• Journal of Information Technology Services
• /
• v.16 no.4
• /
• pp.149-160
• /
• 2017

Sentiment analysis is the process of determining whether a piece of document, text or conversation is positive, negative, neural or other emotion. Sentiment analysis has been applied for several real-world applications, such as chatbot. In the last five years, the practical use of the chatbot has been prevailing in many field of industry. In the chatbot applications, to recognize the user emotion, sentiment analysis must be performed in advance in order to understand the intent of speakers. The specific emotion is more than describing positive or negative sentences. In light of this context, we propose deep learning models for conducting multi-class sentiment analysis for identifying speaker's emotion which is categorized to be joy, fear, guilt, sad, shame, disgust, and anger. Thus, we develop convolutional neural network (CNN), long short term memory (LSTM), and multi-layer neural network models, as deep neural networks models, for detecting emotion in a sentence. In addition, word embedding process was also applied in our research. In our experiments, we have found that long short term memory (LSTM) model performs best compared to convolutional neural networks and multi-layer neural networks. Moreover, we also show the practical applicability of the deep learning models to the sentiment analysis for chatbot.

• Journal of the Society of Naval Architects of Korea
• /
• v.34 no.1
• /
• pp.122-129
• /
• 1997

Thermo-elastic-plastic analyses used in solving plate forming process are often computationally expensive. To obtain an optimal process of line heating typically requires numerous iterations between the simulation and a finite element analysis. This process often becomes prohibitive due to the amount of computer time required for numerical simulation of line heating process. Therefore, a new techniques that could significantly reduce the computer time required to solve a complex analysis problem would be beneficial. In this paper, we considered factors that influence the bending effect by line heating and developed inference engine by using the concept of artificial neural network. To verify the validity of the neural network, we used results obtained from numerical analysis. We trained the neural network with the data made from numerical analysis and experiments varying the structure of neural network, in other words varying the number of hidden layers and the number of neurons in each hidden layers. From that we concluded that if the number of neurons in each hidden layers is large enough neural network having two hidden layers can be trained easily and errors between exact value and results obtained from trained network are not so large. Consequently, if there are enough number of training pairs, artificial neural network can infer similar results. Based on the numerical results, we applied the artificial neural network technique to deal with mechanical behavior of line heating at simulation stage effectively.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.12
• /
• pp.2521-2526
• /
• 2011

This paper proposes a speaker recognition algorithm using a perceptron neural network and LPC (Linear Predictive Coding) cepstrum coefficients. The proposed algorithm first detects the voiced sections at each frame. Then, the LPC cepstrum coefficients which have speaker characteristics are obtained by the linear predictive analysis for the detected voiced sections. To classify the obtained LPC cepstrum coefficients, a neural network is trained using the LPC cepstrum coefficients. In this experiment, the performance of the proposed algorithm was evaluated using the speech recognition rates based on the LPC cepstrum coefficients and the neural network.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.21 no.11
• /
• pp.1020-1028
• /
• 2011

As rotating machines play an important role in industrial applications such as aeronautical, naval and automotive industries, many researchers have developed various condition monitoring system and fault diagnosis system by applying artificial neural network. Since using obtained signals without preprocessing as inputs of neural network can decrease performance of fault classification, it is very important to extract significant features of captured signals and to apply suitable features into diagnosis system according to the kinds of obtained signals. Therefore, this paper proposes a neural-network-based fault diagnosis system using AR coefficients as feature vectors by LPC(linear predictive coding) and EIV(errors-in variables) analysis. We extracted feature vectors from sound, vibration and current faulty signals and evaluated the suitability of feature vectors depending on the classification results and training error rates by changing AR order and adding noise. From experimental results, we conclude that classification results using feature vectors by EIV analysis indicate more than 90 % stably for less than 10 orders and noise effect comparing to LPC.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.23 no.4
• /
• pp.213-224
• /
• 1998

Since the late 1980s, an Increasing number of neural network models have been studied in the areas of financial prediction and analysis. The purpose of this study is to Investigate the possibility of building a neural network model that is able to construct a profitable trading strategy in the Korean Stock Market. This study classifies stocks into the future market winners and losers from the publicly available accounting information and builds portfolios based on this information. The performances of the winner portfolios and the loser portfolios are compared with each other and against the market index. The empirical result of this research is consistent with the traditional fundamental analysis where it is claimed that the financial statements contain firm values that may not be fully reflected In stock prices without delay. Despite the supporting empirical evidence. It is somewhat Inconclusive as to whether or not the abnormal return in excess of market return is the result of the extra knowledge obtained in the neural network models derived from the historical accounting data. This research attempts to open another avenue using neural network models for searching for evidence against market efficiency where statistics and intuition have played a major role.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.290-294
• /
• 1997

Chromosomes, as the genetic vehicles, provide the basic material for a large proportion of genetic investigations. The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room for improving the accuracy of chromosome classification. In this paper, we propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of two-step multi-layer neural network(TMANN). We are employed three morphological feature parameters ; centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.), as input in neural network by preprocessing twenty human chromosome images. The results of our experiments show that our TMANN classifier is much more useful in neural network learning and successful in chromosome classification than the other classification methods.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.10 no.3
• /
• pp.282-289
• /
• 2005

This paper proposes a fuzzy neural network controller based on the vector control for interior permanent magnet synchronous motor(IPMSM) drive system. The hybrid combination of neural network and fuzzy control will produce a powerful representation flexibility and numerical processing capability This paper does not oかy presents speed control of IPMSM using neuro-fuzzy control(NFC) but also speed estimation using artificial neural network(ANN) controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The error between the desired state variable and the actual one is back-propagated to adjust the rotor speed, so that the actual state variable will coincide with the desired one. The back propagation mechanism is easy to derive and the estimated speed tracks precisely the actual motor speed. Thus, it is presented the theoretical analysis as well as the analysis results to verify the effectiveness of the proposed method in this paper.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.41 no.3
• /
• pp.39-46
• /
• 2004

This paper is proposed adaptive fuzzy-neural network(FNN) controller for the speed control of interior permanent magnet synchronous motor(IPMSM) drive. The design of this algorithm based on FNN controller that is implemented by using fuzzy control and neural network. This controller uses fuzzy rule as training patterns of a neural network. Also, this controller uses the back-propagation method to adjust the weights among the neurons of neural network in order to minimize the error between the command output and actual output. A model reference adaptive scheme is proposed in which the adaptation mechanism is executed by fuzzy logic based on the error and change of error measured between the motor speed and output of a reference model. The control performance of the adaptive FNN controller is evaluated by analysis for various operating conditions. The results of analysis prove that the proposed control system has strongly high performance and robustness in parameter variation, steady-state accuracy and transient response.

• Journal of Intelligence and Information Systems
• /
• v.5 no.1
• /
• pp.103-123
• /
• 1999

Input filtering as a preprocessing method is so much crucial to get good performance in time series forecasting. There are a few preprocessing methods (i.e. ARMA outputs as time domain filters, and Fourier transform or wavelet transform as time-frequency domain filters) for handling time series. Specially, the time-frequency domain filters describe the fractal structure of financial markets better than the time domain filters due to theoretically additional frequency information. Therefore, we, first of all, try to describe and analyze specially some issues on the effectiveness of different filtering methods from viewpoint of the performance of a neural network based forecasting. And then we discuss about neural network model architecture issues, for example, what type of neural network learning architecture is selected for our time series forecasting, and what input size should be applied to a model. In this study an input selection problem is limited to a size selection of the lagged input variables. To solve this problem, we simulate on analyzing and comparing a few neural networks having different model architecture and also use an embedding dimension measure as chaotic time series analysis or nonlinear dynamic analysis to reduce the dimensionality (i.e. the size of time delayed input variables) of the models. Throughout our study, experiments for integration methods of joint time-frequency analysis and neural network techniques are applied to a case study of daily Korean won / U. S dollar exchange returns and finally we suggest an integration framework for future research from our experimental results.

• Tribology and Lubricants
• /
• v.14 no.3
• /
• pp.74-80
• /
• 1998

The morphologies of the wear particles are directly indicative of wear process occuring in the machine. The analysis of wear particle morphology can therefore provide very early detection of a fault and can also ofen facilitate a dignosis. For this work, the neural network was applied to identify friction coefficient through four shape parameters (50% volumetric diameter, aspect, roundness and reflectivity) of wear debris generated from the machine. The averages of these parameters were used as inputs to the network. It is shown that collect identification of friction coefficient depends on the ranges of these shape parameters learned. The various kinds of the wear debris had a different pattern characteristics and recognized relation between the friction condition and materials very well by neural network. We discuss how the network determines difference in wear debris feature, and this approach can be applied for machine condition monitoring and fault diagnosis.