• 한국전자거래학회지
• /
• 제26권1호
• /
• pp.107-126
• /
• 2021

전자상거래에서 상품 정보에 따른 신속하고 정확한 자동 상품 분류는 중요하다. 최근의 딥러닝 기술 발전은 자동 상품 분류에도 적용이 시도되고 있다. 성능이 우수한 딥러닝 모델개발에 있어, 학습 데이터의 품질과 모델에 적합한 데이터 전처리는 중요하다. 본 연구에서는, 텍스트 상품 데이터를 기반으로 카테고리를 자동 유추할 때, 데이터의 전처리 정도에 따른 영향력과 학습 데이터 선택 범위 영향력을 CNN모델을 사례 모델로 이용하여 비교 분석한다. 실험 분석에 사용한 데이터는 실제 데이터를 사용하여 연구 결과의 실증을 담보하였다. 본 연구가 도출한 실증 분석 및 결과는 딥러닝 상품 분류 모델 개발 시 성능 향상을 위한 레퍼런스로서 의의가 있다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2009년도 학술발표회 초록집
• /
• pp.1215-1218
• /
• 2009

The goal of this research is to apply the neural networks models for the disaggregation of the pan evaporation (PE) data, Republic of Korea. The neural networks models consist of generalized regression neural networks model (GRNNM) and multilayer perceptron neural networks model (MLP-NNM), respectively. The disaggregation means that the yearly PE data divides into the monthly PE data. And, for the performances of the neural networks models, they are composed of training and test performances, respectively. The training data consist of the mixed data The mixed data involves the historic data and the generated data using PARMA (1,1). And, the testing data consist of the only historic data, respectively. From this research, we evaluate the impact of GRNNM and MLP-NNM for the disaggregation of the nonlinear time series data. We should, furthermore, construct the credible data of the monthly PE data from the disaggregation of the yearly PE data, and can suggest the methodology for the irrigation and drainage networks system.

• 한국전자통신학회논문지
• /
• 제11권4호
• /
• pp.433-440
• /
• 2016

최근 IT분야에서 화두가 되고 있는 빅데이터 처리를 위한 시스템 환경의 구축을 위해서는 다수의 컴퓨터를 네트워크 장비를 통해 연결하여 노드를 구성하거나, 하나의 컴퓨터에 다수의 가상 호스트를 통한 클라우딩 환경을 구축하여야 한다. 그러나 이러한 빅데이터 분석 시스템을 구축하는 것은 복잡한 시스템 구성과 비용적인 측면에서 많은 제약이 따른다. 이러한 제약은 중요한 국가 경쟁력의 하나로 부각되고 있는 빅데이터 전문 인력 양성에 큰 걸림돌이 되고 있다. 이에 본 연구에서는 빅데이터 분야의 인력 양성을 위한 교육현장에서 저렴한 가격으로 실용적인 교육이 가능한 라즈베리파이 보드 기반의 교육용 빅데이터 분석 시스템을 제안하였다.

• 지구물리와물리탐사
• /
• 제26권2호
• /
• pp.62-76
• /
• 2023

최근에 활발히 적용되고 있는 머신러닝 기반 탄성파 내삽 기법들은 대부분 모음 자료를 2차원 영상화 하여 빠짐을 채우는 방법으로 하는 훈련(training)-추론(inference) 전략에 기초하므로 완벽히 채워진 다수의 모음자료가 훈련을 위해 필요하게 된다. 이 연구는 이와는 달리 트레이스 기반 내삽을 수행하는 내삽 기술의 훈련-추론 전략을 기본으로, 불규칙한 빠짐이 있는 현장자료 만을 이용하여 훈련-추론을 모두 수행할 수 있는 머신러닝을 이용한 트레이스 기반 불규칙한 빠짐의 내삽 기술을 제시하였다. 이 연구에서는 불규칙한 빠짐이 있는 자료를 훈련과 추론에 체계적으로 사용하는 최대 연속빠짐 간격에 따라 정해지는 네트워크를 구성하는 방법 및 훈련하는 방법을 기술하였다. 또한, 서호주 Exmouth Sub-basin 지역의 Vincent 유전에서 얻어진 시간 참반사 보정된 탄성파 자료에 개발된 방법을 적용한 후, 예측 결과를 전통적인 내삽 방법의 결과와 비교 및 분석하였다. 신호대잡음비나 구조유사성과 같은 정량적인 지표를 통해 두 방법 모두 내삽 성능이 높은 것을 확인하였으며, 모든 주파수 대역에서도 골고루 좋은 결과를 보임을 확인하였다.

• 노동경제논집
• /
• 제36권2호
• /
• pp.95-124
• /
• 2013

본 연구에서는 정부의 사업주 직업훈련지원제도가 교육훈련투자를 촉진하고, 촉진된 교육훈련투자가 생산향상으로 이어지는지를 기업체 자료를 이용하여 실증분석해 보았다. 분석 결과 정부지원이 기업의 교육훈련투자를 촉진하는 효과가 중소기업에 비해 대기업에서는 분명히 관찰되고 있지 않다. 또 정부지원을 통한 교육훈련투자 증가는 대기업보다 중소기업에서 보다 분명히 생산성향상 효과가 나타났다. 한편 교육훈련투자 수준이 높은 기업일수록 정부지원을 통한 교육훈련투자의 성과향상 효과가 훼손되는 것으로 분석되었다. 따라서 상대적으로 더 높은 수준의 교육훈련투자를 하고 있는 대기업에 대한 정책 효과가 중소기업에 비해 제한적인 것으로 보인다.

• 대한간호학회지
• /
• 제46권4호
• /
• pp.490-500
• /
• 2016

Purpose: This study was conducted to develop assertiveness training applying Dongsasub training for junior nursing students, and to verify effectiveness of the training on assertiveness behavior, self-esteem, clinical practice stress, and clinical competence. Methods: The study design was a non-equivalent control group non-synchronized design. Participants were 63 nursing students in clinical training (31 students in the experimental group and 32 students in the control group). The assertiveness training applying Dongsasub training consisted of four sessions. Outcome variables included assertiveness behavior, self-esteem, clinical practice stress, and clinical competence. Data were analyzed using Chi-square, Fisher's exact test and independent samples t-test with SPSS/WIN 21.0. Results: Scores of assertiveness behavior (t=-2.49, p=.015), self-esteem (t=-4.80, p <.001) and clinical competence (t=-2.33, p=.023) were significantly higher and clinical practice stress (t=4.22, p <.001) was significantly lower in the experimental group compared to the control group. Conclusion: Results indicate that the assertiveness training applying Dongsasub training can be used as a nursing intervention to lower clinical practice stress and improve the clinical competence of nursing students.

• The Journal of Korean Physical Therapy
• /
• 제10권1호
• /
• pp.173-179
• /
• 1998

To overcome obstacles and to attain the goals of practical training for the students in the department of physical therapy it is necessary to effective an effective system for practical training. And to develop a good System it is essential to monitor the response of the students in practical training of physical therapy and to gather fundamental data. The author made up a questionnaire to the students in the department of physical therapy after the end of practical training course. The questionnaire consisted of 13 questionnaire for the general characterisitcs of the students, 19 questions for the degree of satisfaction (4 for the environment of practical training, 4 for the environment of practical training, 4 for the content 3 for the time assignment and 4 for the evaluation) and one open question. As results the students were satisfied with the practicality and fresh experience. But they were relatively unsatisfied with the environment of the practical training and the number and sincerity of the trainers. Especially they were dissatisfied with the correspondence with the objectives of education, conection with the lecture, communication with the trainers, time assignment and evaluation. As a Part of efforts to formulate an effective system fer practical training it is necessary to estabilish concrete goals and detail check lists to guide both trainers and students.

• Journal of Nutrition and Health
• /
• 제37권10호
• /
• pp.881-887
• /
• 2004

Elevated plasma homocysteine is an independent risk factor for the development of cardiovascular disease. Exercise is generally believed to reduce the plasma homocysteine levels and therefore, being beneficial for cardiovascular disease (CVD). However, there is a possibility that athletes undergoing strenuous training and competition which increase oxidative stress may suffer from increased plasma homocysteine levels. The purpose of this study was to investigate the influence of endurance training on the plasma concentrations of B vitamins and homocysteine in 23 male adolescent field hockey players. Data collection and blood sampling was performed during the training period and non-training period. Following the training period, significant changes in energy and vitamin B6 intakes were observed in these subjects. Plasma vitamin B2, pyridoxal phosphate (PLP) and homocysteine levels were significantly higher during the training period than non-training period, whereas no difference was observed in plasma folate and vitamin B12 levels. Positive correlation was observed between plasma folate and folic acid intakes. When energy, B vitamin intakes were adjusted there was a significant negative correlation between plasma homocysteine levels and plasma riboflavin, folate and vitamin B12 levels. In conclusion, it is suggested that athletes with oxidative stress by strenuous exercise may need B vitamins since riboflavin, folic acid and vitamin Bl2 were shown to be negatively correlated with plasma homocysteine in athletes during the training period.

• 한국공간정보시스템학회:학술대회논문집
• /
• 한국공간정보시스템학회 2002년도 춘계학술대회 논문집
• /
• pp.45-52
• /
• 2002

Artificial neural networks (ANN) have been successfully used for classifying remotely sensed imagery. However, ANN still is not the preferable choice for classification over the conventional classification methodology such as the maximum likelihood classifier commonly used in the industry production environment. This can be attributed to the ANN characteristic built-in stochastic process that creates difficulties in dealing with unequally represented training classes, and its training performance speed. In this paper we examined some practical aspects of training classes when using a back propagation neural network model for remotely sensed imagery. During the classification process of remotely sensed imagery, representative training patterns for each class are collected by polygons or by using a region-growing methodology over the imagery. The number of collected training patterns for each class may vary from several pixels to thousands. This unequally populated training data may cause the significant problems some neural network empirical models such as back-propagation have experienced. We investigate the effects of training over- or under- represented training patterns in classes and propose the pattern repopulation algorithm, and an adaptive alpha adjustment (AAA) algorithm to handle unequally represented classes. We also show the performance improvement when input patterns are presented in random fashion during the back-propagation training.

• Child Health Nursing Research
• /
• 제21권3호
• /
• pp.204-215
• /
• 2015

Purpose: This descriptive research was conducted to identify educational needs in pediatric nursing handoff training to improve students' handoff skills. Methods: Data were collected using a survey with 188 senior nursing students and 48 pediatric nursing professors and clinical nurses. The survey included items on general information as well as experiences in handoff training, necessity, training content, and items for a handoff training program in pediatric nursing. Results: Of the nursing students, 30.5% reported receiving handoff training during their clinical hours. After their handoff training, the students' confidence index was only 3.78 out of 10. Significantly, 98.3% of the respondents said that pediatric handoff training is necessary. In addition, participants reported that simulation practice (26.5%) is an appropriate educational method, and the time required for handoff training should be 8.16 hrs. Admission process was placed first as the most critical circumstance for handoff (56.8%). High demands were observed for the necessity of training content for patients with respiratory problems. Conclusion: The results of this study show the various educational needs for developing a patient safety pediatric handoff training program to promote nursing students' skills in handoff.