• Journal of the Korea Society of Computer and Information
• /
• v.10 no.2 s.34
• /
• pp.113-121
• /
• 2005

In this paper, we design the hybrid learning algorithm of LVQ which is to perform EMG pattern recognition. The proposed hybrid LVQ learning algorithm is the modified Counter Propagation Networks(C.p Net. ) which is use SOM to learn initial reference vectors and out-star learning algorithm to determine the class of the output neurons of LVa. The weights of the proposed C.p. Net. which is between input layer and subclass layer can be learned to determine initial reference vectors by using SOM algorithm and to learn reference vectors by using LVd algorithm, and pattern vectors is classified into subclasses by neurons which is being in the subclass layer, and the weights which is between subclass layer and class layer of C.p. Net. is learned to classify the classified subclass. which is enclosed a class . To classify the pattern vectors of EMG. the proposed algorithm is simulated with ones of the conventional LVQ, and it was a confirmation that the proposed learning method is more successful classification than the conventional LVQ.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.54 no.4
• /
• pp.271-278
• /
• 2018

In this study, the conventional cylinder-shaped lower bar on the canvas was modified and its performance was tested to improve the opening force of the stow net on anchor. The improved new lower bar used in the test is consisted of 13 flat bars with a length of 1.8 m, a width of 0.075 m and a thickness of 4 mm, and a pipe with a length of 2.0 m and a diameter of 50 mm. A stow net with the improved lower bar and a stow net with an existing lower bar were installed underwater and their trajectories for 21 hours were examined. To confirm their trajectories, GPS loggers were attached to the buoys on the left and right canvases and the buoy of the hauling rope. As a result of the test, the rotation of the gear with the improved bar was smoother than that with the existing bar. As a result of comparing the changes in the interval of the buoys attached to the canvas after the low and high tide, the buoy spacing of the gear with the improved bar is wider than that of the conventional gear; moreover, the larger the interval, the smoother the rotation of the fishing gear was. Therefore, it is considered that using the improved lower bar can enhance the performance of the stow net.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.22 no.5
• /
• pp.1064-1074
• /
• 1997

In this paper we propose an every-other-row-connecting bilayered ShuffkeNet for optical WDM(wavelength division multiplexing) multihop networks. We calculate the diameter and the average number of hops of the proposed every-other-row-connecting bilayered ShuffleNet. Using the result, we also calcuate throughputs and delays of the proposed topology, which show higher efficiencies compared to the conventional ShuffleNet, the bilayered ShuffleNet and asymmetric bilayered ShuffleNet.

• Journal of the Korean Society of Fisheries and Ocean Technology
• /
• v.16 no.1
• /
• pp.23-26
• /
• 1980

The pure polypropylen rope has been used for the head rope, and the lead cored polypropylen rope for the ground rope in the anchovy boat seine. These ropes revealed the disadvantage that deforms the net shape due to their elongation. Te improve the disadvantage, authors developed the rope of new construction which is cored by wires and wrapped by polypropylene fibers, 20mm in diameter for the head rope and 40tnm for the ground rope. To compare the physical properties of the improved rope with the conventional ones, some factors are valued and the following results are found. 1. The improved ropes rev~al some disadvantages, such as the head rope is heavier, the ground rope lighter, and both of them are stiffer than the conventional ones, contrary to the required condition of ropes) However no special difficulties are found in practical use. 2. The improved ropes display much advantages, such as elongation is 30 percent less, breaking strength is 35 precent greater, and elastic recovery is 10 percent greater than the conventional ones. Thus, it is considered that the improved ropes are more suitable for the head rope and the ground rope of the anchouy boat seine net than the conventional ones.

• 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.

• Journal of Information Technology Applications and Management
• /
• v.12 no.4
• /
• pp.1-12
• /
• 2005

In general, other conventional researches propose the fuzzy Petri net-based fuzzy reasoning algorithms based on the exhaustive search algorithms. If it can allow the certainty factors representing in the fuzzy production rules to use as the heuristic information, then it can allow the reasoning of rule-based systems to perform fuzzy reasoning in more effective manner. This paper presents a fuzzy Petri net(FPN) model to represent the fuzzy production rules of a rule-based system. Based on the fuzzy Petri net model, a weighted fuzzy reasoning algorithm is proposed to Perform the fuzzy reasoning automatically, This algorithm is more effective and more intelligent reasoning than other reasoning methods because it can perform fuzzy reasoning using the certainty factors which are provided by domain experts as heuristic information

• Journal of IKEEE
• /
• v.27 no.4
• /
• pp.456-463
• /
• 2023

In this paper, we introduce the SSResUNet network model, which integrates the SPADE structure with the U-Net network model for accurate land cover classification using high-resolution satellite imagery without requiring user intervention. The proposed network possesses the advantage of preserving the spatial characteristics inherent in satellite imagery, rendering it a robust classification model even in intricate environments. Experimental results, obtained through training on KOMPSAT-3A satellite images, exhibit superior performance compared to conventional U-Net and U-Net++ models, showcasing an average Intersection over Union (IoU) of 76.10 and a Dice coefficient of 86.22.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.49 no.6
• /
• pp.266-271
• /
• 2000

The electric power industries are moving from the conventional monopolistic or vertically integrated environments to deregulated and competitive environments, where each participant is concerned with profit maximization rather than system-wide costs minimization. Consequently, the conventional least-cost approaches for the generation resource schedule can not exactly handle real-world situations. This paper presents a game theory application for analyzing power transactions and market design in a deregulated energy marketplace, where the market participants determine the net profits through the optimal bidding strategies. The demand elasticity of the energy price is considered for the realistic modeling of the deregulated marketplace.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.5
• /
• pp.227-234
• /
• 2020

In this paper, we propose wav-U-Net to improve speech enhancement in heavy noisy environments, and it has implemented three principal techniques. First, as input data, we use 128 modified Mel-scale filter banks which can reduce computational burden instead of 512 frequency bins. Mel-scale aims to mimic the non-linear human ear perception of sound by being more discriminative at lower frequencies and less discriminative at higher frequencies. Therefore, Mel-scale is the suitable feature considering both performance and computing power because our proposed network focuses on speech signals. Second, we add a simple ResNet as pre-processing that helps our proposed network make estimated speech signals clear and suppress high-frequency noises. Finally, the proposed U-Net model shows significant performance regardless of the kinds of noise. Especially, despite using a single channel, we confirmed that it can well deal with non-stationary noises whose frequency properties are dynamically changed, and it is possible to estimate speech signals from noisy speech signals even in extremely noisy environments where noises are much lauder than speech (less than SNR 0dB). The performance on our proposed wav-U-Net was improved by about 200% on SDR and 460% on NSDR compared to the conventional Jansson's wav-U-Net. Also, it was confirmed that the processing time of out wav-U-Net with 128 modified Mel-scale filter banks was about 2.7 times faster than the common wav-U-Net with 512 frequency bins as input values.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.42 no.3
• /
• pp.292-298
• /
• 1997

To compare the growth pattern of ginseng plant under between conventional shading(light transmittance rate 3％) and polyethylene net shading(light transmittance rate 10％), the distribution of leaf area, specific leaf weight (S. L. W), leaf and stem dry weight and changes in light intensity were investigated in 2, 4 and 6 year old ginseng plant populations. Light transmittance rate(L.T.R.) was 3％ at front line, 2％ at middle line and 1.5％ at rear line under conventional shading but it was 12, 10 and 8％ under polyethylene net(P.E) shading, respectively. In 2 year old population, there was a little difference in the growth characteristics investigated between conventional and P.E. shading. In 4 year old field, the leaf area, stem and leaf dry weight decreased in large amount in the order of middle, and rear line on ridge under conventional shading, but with a little difference under P.E. shading. And these trends enlarged in 6 year old field with appearance of a large part of shoot over furrow from ridge planted ginseng. Root yield index was much lowered at the rear 3rd, 4th and 5th line of the conventional shading bed, but there was no yield difference among lines except 5th lines under the P.E. shading with higher yield by 28％ than conventional shading.