• 한국토양동물학회지
• /
• 제2권2호
• /
• pp.98-103
• /
• 1997

This study was investigated, from October to November, 1995, how environmental factors affected both the diversity and the ecology of soil microarthropods according to the sampling sites at althletic training park located in Chonju, Chonbuk. The results obtained are as follow: At the sampling areas, the soil microarthropods were identified into 6 classes, 15 orders, 17,145 individuals. Arachnida showed the highest individual rate (74.10%) in soil mictoarthropods and Acari occupied the great majority (97.98%) in Archinida. Collembola showed the highest individual rate (82.01%) in Insecta. Species planted at althletic training park were 10 famillies 12 genera 20 species 2 varietas 1 forma. In environmental factors which have an effect on the distribution of the soil microarthropods, acarina showed positive correlation for rate of carbon/nitrogen, soil moisture, soil acidity, and lead(Pb) and also negative correlation for solidity and intensity of lightness. Collembola and other animals showed negative correlation for solidity.

• International Journal of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.37-42
• /
• 2019

In this paper, we explore the details of three classic data augmentation methods and two generative model based oversampling methods. The three classic data augmentation methods are random sampling (RANDOM), Synthetic Minority Over-sampling Technique (SMOTE), and Adaptive Synthetic Sampling (ADASYN). The two generative model based oversampling methods are Conditional Generative Adversarial Network (CGAN) and Wasserstein Generative Adversarial Network (WGAN). In imbalanced data, the whole instances are divided into majority class and minority class, where majority class occupies most of the instances in the training set and minority class only includes a few instances. Generative models have their own advantages when they are used to generate more plausible samples referring to the distribution of the minority class. We also adopt CGAN to compare the data augmentation performance with other methods. The experimental results show that WGAN-based oversampling technique is more stable than other approaches (RANDOM, SMOTE, ADASYN and CGAN) even with the very limited training datasets. However, when the imbalanced ratio is too small, generative model based approaches cannot achieve satisfying performance than the conventional data augmentation techniques. These results suggest us one of future research directions.

• 한국통신학회논문지
• /
• 제24권9B호
• /
• pp.1795-1805
• /
• 1999

OFDM(Orthogonal Frequency Division Multiplexing) 시스템에서 송·수신단의 샘플링 주파수가 일치하지 않으면 샘플링 주파수 옵셋에 의한 채널간 간섭(interchannel interference: ICI)이 발생하게 되어 시스템의 성능이 저하된다. 본 논문에서는 고속 전송률을 갖는 OFDM 시스템에서 샘플링 주파수 옵셋을 추정할 수 있는 두 가지 시간영역 기법을 제안한다. 첫 번째 방식은 심볼 동기와 반송파 주파수 동기가 이루어졌다는 가정하에서 송신단에서 훈련심볼을 전송한 후 수신단에서 일정 시간 간격을 갖는 두 샘플신호 사이의 위상차를 구하여 샘플링 주파수 옵셋을 추정한다. 두 번째 방식은 반송파 주파수 옵셋과 샘플링 주파수 옵셋이 동시에 존재하는 경우에 서로 다른 주파수 성분을 갖는 두 OFDM 훈련심볼과 간단한 대수 연산에 의해 두 옵셋을 동시 추정한다. 두 가지 샘플링 주파수 옵셋 추정기법은 모두 시간 영역에서 처리되므로 시간지연이 발생하지 않으며, ICI의 영향을 받지 않으므로 우수한 성능을 갖는다. 제안된 방식의 성능을 여러 가지 모의실험을 통하여 검증한다.

• 융합정보논문지
• /
• 제12권1호
• /
• pp.31-38
• /
• 2022

본 논문은 전문가 독립적 비지도 신경망 학습 기반 다변량 시계열 데이터 분석 모델인 MSCRED(Multi-Scale Convolutional Recurrent Encoder-Decoder)의 실제 현장에서의 적용과 Auto-encoder 기반인 MSCRED 모델의 한계인, 학습 데이터가 오염되지 않아야 된다는 점을 극복하기 위한 학습 데이터 샘플링 기법인 Subset Sampling Validation을 제시한다. 라벨 분류가 되어있는 발전소 장비의 진동 데이터를 이용하여 1) 학습 데이터에 비정상 데이터가 섞여 있는 상황을 재현하고, 이를 학습한 경우 2) 1과 같은 상황에서 Subset Sampling Validation 기법을 통해 학습 데이터에서 비정상 데이터를 제거한 경우의 Anomaly Score를 비교하여 MSCRED와 Subset Sampling Validation 기법을 유효성을 평가한다. 이를 통해 본 논문은 전문가 독립적이며 오류 데이터에 강한 이상 진단 프레임워크를 제시해, 다양한 다변량 시계열 데이터 분야에서의 간결하고 정확한 해결 방법을 제시한다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제9권2호
• /
• pp.141-146
• /
• 2009

Support vector machine is a classification algorithm based on statistical learning theory. It has shown many results with good performances in the data mining fields. But there are some problems in the algorithm. One of the problems is its heavy computing cost. So we have been difficult to use the support vector machine in the dynamic and online systems. To overcome this problem we propose to use stratified sampling of statistical sampling theory. The usage of stratified sampling supports to reduce the size of training data. In our paper, though the size of data is small, the performance accuracy is maintained. We verify our improved performance by experimental results using data sets from UCI machine learning repository.

• The Journal of Asian Finance, Economics and Business
• /
• 제7권11호
• /
• pp.499-506
• /
• 2020

The study examines the influence of individual characteristics, training content, and manager support on the effectiveness of on-the-job (OJT) training in the banking and finance industry. A simple random sampling technique was used to select the samples. Questionnaires were distributed to respondents in order to obtain the data. Using cross-sectional data obtained from 396 respondents in Bank A in Malaysia, the multiple regression results show that self-efficacy, motivation to learn, training content, and manager support have positive influence on OJT training effectiveness. Among all these factors, manager support is very highly correlated with OJT training effectiveness. The findings have given fruitful insight of the crucial roles of OJT training in the respective bank, particularly to bring forward the roles of systematic design and implementation of OJT training. This study is not only expanding knowledge in OJT and training, but offers managers practical insights in developing good OJT training program by considering employees need, capabilities, skills and job requirement. Furthermore, this study also provides a valuable framework in identifying the effectiveness of OJT training program for certain jobs. Further discussion of the research findings and its implications to theoretical knowledge of training and managers are promised at the end of the article.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1998년도 하계종합학술대회논문집
• /
• pp.46-49
• /
• 1998

In this paper, we introduce the notion of intelligent communication by introducing a novel intelligent receiver model. This receiver is continually evolving and learns and improves in performance as it compiles its experience over time. In digital communication context, in a typical training mode, it jearns the concept of "1" as is deteriorated by arbitrary (not necessarily additive as is typically assumed) disturbance and /or modulation. After learning "1", in test mode, it classifies the received signal "1" and "0" almost completely. The intelligent receiver as implemented is grounded on the recently introduced Stochastic Morphological Sampling Theorem(SMST), a distribution-free result which gives theoretical bounds on the sample complexity(training size) needed for the required performance parameters such as accuracy($\varepsilon$) and confidence($\delta$). Based on this theorem, we demonstrate --almost irrespective of channel and modulation model-- the number of samples needed to learn the concept of "1" is not too "large" and the resulting universal receiver structure, that corresponding to classical Nearest Neighbor rule in Pattern Recognition Theory, is trivial. We check the surprising efficiency and validity of this model through some simple simulations. and validity of this model through some simple simulations.

• 대한안전경영과학회지
• /
• 제5권4호
• /
• pp.13-20
• /
• 2003

The purpose of this study is to know the status of prevention on health obstacle in industries with confined space. Total 190 respondents, 95 safety or health managers and 95 confined space workers from 95 industries with confined space are surveyed by hygienists from April 2003, to July 2003. The contents of survey include health-work program in confined space, instrument of oxygen sampling, equipment of ventilation, safety and health education, watching manager, head count, awakening of risk, air condition and emergency training. The results are as follows: 1. It is found 38% of respondents established health-work program in confined space. The percentage of respondents with instrument of oxygen sampling and equipment of ventilation, operation of safety and health education, posting of watching man and operation of head count are 42%, 35%, 75%, 46% and 56%, respectively. 2. The percentage of awakening of risk, confirm of air condition and operation of emergency training are 36%, 25% and 15%, respectively.

• 대한물리의학회지
• /
• 제5권4호
• /
• pp.509-515
• /
• 2010

Purpose : This study was performed to examine the effect of stimulation task-oriented training on the balance ability of the hemiplegic patients caused by stroke. Methods : We made a random sampling of 25 hemiplegic patients caused by stroke. 10 patients(experimental group)were treated by simulation Task-oriented training and Conventional training used by balance pad. The other 10 patients(control group) were only treated by Conventional training used by balance pad. During the training, 3 patients from the experimental group and 2 patients from the control group were excluded by private affairs. The control group has done Conventional training 6 times a week for 6 weeks. And experimental group has done Simulation task-oriented training two times, conventional training four times a week for 6 weeks. Balance ability was assessed by Fuctional Reaching Test (FRT) : unilateral and bilateral reaching. Results : In comparison of FRT before and after training, two groups all was significantly improved(p<.05). But bilateral reaching variation was significantly improved in experimental group. Conclusion : we can use simulation Task-oriented training valuably to increase balance ability of hemiplegic patients.

• 소성∙가공
• /
• 제29권4호
• /
• pp.218-228
• /
• 2020

The prediction of final mass and optimized process conditions of injection molded products using Artificial Neural Network (ANN) were demonstrated. The ANN was modeled with 10 input parameters and one output parameter (mass). The input parameters, i.e.; melt temperature, mold temperature, injection speed, packing pressure, packing time, cooling time, back pressure, plastification speed, V/P switchover, and suck back were selected. To generate training data for the ANN model, 77 experiments based on the combination of orthogonal sampling and random sampling were performed. The collected training data were normalized to eliminate scale differences between factors to improve the prediction performance of the ANN model. Grid search and random search method were used to find the optimized hyper-parameter of the ANN model. After the training of ANN model, optimized process conditions that satisfied the target mass of 41.14 g were predicted. The predicted process conditions were verified through actual injection molding experiments. Through the verification, it was found that the average deviation in the optimized conditions was 0.15±0.07 g. This value confirms that our proposed procedure can successfully predict the optimized process conditions for the target mass of injection molded products.