• Title/Summary/Keyword: 판별자

Search Result 487, Processing Time 0.026 seconds

An Accurate Forward Head Posture Detection using Human Pose and Skeletal Data Learning

  • Jong-Hyun Kim
    • Journal of the Korea Society of Computer and Information
    • /
    • v.28 no.8
    • /
    • pp.87-93
    • /
    • 2023
  • In this paper, we propose a system that accurately and efficiently determines forward head posture based on network learning by analyzing the user's skeletal posture. Forward head posture syndrome is a condition in which the forward head posture is changed by keeping the neck in a bent forward position for a long time, causing pain in the back, shoulders, and lower back, and it is known that daily posture habits are more effective than surgery or drug treatment. Existing methods use convolutional neural networks using webcams, and these approaches are affected by the brightness, lighting, skin color, etc. of the image, so there is a problem that they are only performed for a specific person. To alleviate this problem, this paper extracts the skeleton from the image and learns the data corresponding to the side rather than the frontal view to find the forward head posture more efficiently and accurately than the previous method. The results show that the accuracy is improved in various experimental scenes compared to the previous method.

Comparative Analysis and Applicability Evaluation of River Main Flow Direction Search Method using Spatio-Temporal Volume analysis (시공간체적 분석법을 활용한 하천 주흐름 방향 탐색방법의 비교 분석 및 적용성 평가)

  • Lee, Yun Ho;Yu, Kwon Kyu;Yoon, Byung Man;Kim, Seo Jun
    • Proceedings of the Korea Water Resources Association Conference
    • /
    • 2022.05a
    • /
    • pp.15-15
    • /
    • 2022
  • 우리나라 홍수 발생은 강수량이 집중되는 여름철에 집중되어 있어 홍수피해 방지에 주의가 필요하다. 보와 제방 등 이러한 홍수 피해를 대비하기 위한 구조물에 설계를 위해서는 하천의 유량 조사가 필수적으로 요구된다. 하지만 홍수기 직접적인 유량 조사는 안전상의 이유로 거의 이루어지지지 않고 있으며, 수위를 측정하여 수위-유량 관계를 만들어 유량을 측정하고 있다. 그러나 중소 규모의 하천의 경우 하도 경사가 급해 사류가 발생하거나 하도 단면이 급변하는 경우가 있어 수위-유량 관계를 그대로 적용하기 어려운 문제가 있다. 따라서 이러한 문제를 해결하기 위해 하천에 진입하지 않고 유속을 측정 할 수 있는 영상유속계와 같이 흐름 영상을 사용하여 유속을 측정하는 방법들이 개발되었다. 영상유속계의 측정 방법중 Spatio Temporal Image(시공간 영상)을 사용하는 방법은 일정시간의 시간평균 유속을 산정할 수 있고 한 장의 시공간 영상을 분석하기 때문에 유속 산정에 걸리는 시간이 작은 장점이 있지만 영상 내 흐름 방향을 정확히 설정하지 못하면 오차가 생길 수 있는 문제가 있어 주 흐름 방향을 정확히 탐색할 필요가 있다. 따라서 본 연구에서는 영상에서 시공간 체적을 만들어 주흐름 방향을 찾아내는 기법들의 장단점을 비교하고 안동 하천실험센터의 실규모 하천수로에 적용하여 결과를 비교하고 적용성을 평가하였다. 이를 위해 하천수로에 추적자를 살포하여 영상으로 녹화하였으며 녹화된 영상을 자기상관법과 시간적분법을 적용하였으며, 이를 통해 주 흐름 방향을 판별하였다. 또한 두 방법을 통해 결정된 주흐름 방향을 적용하여 시공간 영상을 제작하고 이를 이용하여 유속을 산정하여 비교하였으며, 주흐름 방향을 산정하는데 생기는 오차가 유속 계산에 얼마만큼의 영향을 끼치는지 분석하였다. 이러한 실험을 통해 하천에서 시공간 영상을 활용한 표면영상 유속계측 방법을 활용하는데 있어 도움이 될 것으로 기대된다.

  • PDF

Characteristics Analysis of SiPM for Detection of High Sensitivity of Portable Detectors (휴대용 검출기의 방사선 고감도 검출을 위한 SiPM 특성 분석)

  • Byung-Wuk Kang;Sun-Kook Yoo
    • Journal of the Korean Society of Radiology
    • /
    • v.17 no.6
    • /
    • pp.897-902
    • /
    • 2023
  • The purpose of this paper is to analyze the characteristics of Silicon Photomultiplier (SiPM) for the realization of high-sensitivity radiation detection in portable detectors. Portable X-ray detectors offer the advantage of quickly accessing the patient's location and obtaining real-time images, allowing physicians to perform rapid diagnoses. However, this mobility comes with challenges in achieving accurate radiation detection. In existing detectors, SiPM is used for a simple purpose of detecting X-ray triggers. To verify the feasibility of high-sensitivity X-ray detection through SiPM, seven types of SiPM sensors were compared and selected, and their characteristics were analyzed. The SiPM used in the final test demonstrated the ability to distinguish signals at the ultra-low radiation level of 10 nGy, and it was observed that the slope of the signal rise curve varies with the X-ray tube voltage. Utilizing the characteristics of SiPM, which exhibits changes in signal level and duration with X-ray dose, it appears possible to achieve high-sensitivity measurements for X-ray detection.

Development for Analysis Service of Crowd Density in CCTV Video using YOLOv4 (YOLOv4를 이용한 CCTV 영상 내 군중 밀집도 분석 서비스 개발)

  • Seung-Yeon Hwang;Jeong-Joon Kim
    • The Journal of the Institute of Internet, Broadcasting and Communication
    • /
    • v.24 no.3
    • /
    • pp.177-182
    • /
    • 2024
  • In this paper, the purpose of this paper is to predict and prevent the risk of crowd concentration in advance for possible future crowd accidents based on the Itaewon crush accident in Korea on October 29, 2022. In the case of a single CCTV, the administrator can determine the current situation in real time, but since the screen cannot be seen throughout the day, objects are detected using YOLOv4, which learns images taken with CCTV angle, and safety accidents due to crowd concentration are prevented by notification when the number of clusters exceeds. The reason for using the YOLO v4 model is that it improves with higher accuracy and faster speed than the previous YOLO model, making object detection techniques easier. This service will go through the process of testing with CCTV image data registered on the AI-Hub site. Currently, CCTVs have increased exponentially in Korea, and if they are applied to actual CCTVs, it is expected that various accidents, including accidents caused by crowd concentration in the future, can be prevented.

Evaluation of Puretone Threshold Using Periodic Health Examination Data on Noise-exposed Workers in Korea (소음 특수건강진단 자료를 이용한 순음청력검사 평가)

  • Kim, Yang-Ho;Choi, Jung-Keun;Park, Jung-Sun;Moon, Young-Han;Kim, Kyoo-Sang
    • Journal of Preventive Medicine and Public Health
    • /
    • v.32 no.1
    • /
    • pp.30-39
    • /
    • 1999
  • Objectives. This study was carried out to evaluate hearing impairment judgement and to investigate the differences in various diagnostic criteria for noise-induced hearing loss (NIHL) among workers who required for close observation (C). Methods. Out of 731,029 workers who had taken the specific periodic health examination in 1994, we used the audiometric data on 37,999 workers (C) eliminating the employees who had previous otologic problems. Many investigators have being using different criteria for the evaluation of hearing impairment. In this study, we used the criteria of early (1989-1994), current, compensation for NIHL in Korea, 2-, 3-, 4-divided classification and hearing loss at 4,000 Hz and compared the evaluation results. Results. The prevalences of C and workers who had occupational disease $(D_1)$ diagnosed for NIHL were 11.1 % and 0.44 %. There were significant difference in the prevalences of C and $D_1$, depending on different province of Korea. Pure tone averages (PTAs) were not appropriately applied in their evaluation 97% of workers whom we studied on were below the level of mild hearing loss judged by ISO standard. However, there were wide variations in the prevalence rate of mild hearing loss by diagnostic criteria. Thus, there were different judgements in determining the degree of NIHL depending on which diagnostic criteria were utilized. PTAs were found 20.54 (Rt) and 20.74 (Lt) when the method of 3-divided classification was applied for audiometric data. The degree of hearing impairment of the left ear was more severe than that of right ear. The prevalence of normal hearing threshold below 20 dB was 75.4% and the range of difference in both ear was below 10 dB. Right sided hearing threshold levels were 21.08 dB (500 Hz), 18.44 dB (1,000 Hz), 22.09 (2,000 Hz) and 52.36 dB (4,000 Hz). There was typical high frequency loss (C5-dip at 4,000 Hz) above 30 - 40 dB in normal hearing level. The increasing trend in hearing threshold level was gradually decreased by the increase of PTAs. The difference between PTAs and threshold at 4,000 Hz was about 10 dB. Conclusions. We could found that PTAs in the previous examination were not appropriately evaluated. This study revealed that they did not use unique criteria for managing the workers of NIHL. For the prevention of NIHL, it was found that the quality control on diagnosis and comprehensive management program were required, especially for those of hearing loss (C).

  • PDF

Interobserver Reproducibility of Segmental Scoring of $^{99m}Tc$-MIBI Myocardial SPECT ($^{99m}Tc$-MIBI 심근 SPECT의 분절 육안 분석시 판독자간의 일치도)

  • Yeo, Jeong-Seok;Lee, Dong-Soo;Lee, Kyung-Han;Kim, Jong-Ho;Shon, Kyung-Soo;Cho, Sung-Wook;Kwark, Cheol-Eun;Chung, June-Key;Lee, Myung-Chul;Seo, Jeong-Don;Koh, Chang-Soon
    • The Korean Journal of Nuclear Medicine
    • /
    • v.28 no.3
    • /
    • pp.317-325
    • /
    • 1994
  • The accuracy of dipyridamole stress/rest $^{99m}Tc$-MIBI myocardial imaging for detection of ischemia depends on reproducible image interpretation. To evaluate the reproducibility of visual assessment, agreement in interpretation among two independent observers, blind-ed to clinical data, was evaluated in SPECT images of 131 patients (94 males, 38 females; mean age $58{\pm}7yr$) with suspected coronary artery disease who underwent both dipyridamole stress/rest $^{99m}Tc$-MIBI myocardial SPECT and coronary angiography. The left ventricle was divided into twenty-nine segments in stress and rest SPECT images and each segment was visually graded according to a five-point scale (segmental score : 0=normal, 1=equivocal, 2=mild decrease, 3=severe decrease and 4=absent uptake). Overall concordance of segmental scoring between the two observers was 80%. The Pear-son's correlation coefficient (r) of the segmental scores for stress and rest images were 0.67 and 0.65, respectively, while the difference in score between the two images showed a correlation of 0.45 (all p<0.001). Agreement between two observers in final SPECT diagnosis as absence or presence of disease was 93%. The degree of agreement in segmental scoring showed no difference between patients with or without agreement as to the presence of disease. Therefore it appeared that cases with inconcordant diagnosis between the 2 observers were mainly due to a difference in individual threshold for interpretating the significance of a particular decreased uptake area rather than to a difference in perceiving the degree of the hypoactivity Thus, establishment of individual optimum thresholds in visual interpretation of myocardial SPECT may be helpful to improve reproducibility and accuracy of scan diagnosis.

  • PDF

Overall risk analysis of shield TBM tunnelling using Bayesian Networks (BN) and Analytic Hierarchy Process (AHP) (베이지안 네트워크와 AHP (Analytic Hierarchy Process)를 활용한 쉴드 TBM 터널 리스크 분석)

  • Park, Jeongjun;Chung, Heeyoung;Moon, Joon-Bai;Choi, Hangseok;Lee, In-Mo
    • Journal of Korean Tunnelling and Underground Space Association
    • /
    • v.18 no.5
    • /
    • pp.453-467
    • /
    • 2016
  • Overall risks that can occur in a shield TBM tunnelling are studied in this paper. Both the potential risk events that may occur during tunnel construction and their causes are identified, and the causal relationship between causes and events is obtained in a systematic way. Risk impact analysis is performed for the potential risk events and ways to mitigate the risks are summarized. Literature surveys as well as interviews with experts were made for this purpose. The potential risk events are classified into eight categories: cuttability reduction, collapse of a tunnel face, ground surface settlement and upheaval, spurts of slurry on the ground, incapability of mucking and excavation, and water leakage. The causes of these risks are categorized into three areas: geological, design and construction management factors. Bayesian Networks (BN) were established to systematically assess a causal relationship between causes and events. The risk impact analysis was performed to evaluate a risk response level by adopting an Analytic Hierarchy Process (AHP) with the consideration of the downtime and cost of measures. Based on the result of the risk impact analysis, the risk events are divided into four risk response levels and these levels are verified by comparing with the actual occurrences of risk events. Measures to mitigate the potential risk events during the design and/or construction stages are also proposed. Result of this research will be of the help to the designers and contractors of TBM tunnelling projects in identifying the potential risks and for preparing a systematic risk management through the evaluation of the risk response level and the migration methods in the design and construction stage.

Production of Feather-Sexing Korean Native Commercial Chickens (깃털 성감별 상업용 토종 실용닭 생산)

  • Sea Hwan Sohn;Eun Jung Cho;Seul Gy Lee;Junho Lee;Suyong Jang;Kwijoong Yong
    • Korean Journal of Poultry Science
    • /
    • v.51 no.2
    • /
    • pp.65-71
    • /
    • 2024
  • The feather-sexing method is widely used commercially for chick sex identification. However, for feather-sexing to be industrially practical, the early-feathering (EF) and late-feathering (LF) genes must existed within the foundation stock, a suitable feather-sexing lines must be established, and the accuracy of sex identification by feather-sexing must be ensured. Therefore, this study introduces the method of constructing the Korean native chickens (KNC) feather-sexing lines using EF and LF genes and evaluates the effectiveness of feather sex determination on commercial chicks produced from the constructed KNC lines. The results showed that both EF and LF chickens existed within the foundation stock, with the frequency of LF genes ranging from 0 to 0.205. In feather-sexing line establishment, the paternal strain of the grandparent stock (GPS) was fixed as EF (kk) for both sexes, while the maternal strain was composed of males with LF homozygotes (ZKZK) and females with EF (ZkW). Thus, in the parent stock (PS), male breeder had EF (ZkZk) and female breeder had LF (ZKW), resulting in chicks produced from their crosses having LF (ZKZk) for males and EF (ZkW) for females, allowing sex determination based on feather development. Additionally, to evaluate the effectiveness of feather-sexing for the produced commercial chicks, a study was conducted on 1,000 samples of the produced chicks to investigate the concordance between vent-sexing and feather-sexing, showing a matching rate of 93.1%.

The Welfare Effects of Advertising: The Economic Rationale for Regulation of Advertising (광고(廣告)의 후생효과(厚生效果) : 광고규제(廣告規制)의 경제적(經濟的) 논거(論據))

  • Lee, Kyu-uck
    • KDI Journal of Economic Policy
    • /
    • v.12 no.3
    • /
    • pp.95-123
    • /
    • 1990
  • Advertising, while providing a linkage between sales and consumption, helps promote rational consumption patterns by expanding the scope of information for consumers facing an ever-increasing array of consumption decisions. In so doing, advertising promotes competition among suppliers and sellers, thereby improving market transparency. Intrinsically, advertising can influence the instantaneous decisions made by consumers, and because of this peculiar feature of advertising, ensuring fair advertising practices is a policy issue of great importance. Concurrently, discerning whether the amount of advertising, which is determined by the profit motive of advertisers, is socially appropriate or whether this amount constitutes a waste of scarce resources is a necessary and indispensable consideration in establishing a public policy to respond to the mounting deluge of advertising. Although the Fair Trade Act and numerous other related laws are being enforced with regard to advertising, it may be difficult to say that a unified, practicable and logical basis for regulating the variegated and complex forms of advertising has been established. This paper examines the various theoretical arguments on the welfare effects of advertising as a rationale to justify regulation from the viewpoint of economics. In this manner, this paper helps define the essential nature of advertising and seeks to present a rational approach toward the regulation of advertising.

  • PDF

GC-MASS Analysis and Microbial Enumeration for the Identification of Spoiled Red Pepper Powder (GC-MASS 분석과 미생물 균수 차이에 의한 희아리 고춧가루 판별)

  • Jeong, Su-Jin;Han, Sang-Bae;Uhm, Tai-Boong
    • Journal of Food Hygiene and Safety
    • /
    • v.23 no.3
    • /
    • pp.191-197
    • /
    • 2008
  • This work was intended for the identification of markers that are found only in the spoiled red pepper powder. When analyzed by GC/MASS, the spoiled red pepper powder contains characteristic naphthalene derivatives, 1, 2, 3, 5, 6, 7, 8, $8\alpha$-octahydro-1, $8\alpha$-dimethyl-7-(1-methylethenyl)-naphthalene and 2-isopropenyl-$4\alpha$, 8-dimethyl-1, 2, 3, 4, $4\alpha$, 5, 6, $8\alpha$-octahydronaphthalene, which have not found in the normal red pepper powder. In addition, microscopic observation and microbial enumeration of the red pepper powder had been performed. Images by scanning electron microscopy showed that the surfaces of spoiled pepper powder were rough with many kinds of microbes, compared with those of normal red pepper powder. A good correlation between the bacterial and fungal counts in the same sample was observed and could be clearly classified into two groups, the normal and the spoiled group, by difference in the microbial counts. These results suggest that the spoiled red pepper powder can be identified by a combination of GC/MASS, microbial counts, and scanning electron microscopy.