• Steel and Composite Structures
• /
• v.51 no.4
• /
• pp.417-440
• /
• 2024

Artificial neural networks (ANN) have been the focus of several studies when it comes to evaluating the pile's bearing capacity. Nonetheless, the principal drawbacks of employing this method are the sluggish rate of convergence and the constraints of ANN in locating global minima. The current work aimed to build four ANN-based prediction models enhanced with methods from the black hole algorithm (BHA), league championship algorithm (LCA), shuffled complex evolution (SCE), and symbiotic organisms search (SOS) to estimate the carrying capacity of piles in cold climates. To provide the crucial dataset required to build the model, fifty-eight concrete pile experiments were conducted. The pile geometrical properties, internal friction angle 𝛗 shaft, internal friction angle 𝛗 tip, pile length, pile area, and vertical effective stress were established as the network inputs, and the BHA, LCA, SCE, and SOS-based ANN models were set up to provide the pile bearing capacity as the output. Following a sensitivity analysis to determine the optimal BHA, LCA, SCE, and SOS parameters and a train and test procedure to determine the optimal network architecture or the number of hidden nodes, the best prediction approach was selected. The outcomes show a good agreement between the measured bearing capabilities and the pile bearing capacities forecasted by SCE-MLP. The testing dataset's respective mean square error and coefficient of determination, which are 0.91846 and 391.1539, indicate that using the SCE-MLP approach as a practical, efficient, and highly reliable technique to forecast the pile's bearing capacity is advantageous.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.48 no.2
• /
• pp.47-55
• /
• 2011

Hemorrhagic shock is a cause of one third of death resulting from injury in the world. Early diagnosis of hemorrhagic shock makes it possible for physician to treat successfully. The objective of this paper was to select an optimal classifier model using physiological signals from rats measured during hemorrhagic experiment. This data set was used to train and predict survival rate using artificial neural network (ANN) and support vector machine (SVM). To avoid over-fitting, we chose the best classifier according to performance measured by a 10-fold cross validation method. As a result, we selected ANN having three hidden nodes with one hidden layer and SVM with Gaussian kernel function as trained prediction model, and the ANN showed 88.9 % of sensitivity, 96.7 % of specificity, 92.0 % of accuracy and the SVM provided 97.8 % of sensitivity, 95.0 % of specificity, 96.7 % of accuracy. Therefore, SVM was better than ANN for survival prediction.

• Journal of Korea Water Resources Association
• /
• v.50 no.10
• /
• pp.681-690
• /
• 2017

This study estimated the daily maximum snow depth using the Artificial Neural Network (ANN) model in Korean Peninsula. First, the optimal ANN model structure was determined through the trial-and-error approach. As a result, daily precipitation, daily mean temperature, and daily minimum temperature were chosen as the input data of the ANN. The number of hidden layer was set to 1 and the number of nodes in the hidden layer was set to 10. In case of using the observed value as the input data of the ANN model, the cross validation correlation coefficient was 0.87, which is higher than that of the case in which the daily maximum snow depth was spatially interpolated using the Ordinary Kriging method (0.40). In order to investigate the performance of the ANN model for estimating the daily maximum snow depth of the ungauged area, the input data of the ANN model was spatially interpolated using Ordinary Kriging. In this case, the correlation coefficient of 0.49 was obtained. The performance of the ANN model in mountainous areas above 200m above sea level was found to be somewhat lower than that in the rest of the study area. This result of this study implies that the ANN model can be used effectively for the accurate and immediate estimation of the maximum snow depth over the whole country.

• Journal of Korea Water Resources Association
• /
• v.36 no.2
• /
• pp.195-209
• /
• 2003

Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.526-532
• /
• 2023

Falls are fatal accidents that occur more than 420,000 times a year worldwide. Therefore, to study patients with falls, we found the association between extrinsic injury codes and principal diagnosis S-codes of patients with falls, and developed a prediction model to predict extrinsic injury codes based on the data of principal diagnosis S-codes of patients with falls. In this study, we received two years of data from 2020 and 2021 from Institution A, located in Gangneung City, Gangwon Special Self-Governing Province, and extracted only the data from W00 to W19 of the extrinsic injury codes related to falls, and developed a prediction model using W01, W10, W13, and W18 of the extrinsic injury codes of falls, which had enough principal diagnosis S-codes to develop a prediction model. 80% of the data were categorized as training data and 20% as testing data. The model was developed using MLP (Multi-Layer Perceptron) with 6 variables (gender, age, principal diagnosis S-code, surgery, hospitalization, and alcohol consumption) in the input layer, 2 hidden layers with 64 nodes, and an output layer with 4 nodes for W01, W10, W13, and W18 exogenous damage codes using the softmax activation function. As a result of the training, the first training had an accuracy of 31.2%, but the 30th training had an accuracy of 87.5%, which confirmed the association between the fall extrinsic code and the main diagnosis S code of the fall patient.

• Journal of Electrical Engineering and Technology
• /
• v.12 no.2
• /
• pp.689-700
• /
• 2017

This paper presents an effective approach for wind turbine (WT) condition assessment based on the data collected from wind farm supervisory control and data acquisition (SCADA) system. Three types of assessment indices are determined based on the monitoring parameters obtained from the SCADA system. Neural Networks (NNs) are used to establish prediction models for the assessment indices that are dependent on environmental conditions such as ambient temperature and wind speed. An abnormal level index (ALI) is defined to quantify the abnormal level of the proposed indices. Prediction errors of the prediction models follow a normal distribution. Thus, the ALIs can be calculated based on the probability density function of normal distribution. For other assessment indices, the ALIs are calculated by the nonparametric estimation based cumulative probability density function. A Back-Propagation NN (BPNN) algorithm is used for the overall WT condition assessment. The inputs to the BPNN are the ALIs of the proposed indices. The network structure and the number of nodes in the hidden layer are carefully chosen when the BPNN model is being trained. The condition assessment method has been used for real 1.5 MW WTs with doubly fed induction generators. Results show that the proposed assessment method could effectively predict the change of operating conditions prior to fault occurrences and provide early alarming of the developing faults of WTs.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.14 no.4
• /
• pp.357-374
• /
• 2012

Considerable uncertainties are included in ground properties used for tunnel designs due to the limited investigation and tests. In this study, a back analysis was performed to find optimal ground properties based on artificial neural network using both face mapping data and convergence measurement data. First of all, the rock class of a study tunnel is determined from face mapping data. Then the possible ranges of ground properties were selected for each rock class through a literature review on the previous studies and utilized to establish more precise learning data. To find an optimal training model, a sensitivity analysis was also conducted by varying the number of hidden layers and the number of nodes more minutely than the previous study. As a result of this study, more accurate ground properties could be obtained. Therefore it was confirmed that the accuracy of the results could be increased by making use of not only convergence measurement data but also face mapping data in tunnel back analyses using artificial neural network. In future, it is expected that the methodology suggested in this study can be used to estimate ground properties more precisely.

• Journal of KIISE:Information Networking
• /
• v.37 no.4
• /
• pp.301-306
• /
• 2010

We propose the control channel access scheme for multi-interface multi-hop cognitive radio (CR) environment having a cluster structure. Due to the difficulty of obtaining common channels across the entire CR network, most multi-interface multi-hop CR networks put the control channel outside the CR bandwidth and dedicate one network interface to it in order to exchange the control information such as the activation of licensed users. However, this will be the waste of the network interface. Our focus is how to alternate between the control and the data channel without multichannel hidden node problem under the cluster structure where CR nodes connect with neighbors through multiple data channels. By using simulation, we evaluate the performance of the proposed scheme. The results show that the proposed scheme achieves higher network throughput than the dedicated scheme where one network interface card should dedicate to the control channel and cannot be used for data transmission.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.14 no.1
• /
• pp.37-53
• /
• 2012

There is considerable uncertainty in ground properties used in tunnel designs. In this study, a back analysis was performed to find optimal ground properties based on the artificial neural network facility of MATLAB program of using tunnel monitoring data. Total 81 data were constructed by changing elastic modulus and coefficient of lateral pressure which have great influence on tunnel convergence. A sensitivity analysis was conducted to establish an optimal training model by varying the number of hidden layers, the number of nodes, learning rate, and momentum. Meanwhile, the optimal training model was selected by comparing MSE (Mean Squared Error) and coefficient of determination ($R^2$) and was used to find the correct elastic moduli of layers and the coefficient of lateral pressure. In future, it is expected that the suggested method of this study can be applied to determine the optimum tunnel support pattern under given ground conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4
• /
• pp.48-53
• /
• 2001

In this paper, selectively attentive learning method has been proposed to improve the learning speed of multilayer Perceptron based on the error backpropagation algorithm. Three attention criterions are introduced to effectively determine which set of input patterns is or which portion of network is attended to for effective learning. Such criterions are based on the mean square error function of the output layer and class-selective relevance of the hidden nodes. The acceleration of learning time is achieved by lowering the computational cost per iteration. Effectiveness of the proposed method is demonstrated in a speaker adaptation task of isolated word recognition system. The experimental results show that the proposed selective attention technique can reduce the learning time more than 60% in an average sense.