• Journal of Biomedical Engineering Research
• /
• v.29 no.6
• /
• pp.502-511
• /
• 2008

This study was designed to develop a new algorithm to extract the voluntary EMG and the evoked EMG from a mixed EMG generated when the muscle is stimulated both voluntarily and by electrical stimulation in the FES system. The proposed parallel filter algorithm consists of three phases: (1) Fourier transform of the mixed EMG, (2) multiplication of the transformed signal to two frequency functions, and (3) inverse Fourier transform. Four incomplete spinal cord injured patients participated in the experiments to evaluate the algorithm by measuring the knee extensor torque and the EMG signals from the quadriceps. Two functions of the algorithms were evaluated: (1) extraction of the evoked EMG and (2) the voluntary EMG from the mixed EMG. The results showed that the algorithm enabled us to separate the two EMG components in real time from the mixed EMG. The algorithm can and will be used for estimating the voluntary torque and the evoked torque independently through an artificial neural network based on the two EMG components, and also for generating a trigger signal to control the on/off time of the FES system.

• Journal of Electrical Engineering and Technology
• /
• v.9 no.6
• /
• pp.2142-2153
• /
• 2014

Linearization of transducer characteristic plays a vital role in electronic instrumentation because all transducers have outputs nonlinearly related to the physical variables they sense. If the transducer output is nonlinear, it will produce a whole assortment of problems. Transducers rarely possess a perfectly linear transfer characteristic, but always have some degree of non-linearity over their range of operation. Attempts have been made by many researchers to increase the range of linearity of transducers. This paper presents a method to compensate nonlinearity of Linear Variable Displacement Transducer (LVDT) based on Extreme Learning Machine (ELM) method, Differential Evolution (DE) algorithm and Artificial Neural Network (ANN) trained by Genetic Algorithm (GA). Because of the mechanism structure, LVDT often exhibit inherent nonlinear input-output characteristics. The best approximation capability of optimized ANN technique is beneficial to this. The use of this proposed method is demonstrated through computer simulation with the experimental data of two different LVDTs. The results reveal that the proposed method compensated the presence of nonlinearity in the displacement transducer with very low training time, lowest Mean Square Error (MSE) value and better linearity. This research work involves less computational complexity and it behaves a good performance for nonlinearity compensation for LVDT and has good application prospect.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.5
• /
• pp.1798-1804
• /
• 2017

This paper presents an approach of the Gustafson-Kessel (GK) clustering algorithm's performance in fault identification on power transmission lines. The clustering algorithm is incorporated in a scheme that uses hybrid intelligent technique to combine artificial neural network and a fuzzy inference system, known as adaptive neuro-fuzzy inference system (ANFIS). The scheme is used to identify the type of fault that occurs on a power transmission line, either single line to ground, double line, double line to ground or three phase. The scheme is also capable an analyzing the fault location without information on line parameters. The range of error estimation is within 0.10 to 0.85 relative to five values of fault resistances. This paper also presents the performance of the GK clustering algorithm compared to fuzzy clustering means (FCM), which is particularly implemented in structuring a data. Results show that the GK algorithm may be implemented in fault identification on power system transmission and performs better than FCM.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.26 no.12
• /
• pp.9-20
• /
• 2012

This paper proposes the efficiency optimization control of interior permanent magnet synchronous motor(IPMSM) drive using series connected-fuzzy neural network PI(SC-FNPI) controller. The PI controller is generally used to control IPMSM drive in industrial field. However, the PI controller has problem which is falling control performance about parameter variation such as command speed, load torque and inertia due to fixed gain of PI controller. Therefore, to improve performance of PI controller, this paper proposes SC-FNPI controller adjusted input of PI controller by FNN controller according to operating conditions. Also, this paper proposes efficiency optimization control which is improving efficiency with minimize loss. The SC-FNPI controller proposed in this paper is compared control performance with conventional FNN and PI controller about command speed, load torque and inertia variation. And the efficiency optimization control is compared with $i_d=0$ control about loss and efficiency. The SC-FNPI controller proposed in this paper shows more excellent control performance for rising time, overshoot and steady-state error. Also efficiency optimization control is increased efficiency by reducing loss.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.294-297
• /
• 2017

SNS와 스마트기기의 발전으로 온라인을 통한 뉴스 배포가 용이해지면서 악의적으로 조작된 뉴스가 급속도로 생성되어 확산되고 있다. 뉴스 조작은 다양한 형태로 이루어지는데, 이 중에서 정상적인 기사 내에 광고나 낚시성 내용을 포함시켜 독자가 의도하지 않은 정보에 노출되게 하는 형태는 독자가 해당 내용을 진짜 뉴스로 받아들이기 쉽다. 본 논문에서는 뉴스 기사 내에 포함된 문단 중에서 부적합한 문단이 포함 되었는지를 판정하기 위한 방법을 제안한다. 제안하는 방식에서는 자연어 처리에 유용한 Convolutional Neural Network(CNN)모델 중 Word2Vec과 tf-idf 알고리즘, 로지스틱 회귀를 함께 이용하여 뉴스 부적합 문단을 검출한다. 본 시스템에서는 로지스틱 회귀를 이용하여 문단의 카테고리를 분류하여 본문의 카테고리 분포도를 계산하고 Word2Vec을 이용하여 문단간의 유사도를 계산한 결과에 가중치를 부여하여 부적합 문단을 검출한다.

• 한국어정보학회:학술대회논문집
• /
• 2017.10a
• /
• pp.137-142
• /
• 2017

원격 지도 학습은 자동으로 매우 큰 코퍼스와 지식베이스 간의 주석 데이터를 생성하여 기계 학습에 필요한 학습 데이터를 사람의 손을 빌리지 않고 저렴한 비용으로 만들 수 있어, 많은 연구들이 관계 추출 문제를 해결하기 위해 원격 지도 학습 방법을 적용하고 있다. 그러나 기존 연구들에서는 모델 학습의 입력으로 사용되는 단어 임베딩에서 단어의 동형이의어 성질을 반영하지 못한다는 단점이 있다. 때문에 서로 다른 의미를 가진 동형이의어가 하나의 임베딩 값을 가지다 보니, 단어의 의미를 정확히 파악하지 못한 채 관계 추출 모델을 학습한다고 볼 수 있다. 본 논문에서는 원격 지도 학습 기반 관계 추출 모델에 다중-어의 단어 임베딩을 적용한 모델을 제안한다. 다중-어의 단어 임베딩 학습을 위해 어의 중의성 해소 모듈을 활용하였으며, 관계 추출 모델은 문장 내 주요 특징을 효율적으로 파악하는 모델인 CNN과 PCNN을 활용하였다. 본 논문에서 제안하는 다중-어의 단어 임베딩 적용 관계추출 모델의 성능을 평가하기 위해 추가적으로 2가지 방식의 단어 임베딩을 학습하여 비교 평가를 수행하였고, 그 결과 어의 중의성 해소 모듈을 활용한 단어 임베딩을 활용하였을 때 관계추출 모델의 성능이 향상된 결과를 보였다.

• Journal of Multimedia Information System
• /
• v.3 no.3
• /
• pp.97-102
• /
• 2016

Deep learning enables machines to have perception and can potentially outperform humans in the medical field. It can save a lot of time and reduce human error by detecting certain patterns from medical images without being trained. The main goal of this paper is to build the optimal model for breast mass classification by applying various methods that influence the performance of Convolutional Neural Network (CNN). Google's newly developed software library Tensorflow was used to build CNN and the mammogram dataset used in this study was obtained from 340 breast cancer cases. The best classification performance we achieved was an accuracy of 0.887, sensitivity of 0.903, and specificity of 0.869 for normal tissue versus malignant mass classification with augmented data, more convolutional filters, and ADAM optimizer. A limitation of this method, however, was that it only considered malignant masses which are relatively easier to classify than benign masses. Therefore, further studies are required in order to properly classify any given data for medical uses.

• Journal of Advanced Navigation Technology
• /
• v.13 no.2
• /
• pp.262-271
• /
• 2009

The purpose of this study was to propose the method to recognize gestures based on inertia sensor which recognizes the movements of the user using inertia sensor and lets the user enjoy the game by comparing the recognized movements with the pre-defined movements for the game contents production. Additionally, it was tried to provide users with various data entry methods by letting them wear small controllers using three-axis accelerator sensor. Users can proceed the game by moving according to the action list printed on the screen. They can proceed the experiential games according to the accuracy and timing of their movements. If they use multiple small wireless controllers together wearing them on the major parts of hands and feet and utilize the proposed methods, they will be more interested in the game and be absorbed in it.

• Journal of KIISE:Computing Practices and Letters
• /
• v.13 no.5
• /
• pp.338-342
• /
• 2007

In this paper we propose a user adaptive post-processing method to improve the accuracy of speaker dependent, isolated word speech recognition, particularly for mobile devices. Our method considers the recognition result of the basic recognizer simply as a high-level speech feature and processes it further for correct recognition result. Our method learns correlation between the output of the basic recognizer and the correct final results and uses it to correct the erroneous output of the basic recognizer. A multi-layer perceptron model is built for each incorrectly recognized word with high frequency. As the result of experiments, we achieved a significant improvement of 41% in recognition accuracy (41% error correction rate).

• Geomechanics and Engineering
• /
• v.10 no.1
• /
• pp.109-124
• /
• 2016

In this paper, process of dynamic powder compaction is investigated experimentally using impact of drop hammer and die tube. A series of test is performed using aluminum powder with different grain size. The energy of compaction of powder is determined by measuring height of hammer and the results presented in term of compact density and rupture stress. This paper also presents a mathematical modeling using experimental data and neural network. The purpose of this modeling is to display how the variations of the significant parameters changes with the compact density and rupture stress. The closed-form obtained model shows very good agreement with experimental results and it provides a way of studying and understanding the mechanics of dynamic powder compaction process. In the considered energy level (from 733 to 3580 J), the relative density is varied from 63.89% to 87.41%, 63.93% to 91.52%, 64.15% to 95.11% for powder A, B and C respectively. Also, the maximum rupture stress are obtained for different types of powder and the results shown that the rupture stress increases with increasing energy level and grain size.