• Journal of the Korean Society of Visualization
• /
• v.21 no.1
• /
• pp.18-25
• /
• 2023

In these days, high dimensional data prediction technology based on neural network shows compelling results in many different kind of field including engineering. Especially, a lot of variants of convolution neural network are widely utilized to develop pixel level prediction model for high dimensional data such as picture, or physical field value from the sensors. In this study, velocity vector field of ideal flow on ship surface is estimated on pixel level by Unet. First, potential flow analysis was conducted for the set of hull form data which are generated by hull form transformation method. Thereafter, four different neural network with a U-shape structure were conFig.d to train velocity vectors at the node position of pre-processed hull form data. As a result, for the test hull forms, it was confirmed that the network with short skip-connection gives the most accurate prediction results of streamlines and velocity magnitude. And the results also have a good agreement with potential flow analysis results. However, in some cases which don't have nothing in common with training data in terms of speed or shape, the network has relatively high error at the region of large curvature.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.33 no.6
• /
• pp.359-366
• /
• 2020

In this study, a simulation-based damage estimation method for helidecks is proposed using an artificial neural network. The structural members that share a connecting node in the helideck are regarded as a damage group, and a total of 37,400 damage scenarios are numerically generated by applying randomly assigned damage to up to three damage groups. Modal analysis is then performed for all the damage scenarios, which are selectively used as either training or validation or verification sets based on the purpose of use. An artificial neural network with three hidden layers is constructed using a PyTorch program to recognize the patterns of the modal responses of the helideck model under both damaged and undamaged states, and the network is successively trained to minimize the loss function. Finally, the estimated damage rate from the proposed artificial neural network is compared to the actual assigned damage rate using 400 verification scenarios to show that the neural network is able to estimate the location and amount of structural damage precisely.

• Advances in environmental research
• /
• v.5 no.3
• /
• pp.153-167
• /
• 2016

We applied multilayer perceptron (MLP) and radial basis function (RBF) neural network in upstream and downstream water quality stations of the Karaj Reservoir in Iran. For both neural networks, inputs were pH, turbidity, temperature, chlorophyll-a, biochemical oxygen demand (BOD) and nitrate, and the output was dissolved oxygen (DO). We used an MLP neural network with two hidden layers, for upstream station 15 and 33 neurons in the first and second layers respectively, and for the downstream station, 16 and 21 neurons in the first and second hidden layer were used which had minimum amount of errors. For learning process 6-fold cross validation were applied to avoid over fitting. The best results acquired from RBF model, in which the mean bias error (MBE) and root mean squared error (RMSE) were 0.063 and 0.10 for the upstream station. The MBE and RSME were 0.0126 and 0.099 for the downstream station. The coefficient of determination ($R^2$) between the observed data and the predicted data for upstream and downstream stations in the MLP was 0.801 and 0.904, respectively, and in the RBF network were 0.962 and 0.97, respectively. The MLP neural network had acceptable results; however, the results of RBF network were more accurate. A sensitivity analysis for the MLP neural network indicated that temperature was the first parameter, pH the second and nitrate was the last factor affecting the prediction of DO concentrations. The results proved the workability and accuracy of the RBF model in the prediction of the DO.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.357-363
• /
• 2023

In underwater signal processing, separating individual signals from mixed signals has long been a challenge due to low signal quality. The common method using Short-time Fourier transform for spectrogram analysis has faced criticism for its complex parameter optimization and loss of phase data. We propose a Triple-path Recurrent Neural Network, based on the Dual-path Recurrent Neural Network's success in long time series signal processing, to handle three-dimensional tensors from multi-channel sensor input signals. By dividing input signals into short chunks and creating a 3D tensor, the method accounts for relationships within and between chunks and channels, enabling local and global feature learning. The proposed technique demonstrates improved Root Mean Square Error and Scale Invariant Signal to Noise Ratio compared to the existing method.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.14 no.1
• /
• pp.84-92
• /
• 2001

In this papers, we proposed the new method in order to diagnosis aging state of transformers. For wavelet transform, Daubechies filter is used, we can obtain wavelet coefficients which is used to extract feature of statistical parameters (maximum value, average value, dispersion skewness, kurtosis) about each acoustic emission signal. Also, these coefficients are used to identify normal and fault signal of internal partial discharge in transformer. As improved method for classification use neural network. Extracted statistical parameters are input into an back-propagation neural network. The number of neurons of hidden layer are obtained through Result of Cross-Validation. The network, after training, can decide whether the test signal is early aging state, alst aging state or normal state. In quantity analysis, capability of proposed method is superior to compared that of classical method.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.35S no.3
• /
• pp.1-8
• /
• 1998

In this paper, we propose a Neural Call Admission Control (CAC) method using a Sparse Distributed Memory(SDM). CAC is a key technology of TM network traffic control. It should be adaptable to the rapid and various changes of the ATM network environment. conventional approach to the ATM CAC requires network analysis in all cases. So, the optimal implementation is said to be very difficult. Therefore, neural approach have recently been employed. However, it does not mett the adaptability requirements. because it requires additional learning data tables and learning phase during CAC operation. We have proposed a neural network CAC method based on SDM that is more actural than conventioal approach to apply it to CAC. We compared it with previous neural network CAC method. It provides CAC with good adaptability to manage changes. Experimenatal results show that it has rapid adaptability and stability without additional learning table or learning phase.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.1
• /
• pp.436-442
• /
• 2017

A novel method of Skin lesion segmentation based on the combination of Texture and Neural Network is proposed in this paper. This paper combines the textures of different pixels in the skin images in order to increase the performance of lesion segmentation. For segmenting skin lesions, a two-step process is done. First, automatic border detection is performed to separate the lesion from the background skin. This begins by identifying the features that represent the lesion border clearly by the process of Texture analysis. In the second step, the obtained features are given as input towards the Recurrent Echo state neural networks in order to obtain the segmented skin lesion region. The proposed algorithm is trained and tested for 862 skin lesion images in order to evaluate the accuracy of segmentation. Overall accuracy of the proposed method is compared with existing algorithms. An average accuracy of 98.8% for segmenting skin lesion images has been obtained.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.28 no.3
• /
• pp.254-262
• /
• 2008

The objective of the proposed study is to produce a tool-condition monitoring (TCM) strategy that will lead to a more efficient and economical drilling tool usage. Drill-wear monitoring is an important attribute in the automatic cutting processes as it can help preventing damages of the tools and workpieces and optimizing the tool usage. This study presents the architectures of a multi-layer feed-forward neural network with back-propagation training algorithm for the monitoring of drill wear. The input features to the neural networks were extracted from the AE signals using the wavelet transform analysis. Training and testing were performed under a moderate range of cutting conditions in the dry drilling of steel plates. The results indicated that the extracted input features from AE signals to the supervised neural networks were effective for drill wear monitoring and the output of the neural networks could be utilized for the tool life management planning.

• Smart Structures and Systems
• /
• v.15 no.1
• /
• pp.227-244
• /
• 2015

This study develops a two stage procedure to identify the structural damage based on the optimized artificial neural networks. Initially, the modal strain energy index (MSEI) is established to extract the damaged elements and to reduce the computational time. Then the genetic algorithm (GA) and artificial neural networks (ANNs) are combined to detect the damage severity. The input of the network is modal strain energy index and the output is the flexural stiffness of the beam elements. The principal component analysis (PCA) is utilized to reduce the input variants of the neural network. By using the genetic algorithm to optimize the parameters, the ANNs can significantly improve the accuracy and convergence of the damage identification. The influence of noise on damage identification results is also studied. The simulation and experiment on beam structures shows that the adaptive parameter selection neural network can identify the damage location and severity of beam structures with high accuracy.

• The Korean Journal of Physiology and Pharmacology
• /
• v.23 no.2
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.