• 한국건축시공학회지
• /
• 제17권3호
• /
• pp.295-303
• /
• 2017

건설 산업 재해 예방을 위한 연구와 노력에도 불구하고 최근 7년간 국내 건설업 재해자 수가 꾸준히 증가했다. 건설현장에서 발생하는 재해는 다른 산업군에 비해 강도 높은 재해가 발생할 가능성이 크기 때문에 근본적으로 예방할 수 있는 방법이 필요하다. 따라서 본 연구에서는 모형에 대한 해석이 쉽고 변수의 상호작용 효과 해석이 용이한 의사결정나무 기법을 활용하여 건설재해 예측 모델을 제안하였다. 제안된 건설 재해 사전 예측 모델의 현장 활용 가능성을 평가하기 위하여 판별분석기법 기반 모델과의 건설 재해 예측 정확도를 비교하였다. 검토 결과 판별분석 모델에 비해 의사결정나무 모델의 누적 예측 정확도가 더 높은 것으로 나타났다. 의사결정나무 기법을 이용한 모델은 시간이 지남에 따라 데이터가 증가하기 때문에 예측 정확도가 더욱 높아지게 된다. 따라서 본 연구에서 제안된 건설 재해 예측 모델이 건설현장에서 활용된다면 효과적으로 안전 관리를 할 수 있고, 건설업 재해율 감소에도 기여할 수 있을 것으로 기대한다.

• 한국산업정보학회논문지
• /
• 제14권4호
• /
• pp.116-127
• /
• 2009

본 연구는 스틸 파이프 생산의 과거 이력을 분석하여 주요 특성별 높은 수율을 갖는 제품을 선별하고 각 공정별 최소 불량률을 가진 제품 모델을 구현함으로써 제품 생산의 효율성을 제고하기 위한 목적으로 수행되었다. 이를 위해 본 논문에서는 주문을 통해 생산되는 각종 스틸 파이프 제품들의 특성을 비교 및 분석하여 어떠한 특성을 가지는 제품들이 가장 높은 수율을 창출해내고 적은 불량을 발생시키는지 의사결정트리 데이터마이닝 기법을 적용하여 분석하였다. 실험 결과로부터 중소구경이 많은 ERW 스틸 파이프는 기호에 의해, 그 외 주로 대구경 범위인 롤벤더, 스파이럴 스틸 파이프 경우에는 외경 범위에 따라 수율과 불량률이 분류되고 있다는 사실을 확인하였다. 본 연구는 주요 특성별 수율과 불량률이 어떠한 형태를 나타내는지 수치적으로 분류 및 구체화하여 그 영향정도를 구분하였다.

• 대한토목학회논문집
• /
• 제29권2C호
• /
• pp.59-69
• /
• 2009

본 연구에서는 화강암, 편마암 등 결정질암 지역에서의 급경사지재해 발생지역 및 미발생지역에 대한 현장조사자료 및 토질시험자료를 토대로 의사결정나무모형을 이용한 급경사지재해 예측모델을 개발하였다. 선정된 급경사지재해 예측모델의 분리기준은 최상위부터 사면경사, 투수계수 및 간극비로 선정되었다. 그리고 이를 토대로 GIS기법을 이용한 국가 주요시설물 주변 급경사지 재해 예측프로그램 SHAPP ver 1.0을 개발하였다. 개발된 예측모델 및 예측프로그램을 검증하기 위하여 강릉시 주문진읍 일대의 현장조사결과와 대상현장에 대한 예측결과를 비교 검토하였다. 검토결과 실제 급경사지 재해가 발생된 구간과 급경사지재해 예측구간이 유사하게 일치하고 있는 것으로 나타났다. 추후 지속적인 연구를 통하여 급경사지재해 예측 결과에 대한 정확도를 높이고, 이를 실용화하여 범용적으로 사용이 가능하도록 할 예정이다.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2007년도 추계학술대회
• /
• pp.269-274
• /
• 2007

Ultimate goal of this research is to develop a web-based forecasting system of industrial accidents. As an initial step for the purpose of this study, this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. In addition, this paper presents the logical process for development of a forecasting system. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. The sample for this work was chosen from 10,536 data related to manufacturing industries during three years(2002$^{\sim}$2004) in korea.

• 디지털산업정보학회논문지
• /
• 제8권2호
• /
• pp.59-65
• /
• 2012

Emergency medical information center performs role of medical direction about disease consult and pre-hospital emergency handling scheme work to people. Emergency medical information system plays a major role to be decreased mortality and disability of emergency patient by providing information of medical institution especially when emergency patient has appeared. But, various attacks as a hacking have been happened in Emergency medical information system recently. In this paper, we proposed security structure which can protect the system securely by detecting attacks from outside effectively. Intrusion detection was performed using rule based detection technique according to protocol for every packet to detect attack and intrusion was reported to control center if intrusion was detected also. Intrusion detection was performed again using decision tree for packet which intrusion detection was not done. We experimented effectiveness using attacks as TCP-SYN, UDP flooding and ICMP flooding for proposed security structure in this paper.

• 스마트미디어저널
• /
• 제13권2호
• /
• pp.85-94
• /
• 2024

Artificial Intelligence of Things (AIoT), which combines AI and the Internet of Things (IoT), has recently gained popularity. Deep neural networks (DNNs) have achieved great success in many applications. Deploying complex AI models on embedded boards, nevertheless, may be challenging due to computational limitations or intelligent model complexity. This paper focuses on an AIoT-based system for smart sewing automation using edge devices. Our technique included developing a detection model and a decision tree for a sufficient testing scenario. YOLOv5 set the stage for our defective sewing stitches detection model, to detect anomalies and classify the sewing patterns. According to the experimental testing, the proposed approach achieved a perfect score with accuracy and F1score of 1.0, False Positive Rate (FPR), False Negative Rate (FNR) of 0, and a speed of 0.07 seconds with file size 2.43MB.

• 한국산학기술학회논문지
• /
• 제14권7호
• /
• pp.3400-3411
• /
• 2013

본 연구의 목적은 회복실 환자의 평균 체류시간을 알아보고, 체류시간에 미치는 요인들을 파악하여 회복실 체류 시간 예측을 위한 분석을 하기 위함이다. 본 연구의 대상자는 상급 종합병원에 입원한 전신 마취 하에 일반외과 수술을 받은 18세 이상 성인 남녀 환자 중 회복실로 입실한 환자를 1,500명을 대상으로 하였고 이중 1,293건을 분석하였다. 회복실 체류시간에 영향을 미치는 요인으로 32항목을 측정하였다. 평균 회복실 체류시간은 72.02분이었다. 수술주기별 관련요인과 회복실 체류시간의 관계를 살펴본 결과 나이, 수술종류, 수술시간, 진통제사용회수가 유의미한 관계를 나타내었다 회복실 체류시간에 가장 영향을 많이 주는 변수는 수술종류이며 그 다음 EKG 이상여부, 나이, 마취제, 수술시간으로 나타났다. 범주 I(30분~60분)은 2개의 경우, 범주 II(61분~90분)도 2개의 경우, 범주 III(91분~120분)은 4개의 경우로 분석되었다.

• 한국의료질향상학회지
• /
• 제8권2호
• /
• pp.186-207
• /
• 2001

Background : This study presented an analysis of healthcare quality indicators using data mining and a development of decision support system for quality improvement. Method : Specifically, important factors influencing the key quality indicators were identified using a decision tree method for data mining based on 8,405 patients who discharged from a medical center during the period between December 1, 2000 and January 31, 2001. In addition, a decision support system was developed to analyze and monitor trends of these quality indicators using a Visual Basic 6.0. Guidelines and tutorial for quality improvement activities were also included in the system. Result : Among 12 selected quality indicators, decision tree analysis was performed for 3 indicators ; unscheduled readmission due to the same or related condition, unscheduled return to intensive care unit, and inpatient mortality which have a volume bigger than 100 cases during the period. The optimum range of target group in healthcare quality indicators were identified from the gain chart. Important influencing factors for these 3 indicators were: diagnosis, attribute of the disease, and age of the patient in unscheduled returns to ICU group ; and length of stay, diagnosis, and belonging department in inpatient mortality group. Conclusion : We developed a decision support system through analysis of healthcare quality indicators and data mining technique which can be effectively implemented for utilization review and quality management in a healthcare organization. In the future, further number of quality indicators should be developed to effectively support a hospital-wide Continuous Quality Improvement activity. Through these endevours, a decision support system can be developed and the newly developed decision support system should be well integrated with the hospital Order Communication System to support concurrent review, utilization review, quality and risk management.

• 대한안전경영과학회:학술대회논문집
• /
• 대한안전경영과학회 2006년도 추계공동학술대회
• /
• pp.293-297
• /
• 2006

Recently most universities are suffering from students leaving their majors. In order to make a countermeasure for reducing major separation rate, many universities are trying to find a proper solution. As a similar endeavor, this paper uses decision tree algorithm which is one of the data mining techniques which conduct grouping or prediction into several sub-groups from interested groups. This technique can analyze a feature of type on students leaving their majors. The dataset consists of 5,115 features through data selection from total data of 13,346 collected from a university in Kangwon-Do during seven years(2000.3.1 $\sim$ 2006.6.30). The main objective of this study is to evaluate performance of algorithms including CHAID, CART and C4.5 for classification of students leaving their majors with ROC Chart, Lift Chart and Gains Chart. Also, this study provides values about accuracy, sensitivity, specificity using classification table. According to the analysis result, CART showed the best performance for classification of students leaving their majors.

• 한국지능정보시스템학회:학술대회논문집
• /
• 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
• /
• pp.289-299
• /
• 2000

This study provides an application of datamining approach to CQI(Continuous Quality Improvement) using the discharge summary. First, we found a process variation in hospital infection rate by SPC (Statistical Process Control) technique. Second, importance of factors influencing hospital infection was inferred through the decision tree analysis which is a classification method in data-mining approach. The most important factor was surgery followed by comorbidity and length of operation. Comorbidity was further divided into age and principal diagnosis and the length of operation was further divided into age and chief complaint. 24 rules of hospital infection were generated by the decision tree analysis. Of these, 9 rules with predictive prover greater than 50% were suggested as guidelines for hospital infection control. The optimum range of target group in hospital infection control were Identified through the information gain summary. Association rule, which is another kind of datamining method, was performed to analyze the relationship between principal diagnosis and comorbidity. The confidence score, which measures the decree of association, between urinary tract infection and causal bacillus was the highest, followed by the score between postoperative wound disruption find postoperative wound infection. This study demonstrated how datamining approach could be used to provide information to support prospective surveillance of hospital infection. The datamining technique can also be applied to various areas fur CQI using other hospital databases.