• Journal of Welding and Joining
• /
• v.32 no.2
• /
• pp.43-47
• /
• 2014

Famous artificial neural network (ANN) is applied to predict proper process window of arc welding. Target weldment is variously combined lap joint fillet welding of automotive steel plates. ANN's system variable such as number of hidden layers, perceptrons and transfer function are carefully selected through case by case test. Input variables are welding condition and steel plate combination, for example, welding machine type, shield gas composition, current, speed and strength, thickness of base material. The number of each input variable referred in welding experiment is counted and provided to make it possible to presume the qualitative precision and limit of prediction. One of experimental process windows is excluded for predictability estimation and the rest are applied for neural network training. As expected from basic ANN theory, experimental condition composed of frequently referred input variables showed relatively more precise prediction while rarely referred set showed poorer result. As conclusion, application of ANN to arc welding process window derivation showed comparatively practical feasibility while it still needs more training for higher precision.

• Journal of Intelligence and Information Systems
• /
• v.4 no.1
• /
• pp.133-147
• /
• 1998

Recently, many researchers have been involved in finding deterministic equations which can accurately predict future event, based on chaotic theory, or fractal theory. The theory says that some events which seem very random but internally deterministic can be accurately predicted by fractal equations. In contrast to the conventional methods, such as AR model, MA, model, or ARIMA model, the fractal equation attempts to discover a deterministic order inherent in time series data set. In discovering deterministic order, researchers have found that neural networks are much more effective than the conventional statistical models. Even though prediction accuracy of the network can be different depending on the topological structure and modification of the algorithms, many researchers asserted that the neural network systems outperforms other systems, because of non-linear behaviour of the network models, mechanisms of massive parallel processing, generalization capability based on adaptive learning. However, recent survey shows that prediction accuracy of the forecasting models can be determined by the model structure and data structures. In the experiments based on actual economic data sets, it was found that the prediction accuracy of the neural network model is similar to the performance level of the conventional forecasting model. Especially, for the data set which is deterministically chaotic, the AR model, a conventional statistical model, was not significantly different from the MLP model, a neural network model. This result shows that the forecasting model. This result shows that the forecasting model a, pp.opriate to a prediction task should be selected based on characteristics of the time series data set. Analysis of the characteristics of the data set was performed by fractal analysis, measurement of Hurst index, and measurement of Lyapunov exponents. As a conclusion, a significant difference was not found in forecasting future events for the time series data which is deterministically chaotic, between a conventional forecasting model and a typical neural network model.

• Journal of Integrative Natural Science
• /
• v.12 no.1
• /
• pp.14-19
• /
• 2019

In this paper, we propose a system for controlling the brightness of street lights by predicting pedestrian paths, identifying the position of pedestrians with motion sensing sensors and obtaining motion vectors based on past walking directions, then predicting pedestrian paths through the route prediction smart street lighting system. In addition, by using motion vector data, the pre-treatment process using linear interpolation method and the fuzzy system and neural network system were designed in parallel structure to increase efficiency and the rough set was used to correct errors. It is expected that the system proposed in this paper will be effective in securing the safety of pedestrians and reducing light pollution and energy by predicting the path of pedestrians in the detection of movement of pedestrians and in conjunction with smart street lightings.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2000.04a
• /
• pp.347-356
• /
• 2000

This paper compares four models of artificial neural networks (ANN) supported by genetic algorithms the prediction of stock price index. Previous research proposed many hybrid models of ANN and genetic algorithms(GA) in order to train the network, to select the feature subsets, and to optimize the network topologies. Most these studies, however, only used GA to improve a part of architectural factors of ANN. In this paper, GA simultaneously optimized multiple factors of ANN. Experimental results show that GA approach to simultaneous optimization for ANN (SOGANN3) outperforms the other approaches.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.11
• /
• pp.98-105
• /
• 1999

As the IC(Integrated Circuit) has been densified and complicated, it is required to thorough process control to improve yield. Experts, for this purpose, focused on the process analysis automation, which is came from the strict data management in semiconductor manufacturing. In this paper, we presents the process analysis system that can analyze causes, for a output after processes. Also, the plasma etching process that highly affects yield among semiconductor process is modeled to predict a output before the process. To approach this problem, we use adaptively trained neural networks that exhibit superior accuracy over statistical techniques. And in comparison with methods in other paper, a method that history of trend for input data is considered is shown to offer advantage in both learning and prediction capability. This research regards CD(Critical Dimension) that is considerable in high integrated circuit as output variable of the prediction model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2002.05a
• /
• pp.59-64
• /
• 2002

An expert system, to assist dam managers for five dams along the Saikawa River, has been developed with a primary objective of achieving swift and accurate reservoir operation decision-makings during floods. The expert system is capable of supporting on decision-makings upon establishment of flood management procedure and release/storage planning. Furthermore, an attempt was made to improve reservoir inflow prediction models for better supporting capability. As a result, accuracy on prediction of inflow up to 7 hours ahead was improved, which is important for flood management of the five dams, using neural network. The neural network inflow prediction models were developed for each types of floods caused by frontal rainfalls, snowmelt and typhoons, after extracting relevant meteorological factors for each.

• Journal of Intelligence and Information Systems
• /
• v.7 no.1
• /
• pp.135-147
• /
• 2001

This study proposes bankruptcy prediction model using fuzzy neural networks. Neural networks offer preeminent learning ability but they are often confronted with the inconsistent and unpredictable performance for noisy financial data. The existence of continuous data and large amounts of records may pose a challenging task to explicit concepts extraction from the raw data due to the huge data space determined by continuous input variables. The attempt to solve this problem is to transform each input variable in a way which may make it easier fur neural network to develop a predictive relationship. One of the methods selected for this is to map each continuous input variable to a series of overlapping fuzzy sets. Appropriately transforming each of the inputs into overlapping fuzzy membership sets provides an isomorphic mapping of the data to properly constructed membership values, and as such, no information is lost. In addition, it is easier far neural network to identify and model high-order interactions when the data is transformed in this way. Experimental results show that fuzzy neural network outperforms conventional neural network for the prediction of corporate bankruptcy.

• Proceedings of the Korea Inteligent Information System Society Conference
• /
• 2004.11a
• /
• pp.179-188
• /
• 2004

Bankruptcy prediction is an important and widely studied topic since it can have significant impact on bank lending decisions and profitability. Recently, support vector machine (SVM) has been applied to the problem of bankruptcy prediction. The SVM-based method has been compared with other methods such as neural network, logistic regression and has shown good results. Genetic algorithm (GA) has been increasingly applied in conjunction with other AI techniques such as neural network, CBR. However, few studies have dealt with integration of GA and SVM, though there is a great potential for useful applications in this area. This study proposes the methods for improving SVM performance in two aspects: feature subset selection and parameter optimization. GA is used to optimize both feature subset and parameters of SVM simultaneously for bankruptcy prediction.

• International Journal of Computer Science & Network Security
• /
• v.21 no.2
• /
• pp.77-87
• /
• 2021

In this study, a novel improved second order Radial Basis Function Neural Network based method with excellent scheduling capabilities is used for the dynamic prediction of short and long-term energy required applications. The effectiveness and the reliability of the algorithm are evaluated using training operations with New England-ISO database. The dynamic prediction algorithm is implemented in Matlab and the computation of mean absolute error and mean absolute percent error, and training time for the forecasted load, are determined. The results show the impact of temperature and other input parameters on the accuracy of solar Photovoltaic load forecasting. The mean absolute percent error is found to be between 1% to 3% and the training time is evaluated from 3s to 10s. The results are also compared with the previous studies, which show that this new method predicts short and long-term load better than sigmoidal neural network and bagged regression trees. The forecasted energy is found to be the nearest to the correct values as given by England ISO database, which shows that the method can be used reliably for short and long-term load forecasting of any electrical system.

• Journal of the military operations research society of Korea
• /
• v.34 no.1
• /
• pp.1-11
• /
• 2008

A methodology for the improvement of simulation based training system for the artillery is proposed in this paper. The complex nonlinear relationship inherent among parameters in artillery firing is difficult to model and analyze. By introducing neural network based simulation, accurate representation of artillery firing is made possible. The artillery training system can greatly benefit from the improved prediction. Neural networks learning is conducted using the conjugate gradient algorithm. The evaluation of the proposed methodology is performed through simulation. Prediction errors of both regression analysis model and neural networks model are analyzed. Implementation of neural networks to training system enables more realistic training, improved combat power and reduced budget.