• Journal of the Korea Society of Computer and Information
• /
• v.9 no.4 s.32
• /
• pp.33-39
• /
• 2004

In this paper. we design the learning algorithm of LVQ which is used Forward Counter Propagation Networks to improve classification performance of LVQ networks. The weights of Forward Counter Propagation Networks which is between input layer and cluster layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVQ algorithm. Finally. pattern vectors is classified into subclasses by neurons which is being in the cluster layer, and the weights of Forward Counter Propagation Networks which is between cluster layer and output layer is learned to classify the classified subclass, which is enclosed a class. Also. kr the number of classes is determined, the number of neurons which is being in the input layer, cluster layer and output layer can be determined. To prove the performance of the proposed learning algorithm. the simulation is performed by using training vectors and test vectors that ate Fisher's Iris data, and classification performance of the proposed learning method is compared with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional classification.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.16 no.1
• /
• pp.104-111
• /
• 1992

In this study, the heat transfer characteristics of the evaporative transpiration cooled system is analytically investigated considering the occurrence of the two-phase evaporation zone. Under the condition of the external heat input, analytical solutions of the three regions (i.e., vapor, liquid and two-phase evaporation zone) are respectively obtained using the matching conditions for the steady-state problem where properties are constant. As results, the length of the evaporation zone increases with increasing heat input and with decreasing mass flow rate. It also increases with increasing particle size, system porosity, thermal conductivity of material, inlet temperature and latent heat of coolant. The position of the lower interface of the evaporation zone have a lot of efforts on the evaporation zone length, the position of the upper interface penetrates deeper into the porous layer with lower thermal conductivity of porous material, higher system porosity and larger particle size.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.130.5-130
• /
• 2001

This paper presents a discrete-time sliding mode control method for linear time-invariant systems with matched uncertainties. In this paper, we suggest a method of adding a command generator using input shaping filter to a discrete-time sliding mode controller. We design the number of steps required to reach the sliding layer and the magnitude of a control input, respectively using the shaping filter. Therefore we can minimize the excitation of the resonance mode and increase the tracking performance of a system. Simulation results are included to show its effectiveness.

• Proceedings of the Optical Society of Korea Conference
• /
• 1991.06a
• /
• pp.35-40
• /
• 1991

In this paper, a new adaptive learning algorithm, Training by Adaptive Gain (TAG) for optical implementation of large-sized neural networks has been developed and its electro-optical implementation for 2-dimensional input and output neurons has been demostrated. The 4-dimensional global fixed interconnections and 2-dimensional adaptive gain-controls are implemented by multi-facet computer generated holograms and LCTV spatial light modulators, respectively. When the input signals pass through optical system to the output classifying layer, the TAG adaptive learning algorithm is implemented by a personal computer. The system classifies three 5$\times$5 input patterns correctly.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.87-90
• /
• 2002

This paper has been studied a new approach using neural network to detect false laser marks. In the proposed approach, input images are segmented into R, G and B colors and implements mask areas respectively. And then average and variation values of the each mask area are extracted for the learning process to minimize input nodes. Using this technique, the new input data is obtained and implemented to the back-propagation algorithm using multi layer perception. This paper reduces the computational complexity necessary and shows better effectiveness to inspect false laser marks.

• Journal of Biomedical Engineering Research
• /
• v.12 no.3
• /
• pp.191-202
• /
• 1991

This paper describes ECG data compression algorithm using neural network. As a learning method, we use back error propagation algorithm. ECG data compression is performed using learning ability of neural network. CSE database, which is sampled 12bit digitized at 500samp1e/sec, is selected as a input signal. In order to reduce unit number of input layer, we modify sampling ratio 250samples/sec in QRS complex, 125samples/sec in P & T wave respectively. hs a input pattern of neural network, from 35 points backward to 45 points forward sample Points of R peak are used.

• Journal of Communications and Networks
• /
• v.12 no.4
• /
• pp.358-365
• /
• 2010

We develop a low complexity cooperative diversity protocol for low energy adaptive clustering hierarchy (LEACH) based wireless sensor networks. A cross layer approach is used to obtain spatial diversity in the physical layer. In this paper, a simple modification in clustering algorithm of the LEACH protocol is proposed to exploit virtual multiple-input multiple-output (MIMO) based user cooperation. In lieu of selecting a single cluster-head at network layer, we proposed M cluster-heads in each cluster to obtain a diversity order of M in long distance communication. Due to the broadcast nature of wireless transmission, cluster-heads are able to receive data from sensor nodes at the same time. This fact ensures the synchronization required to implement a virtual MIMO based space time block code (STBC) in cluster-head to sink node transmission. An analytical method to evaluate the energy consumption based on BER curve is presented. Analysis and simulation results show that proposed cooperative LEACH protocol can save a huge amount of energy over LEACH protocol with same data rate, bit error rate, delay and bandwidth requirements. Moreover, this proposal can achieve higher order diversity with improved spectral efficiency compared to other virtual MIMO based protocols.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.1
• /
• pp.86-93
• /
• 2006

The TAM(Topographic Attentive Mapping) network based on a biologically-motivated neural network model is an especially effective one for pattern analysis. It is composed of of input layer, category layer, and output layer. Fuzzy rule, for input and output data are acquired from it. The TAM network with three pruning rules for reducing links and nodes at the layer is called fuzzy TAM network. In this paper, we apply fuzzy TAM network to pattern analysis of core competency model for subcontractors of construction companies and show its usefulness.

• ETRI Journal
• /
• v.33 no.2
• /
• pp.184-193
• /
• 2011

Tailored for wireless local area networks, the present paper proposes a cross-layer resource allocation scheme for multiple-input multiple-output orthogonal frequency-division multiplexing systems. Our cross-layer resource allocation scheme consists of three stages. Firstly, the condition of sharing the subchannel by more than one user is studied. Secondly, the subchannel allocation policy which depends on the data packets' lengths and the admissible combination of users per subchannel is proposed. Finally, the bits and corresponding power are allocated to users based on a greedy algorithm and the data packets' lengths. The analysis and simulation results demonstrate that our proposed scheme not only achieves significant improvement in system throughput and average packet delay compared with conventional schemes but also has low computational complexity.

• The Journal of the Acoustical Society of Korea
• /
• v.40 no.2
• /
• pp.130-138
• /
• 2021

This paper presents an effective structure by applying various normalization to Convolutional Neural Networks (CNN) for seismic event classification. Normalization techniques can not only improve the learning speed of neural networks, but also show robustness to noise. In this paper, we analyze the effect of input data normalization and hidden layer normalization on the deep learning model for seismic event classification. In addition an effective model is derived through various experiments according to the structure of the applied hidden layer. As a result of various experiments, the model that applied input data normalization and weight normalization to the first hidden layer showed the most stable performance improvement.