• 전자공학회논문지B
• /
• 제33B권10호
• /
• pp.107-119
• /
• 1996

In this paper, we propose multiple component neural network(MCNN) which learn partitioned patterns in each multiple component neural networks by reducing dimensions of input pattern vector using PCA (principal component analysis). Procesed neural network use Oja's rule that has a role of PCA, output patterns are used a slearning patterns on small component neural networks and we call it CBP. For simply not solved patterns in a network, we solves it by regenerating new CBP neural networks and by performing dynamic partitioned pattern learning. Simulation results shows that proposed MCNN neural networks are very small size networks and have very fast learning speed compared with multilayer neural network EBP.

• 한국콘크리트학회:학술대회논문집
• /
• 한국콘크리트학회 2002년도 가을 학술발표회 논문집
• /
• pp.647-652
• /
• 2002

In the previous study, authors presented the I-ProConS (Intelligent PREdiction system of CONcrete Strength) using artificial neural networks (ANN) that provides in-place strength information of the concrete to facilitate concrete form removal and scheduling for construction. The serious problem of the system has occured, which it cannot appropriately predict the concrete strength when the curing temperature of a curing day is changed. This is because it uses the single neural networks, which all nodes are fully connected, and thus it cannot smoothly respond for external impact. However this paper presents that the problem can be solved by multiple neural networks, which is composed of five ANNs.

• 한국CDE학회논문집
• /
• 제2권2호
• /
• pp.77-84
• /
• 1997

This paper is concerning the development of multiple neural networks system of problem domains where the complete input space can be decomposed into several different regions, and these are known prior to training neural networks. We will adopt oblique decision tree to represent the divided input space and sel ect an appropriate subnetworks, each of which is trained over a different region of input space. The overall architecture of multiple neural networks system, called the federated architecture, consists of a facilitator, normal subnetworks, and tile networks. The role of a facilitator is to choose the subnetwork that is suitable for the given input data using information obtained from decision tree. However, if input data is close enough to the boundaries of regions, there is a large possibility of selecting the invalid subnetwork due to the incorrect prediction of decision tree. When such a situation is encountered, the facilitator selects a tile network that is trained closely to the boundaries of partitioned input space, instead of a normal subnetwork. In this way, it is possible to reduce the large error of neural networks at zones close to borders of regions. The validation of our approach is examined and verified by applying the federated neural networks system to the configuration design of a midship structure.

• 한국지능시스템학회논문지
• /
• 제8권6호
• /
• pp.129-135
• /
• 1998

본 논문은 서러 다른 접근방식을 사용하는 카오스 회귀 신경예측모델과 다층 신경회로망이 결합하여 고립음의 인식률을 높이고자 하였다. 전반적으로 다층신경회로망은 MLP와 결합한 인식률은 1.2%에서 2.5% 이상이 개선 되었다. 이는 서로 인식하는 방법이 다르기 때문에 서로 상호 보완되고, 카오스의 다이내믹 성질이 인식률을 개선시켰음을 실험으로 밝혔다. MLP와 결합한 인식률은 카오스 다층신경망일 때가 가장 좋았다. 그러나 학습시 알고리즘이 단순하고, 신뢰도 면에서는 오히려 카오스 단층 신경망이 인식률은 0.5%정도 떨어지지만 더욱 좋다고 생각된다. 주로 MLP는 숫자음 “일”과 “오”에서 우수한 성적을 나타내었고, 카오스 예측 신경망은 숫자음 “영”, “삼”, “칠”에서 우수하였다.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 1999년도 추계종합학술대회 논문집
• /
• pp.468-471
• /
• 1999

In this paper, we present a solution for combining multiple neural networks. Each neural network is trained with different features. And the neural networks are combined by four methods. The recognition rates by four combination methods are compared. The experimental results for handwritten digit recognition shows that the combination at hidden layers by single layer neural network is superior to any other methods. The reasons of the results are explained.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• 제5B권2호
• /
• pp.103-110
• /
• 2005

Broken rotor bars in induction motors can be detected by monitoring any abnormality of the spectrum amplitudes at certain frequencies in the motor current spectrum. Broken rotor bar fault detection schemes should rely on multiple signatures in order to overcome or reduce the effect of any misinterpretation of the signatures that are obscured by factors such as measurement noises and different load conditions. Multiple Discriminant Analysis (MDA) and Artificial Neural Networks (ANN) provide appropriate environments to develop such fault detection schemes because of their multi-input processing capabilities. This paper describes two fault detection schemes for broken rotor bar fault detection with multiple signature processing, and demonstrates that multiple signature processing is more efficient than single signature processing.

• 제어로봇시스템학회논문지
• /
• 제21권4호
• /
• pp.378-384
• /
• 2015

Indoor localization is becoming one of the most important technologies for smart mobile applications with different requirements from conventional outdoor location estimation algorithms. Fingerprinting location estimation techniques based on neural networks have gained increasing attention from academia due to their good generalization properties. In this paper, we propose a novel location estimation algorithm based on an ensemble of multiple neural networks. The neural network ensemble has drawn much attention in various areas where one neural network fails to resolve and classify the given data due to its' inaccuracy, incompleteness, and ambiguity. To the best of our knowledge, this work is the first to enhance the location estimation accuracy in indoor wireless environments based on a neural network ensemble using fingerprinting training data. To evaluate the effectiveness of our proposed location estimation method, we conduct the numerical experiments using the TGn channel model that was developed by the 802.11n task group for evaluating high capacity WLAN technologies in indoor environments with multiple transmit and multiple receive antennas. The numerical results show that the proposed method based on the NNE technique outperforms the conventional methods and achieves very accurate estimation results even in environments with a low number of APs.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2000년도 ITC-CSCC -2
• /
• pp.1053-1056
• /
• 2000

In general, neural networks based modeling involves trying multiple networks with different architectures and/or training parameters in order to achieve the best accuracy. Only the single best-trained neural network is chosen, while the rest are discarded. However, using only the single best network may never give the best solution in every situation. Many researchers, therefore, propose methods to improve the accuracy of neural networks based modeling. In this paper, the idea of the logical combinations of neural networks is proposed and discussed in detail. The logical combination is constructed by combining the corresponding outputs of the neural networks with the logical “And” node. The experimental results based on simulated data show that the modeling accuracy is significantly improved when compared to using only the single best-trained neural network.

• Journal of information and communication convergence engineering
• /
• 제18권2호
• /
• pp.75-81
• /
• 2020

Approximately 1.3 million people die from traffic accidents each year, and smartphone usage while driving is one of the main causes of such accidents. Therefore, detection of smartphone usage by drivers has become an important part of distracted driving detection. Previous studies have used single camera-based methods to collect the driver images. However, smartphone usage detection by employing a single camera can be unsuccessful if the driver occludes the phone. In this paper, we present a driver smartphone usage detection system that uses multiple cameras to collect driver images from different perspectives, and then processes these images with ensemble convolutional neural networks. The ensemble method comprises three individual convolutional neural networks with a simple voting system. Each network provides a distinct image perspective and the voting mechanism selects the final classification. Experimental results verified that the proposed method avoided the limitations observed in single camera-based methods, and achieved 98.96% accuracy on our dataset.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제29권3호
• /
• pp.192-201
• /
• 2002

디지털 형태의 문서가 널리 퍼지고 끊임없이 증가함에 따라 이를 자동으로 가공하고 처리하는 문서 자동분류의 중요성이 널리 인식되고 있다. 최근의 문서 자동분류는 k-최근접 이웃, 결정트리, Support Vector Machine, 신경망 등의 다양한 기계학습 기법을 이용하여 연구되고 있다. 그러나 많은 연구가 잘 조직된 데이타 집합을 이용하여 연구결과를 보여주고 있으며, 실제 문제에의 응용성에는 큰 비중을 두지 않고 있다. 본 논문에서는 문서분류의 응용시스템인 질의 자동응답시스템에 적용할 수 있는 다중분류기 결합 방법을 제안하고 실제 전자우편 문서의 분류문제를 해결한다. 첫째로, 다중신경 망을 이용한 문서분류를 제안한다. 제안한 방법은 최대값 결합, 신경망 결합을 통해 성능의 향상을 가져온다. 둘째로, 여러 분류기의 결합을 통해 문서분류의 성능을 개선한다. 본 논문에서는 투표 결합방법, Borda 결합, 신경망 결합방법 등을 적용하여 여러 분류기의 결합을 수행하였다. 실용 가능성을 분석한 실험결과 90%이상의 정확율을 보여 제안한 방법이 실용적일 수 있음을 알 수 있었다.