• Journal of the Korea Society of Computer and Information
• /
• v.24 no.3
• /
• pp.19-27
• /
• 2019

This paper proposes a new method using multi-layer overlapped windows to improve the performance of YOLO network which is vulnerable to detect small dense objects. In particular, the proposed method uses the YOLO Network based on the multi-layer overlapped windows to track small dense vehicles that approach from long distances. The method improves the detection performance for location and size of small vehicles. It allows crossing area of two multi-layer overlapped windows to track moving vehicles from a long distance to a short distance. And the YOLO network is optimized so that GPU computation time due to multi-layer overlapped windows should be reduced. The superiority of the proposed algorithm has been proved through various experiments using captured images from road surveillance cameras.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.9
• /
• pp.2213-2231
• /
• 2013

Compressed sensing is a novel technology used in the field of wireless communication and sensor networks for channel estimation, signal detection, data gathering, network monitoring, and other applications. It plays a significant role in highly secure, real-time, well organized, and cost-effective data communication in smart-grid (SG) systems, which consist of multi-tier network standards that make it challenging to synchronize in power management communication. In this paper, we present a multi-layer communication model for SG systems and propose compressed-sensing based data transmission at every layer of the SG system to improve data transmission performance. Our approach is to utilize the compressed-sensing procedure at every layer in a controlled manner. Simulation results demonstrate that the proposed monitoring devices need less transmission power than conventional systems. Additionally, secure, reliable, and real-time data transmission is possible with the compressed-sensing technique.

• Journal of the Korea Society of Computer and Information
• /
• v.4 no.3
• /
• pp.67-72
• /
• 1999

The neural network is a static network that consists of a number of layer: input layer, output layer and one or more hidden layer connected in a feed forward way. The popularity of neural network appear to be its ability of learning and approximation capability. The Elman Neural Network proposed the J. Elman. is a type of recurrent network. Is has the feedback links from hidden layer to context layer. So Elman Neural Network is the better performance than the neural network. In this paper. we propose the Modified Elman Neural Network. The structure of a MENN is based on the basic ENN. The recurrency of the network is due to the feedback links from the output layer and the hidden layer to the context layer. In order to certify the usefulness or the proposed method. the MENN apply to the multi target system. Simulation shows that the proposed MENN method is better performance than the multi layer neural network and ENN.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.4 no.2
• /
• pp.189-201
• /
• 2001

For a design of multi-layer armor, the extensive full scale or sub-scale penetration test data are required. In generally, the collection of penetration data is in need of time-consuming and expensive processes. However, the application of numerical or analytical method is very limited due to poor understanding about penetration mechanics. In this paper, we have developed a neural network analyzer which can be used as a design tool for a new armor. Calculation results show that the developed neural network analyzer can predict relatively exact penetration depth of a new armor through the effective analysis of the pre-existing penetration database.

• 제어로봇시스템학회:학술대회논문집
• /
• 1998.10a
• /
• pp.250-253
• /
• 1998

This paper presents a multi-modal neural network composed of a preprocessing module and a multi-layer neural network module in order to enhance the nonlinear characteristics of neural network. The former module is based on spectral method using Chebyschev polynomials and transforms input data into spectra. The latter module identifies the system using the spectra generated by the preprocessing module. The omnibus numerical experiments show that the method is applicable to many a nonlinear dynamic system in the real world, and that preprocessing using Chebyschev polynomials reduces the number of neurons required for the multi-layer neural network.

• Journal of the Korea Society of Computer and Information
• /
• v.6 no.4
• /
• pp.68-73
• /
• 2001

MPLS(Multi protocol Label Switching) is standard skill for added to speed and control the Network Traffic. MPLS concerned the routing protocol to relative Pack line, Each Pack composed label and node, saved the time to seek the address of node. MPLS worked IP, ATM and Network protocol of flame rely. MPLS is Network OSI suport model, 2Layer send to most of Packinsted of 3Layer Switching. MPLS is added speed Traffic of QoS and effective controled the Network.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.40-45
• /
• 2004

This work presents a boundary estimation approach in electrical impedance imaging for binary-mixture fields based on a parallel structured multi-layer neural network. The interfacial boundaries are expressed with the truncated Fourier series and the unknown Fourier coefficients are estimated with the parallel structure of multi-layer neural network. Results from numerical experiments shows that the proposed approach is insensitive to the measurement noise and has a strong possibility in the visualization of binary mixtures for a real time monitoring.

• Proceedings of the IEEK Conference
• /
• 2003.07d
• /
• pp.1565-1568
• /
• 2003

In this paper, we propose modular network to solve difficult and complex problems that are seldom solved with multi-layer neural network. The structure of modular neural network in researched by Jacobs and Jordan is selected in this paper. Modular network consists of several expert networks and a gating network which is composed of single-layer neural network or multi-layer neural network. We propose modular network structure using recurrent neural network, since the state of the whole network at a particular time depends on an aggregate of previous states as well as on the current input. Finally, we show excellence of the proposed network compared with modular network.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.847-851
• /
• 2004

In the original mixture density network(MDN), which was introduced by Bishop and Nabney, the parameters of the conditional probability density function are represented by the output vector of a single multi-layer perceptron. Among the recent modification of the MDNs, there is the so-called modified mixture density network, in which each of the priors, conditional means, and covariances is represented via an independent multi-layer perceptron. In this paper, we consider a further simplification of the modified MDN, in which the conditional means are linear with respect to the input variable together with the development of the MATLAB program for the simplification. In this paper, we first briefly review the original mixture density network, then we also review the modified mixture density network in which independent multi-layer perceptrons play an important role in the learning for the parameters of the conditional probability, and finally present a further modification so that the conditional means are linear in the input. The applicability of the presented method is shown via an illustrative simulation example.