• 전기학회논문지
• /
• 제62권5호
• /
• pp.705-711
• /
• 2013

In this paper, we introduce an design of multi-output fuzzy neural networks based on Interval Type-2 fuzzy set. The proposed Interval Type-2 fuzzy set-based fuzzy neural networks with multi-output (IT2FS-based FNNm) comprise the network structure generated by dividing the input space individually. The premise part of the fuzzy rules of the network reflects the individuality of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions with interval sets such as constant, linear, and modified quadratic inference for pattern recognition. The learning of fuzzy neural networks is realized by adjusting connections of the neurons in the consequent part of the fuzzy rules, and it follows a back-propagation algorithm. In addition, in order to optimize the network, the parameters of the network such as apexes of membership functions, uncertainty factor, learning rate and momentum coefficient were automatically optimized by using real-coded genetic algorithm. The proposed model is evaluated with the use of numerical experimentation.

• 대한전기학회논문지
• /
• 제40권8호
• /
• pp.782-791
• /
• 1991

In the fields of pattern recognition such as speech recognition, several new techniques using Artifical Neural network Models have been proposed and implemented. In particular, the Multilayer Perception Model has been shown to be effective in static speech pattern recognition. But speech has dynamic or temporal characteristics and the most important point in implementing speech recognition systems using Artificial Neural Network Models for continuous speech is the learning of dynamic characteristics and the distributed cues and contextual effects that result from temporal characteristics. But Recurrent Multilayer Perceptron Model is known to be able to learn sequence of pattern. In this paper, the results of applying the Recurrent Model which has possibilities of learning tedmporal characteristics of speech to phoneme recognition is presented. The test data consist of 144 Vowel+ Consonant + Vowel speech chains made up of 4 Korean monothongs and 9 Korean plosive consonants. The input parameters of Artificial Neural Network model used are the FFT coefficients, residual error and zero crossing rates. The Baseline model showed a recognition rate of 91% for volwels and 71% for plosive consonants of one male speaker. We obtained better recognition rates from various other experiments compared to the existing multilayer perceptron model, thus showed the recurrent model to be better suited to speech recognition. And the possibility of using Recurrent Models for speech recognition was experimented by changing the configuration of this baseline model.

• Journal of Information Processing Systems
• /
• 제8권3호
• /
• pp.437-444
• /
• 2012

In this paper, we propose a method for predicting a user's location based on their past movement patterns. There is no restriction on the length of past movement patterns when using this method to predict the current location. For this purpose, a modified search tree has been devised. The search tree is constructed in an effective manner while it additionally learns the movement patterns of a user one by one. In fact, the time complexity of the learning process for a movement pattern is linear. In this process, the search tree expands to take into consideration more details about the movement patterns when a pattern that conflicts with an existing trained pattern is found. In this manner, the search tree is trained to make an exact matching, as needed, for location prediction. In the experiments, the results showed that this method is highly accurate in comparison with more complex and sophisticated methods. Also, the accuracy deviation of users of this method is significantly lower than for any other methods. This means that this method is highly stable for the variations of behavioral patterns as compared to any other method. Finally, 1.47 locations were considered on average for making a prediction with this method. This shows that the prediction process is very efficient.

• 한국초등과학교육학회지:초등과학교육
• /
• 제17권2호
• /
• pp.103-111
• /
• 1998

The purpose of this study was to investigate the relationship among spatial ability, learning styles, visual-perception- recall abiltiy, and the conceptual construction of the earth and moon's motion. Four paper-and-pencil tests were used to measure students' cognitive variables. Spatial ability was measured by Spatial Visualization Test, visual-perception-recall ability was measured by Rey's Figure which also have used to test visual- perception-recall ability of right-temporal lobes, and VVT were used to investigate students' learning styles. further, the test of concept construction was consisted of 15 items about the earth and moon's motion developed by researcher One hundred and twenty-seven 6th-, one hundred and sixteen 7th-, eighty-seven 9th-grade, ninety-three college students were participated in the investigation of the effects of age and learning style on conceptual construction. In the analysis of students' performances, spatial ability, visual-perception-recall ability, and conceptual achievement showed an increasing pattern with grading. In addition, visual learner's conceptual achievement showed a significantly higher score on conceptual test than verbal learner's(p<0.05). The results of the present study supported tile hypothesis that learning styles would differently influence to learning atmospheric concepts by students'learning styles. This study also indicated to be considered the students' spatial ability in learning atmospheric concepts.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권11호
• /
• pp.5427-5445
• /
• 2019

While deep neural networks have achieved remarkable performance in representation learning, a huge amount of labeled training data are usually required by supervised deep models such as convolutional neural networks. In this paper, we propose a new representation learning method, namely generative adversarial networks (GAN) based bagging deep convolutional autoencoders (GAN-BDCAE), which can map data to diverse hierarchical representations in an unsupervised fashion. To boost the size of training data, to train deep model and to aggregate diverse learning machines are the three principal avenues towards increasing the capabilities of representation learning of neural networks. We focus on combining those three techniques. To this aim, we adopt GAN for realistic unlabeled sample generation and bagging deep convolutional autoencoders (BDCAE) for robust feature learning. The proposed method improves the discriminative ability of learned feature embedding for solving subsequent pattern recognition problems. We evaluate our approach on three standard benchmarks and demonstrate the superiority of the proposed method compared to traditional unsupervised learning methods.

• 정보교육학회논문지
• /
• 제8권3호
• /
• pp.307-317
• /
• 2004

웹 기반 교육 환경에서 학습자 특성에 따른 개별 적응적인 피드백 제공의 필요성에도 불구하고 학습자 특성의 변인 도출의 어려움과 이를 위한 체계적인 전략과 실천 도구 개발이 미흡한 실정이다. 본 연구에서는 웹 기반 교수 학습 환경에서 중요시되고 있는 학습자 특성 변인 중에서 학습자의 학습 패턴을 Apriori 알고리즘을 이용하여 분석하고, 유사한 학습 패턴을 갖는 학습자들로 그룹화 하였다. 이를 기반으로 학습자 개인에게 학습 콘텐츠, 학습 경로, 학습 상황 등을 제공하기 위한 e-SRM 피드백 시스템을 설계하고 개발하였다. 개발된 시스템은 학습자 특성에 맞는 최적의 학습 환경을 제공해 줄 수 있는 기반을 조성할 수 있을 것으로 기대된다.

• 융합정보논문지
• /
• 제7권1호
• /
• pp.55-60
• /
• 2017

사물인터넷 환경에서 인간의 개입 없는 지능화된 서비스를 위해서는 IoT 디바이스에서 생성되는 빅데이터로 부터 정상 패턴을 학습하고 이를 기반으로 불량, 오작동과 같은 이상 징후에 대해 예측하는 과정이 요구된다. 본 연구의 목적은 제품 공정의 다양한 기기에서 발생되는 빅데이터를 분석함으로써 제품 불량을 예측할 수 있는 기계 학습모델을 구현하는 것이다. 기계 학습 모델은 어느 정도 볼륨을 가진 기존 데이터를 기반으로 분석을 해야 하므로 빅데이터 분석도구 R을 사용하였으며, 제품 공정에서 수집된 데이터에는 제품에 대한 불량 여부가 포함되어 있으므로 지도 학습 모델을 활용하였다. 연구의 결과, 제품 불량에 영향을 주는 변수 및 변수 조건을 분류하였고, 의사결정 트리를 기반으로 제품의 불량 여부에 대한 예측 모델을 제시하였다. 또한, ROC Curve를 이용한 모델의 적합성 및 성능평가 분석에서 모델의 예측력은 상당히 높게 나타났다.

• The Journal of Korean Physical Therapy
• /
• 제21권1호
• /
• pp.65-71
• /
• 2009

Purpose: Numerous investigators demonstrated that adaptative changes were induced by motor skill acquisition in the central nervous system. We investigated the changes of neuroelectric potential following motor learning with serial reaction time task in young healthy subjects, using electroencephalography (EEG). Methods: Twelve right-handed normal volunteers were recruited, who have no history of neurological dysfunction and were given to written the informed consent. All subjects were assigned to flex to extend the wrist joint or flex the thumb for pressing the matched button as quickly and accurately as possible, when one of five colored lights was displayed on computer screen (red, yellow, green, blue, white). EEG was measured, whenfive types simulations ware presented randomly with equal probabilities of 20% in total 200 times at the pre and post test. And they were scheduled for 30 minutes practice session during two consecutive days in the laboratory. Results: The results showed that the reaction time at the post test was significantly reduced, compared to one of the pre test in serial reaction time task. In EEG map analysis, the broaden bilateral activation tended to be changed to the focused contralateral activation in the frontoparietal area. Conclusion: These findings showed that acquisition of motor skill led to product more fast motor execution, and that motor learning could change cortical activation pattern, from the broaden bilateral activation to the focused contralateral activation. Thus we concluded that the adaptative change was induced by motor learning in healthy subjects.

• 한국정보통신학회논문지
• /
• 제21권9호
• /
• pp.1718-1724
• /
• 2017

최근 IoT기반으로 가전제품을 실시간 모니터링을 하는 스마트 플러그가 활성화 되고 있다. 이를 통해 상시 실시간 에너지 소비 모니터링을 통한 소비자의 에너지 절약 유도를 하고, 소비자 설정 기반의 알람 기능을 통해 소비전력을 절감하는 효과를 보고 있다. 본 논문에서는 이러한 실시간 모니터링을 위해 벽 전원 콘센트에서 나오는 교류 전류를 측정한다. 이때, 가전제품마다의 전류 패턴을 분류하고 어떤 제품이 동작하는지 판단을 위해 딥러닝(Deep learning)으로 실험하였다. 전류 패턴의 학습으로 제품의 종류에 따른 인식 성능을 검증하기 위하여, 교차 검증 방법과 붓스트랩(Bootstrap) 검증 방법을 이용하였다. 또한 Cost function과 학습 성공률(Accuracy)이 Train 데이터와 Test 데이터가 동일함을 확인하였다.

• 산업과 과학
• /
• 제2권3호
• /
• pp.8-14
• /
• 2023

대다수의 IoT 기기들은 이미 AIoT를 사용하고 있지만, AI 애플리케이션을 구축하기 위해서는 아직 해결해야 할 문제가 많이 남아 있다. 본 연구에서는 IoT 에지 자원을 보다 효과적으로 분산하기 위해 머신러닝 기반의 IoT 에지 자원 관리 기법을 제안한다, 제안 기법은 머신러닝을 이용하여 IoT 에지 자원 동향을 파악함으로써 IoT 자원의 할당을 지속적으로 개선하며, 최적화된 IoT 자원은 머신러닝 컨볼루션을 활용하여 항상 변화하는 IoT 에지 자원을 안정적으로 유지한다, 제안 기법은 각각의 머신러닝 기반 IoT 에지 자원을 이전 패턴의 자원과 함께 해시값으로 저장함으로써 분산된 AIoT 맥락에서 공격 패턴으로 자원을 효과적으로 검증한다. 실험 결과에서는 IoT Edge 리소스의 무결성을 검증하기 위해서 이질적인 계산 하드웨어가 있는 복잡한 환경에서 잘 동작하는지 세 가지 다른 테스트 시나리오에서 에너지 효율성을 평가하였다.