• The Journal of the Korea Contents Association
• /
• v.8 no.1
• /
• pp.259-271
• /
• 2008

We propose a protein function finding algorithm that is able to predict specific molecular function for unannotated proteins through domain analysis from protein-protein network. To do this, we first construct protein-protein interaction(PPI) network in Saccharomyces cerevisiae from MIPS databases. The PPI network(proteins; 3,637, interactions; 10,391) shows the characteristics of a scale-free network and a hierarchical network that proteins with a number of interactions occur in small and the inherent modularity of protein clusters. Protein-protein interaction databases obtained from a Y2H(Yeast Two Hybrid) screen or a composite data set include random false positives. To filter the database, we reconstruct the PPI networks based on the cellular localization. And then we analyze Hub proteins and the network structure in the reconstructed network and define structural modules from the network. We analyze protein domains from the structural modules and derive functional modules from them. From the derived functional modules with high certainty, we find tentative functions for unannotated proteins.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.2143-2147
• /
• 2005

Human-Robot interaction (HRI) has recently become one of the most important issues in the field of robotics. Understanding and predicting the intentions of human users is a major difficulty for robotic programs. In this paper we suggest an interaction method allows the robot to execute the human user's desires in an intelligent room-based domain, even when the user does not give a specific command for the action. To achieve this, we constructed a full system architecture of an intelligent room so that the following were present and sequentially interconnected: decision-making based on the Bayesian belief network, responding to human commands, and generating queries to remove ambiguities. The robot obtained all the necessary information from analyzing the user's condition and the environmental state of the room. This information is then used to evaluate the probabilities of the results coming from the output nodes of the Bayesian belief network, which is composed of the nodes that includes several states, and the causal relationships between them. Our study shows that the suggested system and proposed method would improve a robot's ability to understand human commands, intuit human desires, and predict human intentions resulting in a comfortable intelligent room for the human user.

• The KIPS Transactions:PartB
• /
• v.13B no.1 s.104
• /
• pp.1-6
• /
• 2006

The prediction of protein function basically make use of a protein-protein interaction map based on the concept of guilt-by-association. The method however cannot determine the functions of proteins in case that the target protein does not interact with proteins with known functions directly. This paper studies protein function prediction considering the given problem as a K-class classification problem and proposes a predictive approach utilizing a modular neural network. The proposed method uses interaction data and protein related attributes as well. The experimental results demonstrate that the proposed approach can predict the functional roles of Yeast proteins whose interaction knowledge is not known and shows better performance than the graph-based models that use protein interaction data.

• Transactions of the Korean Society of Automotive Engineers
• /
• v.9 no.6
• /
• pp.135-142
• /
• 2001

The effect of tensile hold time on the creep-fatigue interaction in AISI 316 stainless steel was investigated. To study the fatigue characteristics of the material, strain controlled low cycle fatigue(LCF) tests were carried out under the continuous triangular waveshape with three different total strain ranges of 1.0%, 1.5% and 2.0%. To study the creep-fatigue interaction, 5min., 10min., and 30min. of tensile hold times were applied to the continuous triangular waveshape with the same three total strain ranges. The creep-fatigue life was found to be the longest when the 5min. tensile hold time was applied and was the shortest when the 30min. tensile hold time was applied. The cause fur the shortest creep-fatigue life under the 30min. tensile hold time is believed to be the effect of the increased creep damage per cycle as the hold time increases. The creep-fatigue life prediction using artificial neural network(ANN) showed closer prediction values to the experimental values than by the modified Coffin-Manson method.

• Nuclear Engineering and Technology
• /
• v.50 no.7
• /
• pp.1154-1159
• /
• 2018

Precise prediction of the radiation interaction position in scintillators plays an important role in medical and industrial imaging systems. In this research, the incident position of the gamma rays was predicted precisely in a plastic rod scintillator by using attenuation technique and multilayer perceptron (MLP) neural network, for the first time. Also, this procedure was performed using nonlinear regression (NLR) method. The experimental setup is comprised of a plastic rod scintillator (BC400) coupled with two PMTs at two sides, a $^{60}Co$ gamma source and two counters that record count rates. Using two proposed techniques (ANN and NLR), the radiation interaction position was predicted in a plastic rod scintillator with a mean relative error percentage less than 4.6% and 14.6%, respectively. The mean absolute error was measured less than 2.5 and 5.5. The correlation coefficient was calculated 0.998 and 0.984, respectively. Also, the ANN technique was confirmed by leave-one-out (LOO) method with 1% error. These results presented the superiority of the ANN method in comparison with NLR and the other methods. The technique and set up used are simpler and faster than other the previous position sensitive detectors. Thus, the time, cost and shielding and electronics requirements are minimized and optimized.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.43 no.4
• /
• pp.543-552
• /
• 1994

This paper presents a decentralized quadratic regulation architecture with feedforward neural networks for the control problem of complex systems. In this method, the decentralized technique was used to treat several simple subsystems instead of a full complex system in order to reduce training time of neural networks, and the neural networks' nonlinear mapping ability is exploited to handle the nonlinear interaction variables between subsystems. The decentralized regulating architecture is composed of local neuro-controllers, local neuro-identifiers and an overall interaction neuro-identifier. With the interaction neuro-identifier that catches interaction characteristics, a local neuro-identifier is trained to simulate a subsystem dynamics. A local neuro-controller is trained to learn how to control the subsystem by using generalized Backprogation Through Time(BTT) algorithm. The proposed neural network based decentralized regulating scheme is applied in the power System Stabilization(PSS) control problem for an imterconnected power system, and compared with that by a conventional centralized LQ regulator for the power system.

• International Journal of Computer Science & Network Security
• /
• v.22 no.11
• /
• pp.19-24
• /
• 2022

The article determines that, in the preservation of cultural heritage, lifestyle, an important role is played by the subjects' high assessment of the probability of achieving the result they need through the implementation of traditional models, ways of interaction. If dissatisfaction with the results of interaction is great, but there are no necessary conditions for a phased resolution of contradictions, for changing, developing interpersonal relations within the framework of the existing system, interaction becomes more difficult. It has been determined that the presence of effective models that show the possibility of meeting the requirements for the psyche of a variety of individuals from the side of activity, activating an extended search for mutually acceptable ways to success, depends on the development of the personality and its social relations, the success of interaction between people, socially psychological climate in the team.

• Journal of Distribution Research
• /
• v.16 no.2
• /
• pp.95-118
• /
• 2011

The purpose of this study is as follows. First, we investigate empirically the effects of social network properties such as social network density and centrality of a franchisee on its information sharing with various subjects such as the franchisor and other franchisees in the franchise system. Second, we examine exploratively if tie strength between a franchisee and its franchisor plays a moderating role on the relationship between social network properties and information sharing. The study model was established as shown in

• Journal of Information Technology Applications and Management
• /
• v.16 no.3
• /
• pp.87-100
• /
• 2009

The purpose of this study is to investigate the evolution of regional tourism resources from the perspective of business ecosystem network. A regional tourism structure changes due to various factors such as natural resources, facilities, festivals and events, public resources, and etc. An exploratory analysis was conducted to examine the interaction between resource characteristics and alliance complexity in the regional tourism industry. In the process, the duality of technology provides an insight into the interaction among several players within an alliance network which include regional attractions and tourism industry. As a result. we identified four types of tourism alliance network: functional, organizational, resource-oriented, and artificially-allied. The managerial implications are also discussed.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.