• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.12
• /
• pp.2744-2754
• /
• 1997

Recently, the Multi-Layer Restoration(MLR) algorithm was proposed by British Telecom(BT) to restore the network failures in Digital Cross-connect System(DCS) mesh survival network[1, 2]. This algorithm has multi restoration stage which is composed of the pre-planned and dynamic restoration. This algorithm is effective its ability in link or node failures. This reason is that it does not restore in the pre-planned rstoration stage but in dynamic restoration stage. In this paper, we propose the MLR with pre-planned Multi-Chooser(PMC) and successive restoration ratio algorithm. This proposed algorithm has a excellent performance for restortion time and ratio, spare channel availability and fast restoration from multiple link failure or node failure. This paper proposed the modeling and restoration algorithm, and analyzed the performance of the algorithm by simulation using OPNET(OPtimized Network Engineering Tools).

• The KIPS Transactions:PartC
• /
• v.16C no.2
• /
• pp.223-228
• /
• 2009

Efficient service discovery mechanism is a crucial feature for a hybrid ad-hoc network supporting extension of a wireless ad-hoc network to the Internet. We propose an efficient cross-layer service discovery mechanism using non-disjoint multi-path source routing protocol for hybrid ad-hoc networks. Our scheme has advantages of multi-path routing protocol and cross-layer service discovery. Intuitively, it is not difficult to imagine that the cross-layer service discovery mechanism could result in a decreased number of messages compared to the traditional approach for handling routing independently from service discovery. By simulation, we show that faster route recovery is possible by maintaining multiple routing paths in each node, and the route maintenance overhead can be reduced by limiting the number of multiple routing paths and by maintaining link/node non-disjoint multi-path.

• Annual Conference on Human and Language Technology
• /
• 1989.10a
• /
• pp.267-271
• /
• 1989

최근 Scofield는 coulomb energy network에 적용할 수 있는 learning algorithm(supervised learning algorithm)을 제안하였다. 이 learning algorithm은 multi-layer network에도 쉽게 적용이 가능하고 한 layer 에서 발생한 error가 다른 layer에 영향을 주지 않아서 system을 modular하게 구성할 수가 있으며 각 layer를 독립적으로 learning 시킬 수 있는 특징이 있다. 본 논문에서는 coulomb energy network를 이용하여 한글인식을 위한 neural network를 구현하여 인식실험을 한 결과와 구현한 network 에서 인식율을 높이기 위한 방안 (2 stage learning) 을 제시한다.

• Journal of the Korean Society of Mechanical Technology
• /
• v.20 no.6
• /
• pp.776-782
• /
• 2018

After CNN basic structure was introduced by LeCun in 1989, there has not been a major structure change except for more deep network until recently. The deep network enhances the expression power due to improve the abstraction ability of the network, and can learn complex problems by increasing non linearity. However, the learning of a deep network means that it has vanishing gradient or longer learning time. In this study, we proposes a CNN structure with MLP layer. The proposed CNNs are superior to the general CNN in their classification performance. It is confirmed that classification accuracy is high due to include MLP layer which improves non linearity by experiment. In order to increase the performance without making a deep network, it is confirmed that the performance is improved by increasing the non linearity of the network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.7 no.12
• /
• pp.3018-3036
• /
• 2013

In this paper, we investigate power allocation scheme and outage performance for a physical-layer network coding (PNC) relay based secondary user (SU) communication in cognitive multi-antenna relay networks (CMRNs), in which two secondary transceivers exchange their information via a multi-antenna relay using PNC protocol. We propose an optimal energy-efficient power allocation (OE-PA) scheme to minimize total energy consumption per bit under the sum rate constraint and interference power threshold (IPT) constraints. A closed-form solution for optimal allocation of transmit power among the SU nodes, as well as the outage probability of the cognitive relay system, are then derived analytically and confirmed by numerical results. Numerical simulations demonstrate the PNC protocol has superiority in energy efficiency performance over conventional direct transmission protocol and Four-Time-Slot (4TS) Decode-and-Forward (DF) relay protocol, and the proposed system has the optimal outage performance when the relay is located at the center of two secondary transceivers.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.1
• /
• pp.16-25
• /
• 2020

Vegetation segmentation in a field color image is a process of distinguishing vegetation objects of interests like crops and weeds from a background of soil and/or other residues. The performance of the process is crucial in automatic precision agriculture which includes weed control and crop status monitoring. To facilitate the segmentation, color indices have predominantly been used to transform the color image into its gray-scale image. A thresholding technique like the Otsu method is then applied to distinguish vegetation parts from the background. An obvious demerit of the thresholding based segmentation will be that classification of each pixel into vegetation or background is carried out solely by using the color feature of the pixel itself without taking into account color features of its neighboring pixels. This paper presents a new pixel-based segmentation method which employs a multi-layer perceptron neural network to classify the gray-scale image into vegetation and nonvegetation pixels. The input data of the neural network for each pixel are 2-dimensional gray-level values surrounding the pixel. To generate a gray-scale image from a raw RGB color image, a well-known color index called Excess Green minus Excess Red Index was used. Experimental results using 80 field images of 4 vegetation species demonstrate the superiority of the neural network to existing threshold-based segmentation methods in terms of accuracy, precision, recall, and harmonic mean.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.21 no.6
• /
• pp.94-101
• /
• 2007

In the Hard Disk Drive(HDD) production, the detect pattern or defective HDD set is important information to diagnosis of defective HDD set. This paper proposes a pattern recognition neural network for the defect distribution of HDD. In this paper, 5 characteristics are determined for the classification to six standard defect pattern classes. A multi-layer perceptron is trained for the pattern classification the inputs of which are 5 characteristic values and the 6 outputs are the nodes of standard patterns. The experiment with proposed neural network shows satisfactory results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3892-3912
• /
• 2021

The recent rapid growth of mobile network traffic places multi-access edge computing in an important position to reduce network load and improve network capacity and service quality. Contrasting with traditional mobile cloud computing, multi-access edge computing includes a base station cooperative cache layer and user cooperative cache layer. Selecting the most appropriate cache content according to actual needs and determining the most appropriate location to optimize the cache performance have emerged as serious issues in multi-access edge computing that must be solved urgently. For this reason, a cache placement algorithm based on comprehensive utility in big data multi-access edge computing (CPBCU) is proposed in this work. Firstly, the cache value generated by cache placement is calculated using the cache capacity, data popularity, and node replacement rate. Secondly, the cache placement problem is then modeled according to the cache value, data object acquisition, and replacement cost. The cache placement model is then transformed into a combinatorial optimization problem and the cache objects are placed on the appropriate data nodes using tabu search algorithm. Finally, to verify the feasibility and effectiveness of the algorithm, a multi-access edge computing experimental environment is built. Experimental results show that CPBCU provides a significant improvement in cache service rate, data response time, and replacement number compared with other cache placement algorithms.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.4
• /
• pp.231-241
• /
• 2011

Recently, system virtualization has been applied to consumer electronics (CE) such as smart mobile phones. Although multi-core processors have become a viable solution for complex applications of consumer electronics, the issue of utilizing multi-core resources in the virtualization layer has not been researched sufficiently. In this paper, we present a new hypervisor design and implementation for multi-core CE devices. We concretely describe virtualization methods for a multi-core processor and multi-core-related subsystems. We also analyze bottlenecks of network performance in a virtualization environment that supports multimedia applications and propose an efficient virtual interrupt distributor. Our new multi-core hypervisor improves network performance by 5.5 times as compared to a hypervisor without the virtual interrupt distributor.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.4
• /
• pp.832-839
• /
• 2009

In this paper, we introduce an design of fuzzy relation-based fuzzy neural networks with multi-output. Fuzzy relation-based fuzzy neural networks comprise the network structure generated by dividing the entire input space. The premise part of the fuzzy rules of the network reflects the relation of the division space for the entire input space and the consequent part of the fuzzy rules expresses three types of polynomial functions such as constant, linear, and modified quadratic. For the multi-output structure the neurons in the output layer were connected with connection weights. The learning of fuzzy neural networks is realized by adjusting connections of the neurons both in the consequent part of the fuzzy rules and in the output layer, 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, learning rate and momentum coefficient are automatically optimized by using real-coded genetic algorithm. Two examples are included to evaluate the performance of the proposed network.