• Korean Journal of Cognitive Science
• /
• v.19 no.3
• /
• pp.297-310
• /
• 2008

Since speech acts implies speakers' intentions, it is essential to determine speakers' speech acts if we want to implement an intelligent dialogue system. We propose a two-step model for effectively determining speakers' speech acts. In the first step, the proposed model returns speech act candidates by using a neural network model based on machine learning and a predictivity model based on statistics, respectively. In the second step, using speech act candidates which are returned by the predictivity model, the proposed model filters out speech act candidates which are returned by the neural network model. Then, the proposed model selects a speech act with maximum output value among the unremoved speech act candidates. In the experiment on a schedule management domain, the proposed two-step modeling method showed better precisions than the previous methods only using a machine learning model or a probability model.

• Journal of the Korean Society for information Management
• /
• v.21 no.4 s.54
• /
• pp.133-152
• /
• 2004

As the Internet facilitates the rapid increase of information availability, the study on SDI service that provides users with relevant document in a timely manner has been developed. However, the practical use of this service has been low. This thesis aims at analyzing the reasons for this and developing relevance feedback based SDI system to improve the performance of the existing SDI system. Experimental systems that are developed for this study are SDI system based on users' minimum intervention feedback, SDI system based on perfect automation feedback, and SDI system based on users' maximum intervention feedback. The fourth system that utilizes the traditional SDI system is also studied to evaluate the level of performance improvement of the newly developed three types of SDI system. As a result of this study, SDI system based on users' maximum intervention feedback showed greatest performance improvement. The next performance improvement happened in order of SDI system based on perfect automation feedback, SDI system based on users' minimum intervention feedback, and the traditional SDI system. Feedback based systems showed greater performance improvement as they went through more feedback processes.

• Journal of KIISE:Software and Applications
• /
• v.29 no.3
• /
• pp.156-166
• /
• 2002

Decision tree induction is a kind of useful machine learning approach for extracting classification rules from a set of feature-based examples. According to the partitioning style of the feature space, decision trees are categorized into univariate decision trees and multivariate decision trees. Due to observation error, uncertainty, subjective judgment, and so on, real-world data are prone to contain some errors in their feature values. For the purpose of making decision trees robust against such errors, there have been various trials to incorporate fuzzy techniques into decision tree construction. Several researches hove been done on incorporating fuzzy techniques into univariate decision trees. However, for multivariate decision trees, few research has been done in the line of such study. This paper proposes a fuzzy decision tree induction method that builds fuzzy multivariate decision trees named fuzzy oblique decision trees, To show the effectiveness of the proposed method, it also presents some experimental results.

• Journal of Intelligence and Information Systems
• /
• v.15 no.4
• /
• pp.123-140
• /
• 2009

Fuzzy neural network is an integrated model of artificial neural network and fuzzy system and it has been successfully applied in control and forecasting area. Recently ANFIS(Adaptive Network-based Fuzzy Inference System) has been noticed widely among various fuzzy neural network models because of outstanding performance of control and forecasting accuracy. ANFIS has capability to refine its fuzzy rules interactively with human expert. In particular, when we use initial rule structure for machine learning which is generated from human expert, it is highly probable to reach global optimum solution as well as shorten time to convergence. We propose metrics to evaluate interpretability of generated rules as a means of acquiring domain knowledge and compare level of interpretability of ANFIS fuzzy rules to those of C5.0 classification rules. The proposed metrics also can be used to evaluate capability of rule generation for the various machine learning methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.20 no.3
• /
• pp.621-629
• /
• 2016

This paper presents a decision method of middle ear disease which is developed in children and adults. In the proposed method, features are extracted from the middle ear disease images and normal images using HoG (histogram of oriented gradient) descriptor and the extracted features are learned by SVM (support vector machine) classifier. To obtain an input vector into SVM, an input image is resized to a predefined size and then the resized image is partitioned into 16 blocks each of which is partitioned into 4 sub-blocks (namely cell). Finally, the feature vector with 576 components is given by using HoG with 9 bins and it is used as SVM learning and classification. Input images are classified by SVM classifier based on the model of learning features. Experimental results show that the proposed method yields the precision of over 90% in decision.

• Journal of Advanced Navigation Technology
• /
• v.21 no.6
• /
• pp.643-650
• /
• 2017

Photovoltaic generation which has unlimited energy sources are very intermittent because they depend on the weather. Therefore, it is necessary to get accurate generation prediction with reducing the uncertainty of photovoltaic generation and improvement of the economics. The Meteorological Agency predicts weather factors for three days, but doesn't predict the sunshine and solar radiation that are most correlated with the prediction of photovoltaic generation. In this study, we predict sunshine and solar radiation using weather, precipitation, wind direction, wind speed, humidity, and cloudiness which is forecasted for three days at Meteorological Agency. The photovoltaic generation forecasting model is proposed by using predicted solar radiation and sunshine. As a result, the proposed model showed better results in the error rate indexes such as MAE, RMSE, and MAPE than the model that predicts photovoltaic generation without radiation and sunshine. In addition, DNN showed a lower error rate index than using SVM, which is a type of machine learning.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2018.05a
• /
• pp.88-90
• /
• 2018

There are many studies on IR-UWB Radar. A number of studies have been conducted on the Personnel count and measurement distance to person, mainly using IR-UWB. In this paper, however, we use IR-UWB Radar to distinguish objects. In order to distinguish these objects, in this paper, the IR-UWB radar is operated by positioning the object at a certain distance and the object is classified by using the size and shape of the wave reflected by the object. To distinguish objects using only the size and shape of these waveforms, SVM (Support Vector Machine) was used to classify objects by learning shape and size of waveforms. In this paper, we show that the size and shape of the waveform received by the IR-UWB Radar can be identified by SVM pattern learning.

• Korean Journal of Cognitive Science
• /
• v.23 no.3
• /
• pp.295-322
• /
• 2012

In this paper, we cluster similar word senses applying vector space model and HAL (Hyperspace Analog to Language). HAL measures corelation among words through a certain size of context (Lund and Burgess 1996). The similarity measurement between a word pair is cosine similarity based on the vector space model, which reduces distortion of space between high frequency words and low frequency words (Salton et al. 1975, Widdows 2004). We use PCA (Principal Component Analysis) and SVD (Singular Value Decomposition) to reduce a large amount of dimensions caused by similarity matrix. For sense similarity clustering, we adopt supervised and non-supervised learning methods. For non-supervised method, we use clustering. For supervised method, we use SVM (Support Vector Machine), Naive Bayes Classifier, and Maximum Entropy Method.

• Geophysics and Geophysical Exploration
• /
• v.23 no.3
• /
• pp.149-156
• /
• 2020

The genesis of ore bodies is a very diverse and complex process, and the target depth of mineral exploration increases. These create a need for predictive mineral exploration, which may be facilitated by the advancement of machine learning and geological database. In this study, we confirm that the faults and igneous rocks distributions and magnetic data can be used as input data for potential mapping using deep neural networks. When the input data are constructed with faults, igneous rocks, and magnetic data, we can build a potential mapping model of the metal deposit that has a predictive accuracy greater than 0.9. If detailed geological and geophysical data are obtained, this approach can be applied to the potential mapping on a mine scale. In addition, we confirm that the magnetic data, which provide the distribution of the underground igneous rock, can supplement the limited information from the surface igneous rock distribution. Therefore, rather than simply integrating various data sets, it will be more important to integrate information considering the geological correlation to genesis of minerals.

• Journal of Digital Convergence
• /
• v.16 no.6
• /
• pp.151-161
• /
• 2018

Income is a vital aspect of economic life. Knowing what their income will help people create budgets that allow them to pay for their living expenses. Income data is used by banks, stores, and service companies for marketing purposes and for retaining loyal customers; it is a crucial demographic element used at a wide variety of customer touch points. Therefore, it is essential to be able to make income predictions for existing and potential customers. This paper aims to predict employment earnings or income based on history, and uses machine learning techniques such as SVMs (Support Vector Machines), Gaussian, decision tree and DCNNs (Deep Convolutional Neural Networks) for predicting employment earnings. The results show that the DCNN method provides optimum results with 88% compared to other machine learning techniques used in this paper. Improvement of the data length such PCA has the potential to provide more optimum result.