• Korean Journal of Cognitive Science
• /
• v.13 no.1
• /
• pp.13-21
• /
• 2002

Fuzzy logic ignores some information in the reasoning process. Neural network is powerful tools for the pattern processing, but, not appropriate for the logical reasoning. To model human knowledge, besides pattern processing capability, the logical reasoning capability is equally important. Another new neural network called neural logic network is able to do the logical reasoning. Because the fuzzy inference is a fuzzy logical reasoning, we construct fuzzy inference network based on the neural logic network, extending the existing rule-inference network. And the traditional propagation rule is modified. Experiments are performed to compare search costs by sequential searching and searching by priority. The experimental results show that the searching by priority is more efficient than the sequential searching as the size of the fuzzy inference network becomes larder and an the number of searching increases.

• Journal of KIISE:Computer Systems and Theory
• /
• v.35 no.3
• /
• pp.103-110
• /
• 2008

This paper proposes an effective keyword extraction method for the Web videos. The proposed method classifies the Web video pages in one of 4 types. As such, we analyzed the structure of the Web pages based on the number of videos and the layout of the Web pages. And then we applied the keyword extraction algorithm fit to each page type. The experiment with 1,087 Web pages that have total 2,462 videos showed that the recall of the proposed extraction method is 18% higher than ImagerRover[2]. So, the proposed method could be used to build a powerful video search system for WWW.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.11
• /
• pp.2373-2377
• /
• 2009

In this paper, the threshold voltage characteristics have been analyzed using three dimensional Poisson's equation for FinFET. The FinFET is extensively been studing since it can reduce the short channel effects as the nano device. We have presented the short channel effects such as subthreshold swing and threshold voltage for PinFET, using the analytical three dimensional Poisson's equation. We have analyzed for channel length, thickness and width to consider the structural characteristics for FinFET. Using this model, the subthreshold swing and threshold voltage have been analyzed for FinFET since the potential and transport model of this analytical three dimensional Poisson's equation is verified as comparing with those of the numerical three dimensional Poisson's equation.

• Journal of the Korea Society for Simulation
• /
• v.27 no.2
• /
• pp.1-10
• /
• 2018

This paper presents an autonomous detection and aiming point computation of a battle tank by using RGB images. Maximally stable extremal regions algorithm was implemented to find features of the tank, which are matched with images extracted from streaming video to figure out the region of interest where the tank is present. The median filter was applied to remove noises in the region of interest and decrease camouflage effects of the tank. For the tank segmentation, k-mean clustering was used to autonomously distinguish the tank from its background. Also, both erosion and dilation algorithms of morphology techniques were applied to extract the tank shape without noises and generate the binary image with 1 for the tank and 0 for the background. After that, Sobel's edge detection was used to measure the outline of the tank by which the aiming point at the center of the tank was calculated. For performance measurement, accuracy, precision, recall, and F-measure were analyzed by confusion matrix, resulting in 91.6%, 90.4%, 85.8%, and 88.1%, respectively.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.265-270
• /
• 2010

Reinforcement learning performs learning through interacting with trial-and-error in dynamic environment. Therefore, in dynamic environment, reinforcement learning method like TD-learning and TD(${\lambda}$)-learning are faster in learning than the conventional stochastic learning method. However, because many of the proposed reinforcement learning algorithms are given the reinforcement value only when the learning agent has reached its goal state, most of the reinforcement algorithms converge to the optimal solution too slowly. In this paper, we present GDRLS algorithm for finding the shortest path faster in a maze environment. GDRLS is select the candidate states that can guide the shortest path in maze environment, and learn only the candidate states to find the shortest path. Through experiments, we can see that GDRLS can search the shortest path faster than TD-learning and TD(${\lambda}$)-learning in maze environment.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.44 no.3
• /
• pp.23-30
• /
• 2007

RFID it reads information which is it writes, the semiconductor chip for and the radio frequency system which uses the hazard antenna it has built-in transmission of information it talks. Formation which is transmitted like this collection and America which it filtrates wey the RFID search service back to inform the location of the server which has commodity information which relates with an object past record server. The hazard where measurement analysis result the leader for electronic interference does not occur consequently together from with verification test the power level which is received from the antenna grade where it stands must maintain minimum -55dBm and the electronic interference will not occur with the fact that, antenna and reel his recognition distance the maximum 7m until the recognition which is possible but smooth hazard it must stand and and with the fact that it will do from within and and and 3-4m it must be used Jig it is thought.

• Journal of Broadcast Engineering
• /
• v.16 no.1
• /
• pp.133-143
• /
• 2011

In this paper, a complexity-balancing algorithm is proposed for distributed video coding based on entropy coding. In order to reduce complexity of DVC-based decoders, the proposed method employs an entropy coder instead of channel coders and the complexity-balancing method is designed to improve RD performance with minimal computational complexity. The proposed method performs motion estimation in the decoder side and transmits the estimated motion vectors to the encoder. The proposed encoder can perform more accurate refinement using the transmitted motion vectors from the decoder. During the motion refinement, the optimal predicted motion vectors are decided by the received motion vector and the predicted motion vectors and complexity load of block is allocated by adjusting the search range based on the difference between the received motion vector and the predicted motion vectors. The computational complexity of the proposed encoder is decreased 11.9% compared to the H.264/AVC encoder and that of the proposed decoder are reduced 99% compared to the conventional DVC decoder.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.11
• /
• pp.41-50
• /
• 2020

Sentimental analysis begins with the search for words that determine the sentimentality inherent in data. Managers can understand market sentimentality by analyzing a number of relevant sentiment words which consumers usually tend to use. In this study, we propose exploring performance of feature selection methods embedded with Particle Swarm Optimization Multi Objectives Evolutionary Algorithms. The performance of the feature selection methods was benchmarked with machine learning classifiers such as Decision Tree, Naive Bayesian Network, Support Vector Machine, Random Forest, Bagging, Random Subspace, and Rotation Forest. Our empirical results of opinion mining revealed that the number of features was significantly reduced and the performance was not hurt. In specific, the Support Vector Machine showed the highest accuracy. Random subspace produced the best AUC results.

• Journal of IKEEE
• /
• v.7 no.1 s.12
• /
• pp.63-71
• /
• 2003

In this paper, we propose an DSR(Dynamic Source Routing) protocol to support QoS for reliable data transmission in the mobile ad-hoc network. The proposed algorithm uses DSR protocol to support QoS as its basic routing protocol, and uses the nodes which are between source and destination nodes as key QoS support. Because of moving nodes there is some problem that is restricted reliable data transmission. For solve this problem, source node set up the QoS link with destination node. The nodes that are located at QoS link and find out loss of transmission path save the transmitting data packets. Those search a new transmission path to destination node and transmit the saved data packet to destination node. As the result of evaluation, we found the proposed QoS network guaranteed reliable data transmission with almost 100% data reception rate for slowly moving mobile ad-hoc network and with more 96% data reception rate, which is improvement of 3.7737% reception rate compared with none QoS network, for continuously fast moving mobile ad-hoc network.

• The KIPS Transactions:PartD
• /
• v.13D no.7 s.110
• /
• pp.1027-1038
• /
• 2006

There are many technical problems in the recommendation system based on very large database(VLDB). So, it is necessary to study the recommendation system' structure and the data-mining technique suitable for the large scale Internet shopping mail. Thus we design and implement the product recommendation system using k-means clustering algorithm and sequential pattern technique which can be used in large scale Internet shopping mall. This paper processes user information by batch processing, defines the various categories by hierarchical structure, and uses a sequential pattern mining technique for the search engine. For predictive modeling and experiment, we use the real data(user's interest and preference of given category) extracted from log file of the major Internet shopping mall in Korea during 30 days. And we define PRP(Predictive Recommend Precision), PRR(Predictive Recommend Recall), and PF1(Predictive Factor One-measure) for evaluation. In the result of experiments, the best recommendation time and the best learning time of our system are much as O(N) and the values of measures are very excellent.