• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.10
• /
• pp.1445-1453
• /
• 2017

In this paper, we propose a fault detection model based on multi-layer neural network using data mining technique for faults due to boiler tube leakage in a thermal power plant. Major measurement data related to faults are analyzed using statistical methods. Based on the analysis results, the number of input data of the proposed fault detection model is simplified. Then, each input data is clustering with normal data and fault data by applying K-Means algorithm, which is one of the data mining techniques. fault data were trained by the neural network and tested fault detection for boiler tube leakage fault.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.5 no.1
• /
• pp.13-20
• /
• 2005

This paper addresses a new blind channel equalization method using fourth-order cumulants of channel inputs and a three-layer neural network equalizer. The proposed algorithm is robust with respect to the existence of heavy Gaussian noise in a channel and does not require the minimum-phase characteristic of the channel. The transmitted signals at the receiver are over-sampled to ensure the channel described by a full-column rank matrix. It changes a single-input/single-output (SISO) finite-impulse response (FIR) channel to a single-input/multi-output (SIMO) channel. Based on the properties of the fourth-order cumulants of the over-sampled channel inputs, the iterative algorithm is derived to estimate the deconvolution matrix which makes the overall transfer matrix transparent, i.e., it can be reduced to the identity matrix by simple recordering and scaling. By using this estimated deconvolution matrix, which is the inverse of the over-sampled unknown channel, a three-layer neural network equalizer is implemented at the receiver. In simulation studies, the stochastic version of the proposed algorithm is tested with three-ray multi-path channels for on-line operation, and its performance is compared with a method based on conventional second-order statistics. Relatively good results, withe fast convergence speed, are achieved, even when the transmitted symbols are significantly corrupted with Gaussian noise.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.1
• /
• pp.35-45
• /
• 1991

Multi layer neural network using backpropagation learning algorithm is used to achieve identification and orientation estimation of different classes of aircraft in the variety of 3-D orientations. In-plane distortion invarient$(L,\;{\Phi})$ feature was extracted from each aircraft image to be used for training neural network aircraft classifier. For aircraft identification the optimum structure of the neural network classifier is studied to obtain high classification performance. Effective reductioin of learning time was achieved by using modified backpropagation learning algorithm and varying, learning parameters.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.111-117
• /
• 2011

In this paper, we propose an QoS aware multi-layer MAC(QAML-MAC) protocol in a wireless sensor networks. Since the proposed protocol is based on the sleep-awake architecture, which save node's energy to prolong the entire network lifetime. For this purpose the QAML-MAC first classifies incoming data according to their transmission urgency and then saves them. The protocol also adapts the cross-layer concept to re-arrange the order of transmission with the same destination. So the delay can be decreased, which can not be obtained with the previous related protocols. And high priority data such as real-time multimedia or critical value in the field monitoring applications can be transmitted quickly, Furthermore the proposed protocol has advantage of decreasing transmitted data collisions using multiple layers of idle listening when there is no high-priority data. So energy consumptions of sensor nodes can be saved and the network lifetime can be prolonged.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.7
• /
• pp.1465-1470
• /
• 2011

In this paper, we propose a new MAC protocol, namely DM-MMAC (Doze Mode Multi-Channel MAC) for ad hoe wireless networks which can utilize multiple channels effectively, thereby enhancing the network throughput considerably. Basically, the IEEE 802.11 specification allows for the use of multiple channels available at the physical layer, but its MAC protocol is designed only for a single channel with the fatal drawback, so called multi-channel hidden terminal problem in multi-channel environments. In this vein, several multi-channel MAC protocols have been proposed, but most of them demonstrate the performance problem that its throughput drastically decreases as the number of mobile hosts residing in a given network increases with small number of available channels. In this work, we tried to improve the performance of multi-channel MAC protocols in terms of network throughput as well as power saving effects by simplifying the channel assignment and channel capturing procedures and reducing the possibility of collisions between mobile hosts.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.15 no.5
• /
• pp.114-122
• /
• 2006

This paper presents a new control scheme that combines a sliding mode control and a neural network. In the proposed sliding mode control, a continuous control is employed removing the switching phenomena and the equivalent control within the boundary layer is estimated through on-line teaming of the neural network. The performances of the proposed control are compared with off-line neural network and on-line neural sliding mode control by computer simulation. The simulation results show that the proposed control reduces high frequency chattering and tracking error in example of the two link manipulator.

• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.56-59
• /
• 2017

CNN(Convolutional Neural Network)을 이용하여 발화 주제 다중 분류 task를 multi-labeling 방법과, cluster 방법을 이용하여 수행하고, 각 방법론에 MSE(Mean Square Error), softmax cross-entropy, sigmoid cross-entropy를 적용하여 성능을 평가하였다. Network는 음절 단위로 tokenize하고, 품사정보를 각 token의 추가한 sequence와, Naver DB를 통하여 얻은 named entity 정보를 입력으로 사용한다. 실험결과 cluster 방법으로 문제를 변형하고, sigmoid를 output layer의 activation function으로 사용하고 cross entropy cost function을 이용하여 network를 학습시켰을 때 F1 0.9873으로 가장 좋은 성능을 보였다.

• IEIE Transactions on Smart Processing and Computing
• /
• v.5 no.4
• /
• pp.289-293
• /
• 2016

As more mobile devices are equipped with multi-core CPUs and are required to execute many compute-intensive multimedia applications, it is important to optimize the systems, considering the underlying parallel hardware architecture. In this paper, we implement and optimize ray-tracing application tailored to a given mobile computing platform with multiple heterogeneous processing elements. In this paper, a lightweight ray-tracing application is specified and implemented in Kahn process network (KPN) model-of-computation, which is known to be suitable for the description of real-time applications. We take an open-source C/C++ implementation of ray-tracing and adapt it to KPN description in the Distributed Application Layer framework. Then, several possible configurations are evaluated in the target mobile computing platform (Exynos 5422), where eight heterogeneous ARM cores are integrated. We derive the optimal degree of parallelism and a suitable distribution of the replicated tasks tailored to the target architecture.

• Journal of Communications and Networks
• /
• v.18 no.1
• /
• pp.65-74
• /
• 2016

Ship ad-hoc network (SANET) extends the coverage of the maritime communication among ships with the reduced cost. To fulfill the growing demands of real-time services, the SANET requires an efficient clock time synchronization algorithm which has not been carefully investigated under the ad-hoc maritime environment. This is mainly because the conventional algorithms only suggest to decrease the beacon collision probability that diminishes the clock drift among the units. However, the SANET is a very large-scale network in terms of geographic scope, e.g., with 100 km coverage. The key factor to affect the synchronization performance is the signal propagation delay, which has not being carefully considered in the existing algorithms. Therefore, it requires a robust multi-hop synchronization algorithm to support the communication among hundreds of the ships under the maritime environment. The proposed algorithm has to face and overcome several challenges, i.e., physical clock, e.g., coordinated universal time (UTC)/global positioning system (GPS) unavailable due to the atrocious weather, network link stability, and large propagation delay in the SANET. In this paper, we propose a logical clock synchronization algorithm with multi-hop function for the SANET, namely multi-hop clock synchronization for SANET (MCSS). It works in an ad-hoc manner in case of no UTC/GPS being available, and the multi-hop function makes sure the link stability of the network. For the proposed MCSS, the synchronization time reference nodes (STRNs) are efficiently selected by considering the propagation delay, and the beacon collision can be decreased by the combination of adaptive timing synchronization procedure (ATSP) with the proposed STRN selection procedure. Based on the simulation results, we finalize the multi-hop frame structure of the SANET by considering the clock synchronization, where the physical layer parameters are contrived to meet the requirements of target applications.

• Proceedings of the Korean Institute of Surface Engineering Conference
• /
• 2000.11a
• /
• pp.83-84
• /
• 2000