• 한국학교수학회논문집
• /
• 제10권2호
• /
• pp.263-288
• /
• 2007

본 연구는 수학 7-가, 수학 8-가 교과서의 함수단원 분석을 통해 지필환경의 제한점을 알아본 후 탐구용 소프트웨어인 엑셀이 학생들의 일차함수의 과정-대상관점 형성 과정에 어떠한 영향을 미치는지 알아보는 것이다. 엑셀을 활용한 교수 실험은 학습능력 수준이 다른 다섯 명의 학생을 선정하여 중학교에서 다루고 있는 함수관련 내용을 중심으로 실시하였다. 교수실험은 5차시로 이루어졌으며, 각 학생의 활동 과정을 녹화, 녹음한 내용과 학생과의 면담, 관찰, 활동지 등을 분석하였다. 교수실험 결과, 엑셀을 활용해 식과 표와 그래프를 다양하게 조작한 역동적 탐구활동은 일차함수의 과정관점과 대상관점을 형성하는 데 중요한 비계설정(scaffolding) 역할을 했다.

• 생물정신의학
• /
• 제12권2호
• /
• pp.165-172
• /
• 2005

Objectives:The purpose of this study is to 1) conduct a discrimination analysis of schizophrenia and bipolar affective disorder using MMPI profile through artificial neural network analysis and logistic regression analysis, 2) to make a comparison between advantages and disadvantages of the two methods, and 3) to demonstrate the usefulness of artificial neural network analysis of psychiatric data. Procedure:The MMPI profiles for 181 schizophrenia and bipolar affective disorder patients were selected. Of these profiles, 50 were randomly placed in the learning group and the remaining 131 were placed in the validation group. The artificial neural network was trained using the profiles of the learning group and the 131 profiles of the validation group were analyzed. A logistic regression analysis was then conducted in a similar manner. The results of the two analyses were compared and contrasted using sensitivity, specificity, ROC curves, and kappa index. Results:Logistic regression analysis and artificial neural network analysis both exhibited satisfactory discriminating ability at Kappa index of greater than 0.4. The comparison of the two methods revealed artificial neural network analysis is superior to logistic regression analysis in its discriminating capacity, displaying higher values of Kappa index, specificity, and AUC(Area Under the Curve) of ROC curve than those of logistic regression analysis. Conclusion:Artificial neural network analysis is a new tool whose frequency of use has been increasing for its superiority in nonlinear applications. However, it does possess insufficiencies such as difficulties in understanding the relationship between dependent and independent variables. Nevertheless, when used in conjunction with other analysis tools which supplement it, such as the logistic regression analysis, it may serve as a powerful tool for psychiatric data analysis.

• 지구물리와물리탐사
• /
• 제23권3호
• /
• pp.149-156
• /
• 2020

복잡하고 다양한 광상 생성 과정과 부존 위치의 심부화로 인하여 광물자원 탐사의 효율을 높일 수 있는 예측탐사의 필요성이 점차 높아지고 있다. 최근의 머신러닝 기법의 활용성 증가와 광역 지질 데이터베이스의 구축 상황을 고려하면, 예측탐사의 기반인 광상 배태 가능성 평가 기술의 신뢰도는 점차 높아질 것으로 예상된다. 이번 연구에서는 심층신경망을 이용하여 화성암과 단층 및 자력탐사 정보의 광화 인자로의 활용 가능성을 확인하였다. 지질 정보의 수치화 기법으로 단층, 화성암, 자력 정보를 입력 자료로 구성하여 0.9 이상의 정확도를 가지며 예측 값이 안정적으로 수렴하는 금속 광상 예측 모델을 구축할 수 있었다. 이 기술은 추후 정밀한 지질 조사 결과와 물리탐사 정보가 확보된다면, 광화대 규모에서의 예측 탐사에도 활용할 수 있을 것으로 기대된다. 또한, 이 연구를 통해 지하의 화성암 정보를 제공하는 자력자료를 활용할 경우 지표의 화성암 정보를 보완하여 보다 높은 성능의 모델을 구축할 수 있는 것으로 확인되었다. 즉, 단순히 많은 자료를 융합하는 것 보다는 광체 성인과의 지질학적 상관관계를 고려하여 입력 자료를 구성하는 것이 보다 중요하다.

• International Journal of Advanced Culture Technology
• /
• 제8권3호
• /
• pp.61-72
• /
• 2020

The fear of crime, discussed in the early 1960s in the United States, is a psychological response, such as anxiety or concern about crime, the potential victim of a crime. These anxiety factors lead to the burden of the individual in securing the psychological stability and indirect costs of the crime against the society. Fear of crime is not a good thing, and it is a part that needs to be adjusted so that it cannot be exaggerated and distorted by the policy together with the crime coping and resolution. This is because fear of crime has as much harm as damage caused by criminal act. Eric Pawson has argued that the popular impression of violent crime is not formed because of media reports, but by official statistics. Therefore, the police should watch and analyze news related to fear of crime to reduce the social cost of fear of crime and prepare a preemptive response policy before the people have 'fear of crime'. In this paper, we propose a deep - based news classification system that helps police cope with crimes related to crimes reported in the media efficiently and quickly and precisely. The goal is to establish a system that can quickly identify changes in security issues that are rapidly increasing by categorizing news related to crime among news articles. To construct the system, crime data was learned so that news could be classified according to the type of crime. Deep learning was applied by using Google tensor flow. In the future, it is necessary to continue research on the importance of keyword according to early detection of issues that are rapidly increasing by crime type and the power of the press, and it is also necessary to constantly supplement crime related corpus.

• 전자공학회논문지
• /
• 제54권3호
• /
• pp.70-77
• /
• 2017

최근 IoT 및 딥러닝 관련 기술요소들이 영상보안감시시스템에서도 다양하게 응용되고 있다. 그 중 CCTV를 통해 촬영된 동영상에서 자동으로 특정 객체를 검출, 추적, 분류 하는 감시 기능이 점점 지능화되고 있다. 본 논문에서는 보급형 CPU만 사용하는 PC 환경에서도 실시간 처리가 가능한 알고리즘을 목표로 하였다. GMM(Gaussian Mixture Model)을 이용한 배경 모델링과 헝가리안 알고리즘, 그리고 칼만 필터를 조합한 추적 알고리즘은 전통적이며 복잡도가 비교적 적지만 검출 오류가 높다. 이를 보강하기 위해 대용량 데이터 학습에 적합한 딥러닝을 기술을 적용하였다. 특히 움직임이 있는 사람의 특징을 강조하기 위해 추적된 객체에 대해 SRGB-3 Layer CNN을 사용하였다. 성능 평가를 위해 기존의 HOG와 SVM을 이용한 시스템과 비교했을 때 Move-in은 7.6%, Move-out은 9.0%의 오류율 감소가 있었다.

• Journal of Ginseng Research
• /
• 제40권3호
• /
• pp.211-219
• /
• 2016

Background: Panax ginseng root is used in traditional oriental medicine for human health. Its main active components such as saponins and polysaccharides have been widely evaluated for treating diseases, but secondary active components such as oligosaccharides have been rarely studied. This study aimed to assess the impact of water-soluble ginseng oligosaccharides (WGOS), which were isolated from the warm-water extract of Panax ginseng root, on scopolamine-induced cognitive impairment in mice and its antineuroinflammatory mechanisms. Methods: We investigated the impact of WGOS on scopolamine-induced cognitive impairment in mice by using Morris water maze and novel object recognition task. We also analyzed the impact of WGOS on scopolamine-induced inflammatory response (e.g., the hyperexpression of proinflammatory cytokines IL-$1{\beta}$ and IL-6 and astrocyte activation) by quantitative real-time polymerase chain reaction and glial fibrillary acid protein (GFAP) immunohistochemical staining. Results: WGOS pretreatment protected against scopolamine-induced learning and memory deficits in the Morris water maze and in the novel object recognition task. Furthermore, WGOS pretreatment downregulated scopolamine-induced hyperexpression of proinflammatory cytokines interleukin (IL)-$1{\beta}$ and IL-6 mRNA and astrocyte activation in the hippocampus. These results indicate that WGOS can protect against scopolamine-induced alterations in learning and memory and inflammatory response. Conclusion: Our data suggest that WGOS may be beneficial as a medicine or functional food supplement to treat disorders with cognitive deficits and increased inflammation.

• 교육시설 논문지
• /
• 제25권4호
• /
• pp.19-30
• /
• 2018

The school classroom is a common living place where students spend 7 to 14 hours a day to prepare for their careers. Therefore, if the ventilation of the classroom is not properly performed, it may lead to the deterioration of learning ability due to the unclear air. The concentration of carbon dioxide in the classroom is reported to be high, and the increase in carbon dioxide concentration has a negative effect on the learner's academic performance. In this context, the purpose of this study is to propose a methodology for intelligent and responsive window opening-closing operation process that can reduce the concentration of $CO_2$ in the classroom in order to build a support space that can create an effective teaching-learning environment for adolescents. The specific objectives are as follows. First of all, we define the concept of window opening-closing operation. Secondly, twe develop the operation process of window opening-closing. Thirdly, we develop an algorithm for real-time window opening and closing (process) (Window Opening-Closing Operation Process). Finally, we verify the intelligent responsive window opening-closing operation process through developing examples of window opening-closing operation process using the parametric design program. This study is a preliminary study to develop algorithms necessary for window opening-closing operation. Based on the first-order algorithm, We simulated window opening-closing operations according to a hypothetical scenario. As a result, This study can show that the window is open and close depending on the $CO_2$ concentration, but the $CO_2$ concentration in the room is higher than outdoors. Consequentially, we suggest that it is necessary to develop an algorithm to supplement these results because window is often not working when the temperature difference between indoor and outdoor in winter is large.

• 대한수학교육학회지:학교수학
• /
• 제8권3호
• /
• pp.265-290
• /
• 2006

본 연구의 목적은 엑셀의 활용이 일차함수의 문제해결에 어떤 영향을 미치는가를 알아보는데 있다. 엑셀을 활용한 교수실험 전과 후에 학생들의 함수에 관한 문제해결에서의 변화를 알아보기 위해 사전 사후 문제해결검사를 실시하였다. 문제해결검사 분석은 정확한 과정-대상관점, 근접한 과정-대상관점, 부정확한 과정-대상관점으로 범주화해 이루어졌다. 문제해결검사 분석 결과, 교수실험에 참여한 학생들 모두 일차함수에 관한 문제해결관점이 바람직한 방향으로 변화되었다. 엑셀을 활용한 탐구학습환경이 지필환경의 제한점을 보완할 수 있다는 시사점을 도출하였다.

• 한국해양공학회지
• /
• 제33권5호
• /
• pp.427-434
• /
• 2019

Artificial intelligence (AI)-aided research currently enjoys active use in a wide array of fields thanks to the rapid development of computing capability and the use of Big Data. Until now, forecasting methods were primarily based on physics models and statistical studies. Today, AI is utilized in disaster prevention forecasts by studying the relationships between physical factors and their characteristics. Current studies also involve combining AI and physics models to supplement the strengths and weaknesses of each aspect. However, prior to these studies, an optimization algorithm for the AI model should be developed and its applicability should be studied. This study aimed to improve the forecast performance by constructing a model for neural network optimization. An artificial neural network (ANN) followed the ever-changing path of a typhoon to produce similar typhoon predictions, while the optimization achieved by the neural network algorithm was examined by evaluating the activation function, hidden layer composition, and dropouts. A learning and test dataset was constructed from the available digital data of one typhoon that affected Korea throughout the record period (1951-2018). As a result of neural network optimization, assessments showed a higher degree of forecast accuracy.

• 한국콘텐츠학회논문지
• /
• 제21권12호
• /
• pp.13-22
• /
• 2021

임상의사결정시스템은 누적된 의료 데이터를 활용하여 머신러닝으로 학습된 AI 모델을 환자의 진단 및 진료 예측에 적용한다. 그러나 기존의 블랙박스 기반의 AI 응용은 시스템이 예측한 결과에 대해 타당한 이유를 제시하지 못하여 설명성이 부족한 한계점이 존재한다. 이와 같은 문제점을 보완하기 위해 이 논문에서는 임상의사결정시스템의 개발 단계에서 설명이 가능한 XAI를 적용하는 시스템 모델을 제안한다. 제안 모델은 기존의 AI모델에 설명성이 가능한 특정 XAI 기술을 추가로 적용시켜 블랙박스의 한계점을 보완할 수 있다. 제안 모델의 적용을 보이기 위해 LIME과 SHAP을 활용한 XAI 적용 사례를 제시한다. 테스트를 통해 데이터들이 모델의 예측 결과에 어떤 영향을 미치는지 다양한 관점에서 설명할 수 있다. 제안된 모델은 사용자에게 구체적인 이유를 제시함으로써 사용자의 신뢰를 높일 수 있는 장점을 가진다. 아울러 XAI의 적극적인 활용을 통해 기존 임상의사결정시스템의 한계를 극복하고 더 나은 진단 및 의사결정 지원을 가능하게 할 것으로 기대한다.