• Title/Summary/Keyword: 위험도 판별

Search Result 173, Processing Time 0.03 seconds

High-quality data collection for machine learning using block chain (블록체인을 활용한 양질의 기계학습용 데이터 수집 방안 연구)

  • Kim, Youngrang;Woo, Junghoon;Lee, Jaehwan;Shin, Ji Sun
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.23 no.1
    • /
    • pp.13-19
    • /
    • 2019
  • The accuracy of machine learning is greatly affected by amount of learning data and quality of data. Collecting existing Web-based learning data has danger that data unrelated to actual learning can be collected, and it is impossible to secure data transparency. In this paper, we propose a method for collecting data directly in parallel by blocks in a block - chain structure, and comparing the data collected by each block with data in other blocks to select only good data. In the proposed system, each block shares data with each other through a chain of blocks, utilizes the All-reduce structure of Parallel-SGD to select only good quality data through comparison with other block data to construct a learning data set. Also, in order to verify the performance of the proposed architecture, we verify that the original image is only good data among the modulated images using the existing benchmark data set.

A Case Study on Text Analysis Using Meal Kit Product Review Data (밀키트 제품 리뷰 데이터를 이용한 텍스트 분석 사례 연구)

  • Choi, Hyeseon;Yeon, Kyupil
    • The Journal of the Korea Contents Association
    • /
    • v.22 no.5
    • /
    • pp.1-15
    • /
    • 2022
  • In this study, text analysis was performed on the mealkit product review data to identify factors affecting the evaluation of the mealkit product. The data used for the analysis were collected by scraping 334,498 reviews of mealkit products in Naver shopping site. After preprocessing the text data, wordclouds and sentiment analyses based on word frequency and normalized TF-IDF were performed. Logistic regression model was applied to predict the polarity of reviews on mealkit products. From the logistic regression models derived for each product category, the main factors that caused positive and negative emotions were identified. As a result, it was verified that text analysis can be a useful tool that provides a basis for maximizing positive factors for a specific category, menu, and material and removing negative risk factors when developing a mealkit product.

Reminder module design to prevent collision accidents while wearing HMD (HMD 착용 중의 충돌 사고 방지를 위한 알리미 모듈 설계)

  • Lee, Min-Hye;Cho, Seung-Pyo;Shin, Seung-Yoon;Lee, Hongro
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.26 no.11
    • /
    • pp.1653-1659
    • /
    • 2022
  • Virtual reality content provides users with a high sense of immersion by using HMD devices. However, while wearing the HMD device, it is difficult to determine the user's location or distance from obstacles, resulting in injuries due to physical collisions. In this paper, we propose a reminder module to prevent accidents by notifying the risk of collision with obstacles while wearing the HMD device. The proposed module receives the user's state from the acceleration and gyro sensor and determines the motion that is likely to cause a collision. If there is an obstacle in the expected collision range, a buzzer sounds to the wearer. As a result of the experiment, the accuracy of obstacle detection in the state of wearing the HMD was 86.6% in the 1st stage and 83.3% in the 2nd stage, confirming the performance of the accident prevention reminder.

Subway Line 2 Congestion Prediction During Rush Hour Based on Machine Learning (머신러닝 기반 2호선 출퇴근 시간대 지하철 역사 내 혼잡도 예측)

  • Jinyoung Jang;Chaewon Kim;Minseo Park
    • The Journal of the Convergence on Culture Technology
    • /
    • v.9 no.6
    • /
    • pp.145-150
    • /
    • 2023
  • The subway is a public transportation that many people use every day. Line 2 especially has the most crowded stations during the day. However, the risk of crush accidents is increasing due to high congestion during rush hour and this reduces the safety and comfort of passengers. Subway congestion prediction is helpful to forestall problems caused by high congestion. Therefore, this study proposes machine learning classification models that predict subway congestion during commuting time. To predict congestion in Line 2 based in machine learning, we investigate variables that affect subway congestion through previous research and collect a dataset of subway congestion on Line 2 during rush hour from PUBLIC DATA PORTAL. The proposed model is expected to establish the subway operation plane to make passengers safe and satisfied.

A Study on the Effectiveness of Virtual and Real Experience Type Safety Education at Construction Sites (건설현장에 접목한 가상체험·실물체험 안전교육의 효과성 연구)

  • Cho Choonhwan
    • Journal of the Korea Institute of Construction Safety
    • /
    • v.6 no.1
    • /
    • pp.1-6
    • /
    • 2024
  • Existing safety education delivered to construction workers has limitations in concentration and immersion, so delivery power and interest are low. In order to improve the unstable behavior of construction workers and prevent safety accidents through education, a paradigm shift to hands-on education is necessary. Experiential safety education aims to contribute to the prevention of safety accidents and induce safe behavior by construction workers to recognize risks faster, select safe working methods suitable for the working environment, and improve emergency response and proactive response. Experiential education facilities have a follow-up learning effect in case of danger. The experience facility, which consists of the same working environment as the actual construction site, is designed to experience falls, equipment contraction, fire, and electric shock. In order to achieve the results of safety education that has invested a lot of time, construction workers must have motivation to participate, and "experiential safety education" through playful, deviant, and aesthetic experiences reduces serious accidents.

Validity of Referral of High Risk Pregnancy in MCH Center (모자 보건 센터에서의 고위험 산모 의뢰 기준의 타당성)

  • Kim, Gui-Yeon;Park, Jung-Han
    • Journal of Preventive Medicine and Public Health
    • /
    • v.22 no.1 s.25
    • /
    • pp.146-152
    • /
    • 1989
  • To test the validity of referral of high risk pregnancy in the MCH Center, 6,017 pregnant women who visited MCH Center of South District Health Center for delivery between 1 April 1985 and 31 March 1987 were interviewed on arrival to obtain the data for demographic characteristics and obsteric history and traced to check the delivery outcome. Out of 5,820 women whose delivery outcomes were confrmed, 704 women(12.1%) were referred to other hospital or clinic for high risk factors. The proportion of poor delivery outcome(stillbirth, low birth weight and neonatal death) among referred cases was 4.4% while that of the women delivered at the MCH Center was 2.2% (p<0.01). Decision of the midwives for the referral of high risk pregnancy based on their clinical assessment was consistent with the delivery outcome (good or poor) in 86.5%. Major reasons for referral were premature rupture of membrane(46.5%) and cephalopelvic disproportion(20.0%) and the C-section rates for these cases were 10.1%, 17.6%, respectively. Discriminant analysis of the demographic characteristics and obstertric history for the discrimination of delivery outcome showed that gestational age had the highest discriminant function coefficient(0.88) and it was followed by parity(0.37) and maternal education(0.30). Referral of high risk pregnancy by the midwives based on their clinical assessment was considered to be reasonably valid. However, a risk scoring system for an MCH Center which can improve the validity may be developed if one applies the discriminant analysis for more comprehensive independent variable(including clinical assessment of midwife, demographic characteristics and obstetric history) and dependent variable (including medically indicated C-section, complication of pregnancy and delivery, stillbirth, low birth weight, neonatal death and maternal death).

  • PDF

Prognostic Factors of Thymic Carcinoma (흉선암의 예후인자)

  • Park, In-Kyu;Kim, Dae-Joon;Kim, Kil-Dong;Bae, Mi-Kyung;Chung, Kyung-Young
    • Journal of Chest Surgery
    • /
    • v.38 no.8 s.253
    • /
    • pp.564-569
    • /
    • 2005
  • Background: Thymic carcinoma is a rare malignant disease with sparse data for treatment and prognosis. We intended to investigate the prognostic factors of thymic carcinoma. Material and Method: Data of 42 patients, who were diagnosed and treated for thymic carcinoma from January of 1986 to August of 2003 were reviewed retrospectively. Influences of characteristics of patients, Masaoka stage, histologic grade, completeness of resection and adjuvant treatment on survival were evaluated. Result: There were 30 male and 12 female patients and their mean age was $52.0\pm15.7$ years old. There were 28 patients with low-grade histology and 13 patients with high-grade histology. Clinical stage according to Masaoka stage were I in 2, II in 2, III in 15 $(35.7\%)$, IVa in 10 $(23.8\%),\;and\;IVb\;in\;13\;(31\%)$ patients. Surgical resection was done in 22 patients, Complete resection was possible in 13 patients and incomplete resection was done in 9 patients. Among 20 patients without resection, 8 patients received chemotherapy, 7 patients received radiotherapy and 5 patients received combined therapy. Median survival time was $31.7\pm6.1$ months and 5 year survival rate was $28.5\%$. High grade histology (hazard ratio=3.009, $95\%\;confidence\;interval=1.178\sim7.685,$ p=0.021) and incompleteness of resection (hazard ratio=3.605, $95\%$ confidence interval= $1.1541\sim1.580$, p=0.023) were the prognostic factors of thymic carcinoma. Conclusion: In thymic carcinoma, low grade histology is a good prognostic factor and complete resection can prolong the survival of patients.

Comparison of PANA RealTyper HPV Kit with AdvanSure HPV GenoBlot Assay for Human Papillomavirus Genotyping (인유두종바이러스 유전자형 검사법 PANA RealTyper HPV Kit와 AdvanSure HPV GenoBlot Assay의 비교)

  • Kim, Yi Hyeon;Chung, Hae-Sun;Lee, Miae
    • Annals of Clinical Microbiology
    • /
    • v.21 no.4
    • /
    • pp.86-91
    • /
    • 2018
  • Background: The PANA RealTyper HPV kit (PANAGENE, Korea; PANA RealTyper) was developed to genotype human papillomavirus (HPV) and was based on multiplex real-time PCR amplification and melting curve analysis. In this study, we compared PANA RealTyper to the AdvanSure HPV GenoBlot assay (LG Life Sciences, Korea; AdvanSure assay) and attempted to evaluate the performance of PANA RealTyper. Methods: A total of 60 cervical specimens were collected from women undergoing routine cervical cancer screening. The AdvanSure assay and PANA RealTyper kit identified the same 20 high-risk genotypes. However, the AdvanSure assay identified 15 low-risk genotypes, while the PANA RealTyper kit identified only 2 but detected 18 low-risk genotypes. Results: Among the total 60 specimens, 54 high-risk genotypes (40 specimens) and 20 low-risk genotypes (18 specimens) were detected. The agreement rates of the assays ranged from 94.4 to 100% for high-risk genotypes. Among 9 genotypes that were positive in the PANA RealTyper kit but negative in the AdvanSure assay, 7 were confirmed as true positive (HPV genotypes 16 (n=1), 39 (n=1), 52 (n=1), 58 (n=2), 68 (n=2)). Among 4 genotypes that were negative in the PANA RealTyper kit but positive in the AdvanSure assay, 3 were confirmed as HPV genotype 59. Among the 19 low-risk genotypes positive in the AdvanSure assay, there were 2 cases of HPV 6 and 1 case of HPV 11. In comparison, only 1 positive case of HPV 6 was determined by the PANA RealTyper kit. Conclusion: The PANA RealTyper kit was comparable with the AdvanSure assay. The PANA RealTyper kit would be useful and suitable for HPV genotyping in the clinical laboratory.

Forward Security Protection Protocol of RFID System using New Key Generation Method (새로운 키 생성 방법을 통한 RFID시스템의 전방위보안성 보호 프로토콜)

  • Cho Jung-Hwan;Cho Jung-Sik;Yeo Sang-Soo;Kim Sung kwon
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2005.11a
    • /
    • pp.19-21
    • /
    • 2005
  • 현대의 산업화 사회에서는 자동인식을 통해서 사람과 사물을 식별하고자 하는 연구들이 진행되고 있다. 그 대표적인 예로 바코드를 이용한 접촉식 판별기술이 있고, 라디오 주파수를 이용한 RFID(Radio Frequency Identification) 기술을 들 수 있다. RFID의 경우는 무선 주파수를 이용하기 때문에 대량의 사물을 동시에 인식 할 수 있다는 장점이 있다. 하지만. 어떠한 상황에서 리더의 요청에 응답을 하는 리더-태그 시스템이기 때문에 사용자의 프라이버시 침해 문제를 야기 할 수 있다. 사용자의 프라이버시 침해문제를 막기 위해서 많은 연구들이 진행되고 있다. 그 중에서, Miyako Ohkubo의 Hash체인을 이용한 프라이버시 보호 기법은 정보유출, 위치추적공격(Location Tracking Attack), 전방위보안성(Forward Security)과 같은 프라이버시 침해문제들로부터 사용자의 프라이버시를 보호 할 수 있는 프로토콜이다. 그러나 Hash함수를 태그에 구현하는 것은 현재까지는 불가능한 상황이다. 또, Martin Feldhofer의 AES(Advanced Encryption Standard)를 사용한 프로토콜은 실제로 태그에 구현 가능하면서 내부구조가 8bit인 AES를 사용함으로써 암호학적인 강도를 높였으나, 프라이버시 침해 문제에서 단점을 드러냈다. 이러한 단점을 보완한 AES기반에서의 개선된 RFID 프라이버시 보호 프로토콜은 실제적으로 태그에 구현 가능한 AES를 이용한 암호화 체인을 통해서 프라이버시 보호에 우수하면서 실제 사용이 가능한 프로토콜을 제안하였다[1]. 그러나, 이 프로토콜은 생성되는 키 값들이 물리적 공격을 통해서 노출이 되었을 때, 이전의 seed값과 키 값들이 노출 되는 단점이 있다. 본 논문에서는 이러한 문제들을 해결하고자 프라이버시보호에 새로운 키 생성 방법을 통한 강력한 프로토콜을 제안 한다.하였으나 사료효율은 증진시켰으며, 후자(사양, 사료)와의 상호작용은 나타나지 않았다. 이상의 결과는 거세비육돈에서 1) androgen과 estrogen은 공히 자발적인 사료섭취와 등지방 침적을 억제하고 IGF-I 분비를 증가시키며, 2) 성선스테로이드호르몬의 이 같은 성장에 미치는 효과의 일부는 IGF-I을 통해 매개될 수도 있을을 시사한다. 약 $70 {\~} 90\%$의 phenoxyethanol이 유상에 존재하였다. 또한, 미생물에 대한 항균력도 phenoxyethanol이 수상에 많이 존재할수록 증가하는 경향을 나타내었다. 따라서, 제형 내 oil tomposition을 변화시킴으로써 phenoxyethanol의 사용량을 줄일 수 있을 뿐만 아니라, 피부 투과를 감소시켜 보다 피부 자극이 적은 저자극 방부시스템 개발이 가능하리라 보여 진다. 첨가하여 제조한 curd yoghurt는 저장성과 관능적인 면에서 우수한 상품적 가치가 인정되는 새로운 기능성 신제품의 개발에 기여할 수 있을 것으로 사료되었다. 여자의 경우 0.8이상이 되어서 심혈관계 질환의 위험 범위에 속하는 수준이었다. 삼두근의 두겹 두께는 남녀 각각 $20.2\pm8.58cm,\;22.2\pm4.40mm$으로 남녀간에 유의한 차이는 없었다. 조사대상자의 식습관 상태는 전체 대상자의 $84.4\%$가 대부분이 하루 세끼 식사를 규칙적으로 하고 있었으며 식사속도는 허겁지겁 빨리 섭취하는 경우가 남자는 $31.0\%$, 여자는 $21.4\%$로 나타났고 이들을 제외한 나머지 사람들은 보통 속도 혹은 충분한 시간을 가지고 식사를 하였다. 평소 식사량은 조금 적게 혹은 적당하게 섭취하는 사람이 대부분이었으며 남자가 여자보다는 배부르게 먹는 경 향이 유의적으로 높았다(p<0.05). 식사는 혼자 하는 경우가 남자

  • PDF

THE PSYCHOSOCIAL CHARACTERISTICS OF ADOLESCENT DRUG USER (약물사용 청소년의 심리-사회적 특성)

  • Park, Joong-Kyu;Choi, Jung-Hun
    • Journal of the Korean Academy of Child and Adolescent Psychiatry
    • /
    • v.1 no.1
    • /
    • pp.130-147
    • /
    • 1990
  • This study intended to investigate the characteristics of adolescent drug user in Korea. A questionnaire on adolescent drug use was administered to 1st or 2nd grade 898 students (465 males, 433 females) from 9 senior high schools in Seoul area. The extent of current using six representative drugs such as cigarettes, alcohol, chemical substance inducing hallucination(e,g., thinner, bond etc.), psychostimulant, hypnotic and minor tranqulizer was self-reported. Also their psychological distress, self-concept and individual-related variables such as academic grade, deviant behavior, drug-using peers, the perceived availability of drugs, the degree of family discipline, and the perceived parents' attitude for drinking and smoking were surveyed. Subjects were grouped into six(male) or five(female) subgroups (nonuser, simple experiencer, one kind of drug user, two kinds of drugs user, three kinds of drugs user(male only), minor tranqulizer user) to their extent of drug use. Then ANOVA procedure performed for group comparison of their psychological distress, self-concept and individual-related variables. The results showed that the most popular drugs among adolescents in Korea were cigarettes and alcohol. Minor tranqulizer was used by about 2.8% of male and 7.41% of female subjects. In general abusers showed lower academic grade, more deviant experiences, having more drug-using peers, higher degree of psychological distress, and lower postitive self-concept than nonuser group. According to the results of discriminant analysis, hostility and deviant behavior were reliable predictive variables that distinguished abuser group from nonuser group among the associated variables in this study. These results suggest that some common factors affect drug use of Korean high school students : high school students who have many common risk factors could be abusers more easily. These findings supported risk factor theory that the extent of drug use of adolescents might be associated with general maladjustment in everyday life.

  • PDF