• Journal of IKEEE
• /
• v.27 no.3
• /
• pp.345-349
• /
• 2023

In this paper, we propose a study on the development of deep learning structure for defective pixel detection of next-generation smart LED display board using imaging device. In this research, a technique utilizing imaging devices and deep learning is introduced to automatically detect defects in outdoor LED billboards. Through this approach, the effective management of LED billboards and the resolution of various errors and issues are aimed. The research process consists of three stages. Firstly, the planarized image data of the billboard is processed through calibration to completely remove the background and undergo necessary preprocessing to generate a training dataset. Secondly, the generated dataset is employed to train an object recognition network. This network is composed of a Backbone and a Head. The Backbone employs CSP-Darknet to extract feature maps, while the Head utilizes extracted feature maps as the basis for object detection. Throughout this process, the network is adjusted to align the Confidence score and Intersection over Union (IoU) error, sustaining continuous learning. In the third stage, the created model is employed to automatically detect defective pixels on actual outdoor LED billboards. The proposed method, applied in this paper, yielded results from accredited measurement experiments that achieved 100% detection of defective pixels on real LED billboards. This confirms the improved efficiency in managing and maintaining LED billboards. Such research findings are anticipated to bring about a revolutionary advancement in the management of LED billboards.

• Korean Journal of Forensic Psychology
• /
• v.12 no.1
• /
• pp.53-73
• /
• 2021

This study is an experimental study comparing the psycho-physiological response differences of subjects according to the rapport building in polygraph tests. We randomly assigned 84 adults into a 2(veracity: Truth vs. Lie) x 2(rapport; Rapport building vs. Non-rapport building) between-subject design and measured ESS total scores as psycho-physiological responses. In order to manipulate the veracity conditions, participants in the truthful condition were told to tell their actual scores on several simple tasks but those in the lie condition were asked to tell higher scores than their actual scores. Afterwards all participants were polygraph tested in the order of pre-interview and main examination. The rapport conditions were manipulated by structured pre-interview scripts. As a result, there were significant differences in the examinee's total ESS scores depending on the veracity and rapport conditions. For truth-tellers, the ESS total scores were greater in the positive(+) direction in the rapport building condition than in the non-rapport building condition, indicating a prominent true response in the former condition. For liars, however, the ESS total scores were not significantly greater in the negative(-) direction in the rapport building condition than in the non-rapport building condition. Based on this study's results, we discussed the importance of rapport building in the pre-interview phase of a polygraph test and the need to operationalize verbal and non-verbal rapport building techniques.

• Journal of Dental Rehabilitation and Applied Science
• /
• v.38 no.4
• /
• pp.249-256
• /
• 2022

The implant prosthesis of anterior maxilla requires careful consideration in planning. In order to satisfy both esthetic and functional needs of a patient, fusion of intra-oral scan in Cone-beam computed tomography (CBCT) and facial scan can be considered. Bony structures and soft tissues captured in CBCT and occlusal surfaces of intra oral scan were incorporated into personal characteristics from facial scan. The patient had insufficient buccal bone on maxillary anterior area. The maxillary implants could not be placed on the most ideal position. However, the "top down" approach completed by computer-generated arranging of teeth in implant planning and surgery with surgical guide resulted in esthetically and functionally satisfying result regardless of the limitation. Careful diagnosis with digital technique and the usage of surgical guide resulted in successful surgery and esthetic restoration. The temporary fixed prostheses were designed, restored and evaluated. The patient was not satisfied with the first design of temporary prosthesis, which showed uneven space distribution between teeth due to the position of maxillary implant. The design was modified by changing proximal emergence contours and line angle to alter the perceived since of incisors. The patient was satisfied with the new design of provisional restoration. A digital occlusion analyzer (Arcus Digma II, KaVo, Leutkirch, Germany) was used to measure inherent condylar guidance and anterior guidance of a patient to provide a definitive prosthesis.

• Journal of the Korean Geotechnical Society
• /
• v.24 no.10
• /
• pp.33-43
• /
• 2008

In this study, for the purpose of evaluating the shear wave velocity in core zone, cross-hole test, down-hole test, MASW (Multi-channel Analysis of Surface Wave), and seismic reflection survey were carried out on the crest of the existing 'Y' dam. The results of field tests were compared one another. Furthermore, the field test results were compared with the result by the Sawada's empirical recommendation method. The purpose of this study is to compare the results of four kinds of field tests for evaluation of shear wave velocity in core zone of existing dam, to verify applicability of the empirical method which was recommended by Sawada and Takahashi, and to recommend a reasonable method for evaluation of shear wave velocity which is needed to evaluate tile maximum shear modulus of core zone. From the results of four kinds of field tests such as cross-hole test, down-hole test, MASW, and seismic reflection survey, it was found that the shear wave velocity distributions were similar within 18 m in depth and the results obtained by MASW and seismic reflection survey were almost the same by 30 m in depth. For evaluation of shear wave velocity in core zone of the existing dam, in consideration that it is not easy to bore the hole ill the core zone of existing dam, surface surveys such as MASW and seismic reflection method are recommended as realistic methods. On condition that it is impossible to conduct the field test and it is preliminary investigation, it is recommended that Sawada's low bound empirical equation be used.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.3
• /
• pp.145-151
• /
• 2023

3D-CNN is one of the deep learning techniques for learning time series data. Such three-dimensional learning can generate many parameters, so that high-performance machine learning is required or can have a large impact on the learning rate. When learning dynamic hand-gestures in spatiotemporal domain, it is necessary for the improvement of the efficiency of dynamic hand-gesture learning with 3D-CNN to find the optimal conditions of input video data by analyzing the learning accuracy according to the spatiotemporal change of input video data without structural change of the 3D-CNN model. First, the time ratio between dynamic hand-gesture actions is adjusted by setting the learning interval of image frames in the dynamic hand-gesture video data. Second, through 2D cross-correlation analysis between classes, similarity between image frames of input video data is measured and normalized to obtain an average value between frames and analyze learning accuracy. Based on this analysis, this work proposed two methods to effectively select input video data for 3D-CNN deep learning of dynamic hand-gestures. Experimental results showed that the learning interval of image data frames and the similarity of image frames between classes can affect the accuracy of the learning model.

• Journal of agriculture & life science
• /
• v.50 no.1
• /
• pp.117-124
• /
• 2016

Researches on soil microbial community are increasing to assess ecosystem responses to anthropogenic disturbances and to provide an indicator of ecosystem recovery. Microbial communities are able to respond more rapidly to environmental changes than plants and therefore they may provide an early indication of the ecosystem recovery trajectory. This study was conducted using 16S rRNA gene pyrosequencing of soil samples to compare soil bacterial community composition between artificially covered soils of the Baedudaegan ridgeline and their adjacent forest soils in two restoration project sites, Ihwaryeong and Yuksimnyeong, which were completed in 2012 and 2013, respectively. Richness of the Phylum level was 29.3 in Ihwaryeong and 32.3 in Yuksimnyeong. Significant difference in the richness between artificial restored soils and adjacent forest soils(p<0.01) was observed, however no significant difference was observed for site location and soil depth. Acidobacteria(37.3%) and Proteobacteria(31.1%) were more abundant than any other phylum in collected soil samples. Also, we found the significant difference in the relative abundance of the two abundant phyla between artificially restored soils and their adjacent forest soils (Proteobacteria, 38.1% in restored soils vs 24.2% in adjacent forest soils, p<0.01; Acidobacteria, 55.4% in restored soils vs 19.2% in adjacent forest soils, p<0.001). The results support the previous researches indicating that soil bacterial community composition is affected by nutritional status of soils and that Acidobacteria is also strongly influenced by pH, thus favoring soils with lower pH. This study could be utilized to monitor and evaluate restoration success of forest soil environment quantitatively.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.274-274
• /
• 2020

환경부 홍수통제소의 경우는 전국단위의 강수량(지상, 레이더), 하천수위, 유사량 관측과 국부적으로 증발산량과 토양수분 관측이 이루어지고 있는 상황이며, 기상청 및 다른 공공기관도 각 목적에 맞게 수문기상관측이 이루어지나 유역(또는 지역) 단위의 물순환 과정(강우량, 유출량, 증발산량, 지하수함양량, 토양수분량 등 포함)을 규명하는 조사·연구는 매우 미비한 실정이다. 개별적인 물순환 성분별 수문조사에서 벗어난 전체적인 관점을 고려한 유역단위의 물순환 과정을 규명하는 것은 매우 중요하다. 즉 물순환 성분별 명확한 수문량 산정 결과는 수자원 개발과 물환경 보전에 중요한 정보를 제공할 수 있다. 따라서 물순환 성분별 명확한 분석을 위해서는 중·소규모 유역 단위를 대상으로 지속적이고 신뢰성 있는 자료의 획득과 축적이 중요하므로 중·소규모 유역 단위의 대표성 있는 시험유역의 운영은 매우 의미가 있다고 볼 수 있다. 본 논문에서는 한국건설기술연구원에서 운영하는 설마천 유역(유역면적 8.48㎢, 유로경사 2.15%, 경기도 파주시 적성면 소재)의 신뢰성 높은 2019년 관측자료를 이용하여 물순환 성분인 강우량, 하천유출량, 증발산량과 지하수 함양량의 자료를 산정하였으며, 물순환 성분별 균형을 이루는 자료를 생성하였다. 기본 관측자료인 강우량은 각 지점강우량의 관측자료의 비교·검토 등 품질관리를 통해 자료를 확정하고 유역평균강우량을 산정하였다. 하천수위는 기준수위표와의 검토를 통해 자료를 확정하였으며, 하천유출량은 유량측정성과와 단면검토를 통해 수위-유량관계곡선식을 개발하고, 확정된 수위자료를 적용하여 산정하였다. 그리고 증발산량은 유역내의 기상관측자료를 활용하여 잠재증발산량을 산정하였으며, 지하수함양량은 유역내에 관측된 지하수위자료를 이용하여 지하수 함양량을 산정하였다. 각 물순환 성분별로 산정된 자료는 과거년 자료와 비교·평가를 통해 균형성을 판단하였다. 각 성분별 최대치와 최소범위, 평균값을 고려하고, 강우일수, 강우의 강우강도와 지속기간, 기상자료(기온, 일조시간, 습도, 풍속 등)를 충분히 고려하였다. 각 물순환 성분별로 생성된 2019년의 설마천 유역의 총강우량은 1,024.1mm이며, 하천유출량은 608.6mm(총강우량 대비 59.4%), 실제증발산량은 385.1mm(37.6%), 지하수함양량은 30.4mm(3.0%)이다. 여기서, 실제증발산량과 지하수 함양량은 1개 지점에서 산정값이나, 물순환의 폐합 조건을 고려하여 산정된 결과이다. 향후 유역 전체를 대표하는 기법의 개발은 필요한 실정이다. 이와 같이 산정된 물순환 성분별 자료는 유역의 물순환 과정 규명을 위한 기초자료로 매우 유용하게 활용될 수 있으며, 유역 물관리를 위한 의사결정 과정에 중요한 역할을 할 수 있을 것으로 기대된다.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.71-84
• /
• 2021

Since small and medium-sized enterprises fell short of the securement of technological competitiveness in the field of big data and artificial intelligence (AI) field-core technologies of the Fourth Industrial Revolution, it is important to strengthen the competitiveness of the overall industry through technology commercialization. In this study, we aimed to propose a priority related to technology transfer and commercialization for practical use of public research results. We utilized public research performance information, improving missing values of 6T classification by deep learning model with an ensemble method. Then, we conducted topic modeling to derive the converging fields of big data and AI. We classified the technology fields into four different segments in the technology portfolio based on technology activity and technology efficiency, estimating the potential of technology commercialization for those fields. We proposed a priority of technology commercialization for 10 detailed technology fields that require long-term investment. Through systematic analysis, active utilization of technology, and efficient technology transfer and commercialization can be promoted.

• Analytical Science and Technology
• /
• v.19 no.1
• /
• pp.96-102
• /
• 2006

Trimethylamine (TMA) is one of the difficult odorous compounds for the collection and analysis. Although sulfuric acid absorption and/or sulfuric acid impregnated filter method are commonly recommended for its sampling, these methods also suffer from difficulties involved in sample treatment and operational procedures. Hence, as an ancillary approach to measure TMA, we investigated the combination of bag sampling and SPME analysis for TMA measurements. For the purpose of our study, we investigated the following three subjects: 1) temporal variability of standard storage, 2) bag loss effect of TMS, and 3) TMA loss due to repetitive analysis of an identical bag sample. According to our storage test up to 7 or 20 dyas, TMA loss were found to occur up to 40 to 50% within relatively short period of up to 48 hrs depending on its concentration ranges. When the tests were made for bag loss by transferring TMA standards across different size bags, we were able to find that the extent of bag loss are not significant with 5 to 20% loss rate. Finally, the TMA sorptive loss via its exposure to SPME fiber was generally estimated to run from 2 to 3%.

• The Journal of the Korea Contents Association
• /
• v.22 no.5
• /
• pp.15-25
• /
• 2022

This study aims to identify the family and lineage of a part of a "Fish Tribe Conference" in the section Tokkijeon by utilizing computer literature analysis techniques. First of all, we encode the classification for a pairwise comparison's type of each paragraph to build a corpus, and based on this, we use the Hamming distance to calculate the distance matrix between each classification for a pairwise comparison's. We visualized classification for a pairwise comparison's clustering pattern by applying multidimensional scale method, and hierarchical clustering to explore the characteristics of the 'fish family' line and lineage compared to the existing cluster analysis study on entire paragraphs of "Tokkijeon". As a result, unlike the cluster analysis of the entire paragraph of "Tokkijeon", which consists of six categories, the "Fish Tribe Conference" section has five categories and some classification for a pairwise comparison's accesses. The results of this study are that the relative distance between Yibon was measured and systematic classification was performed in an objective and empirical way by calculation, and the characteristics of the line of the fish family were revealed compared to the analysis of the entire rabbit exhibition.