• Structural Monitoring and Maintenance
• /
• 제8권4호
• /
• pp.379-402
• /
• 2021

Traditional approaches for structural health monitoring (SHM) seldom take ambient uncertainty (temperature, humidity, ambient vibration) into consideration, while their impacts on structural responses are substantial, leading to a possibility of raising false alarms. A few predictors model-based approaches deal with these uncertainties through complex numerical models running online, rendering the SHM approach to be compute-intensive, slow, and sometimes not practical. Also, with model-based approaches, the imperative need for a precise understanding of the structure often poses a problem for not so well understood complex systems. The present study employs a data-based approach coupled with Empirical mode decomposition (EMD) to correlate recorded response time histories under varying temperature conditions to corresponding damage scenarios. EMD decomposes the response signal into a finite set of intrinsic mode functions (IMFs). A two-dimensional Convolutional Neural Network (2DCNN) is further trained to associate these IMFs to the respective damage cases. The use of IMFs in place of raw signals helps to reduce the impact of sensor noise while preserving the essential spatio-temporal information less-sensitive to thermal effects and thereby stands as a better damage-sensitive feature than the raw signal itself. The proposed algorithm is numerically tested on a single span bridge under varying temperature conditions for different damage severities. The dynamic strain is recorded as the response since they are frame-invariant and cheaper to install. The proposed algorithm has been observed to be damage sensitive as well as sufficiently robust against measurement noise.

• 한국환경보건학회지
• /
• 제40권2호
• /
• pp.105-113
• /
• 2014

Objectives: It is necessary to apply quantitative structure activity relationship (QSAR) for the various chemicals with insufficient toxicity data that are used in the workplace, based on the precautionary principle. This study aims to find application plan of QSAR software tool for predicting health hazards such as genetic toxicity, and carcinogenicity for some chemicals used in the electronics industries. Methods: Toxicity prediction of 21 chemicals such as 5-aminotetrazole, ethyl lactate, digallium trioxide, etc. used in electronics industries was assessed by Toxicity Prediction by Komputer Assisted Technology (TOPKAT). In order to identify the suitability and reliability of carcinogenicity prediction, 25 chemicals such as 4-aminobiphenyl, ethylene oxide, etc. which are classified as Group 1 carcinogens by the International Agency for Research on Cancer (IARC) were selected. Results: Among 21 chemicals, we obtained prediction results for 5 carcinogens, 8 non-carcinogens and 8 unpredictability chemicals. On the other hand, the carcinogenic potential of 5 carcinogens was found to be low by relevant research testing data and Oncologic TM tool. Seven of the 25 carcinogens (IARC Group 1) were wrongly predicted as non-carcinogens (false negative rate: 36.8%). We confirmed that the prediction error could be improved by combining genetic toxicity information such as mutagenicity. Conclusions: Some compounds, including inorganic chemicals and polymers, were still limited for applying toxicity prediction program. Carcinogenicity prediction may be further improved by conducting cross-validation of various toxicity prediction programs, or application of the theoretical molecular descriptors.

• Structural Engineering and Mechanics
• /
• 제91권5호
• /
• pp.443-457
• /
• 2024

At present, the traditional concrete surface inspection methods based on artificial vision have the problems of high cost and insecurity, while the computer vision methods rely on artificial selection features in the case of sensitive environmental changes and difficult promotion. In order to solve these problems, this paper introduces deep learning technology in the field of computer vision to achieve automatic feature extraction of structural damage, with excellent detection speed and strong generalization ability. The main contents of this study are as follows: (1) A method based on DeepLabV3+ convolutional neural network model is proposed for surface detection of post-earthquake structural damage, including surface damage such as concrete cracks, spaling and exposed steel bars. The key semantic information is extracted by different backbone networks, and the data sets containing various surface damage are trained, tested and evaluated. The intersection ratios of 54.4%, 44.2%, and 89.9% in the test set demonstrate the network's capability to accurately identify different types of structural surface damages in pixel-level segmentation, highlighting its effectiveness in varied testing scenarios. (2) A semantic segmentation model based on DeepLabV3+ convolutional neural network is proposed for the detection and evaluation of post-earthquake structural components. Using a dataset that includes building structural components and their damage degrees for training, testing, and evaluation, semantic segmentation detection accuracies were recorded at 98.5% and 56.9%. To provide a comprehensive assessment that considers both false positives and false negatives, the Mean Intersection over Union (Mean IoU) was employed as the primary evaluation metric. This choice ensures that the network's performance in detecting and evaluating pixel-level damage in post-earthquake structural components is evaluated uniformly across all experiments. By incorporating deep learning technology, this study not only offers an innovative solution for accurately identifying post-earthquake damage in civil engineering structures but also contributes significantly to empirical research in automated detection and evaluation within the field of structural health monitoring.

• 여성건강간호학회지
• /
• 제29권1호
• /
• pp.20-31
• /
• 2023

Purpose: As more newborns have received expanded newborn screening (NBS) for metabolic disorders, the overall number of false-positive results has increased. The purpose of this study was to explore the psychological impacts experienced by mothers related to the NBS process. Methods: An online parenting community in Korea was selected, and questions regarding NBS were collected using web crawling for the period from October 2018 to August 2021. In total, 634 posts were analyzed. The collected unstructured text data were preprocessed, and keyword analysis, topic modeling, and visualization were performed. Results: Of 1,057 words extracted from posts, the top keyword based on 'term frequency-inverse document frequency' values was "hypothyroidism," followed by "discharge," "close examination," "thyroid-stimulating hormone levels," and "jaundice." The top keyword based on the simple frequency of appearance was "XXX hospital," followed by "close examination," "discharge," "breastfeeding," "hypothyroidism," and "professor." As a result of LDA topic modeling, posts related to inborn errors of metabolism (IEMs) were classified into four main themes: "confirmatory tests of IEMs," "mother and newborn with thyroid function problems," "retests of IEMs," and "feeding related to IEMs." Mothers experienced substantial frustration, stress, and anxiety when they received positive NBS results. Conclusion: The online parenting community played an important role in acquiring and sharing information, as well as psychological support related to NBS in newborn mothers. Nurses can use this study's findings to develop timely and evidence-based information for parents whose children receive positive NBS results to reduce the negative psychological impact.

• Environmental Analysis Health and Toxicology
• /
• 제31권
• /
• pp.15.1-15.6
• /
• 2016

A number of absurdities surrounding the humidifier disinfectant (HD) incident may have occurred because 1) a judicial system operates on the underlying false assumption that the involved parties are equals in knowledge, information and resource mobilization capabilities, regardless of respective real status as company or individual; 2) there is a lack of a system that mandates a company to prevent and actively manage possible catastrophes; 3) the regulatory scheme makes companies believe that as long as they are complying with the existing regulations, they have satisfied all of their responsibilities. I believe that this issue is an opportunity to bring about changes in the judicial redress system, the system of internal management of manufacturers, and the regulatory system of the government. The following regulation amendments are needed to move towards the changes stated above. First, legislation relating to victim relief that is applicable to the HD incident must be established. Second, a risk management system must be formed within the manufacturing company and to this end an institutional environment for the system must be established within regulatory framework. Furthermore, legislation must be passed that could punish companies themselves that have caused severe damage to individuals because they had failed to take necessary actions to avoid foreseeable harm. Finally, the framework of regulation must be changed so that the company, who has the necessary information regarding the product and the component chemicals used in the product, must self-directed experiment and assessment of the safety of their own products.

• 한국식품위생안전성학회지
• /
• 제38권1호
• /
• pp.12-18
• /
• 2023

쇠고기 이력추적제는 소 개체마다 이력번호를 부여하여 수입쇠고기가 한우고기로 둔갑하는 사례를 막고, 소비자에게 구입한 한우고기의 세부 이력 정보들을 제공하는 데 도움을 준다. 이번 연구는 2021년-2022년 서울지역 대형 축산물판매업소에서 유통되는 한우고기 344건에서 DNA 동일성 검사를 실시하여 이력번호 등 주요 표시정보들의 진위를 판별하였다. 그 결과 45건(13.1%)에서 이력번호가 불일치한 것으로 확인되었다. 불일치율은 2021년(14.7%)에 비해 2022년(11.3%) 감소하였고, 도심서북권 20.7%, 동북권 14.4%, 서남권 및 동남권 10.2% 순으로, 북부권(16.9%)이 남부권(10.2%)에 비해 높게 나타났다. 또한 6개 브랜드 중 B사 및 D사는 이력관리가 양호한 반면, E사 및 A사는 이력관리가 취약한 것으로 확인되었고, 통계적으로 유의한 결과 차이를 보였다(P<0.001). 이력번호 불일치 시료의 실제 이력번호는 업소 내 입(출)고 거래내역 자료를 근거로 조사하였고, 그 결과 실제 이력번호 확인율은 53.9%에 불과하였으나, 확인된 범위 내에서 시료의 표시정보 진위 판별 결과, 거짓 표시는 이력번호 13.1%, 성별 2.9%, 도축장명 2.2%, 등급 1.6% 순으로 나타났고, 품종(한우) 거짓 표시는 없었다. 거짓 표시 축산물의 유통 차단을 위해 표시정보의 신속한 진위 판별이 중요하므로 업소 내 이력번호가 기재된 날짜별 부분육 소분할 작업내역 작성을 의무화하는 법적 근거 마련이 필요하다. 본 연구 결과는 투명한 축산물 유통 거래 질서 정착을 위한 이력관리 방향 설정에 참고자료로 활용하고자 한다.

• 한국컴퓨터정보학회논문지
• /
• 제21권6호
• /
• pp.97-106
• /
• 2016

This study tries to seek the is the realistic improvements and legislative measures about current medical advertising which was in the Court on 12 May 2015 by presenting and discussion the understanding, problems and its alternative direction of pre-deliberation on the existing law which is the decision on the constitutionality of health care advertising regulated health care advertising General commercial advertising has the right which have to be protected as the terms of the protection of know and freedom of expression and advertiser's there are sure to be in a value to be protected. Medical advertising is also a person in addition to the absolute value that includes both Due to the particularity of medical advertising in terms of life and the right to health Until now, this has been the target of strong regulations are changing the policy of gradual deregulation in our country, including the country. Medical advertising on the current medical law had been to be checked by pre-deliberation of the executive power. However, due to unconstitutional, in the circumstances which a false hype is flooding and increasing, it has been realized that the fair competition of medical community, life and health rights of the people are threatened by in reverse. In this regard, the abolition of the pre-deliberation system of medical advertising can be welcomed by abolition of the old system which is the legal and institutional censorship. Since its abolition, the alternative policy direction is insufficient also it is not clear. Therefore we need to study this. Therefore, in this paper, we try to find general theoretical background and problem of pre-deliberation system of medical advertising. Also, as trying to find feasibility or ambiguity of regulation and issues about medical advertising on medical law, we argued the provision of special measures of the medical advertising for introduction of integrated medical advertising deliberation committee which can ensure the independence and autonomy, strengthening of the monitoring on the internet advertising, legal resolving through amendments, strengthening of penalties, and establish special measures of medical advertising for the medical privatization and demand for the foreign medical tourist, etc. Empirical study about practical regulatory measures of medical advertising which converged the various opinions of consumer groups, government and academia, and medical community, and we expect hope to see the more realistic alternative provision.

• 한국콘텐츠학회논문지
• /
• 제20권5호
• /
• pp.525-535
• /
• 2020

본 연구의 목적은 공공부문에서 활용되는 기상청의 여름철 폭염특보 정보의 가치를 평가하는 것이다. 폭염특보는 각 지방자치단체에서 매년 발생하는 고온 피해를 저감하기 위한 대비계획의 행동 수준을 결정하는 주요 투입변수로 활용되고 있다. 비 시장재인 폭염특보 정보의 가치를 평가하기 위해 비용-손실을 고려한 의사결정모델을 수립하였다. 의사결정모델 변수인 비용과 손실은 각각 서울과 부산에서 2016년 사용한 폭염 대책 예산과 건강보험심사평가원이 제공하는 65세 이상 고령자의 건강보험 청구금액으로 설정하였다. 분석 결과 2016년 기상청 폭염특보는 서울과 부산에 각각 41.3억 원과 10.9억 원의 가치를 제공한 것으로 평가되었다. 또한 기상청이 폭염특보의 False Alarm (FA) 오류를 1회 줄이면 서울과 부산에서 각각 76.6백만 원, 16.8백만 원의 가치가 증가하는 것으로 나타났다. 연구 결과는 공공부문에서 활용되는 폭염특보의 가치를 정량적으로 추정한데 의의가 있다.

• 디지털융복합연구
• /
• 제17권5호
• /
• pp.137-143
• /
• 2019

가짜 뉴스는 소셜 미디어와 같이 사용자가 상호작용하는 미디어 플랫폼에서 정보가 빠른 속도로 확산되는 이점을 가지는 오류 정보(misinformation)의 한 형태이다. 최근 가짜 뉴스의 증가로 인해 사회적으로 많은 문제가 발생하고 있다. 본 논문에서는 이러한 가짜 뉴스를 탐지하는 방법을 제안한다. 이전의 가짜 뉴스 탐지는 텍스트 분석을 사용한 연구가 주로 수행되었다. 본 연구는 소셜 미디어의 뉴스가 확산되는 네트워크에 초점을 두고, 네트워크 임베딩 방법인 DeepWalk 로 자질을 생성하고 로지스틱 회귀분석을 사용하여 가짜 뉴스를 분류한다. 인터넷에 공개된 뉴스 211개와 120만개의 뉴스 확산 네트워크 데이터를 사용한 가짜 뉴스 탐지에 대한 실험을 수행하였다. 연구 결과 텍스트 분석에 비하여 네트워크 임베딩을 사용한 가짜 뉴스 탐지의 정확도가 최소 1.7%에서 최대 10.6% 더 높게 나타났다. 또한, 텍스트 분석과 네트워크 임베딩을 결합한 가짜 뉴스 탐지는 네트워크 임베딩에 비해 정확도의 상승이 나타나지 않았다. 본 연구의 결과는 기업이나 조직은 온라인 상에서 확산되는 가짜 뉴스 탐지에 효과적으로 활용될 수 있다.

• Asian Pacific Journal of Cancer Prevention
• /
• 제17권7호
• /
• pp.3123-3129
• /
• 2016

Background: Cancer is the fourth leading cause of death in Sabah Malaysia with a reported age-standardized incidence rate was 104.9 per 100,000 in 2007. The incidence rate depends on non-mandatory notification in the registry. Under-reporting will provide the false picture of cancer control program effectiveness. The present study was to evaluate the performance of the cancer registry system in terms of representativeness, data quality, simplicity, acceptability and timeliness and provision of recommendations for improvement. Materials and Methods: The evaluation was conducted among key informants in the National Cancer Registry (NCR) and reporting facilities from Feb-May 2012 and was based on US CDC guidelines. Representativeness was assessed by matching cancer case in the Health Information System (HIS) and state pathology records with those in NCR. Data quality was measured through case finding and re-abstracting of medical records by independent auditors. The re-abstracting portion comprised 15 data items. Self-administered questionnaires were used to assess simplicity and acceptability. Timeliness was measured from date of diagnosis to date of notification received and data dissemination. Results: Of 4613 cancer cases reported in HIS, 83.3% were matched with cancer registry. In the state pathology centre, 99.8% was notified to registry. Duplication of notification was 3%. Data completeness calculated for 104 samples was 63.4%. Registrars perceived simplicity in coding diagnosis as moderate. Notification process was moderately acceptable. Median duration of interval 1 was 5.7 months. Conclusions: The performances of registry's attributes are fairly positive in terms of simplicity, case reporting sensitivity, and predictive value positive. It is moderately acceptable, data completeness and inflexible. The usefulness of registry is the area of concern to achieve registry objectives. Timeliness of reporting is within international standard, whereas timeliness to data dissemination was longer up to 4 years. Integration between existing HIS and national registration department will improve data quality.