• Proceedings of the IEEK Conference
• /
• 1998.10a
• /
• pp.479-482
• /
• 1998

Whether a given tree is a subgraph of the interconnection network topology is one of the important problem in parallel computing. Trees are used as the underlying structure for divide and conquer algorithms and provide the solution spaces for NP-complete problems. Complete binary trees are the basic structure among those trees. Binomial trees play an important role in broadcasting messages in parallel networks. If binomial trees can be efficiently embedded in complex binary trees, broadcasting algorithms can be effeciently performed on the interconnection networks. In this paper, we present average dilation 2 embedding of binomial trees in complete binary trees.

• Proceedings of the IEEK Conference
• /
• 1999.06a
• /
• pp.579-582
• /
• 1999

In this paper, we propose a human face detection algorithm using adaptive skin color model and neural networks. To attain robustness in the changes of illumination and variability of human skin color, we perform a color segmentation of input image by thresholding adaptively in modified hue-saturation color space (TSV). In order to distinguish faces from other segmented objects, we calculate invariant moments for each face candidate and use the multilayer perceptron neural network of backpropagation algorithm. The simulation results show superior performance for a variety of poses and relatively complex backgrounds, when compared to other existing algorithm.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1181-1186
• /
• 1993

In the paper, a new design method of rule-based fuzzy modeling is proposed for model identification of nonlinear systems. The structure indentification is carried out, utilizing fuzzy c-means clustering. Fuzzy-neural networks composed back-propagation algorithm and linear fuzzy inference method, are used to identify parameters of the premise and consequence parts. To obtain optimal linguistic fuzzy implication rules, the learning rates and momentum coefficients are tuned automatically using a modified complex method.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.37 no.9
• /
• pp.663-670
• /
• 1988

Advances in VLSI technology have made it possible to have a larger number of processing elements to be included in highly parallel processor system. A system with a large number of processing elements and memory requires a complex data path. Multistage Interconnection networks(MINS) are useful in providing programmable data path between processing elements and memory modules in multiprocessor system. In this thesis, the performance of MINS for the star network has been analyzed and compared with other networks, such as generalized shuffle network, delta network, and referenced crossbar network.

• The Journal of the Korea Contents Association
• /
• v.12 no.11
• /
• pp.519-526
• /
• 2012

Human-human interaction network derived from Roman-fleuve, Togi was constructed. The network has a scale free properties as if most social networks do. The Togi is excellent model system for analyzing network dynamics because it has various characters and complex their interactions. The novel is composed of well-separated 5 sections. I constructed 5 different sub-netwotks from each section. As employing k-core algorithm as a useful tool for obtaining a core network from the complex networks, it is possible to obtain hidden and valuable information from a complex network. As gradually extending one section to another one, I constructed 4 different extended networks. The final one is whole network from the Togi. These results provide new insight that is analyzed by network-based approaches for network dynamics from literature, Togi.

• Nutrition Research and Practice
• /
• v.13 no.6
• /
• pp.521-528
• /
• 2019

BACKGROUND/OBJECTIVES: The aim of this study was to develop Korean food image detection and recognition model for use in mobile devices for accurate estimation of dietary intake. MATERIALS/METHODS: We collected food images by taking pictures or by searching web images and built an image dataset for use in training a complex recognition model for Korean food. Augmentation techniques were performed in order to increase the dataset size. The dataset for training contained more than 92,000 images categorized into 23 groups of Korean food. All images were down-sampled to a fixed resolution of $150{\times}150$ and then randomly divided into training and testing groups at a ratio of 3:1, resulting in 69,000 training images and 23,000 test images. We used a Deep Convolutional Neural Network (DCNN) for the complex recognition model and compared the results with those of other networks: AlexNet, GoogLeNet, Very Deep Convolutional Neural Network, VGG and ResNet, for large-scale image recognition. RESULTS: Our complex food recognition model, K-foodNet, had higher test accuracy (91.3%) and faster recognition time (0.4 ms) than those of the other networks. CONCLUSION: The results showed that K-foodNet achieved better performance in detecting and recognizing Korean food compared to other state-of-the-art models.

• Journal of Communications and Networks
• /
• v.18 no.2
• /
• pp.227-237
• /
• 2016

Data collection is a key function for wireless sensor networks. There has been numerous data collection scheduling algorithms, but they fail to consider the deep and complex relationship among network lifetime, sink aggregated information and sample cycle for wireless sensor networks. This paper gives the upper bound on the sample period under the given network topology. An optimal schedule algorithm focusing on aggregated information named OSFAI is proposed. In the schedule algorithm, the nodes in hotspots would hold on transmission and accumulate their data before sending them to sink at once. This could realize the dual goals of improving the network lifetime and increasing the amount of information aggregated to sink. We formulate the optimization problem as to achieve trade-off among sample cycle, sink aggregated information and network lifetime by controlling the sample cycle. The results of simulation on the random generated wireless sensor networks show that when choosing the optimized sample cycle, the sink aggregated information quantity can be increased by 30.5%, and the network lifetime can be increased by 27.78%.

• Journal of Information Technology Services
• /
• v.15 no.4
• /
• pp.85-95
• /
• 2016

Recently, deep learning and machine learning have attracted considerable attention and many supporting frameworks appeared. In artificial intelligence field, a large body of research is underway to apply the relevant knowledge for complex problem-solving, necessitating the application of various learning algorithms and training methods to artificial intelligence systems. In addition, there is a dearth of performance evaluation of decision making agents. The decision making agent that can find optimal solutions by using reinforcement learning methods designed through this research can collect raw pixel data observed from dynamic environments and make decisions by itself based on the data. The decision making agent uses convolutional neural networks to classify situations it confronts, and the data observed from the environment undergoes preprocessing before being used. This research represents how the convolutional neural networks and the decision making agent are configured, analyzes learning performance through a value-based algorithm and a policy-based algorithm : a Deep Q-Networks and a Policy Gradient, sets forth their differences and demonstrates how the convolutional neural networks affect entire learning performance when using pixel data. This research is expected to contribute to the improvement of artificial intelligence systems which can efficiently find optimal solutions by using features extracted from raw pixel data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2419-2435
• /
• 2023

Command and control networks(C2N) exhibit evident multi-network interdependencies owing to their complex hierarchical associations, interleaved communication links, and dynamic network changes. However, the existing command and control networks do not consider the effects of dependent nodes on the load distribution. Thus, we proposed a command and control networks load allocation strategy based on interdependence strength. First, a new measure of interdependence strength was proposed based on the edge betweenness, which was followed by proposing the inter-layer load allocation strategy based on the interdependence strength. Eventually, the simulation experiments of the aforementioned strategy were designed to analyze the network invulnerability with different initial load capacity parameters, allocation model parameters, and allocation strategies. The simulation indicates that the strategy proposed in this study improved the node survival rate of the interdependent command and control networks model and successfully prevented cascade failures.

• Journal of Welding and Joining
• /
• v.11 no.2
• /
• pp.27-41
• /
• 1993

The estimation of nugget sizes was attempted by utilizing the artificial neural networks method. Artificial neural networks is a highly simplified model of the biological nervous system. Artificial neural networks is composed of a large number of elemental processors connected like biological neurons. Although the elemental processors have only simple computation functions, because they are connected massively, they can describe any complex functional relationship between an input-output pair in an autonomous manner. The electrode head movement signal, which is a good indicator of corresponding nugget size was determined by measuring the each test specimen. The sampled electrode movement data and the corresponding nugget sizes were fed into the artificial neural networks as input-output pairs to train the networks. In the training phase for the networks, the artificial neural networks constructs a fuctional relationship between the input-output pairs autonomusly by adjusting the set of weights. In the production(estimation) phase when new inputs are sampled and presented, the artificial neural networks produces appropriate outputs(the estimates of the nugget size) based upon the transfer characteristics learned during the training mode. Experimental verification of the proposed estimation method using artificial neural networks was done by actual destructive testing of welds. The predicted result by the artifficial neural networks were found to be in a good agreement with the actual nugget size. The results are quite promising in that the real-time estimation of the invisible nugget size can be achieved by analyzing the process variable without any conventional destructive testing of welds.