• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.75-88
• /
• 2021

Automobile credit business has developed rapidly in recent years, and corresponding default phenomena occur frequently. Credit default will bring great losses to automobile financial institutions. Therefore, the successful prediction of automobile credit default is of great significance. Firstly, the missing values are deleted, then the random forest is used for feature selection, and then the sample data are randomly grouped. Finally, six prediction models of support vector machine (SVM), random forest and k-nearest neighbor (KNN), logistic, decision tree, and artificial neural network (ANN) are constructed. The results show that these six machine learning models can be used to predict the default of automobile credit. Among these six models, the accuracy of decision tree is 0.79, which is the highest, but the comprehensive performance of SVM is the best. And random grouping can improve the efficiency of model operation to a certain extent, especially SVM.

• Earthquakes and Structures
• /
• v.22 no.4
• /
• pp.401-419
• /
• 2022

A novel hybrid extreme machine learning-multiverse optimizer (ELM-MVO) framework is proposed to predict the liquefaction phenomenon in seismically excited tunnel lining inside the sand lens. The MVO is applied to optimize the input weights and biases of the ELM algorithm to improve its efficiency. The tunnel located inside the liquefied sand lens is also evaluated under various near- and far-field earthquakes. The results demonstrate the superiority of the proposed method to predict the liquefaction event against the conventional extreme machine learning (ELM) and artificial neural network (ANN) algorithms. The outcomes also indicate that the possibility of liquefaction in sand lenses under far-field seismic excitations is much less than the near-field excitations, even with a small magnitude. Hence, tunnels designed in geographical areas where seismic excitations are more likely to be generated in the near area should be specially prepared. The sand lens around the tunnel also has larger settlements due to liquefaction.

• Advances in nano research
• /
• v.14 no.4
• /
• pp.329-334
• /
• 2023

Organic ferroelectric material found vast application in a verity of engineering and health technology fields. In the present study, we investigated the application of the deformable organic ferroelectric in motion measurement and improving performance in tennis players. Flexible ferroelectric material P(VDF-TrFE) could be used in wearable motion sensors in tennis player transferring velocity and acceleration data to collecting devises for analyzing the best pose and movements in tennis players to achieve best performances in terms of hitting ball and movement across the tennis court. In doing so, ferroelectric-based wearable sensors are used in four different locations on the player body to analyze the movement and also a sensor on the tennis ball to record the velocity and acceleration. In addition, poses of tennis players were analyzed to find out the best pose to achieve best acceleration and movement. The results indicated that organic ferroelectric-based sensors could be used effectively in sensing motion of tennis player which could be utilized in the optimization of posing and ball hitting in the real games.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.1-11
• /
• 2023

Breast cancer is the disease that affects women the most worldwide. Due to the development of computer technology, the efficiency of machine learning has increased, and thus plays an important role in cancer detection and diagnosis. Deep learning is a field of machine learning technology based on an artificial neural network, and its performance has been rapidly improved in recent years, and its application range is expanding. In this paper, we propose a DNN-SVM hybrid model that combines the structure of a deep neural network (DNN) based on transfer learning and a support vector machine (SVM) for breast cancer classification. The transfer learning-based proposed model is effective for small training data, has a fast learning speed, and can improve model performance by combining all the advantages of a single model, that is, DNN and SVM. To evaluate the performance of the proposed DNN-SVM Hybrid model, the performance test results with WOBC and WDBC breast cancer data provided by the UCI machine learning repository showed that the proposed model is superior to single models such as logistic regression, DNN, and SVM, and ensemble models such as random forest in various performance measures.

• The Journal of the Acoustical Society of Korea
• /
• v.25 no.3
• /
• pp.144-150
• /
• 2006

Clinicians usually use stethoscopic auscultation for the diagnosis of heart diseases. However, the heart sound signal has varying characteristics due to the noise and/or the conditions of the patients. Also, it is not easy for junior clinicians to find the acoustical differences between different kinds or heart sound signals. which may result in errors in the diagnosis. Thus it will be quite useful for the clinicians to make use of an automatic classification system using signal processing techniques. In this paper, we propose to use hidden Markov models in stead of artificial neural networks which have been conventionally used for the automatic classification of heart sounds. In the experiments classifying heart sound signals. we could see that the proposed methods were quite successful in the classification accuracy.

• Journal of Power Electronics
• /
• v.13 no.4
• /
• pp.516-527
• /
• 2013

This paper presents a new overall system for state-of-available-power (SoAP) prediction for a lithium-ion battery pack. The essential part of this method is based on an adaptive network architecture which utilizes both fuzzy model (FIS) and artificial neural network (ANN) into the framework of adaptive neuro-fuzzy inference system (ANFIS). While battery aging proceeds, the system is capable of delivering accurate power prediction not only for room temperature, but also at lower temperatures at which power prediction is most challenging. Due to design property of ANN, the network parameters are adapted on-line to the current battery states (state-of-charge (SoC), state-of-health (SoH), temperature). SoC is required as an input parameter to SoAP module and high accuracy is crucial for a reliable on-line adaptation. Therefore, a reasonable way to determine the battery state variables is proposed applying a combination of several partly different algorithms. Among other SoC boundary estimation methods, robust extended Kalman filter (REKF) for recalibration of amp hour counters was implemented. ANFIS then achieves the SoAP estimation by means of time forward voltage prognosis (TFVP) before a power pulse occurs. The trade-off between computational cost of batch-learning and accuracy during on-line adaptation was optimized resulting in a real-time system with TFVP absolute error less than 1%. The verification was performed on a software-in-the-loop test bench setup using a 53 Ah lithium-ion cell.

• Journal of Intelligence and Information Systems
• /
• v.21 no.3
• /
• pp.79-99
• /
• 2015

The prediction of bankruptcy has been extensively studied in the accounting and finance field. It can have an important impact on lending decisions and the profitability of financial institutions in terms of risk management. Many researchers have focused on constructing a more robust bankruptcy prediction model. Early studies primarily used statistical techniques such as multiple discriminant analysis (MDA) and logit analysis for bankruptcy prediction. However, many studies have demonstrated that artificial intelligence (AI) approaches, such as artificial neural networks (ANN), decision trees, case-based reasoning (CBR), and support vector machine (SVM), have been outperforming statistical techniques since 1990s for business classification problems because statistical methods have some rigid assumptions in their application. In previous studies on corporate bankruptcy, many researchers have focused on developing a bankruptcy prediction model using financial ratios. However, there are few studies that suggest the specific types of bankruptcy. Previous bankruptcy prediction models have generally been interested in predicting whether or not firms will become bankrupt. Most of the studies on bankruptcy types have focused on reviewing the previous literature or performing a case study. Thus, this study develops a model using data mining techniques for predicting the specific types of bankruptcy as well as the occurrence of bankruptcy in Korean small- and medium-sized construction firms in terms of profitability, stability, and activity index. Thus, firms will be able to prevent it from occurring in advance. We propose a hybrid approach using two artificial neural networks (ANNs) for the prediction of bankruptcy types. The first is a back-propagation neural network (BPN) model using supervised learning for bankruptcy prediction and the second is a self-organizing map (SOM) model using unsupervised learning to classify bankruptcy data into several types. Based on the constructed model, we predict the bankruptcy of companies by applying the BPN model to a validation set that was not utilized in the development of the model. This allows for identifying the specific types of bankruptcy by using bankruptcy data predicted by the BPN model. We calculated the average of selected input variables through statistical test for each cluster to interpret characteristics of the derived clusters in the SOM model. Each cluster represents bankruptcy type classified through data of bankruptcy firms, and input variables indicate financial ratios in interpreting the meaning of each cluster. The experimental result shows that each of five bankruptcy types has different characteristics according to financial ratios. Type 1 (severe bankruptcy) has inferior financial statements except for EBITDA (earnings before interest, taxes, depreciation, and amortization) to sales based on the clustering results. Type 2 (lack of stability) has a low quick ratio, low stockholder's equity to total assets, and high total borrowings to total assets. Type 3 (lack of activity) has a slightly low total asset turnover and fixed asset turnover. Type 4 (lack of profitability) has low retained earnings to total assets and EBITDA to sales which represent the indices of profitability. Type 5 (recoverable bankruptcy) includes firms that have a relatively good financial condition as compared to other bankruptcy types even though they are bankrupt. Based on the findings, researchers and practitioners engaged in the credit evaluation field can obtain more useful information about the types of corporate bankruptcy. In this paper, we utilized the financial ratios of firms to classify bankruptcy types. It is important to select the input variables that correctly predict bankruptcy and meaningfully classify the type of bankruptcy. In a further study, we will include non-financial factors such as size, industry, and age of the firms. Thus, we can obtain realistic clustering results for bankruptcy types by combining qualitative factors and reflecting the domain knowledge of experts.

• Journal of Biomedical Engineering Research
• /
• v.24 no.5
• /
• pp.411-419
• /
• 2003

This paper aims at developing 'gyro-mouse' which provides decent and comfortable human-computer interface that supports the usage of such software as an internet-browser in PC for the people paralyzed in upper limbs. This interface operates on information collected from head movement to get the cursor control. The interface is composed of two modules. One is hardware module in which the head horizontal and vertical angular velocities are detected and transmitted into PC. The other is a PC software that translates the received data into movement and click signals of the mouse. The ANN (artificial neural network) learns the quick nodding pattern of each user as click input so that it can provide user-friendly interface. The performance of the system was evaluated by three indices that are click recognition rate. error in cursor position control. and click rate of the moving target box. The performance result of the gyro-mouse was compared with that of the optical-mouse to assess the efficiency of the gyro-mouse. The average click recognition rate was 93%, average error in cursor position control was 1.4∼5 times of optical mouse. and the click rate with 50 pixels target box was 40%(30 clicks/min) to that of optical mouse. The click rate increased monotonously with the number of trial from 35% to 44%. The suggested system is expected to provide a new possibility to communicate with the society.

• Journal of the Korean Institute of Gas
• /
• v.19 no.1
• /
• pp.28-37
• /
• 2015

This study presents the development of a well placement optimization model, combining an artificial neural network, which enables high-speed calculation, with a simulated annealing algorithm. The conventional FDM simulator takes excessive time when used to perform a field scale reservoir simulation. In order to solve this problem, an artificial neural network was applied to the model to allow the simulation to be executed within a short time. Also by using the given result, the optimization method, SA algorithm, was implemented to automatically select the optimal location without taking any subjective experiences into consideration. By comparing the result of the developed model with the eclipse simulator, it was found that the prediction performance of the developed model has become favorable, and the speed of calculation performance has also been improved. Especially, the optimum value was estimated by performing a sensitivity analysis for the cooling rate and the initial temperature, which is the control parameter of SA algorithm. From this result, it was verified that the calculation performance has been improved, as well. Lastly, an optimization for the well placement was performed using the model, and it concluded the optimized place for the well by selecting regions with great productivity.

• Proceedings of the Optical Society of Korea Conference
• /
• 2003.07a
• /
• pp.60-61
• /
• 2003

A new approach to reduce the computation time of genetic algorithm (GA) for making binary phase holograms is described. Synthesized holograms having diffraction efficiency of 75.8% and uniformity of 5.8% are proven in computer simulation and experimentally demonstrated. Recently, computer-generated holograms (CGHs) having high diffraction efficiency and flexibility of design have been widely developed in many applications such as optical information processing, optical computing, optical interconnection, etc. Among proposed optimization methods, GA has become popular due to its capability of reaching nearly global. However, there exits a drawback to consider when we use the genetic algorithm. It is the large amount of computation time to construct desired holograms. One of the major reasons that the GA' s operation may be time intensive results from the expense of computing the cost function that must Fourier transform the parameters encoded on the hologram into the fitness value. In trying to remedy this drawback, Artificial Neural Network (ANN) has been put forward, allowing CGHs to be created easily and quickly (1), but the quality of reconstructed images is not high enough to use in applications of high preciseness. For that, we are in attempt to find a new approach of combiningthe good properties and performance of both the GA and ANN to make CGHs of high diffraction efficiency in a short time. The optimization of CGH using the genetic algorithm is merely a process of iteration, including selection, crossover, and mutation operators [2]. It is worth noting that the evaluation of the cost function with the aim of selecting better holograms plays an important role in the implementation of the GA. However, this evaluation process wastes much time for Fourier transforming the encoded parameters on the hologram into the value to be solved. Depending on the speed of computer, this process can even last up to ten minutes. It will be more effective if instead of merely generating random holograms in the initial process, a set of approximately desired holograms is employed. By doing so, the initial population will contain less trial holograms equivalent to the reduction of the computation time of GA's. Accordingly, a hybrid algorithm that utilizes a trained neural network to initiate the GA's procedure is proposed. Consequently, the initial population contains less random holograms and is compensated by approximately desired holograms. Figure 1 is the flowchart of the hybrid algorithm in comparison with the classical GA. The procedure of synthesizing a hologram on computer is divided into two steps. First the simulation of holograms based on ANN method [1] to acquire approximately desired holograms is carried. With a teaching data set of 9 characters obtained from the classical GA, the number of layer is 3, the number of hidden node is 100, learning rate is 0.3, and momentum is 0.5, the artificial neural network trained enables us to attain the approximately desired holograms, which are fairly good agreement with what we suggested in the theory. The second step, effect of several parameters on the operation of the hybrid algorithm is investigated. In principle, the operation of the hybrid algorithm and GA are the same except the modification of the initial step. Hence, the verified results in Ref [2] of the parameters such as the probability of crossover and mutation, the tournament size, and the crossover block size are remained unchanged, beside of the reduced population size. The reconstructed image of 76.4% diffraction efficiency and 5.4% uniformity is achieved when the population size is 30, the iteration number is 2000, the probability of crossover is 0.75, and the probability of mutation is 0.001. A comparison between the hybrid algorithm and GA in term of diffraction efficiency and computation time is also evaluated as shown in Fig. 2. With a 66.7% reduction in computation time and a 2% increase in diffraction efficiency compared to the GA method, the hybrid algorithm demonstrates its efficient performance. In the optical experiment, the phase holograms were displayed on a programmable phase modulator (model XGA). Figures 3 are pictures of diffracted patterns of the letter "0" from the holograms generated using the hybrid algorithm. Diffraction efficiency of 75.8% and uniformity of 5.8% are measured. We see that the simulation and experiment results are fairly good agreement with each other. In this paper, Genetic Algorithm and Neural Network have been successfully combined in designing CGHs. This method gives a significant reduction in computation time compared to the GA method while still allowing holograms of high diffraction efficiency and uniformity to be achieved. This work was supported by No.mOl-2001-000-00324-0 (2002)) from the Korea Science & Engineering Foundation.