• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2017년도 춘계학술발표대회
• /
• pp.787-790
• /
• 2017

Data quality is the main issue in the classification problems; generally, the presence of noisy instances in the training dataset will not lead to robust classification performance. Such instances may cause the generated decision tree to suffer from over-fitting and its accuracy may decrease. Decision trees are useful, efficient, and commonly used for solving various real world classification problems in data mining. In this paper, we introduce a preprocessing technique to improve the classification accuracy rates of the C4.5 decision tree algorithm. In the proposed preprocessing method, we applied the naive Bayes classifier to remove the noisy instances from the training dataset. We applied our proposed method to a real e-commerce sales dataset to test the performance of the proposed algorithm against the existing C4.5 decision tree classifier. As the experimental results, the proposed method improved the classification accuracy by 8.5% and 14.32% using training dataset and 10-fold crossvalidation, respectively.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2521-2525
• /
• 2005

In this paper, we presented a predictive control technique, which is based on wavelet neural network (WNN), for the control of chaotic systems whose precise mathematical models are not available. The WNN is motivated by both the multilayer feedforward neural network definition and wavelet decomposition. The wavelet theory improves the convergence of neural network. In order to design predictive controller effectively, the WNN is used as the predictor whose parameters are tuned by error between the output of actual plant and the output of WNN. Also the training method for the finding a good WNN model is the Extended Kalman algorithm which updates network parameters to converge to the reference signal during a few iterations. The benefit of EKF training method is that the WNN model can have better accuracy for the unknown plant. Finally, through computer simulations, we confirmed the performance of the proposed control method.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2007년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.407-408
• /
• 2007

In this paper, we present a new method for classifying object using LVQ (Learning Vector Quantization) with flexible output layer. The proposed LVQ is a supervised learning method that dynamically generates output neurons and initializes automatically the weight vectors from training patterns. If the classes of the nearest output neuron is different from the class of the training pattern, a new output neuron is created and the given training pattern is used to initialize the weight vector of the created neuron. The proposed method is significantly different from the previous competitive learning algorithms in the point that the output neurons are dynamically generated during the learning process.

• 제어로봇시스템학회논문지
• /
• 제3권6호
• /
• pp.594-601
• /
• 1997

A new algorithm is proposed for training the multilayer perceptrion(MLP) in pattern classification problems to accelerate the learning speed. It is shown that the sigmoid activation function of the output node can have deterimental effect on the performance of learning. To overcome this detrimental effect and to use the information fully in supervised learning, an objective function for binary modes is proposed. This objective function is composed with two new output activation functions which are selectively used depending on desired values of training patterns. The effect of the objective function is analyzed and a training algorithm is proposed based on this. Its performance is tested in several examples. Simulation results show that the performance of the proposed method is better than that of the conventional error back propagation (EBP) method.

• 전자공학회논문지S
• /
• 제35S권5호
• /
• pp.59-67
• /
• 1998

This paper propose a new vector-quantizer design method for coefficients of wavelet transformed images. In conventional wavelet transform, it is quite often to employ wavelet transformed coefficients, not containing images to be encoded, as training sequences for designing a vector-quantizer. This method has a serious drawback ; it is not known how to find a proper set of training images. This paper investigates characteristics of images that should be considered in the design of vector-quantizers for wavelet transformed images. Besides the statistical parameters such as correlation and standard deviation, edge components are shown to characterise wavelet transform images. Training sequences established in accordance with the above knowledge are used in the design of quantizers having guaranteed range of applicable images. Results of computer simulations are shown to demonstrate the effectiveness of the proposed method.

• 유통과학연구
• /
• 제16권11호
• /
• pp.29-36
• /
• 2018

Purpose - Research on community empowerment based on superior commodities to improve the economic resilience of the tourist village of Lumajang Regency is an investigative descriptive study to obtain an overview of the problems of community economic development, especially regarding economic resilience. The output of this research activity is the formation of integrated and comprehensive strategic programs and activities in order to improve economic empowerment and food security of the community around the tourist village. Research design, data, and methodology - This research method applies several methods of analysis such as the Loqation Quotion (LQ) method, SWOT analysis, Trend analysis, and analysis of Community Economic Empowerment in the agricultural sub-sector. Results - This research has strategic values and objectives in addition to providing important information to improve food security of tourism villages in Lumajang district in particular and disadvantaged communities in Indonesia in general. Through this supportive community economic empowerment programs, Lumajang District has an agricultural area and at the same time as a nature-based tourism area that supports it. Conclusion - Village tourism community empowerment activities are taken based on existing superior commodities. The existing tourism village program in Lumajang district can be used as one of the references for the upcoming tourism village program.

• 문화기술의 융합
• /
• 제3권4호
• /
• pp.171-175
• /
• 2017

최근 CNN(Convolutional Neural Network)의 구조가 복잡해지고 신견망의 깊이가 깊어지고 있다. 이에 따라 신경망의 학습에 요구되는 연산량 및 학습 시간이 증가하게 되었다. 최근 GPGPU 및 FPGA를 이용하여 신경망의 학습 속도를 가속화 하는 방법에 대한 연구가 활발히 진행되고 있다. 본 논문에서는 NVIDIA GPGPU를 제어하는 CUDA를 이용하여 CNN의 특징추출부와 분류부에 대한 연산을 가속화하는 방법을 제시한다. 특징추출부와 분류부에 대한 연산을 GPGPU의 블록 및 스레드로 할당하여 병렬로 처리하였다. 본 논문에서 제안하는 방법과 기존 CPU를 이용하여 CNN을 학습하여 학습 속도를 비교하였다. MNIST 데이터세트에 대하여 총 5 epoch을 학습한 결과 제안하는 방법이 CPU를 이용하여 학습한 방법에 비하여 약 314% 정도 학습 속도가 향상된 것을 확인하였다.

• 대한물리치료과학회지
• /
• 제27권2호
• /
• pp.63-79
• /
• 2020

Background: A physical therapy is required to restore motor function of stroke patients, especially gait function improvement is very important to them. Design: Systemic review. Methods: The purpose of this study is to provide objective evidence for the effectiveness of the treadmill training method applied to stroke patients. The literature search for a systematic review was performed on domestic data published from 2010 to 2020 at KISS, RISS, and DBpia. Results: 40 papers meeting the inclusion/exclusion criteria were finally selected. Data analysis was performed according to the research type, intervention method and process, measurement variables, and the risk of bias assessment was conducted as quality evaluation. Conclusion: Various training methods have been suggested and proved that treadmill intervention is an effective method for improving gait and balance. As the goal of rehabilitation for stroke patients is to improve walking and balance, we expect continuous clinical research to continue to establish a more systematic training program and present a new paradigm.

• 대한간호학회지
• /
• 제46권1호
• /
• pp.128-139
• /
• 2016

Purpose: This study was designed to evaluate the effects of an individual breast-feeding promotion program to address breast-feeding knowledge, attitude, method and rate of practice for married immigrant women. Methods: A non-equivalent control group quasi-experimental design was used (experimental group=16, control group=17). The intervention consisted of 3 phases: (1) Within 2 hours of delivery - individual breast-feeding training through video/verbal/practical training education and demonstration (2) After 1~2 days - group training using video, model doll, and breast models (3) After 7 days - family visit, counseling, retraining and reinforcement training. The data were analyzed using non-parametric tests with the SPSS program. Results: Married immigrant women who participated in the individual breast-feeding program scored high in knowledge, attitude, method and rate of practice compared to the control group. Conclusion: The results indicate that the individual breast-feeding program is very effective in increasing breast-feeding knowledge, attitude, method and rate of practicing breast feeding for married immigrant women. So, nurses are encouraged to aggressively utilize individual breast-feeding programs to help married immigrant women, who are exposed to vulnerability due to various situations.

• Physical Therapy Rehabilitation Science
• /
• 제2권1호
• /
• pp.7-11
• /
• 2013

Objective: Final goal of nerve advancement therapy is to provide maximum ability to function independently in life to patients. This paper appraises and describes basic concepts of the virtual reality (VR) based exercise program to improve functional movement for neurologically impaired patients. Design: Review article. Methods: Stroke patients from the physical therapy department while wearing comfortable clothing receive therapy and also VR based motion therapy administered by the therapist in charge. After evaluation of stroke patients, therapy includes an exercise program that is suitable for use with stroke patients; stroke patients wear head-mounted display while in front of the computer, where the camera is located; they follow the action on the screen and the computer perceives the operation of the stroke patients according to subject accomplishment. Results: According to obstacle condition of stroke patients using the method, which is various environments after setting, in stroke patients, there is a possibility of presenting suitable therapeutic environments. The display presentation of the method, which is identical, causes difficulty for all stroke patients. According to subject accomplishment; stroke patients result in execution of repetition training and deepening study, which leads to mobility. Conclusions: The VR based rehabilitation training programs is a difference of the existing video training program, is immediate feedback and compensation method. It will provide rehabilitation training services for the family of the patient whose condition could be improved with rehabilitative therapy where it is a continuous circumstance as a matter of the social welfare facility therapy.