object detection on infrared (IR) images. Due to the characteristics of IR images being influenced by factors such as time and temperature, it's crucial to ensure a consistent representation of object features in various environments when training the model. A simple way to address this is by emphasizing the features of target objects and reducing noise within the infrared images through appropriate pre-processing techniques. However, in previous studies, there has not been sufficient discussion on pre-processing methods in learning deep learning models based on infrared images. In this paper, we aim to investigate the impact of image pre-processing techniques on infrared image-based training for object detection. To achieve this, we analyze the pre-processing results on infrared images that utilized global or local information from the video and the image. In addition, in order to confirm the impact of images converted by each pre-processing technique on object detector training, we learn the YOLOX target detector for images processed by various pre-processing methods and analyze them. In particular, the results of the experiments using the CLAHE (Contrast Limited Adaptive Histogram Equalization) shows the highest detection accuracy with a mean average precision (mAP) of 81.9%.

• Journal of Radiation Protection and Research
• /
• v.41 no.1
• /
• pp.71-79
• /
• 2016

Background: It is necessary to analyze radioactivity of naturally occurring radioactive materials (NORM) in products to ensure radiological safety required by Natural Radiation Safety Management Act. The pretreatments for the existing analysis methods require high technology and time. Such destructive pretreatments including grinding and dissolution of samples make impossible to reuse products. We developed a rapid and simple procedure of radioactivity analysis for thorium series in the products containing NORM. Materials and Methods: The developed method requires non-destructive or minimized pretreatment. Radioactivity of the product without pretreatment is initially measured using gamma spectroscopy and then the measured radioactivity is adjusted by considering material composition, mass density, and geometrical shape of the product. The radioactivity adjustment can be made using scaling factors, which is derived by radiation transport Monte Carlo simulation. Necklace, bracelet, male health care product, and tile for health mat were selected as representative products for this study. The products are commonly used by the public and directly contacted with human body and thus resulting in high radiation exposure to the user. Results and Discussion: The scaling factors were derived using MCNPX code and the values ranged from 0.31 to 0.47. If radioactivity of the products is measured without pretreatment, the thorium series may be overestimated by up to 2.8 times. If scaling factors are applied, the difference in radioactivity estimates are reduced to 3-24%. Conclusion : The developed procedure in this study can be used for other products with various materials and shapes and thus ensuring radiological safety.

• Journal of Intelligence and Information Systems
• /
• v.16 no.3
• /
• pp.55-75
• /
• 2010

Sequential pattern mining aims to discover interesting sequential patterns in a sequence database, and it is one of the essential data mining tasks widely used in various application fields such as Web access pattern analysis, customer purchase pattern analysis, and DNA sequence analysis. In general sequential pattern mining, only the generation order of data element in a sequence is considered, so that it can easily find simple sequential patterns, but has a limit to find more interesting sequential patterns being widely used in real world applications. One of the essential research topics to compensate the limit is a topic of weighted sequential pattern mining. In weighted sequential pattern mining, not only the generation order of data element but also its weight is considered to get more interesting sequential patterns. In recent, data has been increasingly taking the form of continuous data streams rather than finite stored data sets in various application fields, the database research community has begun focusing its attention on processing over data streams. The data stream is a massive unbounded sequence of data elements continuously generated at a rapid rate. In data stream processing, each data element should be examined at most once to analyze the data stream, and the memory usage for data stream analysis should be restricted finitely although new data elements are continuously generated in a data stream. Moreover, newly generated data elements should be processed as fast as possible to produce the up-to-date analysis result of a data stream, so that it can be instantly utilized upon request. To satisfy these requirements, data stream processing sacrifices the correctness of its analysis result by allowing some error. Considering the changes in the form of data generated in real world application fields, many researches have been actively performed to find various kinds of knowledge embedded in data streams. They mainly focus on efficient mining of frequent itemsets and sequential patterns over data streams, which have been proven to be useful in conventional data mining for a finite data set. In addition, mining algorithms have also been proposed to efficiently reflect the changes of data streams over time into their mining results. However, they have been targeting on finding naively interesting patterns such as frequent patterns and simple sequential patterns, which are found intuitively, taking no interest in mining novel interesting patterns that express the characteristics of target data streams better. Therefore, it can be a valuable research topic in the field of mining data streams to define novel interesting patterns and develop a mining method finding the novel patterns, which will be effectively used to analyze recent data streams. This paper proposes a gap-based weighting approach for a sequential pattern and amining method of weighted sequential patterns over sequence data streams via the weighting approach. A gap-based weight of a sequential pattern can be computed from the gaps of data elements in the sequential pattern without any pre-defined weight information. That is, in the approach, the gaps of data elements in each sequential pattern as well as their generation orders are used to get the weight of the sequential pattern, therefore it can help to get more interesting and useful sequential patterns. Recently most of computer application fields generate data as a form of data streams rather than a finite data set. Considering the change of data, the proposed method is mainly focus on sequence data streams.

• Korean Journal of Food Science and Technology
• /
• v.34 no.3
• /
• pp.361-364
• /
• 2002

This study was performed to establish a simple and accurate method for the determination of oxygen that is a processing aid in various beverage. The quantitative determination of dissolved oxygen (DO) contents in 30 cases of samples were performed by traditional titration method and polarography. As a result of the study, the analysis of DO contents in fruit-extract beverages containing oxygen by titration method was time consuming and large sample volumes were needed. Besides, serious interferences with compounds such as hydroxylamine and nitric oxide were observed, leading to false response. Although the polarography is easily affected by $H_2S$, proteins, and various organic compounds, it is a simple and practical method that provides inexpensive and relatively rapid analysis. The polarography is best suited to the routine determination of DO in a large number of samples and it is expected that the polarography can directly be applied to the quality control of the beverages containing added oxygen. The analysis results of DO contents in various fruit-extract beverages with oxygen and without oxygen were as follows: 23.10 ppm to 32.60 ppm for various frutis extract beverages with oxygen, 0.70 pp to 2.54 ppm for mixed beverages without oxygen, 7.63 ppm to 8.28 ppm for drinking water.

• Investigative Magnetic Resonance Imaging
• /
• v.3 no.2
• /
• pp.154-158
• /
• 1999

Purpose : The purpose of this study was to find the optimum TE value for enhancing $T_2^{*}$ weighting effect and minimizing the SNR degradation and to compare the BOLD effects according to the changes of TE in 1.5T and 3.0T MRI systems. Materials and Methods : Healthy normal volunteers (eight males and two females with 24-38 years old) participated in this study. Each volunteer was asked to perform a simple finger-tapping task (sequential opposition of thumb to each of the other four fingers) with right hand with a mean frequency of about 2Hz. The stimulus was initially off for 3 images and was then alternatively switched on and off for 2 cycles of 6 images. Images were acquired on the 1.5T and 3.0T MRI with the FLASH (fast low angle shot) pulse sequence (TR : 100ms, FA : $20^{\circ}$, FOV : 230mm) that was used with 26, 36, 46, 56, 66, 76ms of TE times in 1.5T and 16, 26, 36, 46, 56, 66ms of TE in 3.0T MRI system. After the completion of scan, MR images were transferred into a PC and processed with a home-made analysis program based on the correlation coefficient method with the threshold value of 0.45. To search for the optimum TE value in fMRI, the difference between the activation and the rest by the susceptibility change for each TE was used in 1.5T and 3.0T respectively. In addition, the functional $T_2^{*}$ map was calculated to quantify susceptibility change. Results : The calculated optimum TE for fMRI was $61.89{\pm}2.68$ at 1.5T and $47.64{\pm}13.34$ at 3.0T. The maximum percentage of signal intensity change due to the susceptibility effect inactivation region was 3.36% at TE 66ms in 1.5T 10.05% at TE 46ms in 3.0T, respectively. The signal intensity change of 3.0T was about 3 times bigger than of 1.5T. The calculated optimum TE value was consistent with TE values which were obtained from the maximum signal change for each TE. Conclusion : In this study, the 3.0T MRI was clearly more sensitive, about three times bigger than the 1.5T in detecting the susceptibility due to the deoxyhemoglobin level change in the functional MR imaging. So the 3.0T fMRI I ore useful than 1.5T.