• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.305-312
• /
• 2023

Physics-Informed Neural Network (PINN) is used to invert bubble size distributions from attenuation losses. By considering a linear system for the bubble population inversion, Adaptive Learned Iterative Shrinkage Thresholding Algorithm (Ada-LISTA), which has been solved linear systems in image processing, is used as a neural network architecture in PINN. Furthermore, a regularization based on the linear system is added to a loss function of PINN and it makes a PINN have better generalization by a solution satisfying the bubble physics. To evaluate an uncertainty of bubble estimation, deep ensemble is adopted. 20 Ada-LISTAs with different initial values are trained using the same training dataset. During test with attenuation losses different from those in the training dataset, the bubble size distribution and corresponding uncertainty are indicated by average and variance of 20 estimations, respectively. Deep ensemble Ada-LISTA demonstrate superior performance in inverting bubble size distributions than the conventional convex optimization solver of CVX.

• 제어로봇시스템학회:학술대회논문집
• /
• 1996.10b
• /
• pp.1404-1407
• /
• 1996

A quality monitoring system in butt welding process is proposed to estimate weld pool sizes. The geometrical parameters of the weld pool such as the top bead width and the penetration depth plus half back width are utilized to prove the integrity of the weld quality. The monitoring variables used are the surface temperatures measured at three points on the top surface of the weldment. The temperature profile is assumed that it has a gaussian distribution in vertical direction of torch movement and verify this assumption through temperature analysis. A neural network estimator is designed to estimate weld pool size from temperature informations. The experimental results show that the proposed neural network estimator which used gaussian distribution as temperature information can estimate the weld pool sizes accurately than used three point temperatures as temperature information. Considering the change of gap size in butt welding, the experiment were performed on various gap size.

• Journal of KIISE:Information Networking
• /
• v.34 no.4
• /
• pp.256-261
• /
• 2007

2-Dimensional Ring-banyan network is a high-performance fault-tolerant switching network using a deflection self-routing. The throughput of the switching network is better than that of Cyclic Banyan network under non-uniform traffic. In this paper, we present an analytic reliability analysis of the fault-tolerant switching network. We present the Mean-Time-to-Failure that is calculated by using probabilistic model. This model also takes into account a hardware complexity. In case of $16\;{\times}\;16$ size, the presented switching network is 1.275 times more reliable than Hui's switching network. And it is 1.510 times more reliable than Hui's network in case of $64\;{\times}\;64$ size.

• Journal of the Korean Home Economics Association
• /
• v.33 no.3
• /
• pp.43-57
• /
• 1995

The purpose of this study is to explore the characteristics of interaction between the social support network and the korean eldery and to provide information on the structure and function of the social network which influences the life satisfaction in the aged. The sample of this study was selected from the elderly living in korean urban and rural areas. 213 out of urban respondent and 350 out of rural respondent were selected as data sources. The methodological instrument was the questionnaire. The major findings of this study can be summarized as follows : 1. most of the elderly had the relationship with all kinds of social support network-family, kin, neighbors and friends. 2. the elderly having contact with all kinds of the social support network showed the highest life satisfaction. 3. the size, the frequency and the distance weren't important factors in influencing the family, the kin and the neighbors support network in the urban elderly. In the rural elderly the size was an important factor in all the support network. Also the frequency had effect upon all networks except the neighbors and the distance had significant effect upon the family support network. 4. In the urban elderly the friends support network had the positive correlation with life satisfaction. the rural elderly having contact with all kinds of the social support network showed high life satisfaction.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.24 no.1 s.173
• /
• pp.52-61
• /
• 2000

The role of quantitative nondestructive evaluation of defects is becoming more important to assure the reliability and the safety of structure, which can eventually be used for residual life evaluation of structure on the basis of fracture mechanics approach. Although ultrasonic technique is one of the most widely used techniques for application of practical field test among the various nondestructive evaluation technique, there are still some problems to be solved in effective extraction and classification of ultrasonic signal from their noisy ultrasonic waveforms. Therefore, crack size determination through a neural network based on the back-propagation algorithm using back-scattered ultrasonic signals is established in this study. For this purpose, aluminum plate containing vertical or inclined surface breaking crack with different crack length was used to receive the back-scattered ultrasonic signals by pulse echo method. Some features extracted from these signals and sizes of cracks were used to train neural network and the neural network's output of the crack size are compared with the true answer.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2007.06a
• /
• pp.389-392
• /
• 2007

In this paper, we propose an algorithm that improve network lifetime by adjusting cluster size according to location information of sensor node in wireless sensor network (WSN) using clustering technique. The sensed information in each cluster transfers to sink node through inter-cluster communications. Cluster head (CH) that nearby located in sink node much more spend own energy than far away CHs, because nearer CH forwards more data, so network lifetime is decreased. Proposed algorithm minimizes energy consumption in adjacent cluster to sink node by decreasing cluster site, and improve CH lifetime by distributing transmission paths. As a result of analysis, the proposed algorithm shows longer network lifetime in WSN.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.24 no.1
• /
• pp.63-70
• /
• 2010

In this paper, we study the structure of neural network for predicting defect size of steam generator tube. After extracting the features from the eddy current testing (ECT) signals, multi-layer neural networks are used to predict the defect size. In order to maximize the prediction performance for the defect size, we should carefully choose the structure of neural networks, especially the number of neurons in the hidden layer. In this paper, it is shown that, for the prediction of defect size, the number of neurons in the hidden layer can be efficiently determined by using cross-validation.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.20 no.3
• /
• pp.255-264
• /
• 2002

The topography is recognized as an important factor in determining the streamflow response of watershed to precipitation. In watershed analysis, stream networks are very important parameters. Each DEM grid size and flowaccumulation threshold value of drainage accumulation matrix have influence on stream networks extracted by using grid DEM. Therefore, stream networks extracted from DEM varies with each DEM grid size and flowaccumulation threshold value. Generally, small threshold values will generate more detailed stream network with higher drainage density High threshold values will generate coarser stream networks. In this paper, total stream length in the study area was used to calculate the flowaccumulation threshold value by each DEM grid size. Stream network was derived by each DEM grid size, which is applied flowaccumulation threshold value. Regression equation was derived by correlation between flowaccumulation threshold value and each DEM grid size.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.5 no.3
• /
• pp.59-67
• /
• 2009

This paper proposes a improved bitmap routing protocol, which finds the best energy efficient routing path by minimizing the network overheads and prolongs the overall network lifetime. Jung proposed a bitmap scheme for sensor networks. His scheme uses a bitmap table to represent the connection information between nodes. However, it has a problem that the table size is depends on the number of nodes in the sensor networks. The problem is very serious in the sensor node with a limited memory. Thereby, this paper proposes a improved bitmap routing protocol to solve the problem in Jung's scheme. Proposed protocol over the memory restricted sensor network could optimize the size of bitmap table by applying the deployed network property. Proposed protocol could be used in the diversity of sensor networks due to it has minimum memory overheads.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.1
• /
• pp.39-51
• /
• 1998

In this paper, we propose signaling procedures amon network elements for a connection rerouting method which can reduce inter-switch handoff processing delay reduces the delay in the connection re-routing by reserving VPI/VCIs for possible inter-switch handoff calls in advance. Additionally, we mathematically analyze the signaling procedures and then suggest solutions to the relations with cluser size, network topoloty, handoff-request rete and handoff delay. With simulation, the solutions are validated. From numerical examples, we concluded taht handoff delay, one of the handoff QoSs, can be satisfied by adjusting the cluster size and network topology according to the handoff -request rate of service area. With our proposed signaling and analytic methods, we concluded that the connection rerouting method using cluster-sectoring effectively reduces the delay of inter-switch handoff processing than dynamic connection rerouting method. Our solutions are useful in guaranteeing the requested handoff delay (especially, inter-switch handoff delay) when the connection rerouting method is applied to ATM-based wireless/wired integrated network.