• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.11a
• /
• pp.384-388
• /
• 2000

One-port acoustic characteristics of an in-duct source can be measured by the multi-load method using an overdetermined set of open pipes with different lengths as applied loads. The input data. viz. load pressure and load impedance, are usually contaminated by measurement error in the actual measurements, which result in errors in the calculated source parameters. In this paper, the effects of the errors in the input data on the results have been studied numerically, varying the number of loads and their impedances in order to determine what combination of the loads will yield the best result. An error analysis is applied to each case of possible loads, which consist of open pipes. It is noted that, frequently, only a set of open pipes is used when applying the multi-load method to the intake or exhaust sides of internal combustion engines. A set of pipe lengths which cause the calculated results to be least sensitive to the input data error can be found when using open pipe loads. The present work is intended to produce guidelines for preparing an appropriate load set in order to obtain accurate source properties of fluid machines.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.33-38
• /
• 2021

This paper presents a comparative study between the parameter-optimized Pacejka model and artificial neural network model for the tire force estimation. The two different approaches are investigated and compared in this study. First, offline optimization is conducted based on Pacejka Magic Formula model to determine the proper parameter set for the minimization of tire force error between the model and test data set. Second, deep neural network model is used to fit the model to the tire test data set. The actual tire forces are measured using MTS Flat-Track test platform and the measurements are used as the reference tire data set. The focus of this study is on the applicability of machine learning technique to tire force estimation. It is shown via the regression results that the deep neural network model is more effective in describing the tire force than the parameter-optimized Pacejka model.

• Journal of the Korean Data and Information Science Society
• /
• v.17 no.2
• /
• pp.475-486
• /
• 2006

Space time series data can be viewed either as a set of time series collected simultaneously at a number of spatial locations or as sets of spatial data collected at a number of time points. The major purpose of this article is to formulate a class of space time autoregressive moving average (STARMA) model, to discuss some of the their statistical properties such as model identification approaches, some procedure for estimation and the predictions. For illustration, we apply this STARMA model to the mumps data. The data set of mumps cases consists of the number of cases of mumps reported from twelve states monthly over the years 1969-1988.

• Journal of Advanced Marine Engineering and Technology
• /
• v.34 no.3
• /
• pp.407-412
• /
• 2010

According to the remarkable advances in sonar technology, positioning capabilities and computer processing power we can accurately image and explore the seafloor in hydrography. Especially, Multibeam Echo Sounder can provide nearly perfect coverage of the seafloor with high resolution. Since the mid-1990's, Multibeam Echo Sounders have been used for hydrographic surveying in Korea. In this study, new marine data set as an effective decision-making tool in various fields was proposed by visualizing and combining with Multibeam sonar data and marine spatial data sets such as satellite image and digital nautical chart. The proposed method was tested around the port of PyeongTaek-DangJin in the west coast of Korea. The Visualization and fusion methods are described with various marine data sets with processing. We demonstrated that new data set in marine GIS is useful in safe navigation and port management as an efficient decision-making tool.

• Proceedings of the KSRS Conference
• /
• 1998.09a
• /
• pp.134-137
• /
• 1998

NOAA satellite data and GMS data have been received at the Institute of Industrial Science, University of Tokyo since early 80's and 1994, respectively. So far, all data are archived and users can look their quick look images through the Internet and get the data by request. The following processed data set will be available soon with the corporation with the Science University of Tokyo: Radiometrically corrected by 65 code and geometrically corrected NOAA data with the corporation with Iwate University and NDVI, SST and cloud classified images as their products. 1 km AVHRR Land Project Data Set of Asia and their 14 regional subsets. Geometrically corrected GMS images and surface temperature maps, sea surface temperature maps and cloud classification maps.

• New & Renewable Energy
• /
• v.18 no.2
• /
• pp.18-25
• /
• 2022

In this study, we propose a wind power generation prediction system that applies machine learning and data mining to predict wind power generation. This system increases the utilization rate of new and renewable energy sources. For time-series data, the data set was established by measuring wind speed, wind generation, and environmental factors influencing the wind speed. The data set was pre-processed so that it could be applied appropriately to the model. The prediction system applied the CNN (Convolutional Neural Network) to the data mining process and then used the LSTM (Long Short-Term Memory) to learn and make predictions. The preciseness of the proposed system is verified by comparing the prediction data with the actual data, according to the presence or absence of data mining in the model of the prediction system.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.38 no.4
• /
• pp.53-63
• /
• 2013

Together with soaring interest on Big Data, now there are vigorous reports that unearth various social values lying underneath those data from a number of application areas. Among those reports many are using such data as Internet search histories from Google site, social relationships from Facebook, and transactional or locational traces collected from various ubiquitous devices. Many of those researches, however, are conducted based on the data sets that are accumulated over the North American and European areas, which means that direct interpretation and application of social values exhibited by those researches to the other areas like Korea can be a disturbing task. This research has started from a validation study against Korean environment of the former paper which says an investment strategy that exploits up and down of Google search volume on a carefully selected set of terms shows high market performance. A huge difference between North American and Korean environment can be eye witnessed via the distinction in profit rates that are exhibited by the corresponding set of search terms. Two sets of search terms actually presented low correlation in their profit rates over two financial markets. Even in an experiment which compares the profit rates with two different investment periods with the same set of search terms showed no such meaningful result that outperforms the market average. With all these results, we cautiously conclude that establishing an investment strategy that exploits Internet search volume over a specified word set needs more conscious approach.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.3
• /
• pp.132-137
• /
• 2019

The amount of data generated from medical images is increasingly exceeding the limits of professional visual analysis, and the need for automated medical image analysis is increasing. For this reason, this study evaluated the classification and accuracy according to the presence or absence of tumor using Inception V3 deep learning model, using MRI medical images showing normal and tumor findings. As a result, the accuracy of the deep learning model was 90% for the training data set and 86% for the validation data set. The loss rate was 0.56 for the training data set and 1.28 for the validation data set. In future studies, it is necessary to secure the data of publicly available medical images to improve the performance of the deep learning model and to ensure the reliability of the evaluation, and to implement modeling by improving the accuracy of labeling through labeling classification.

• Journal of Intelligence and Information Systems
• /
• v.19 no.2
• /
• pp.125-140
• /
• 2013

We call a data set in which the number of records belonging to a certain class far outnumbers the number of records belonging to the other class, 'imbalanced data set'. Most of the classification techniques perform poorly on imbalanced data sets. When we evaluate the performance of a certain classification technique, we need to measure not only 'accuracy' but also 'sensitivity' and 'specificity'. In a customer churn prediction problem, 'retention' records account for the majority class, and 'churn' records account for the minority class. Sensitivity measures the proportion of actual retentions which are correctly identified as such. Specificity measures the proportion of churns which are correctly identified as such. The poor performance of the classification techniques on imbalanced data sets is due to the low value of specificity. Many previous researches on imbalanced data sets employed 'oversampling' technique where members of the minority class are sampled more than those of the majority class in order to make a relatively balanced data set. When a classification model is constructed using this oversampled balanced data set, specificity can be improved but sensitivity will be decreased. In this research, we developed a hybrid model of support vector machine (SVM), artificial neural network (ANN) and decision tree, that improves specificity while maintaining sensitivity. We named this hybrid model 'hybrid SVM model.' The process of construction and prediction of our hybrid SVM model is as follows. By oversampling from the original imbalanced data set, a balanced data set is prepared. SVM_I model and ANN_I model are constructed using the imbalanced data set, and SVM_B model is constructed using the balanced data set. SVM_I model is superior in sensitivity and SVM_B model is superior in specificity. For a record on which both SVM_I model and SVM_B model make the same prediction, that prediction becomes the final solution. If they make different prediction, the final solution is determined by the discrimination rules obtained by ANN and decision tree. For a record on which SVM_I model and SVM_B model make different predictions, a decision tree model is constructed using ANN_I output value as input and actual retention or churn as target. We obtained the following two discrimination rules: 'IF ANN_I output value <0.285, THEN Final Solution = Retention' and 'IF ANN_I output value ${\geq}0.285$, THEN Final Solution = Churn.' The threshold 0.285 is the value optimized for the data used in this research. The result we present in this research is the structure or framework of our hybrid SVM model, not a specific threshold value such as 0.285. Therefore, the threshold value in the above discrimination rules can be changed to any value depending on the data. In order to evaluate the performance of our hybrid SVM model, we used the 'churn data set' in UCI Machine Learning Repository, that consists of 85% retention customers and 15% churn customers. Accuracy of the hybrid SVM model is 91.08% that is better than that of SVM_I model or SVM_B model. The points worth noticing here are its sensitivity, 95.02%, and specificity, 69.24%. The sensitivity of SVM_I model is 94.65%, and the specificity of SVM_B model is 67.00%. Therefore the hybrid SVM model developed in this research improves the specificity of SVM_B model while maintaining the sensitivity of SVM_I model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.1
• /
• pp.32-40
• /
• 2008

Fuzzy rules are very useful and efficient to describe classification rules especially when the attribute values are continuous and fuzzy in nature. However, it is generally difficult to determine membership functions for generating efficient fuzzy classification rules. In this paper, we propose a method of automatic generation of efficient fuzzy classification rules using evolutionary algorithm. In our method we generate a set of initial membership functions for evolutionary algorithm by supervised clustering the training data set and we evolve the set of initial membership functions in order to generate fuzzy classification rules taking into consideration both classification accuracy and rule comprehensibility. To reduce time to evaluate an individual we also propose an evolutionary algorithm with data partition evaluation in which the training data set is partitioned into a number of subsets and individuals are evaluated using a randomly selected subset of data at a time instead of the whole training data set. We experimented our algorithm with the UCI learning data sets, the experiment results showed that our method was more efficient at average compared with the existing algorithms. For the evolutionary algorithm with data partition evaluation, we experimented with our method over the intrusion detection data of KDD'99 Cup, and confirmed that evaluation time was reduced by about 70%. Compared with the KDD'99 Cup winner, the accuracy was increased by 1.54% while the cost was reduced by 20.8%.