• Journal of Information Processing Systems
• /
• v.17 no.1
• /
• pp.203-212
• /
• 2021

To eliminate ambiguities in the existing methods to simplify Chinese pronunciation learning, we propose a model that can predict the pronunciation of Chinese characters automatically. The proposed model relies on a statistical machine translation (SMT) framework. In particular, we consider the components of Chinese characters as the basic unit and consider the pronunciation prediction as a machine translation procedure (the component sequence as a source sentence, the pronunciation, pinyin, as a target sentence). In addition to traditional features such as the bidirectional word translation and the n-gram language model, we also implement a component similarity feature to overcome some typos during practical use. We incorporate these features into a log-linear model. The experimental results show that our approach significantly outperforms other baseline models.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.67 no.4
• /
• pp.183-190
• /
• 2018

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

• Journal of the Ergonomics Society of Korea
• /
• v.31 no.3
• /
• pp.427-435
• /
• 2012

The aim of this study is to investigate facial temperature changes induced by facial expression and emotional state in order to recognize a persons emotion using facial thermal images. Background: Facial thermal images have two advantages compared to visual images. Firstly, facial temperature measured by thermal camera does not depend on skin color, darkness, and lighting condition. Secondly, facial thermal images are changed not only by facial expression but also emotional state. To our knowledge, there is no study to concurrently investigate these two sources of facial temperature changes. Method: 231 students participated in the experiment. Four kinds of stimuli inducing anger, fear, boredom, and neutral were presented to participants and the facial temperatures were measured by an infrared camera. Each stimulus consisted of baseline and emotion period. Baseline period lasted during 1min and emotion period 1~3min. In the data analysis, the temperature differences between the baseline and emotion state were analyzed. Eyes, mouth, and glabella were selected for facial expression features, and forehead, nose, cheeks were selected for emotional state features. Results: The temperatures of eyes, mouth, glanella, forehead, and nose area were significantly decreased during the emotional experience and the changes were significantly different by the kind of emotion. The result of linear discriminant analysis for emotion recognition showed that the correct classification percentage in four emotions was 62.7% when using both facial expression features and emotional state features. The accuracy was slightly but significantly decreased at 56.7% when using only facial expression features, and the accuracy was 40.2% when using only emotional state features. Conclusion: Facial expression features are essential in emotion recognition, but emotion state features are also important to classify the emotion. Application: The results of this study can be applied to human-computer interaction system in the work places or the automobiles.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.17 no.6
• /
• pp.14-22
• /
• 2008

This study is aimed at suggesting a linear-type diffuser which is excellent in terms of range and elegance like existing diffusers in which amount and direction of wind can be freely controled, out of linear-type diffusers with the highest possibility to be adopted for living space of apartments whose height between floors is not so high and utilizing the linear-type diffuser in design. For the purpose, I examined necessary flow and noise properties of linear-type diffusers. Besides, I evaluated its ventilation capacity for persons in there by applying this in the actual living space. I evaluated features and air blast and found that in time of horizontal and vertical effusion, its T/L ratio is 1-1.5, similar to existing cardioid-type linear diffusers, while in time of slope effusion, it is similar to horizontal effusion in terms of range and it has medium figure in terms of pressure drop and effusion speed, indicating it can provide safe and pleasant indoor environment for persons in there in terms of ventilation.

• Smart Structures and Systems
• /
• v.26 no.1
• /
• pp.23-33
• /
• 2020

Majority of the damage in engineering structures is nonlinear. Damage sensitive features (DSFs) extracted by traditional methods from linear time series models cannot effectively handle nonlinearity induced by structural damage. A new DSF is proposed based on vector space cosine similarity (VSCS), which combines K-means cluster analysis and Bayesian discrimination to detect nonlinear structural damage. A reference autoregressive moving average (ARMA) model is built based on measured acceleration data. This study first considers an existing DSF, residual standard deviation (RSD). The DSF is further advanced using the VSCS, and then the advanced VSCS is classified using K-means cluster analysis and Bayes discriminant analysis, respectively. The performance of the proposed approach is then verified using experimental data from a three-story shear building structure, and compared with the results of existing RSD. It is demonstrated that combining the linear ARMA model and the advanced VSCS, with cluster analysis and Bayes discriminant analysis, respectively, is an effective approach for detection of nonlinear damage. This approach improves the reliability and accuracy of the nonlinear damage detection using the linear model and significantly reduces the computational cost. The results indicate that the proposed approach is potential to be a promising damage detection technique.

• Journal of Internet Computing and Services
• /
• v.6 no.6
• /
• pp.23-34
• /
• 2005

In a large scale parallel computation, failures of some nodes or communication links end up with waste of computing resources, Several fault-tolerant MPI libraries have been proposed so far, but the programs written by using such libraries have a portability problem since fault-tolerant features are not supported by the MPI standard yet, In this paper, we propose an application-level fault-tolerant linear system solver that uses the asynchronous iteration algorithm and the standard MPI functions only, which does not have a portability problem and is more efficient by adopting a simplified recovery mechanism.

• The Bulletin of The Korean Astronomical Society
• /
• v.40 no.2
• /
• pp.48.3-49
• /
• 2015

Scaling relations of early-type galaxies (ETG) provide a deep insight into their formation and evolution. Interestingly enough, most relations extending into the dwarf regimes display non-linear or broken-linear features, unlike the linear relations for normal (i.e., intermediate-mass to giant) ETGs only. Here we investigate the mass-size scaling relation of ETGs using a massive database of galaxies from SDSS DR12. We divide ETGs into two groups by the indication of star formation such as colors, and examine their distinction along the mass-size relation. We find that the mass-size distribution of blue, young normal galaxies is in good agreement with that of dwarf ETGs. Our result suggests that blue, young normal ETGs may serve as links between (passive) normal ETGs and dwarfs. We discuss the possibility of blue, young ETGs being progenitors of dwarf ETGs.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.58 no.3
• /
• pp.614-620
• /
• 2009

The force distribution in multi-legged robots is a constrained, optimization problem. The solution to the problem is the set points of the leg contact forces for a particular system task. In this paper, an efficient and general formulation of the force distribution problem is developed using linear programming. The considered walking robot is a quadruped robot with a locked-joint failure, i.e., a joint of the failed leg is locked at a known place. For overcoming the drawback of marginal stability in fault-tolerant gaits, we define safety margin on friction constraints as the objective function to be maximized. Dynamic features of locked-joint failure are represented by equality and inequality constraints of linear programming. Unlike the former study, our result can be applied to various forms of walking such as crab and turning gaits. Simulation results show the validity of the proposed scheme.

• Proceedings of the KIEE Conference
• /
• 1987.07b
• /
• pp.1268-1270
• /
• 1987

This paper suggests several simple and efficient algorithms for detecting the ECG Signal by Microcomputer's software. The ECG signal detection was performed with the Linear Approximation and the feature extraction. The linear transformation approximates a given waveform by a piecewise-linear function with a preset upper bound on the absolute error between the functional values of the original function and the approximation. And the feature extraction from ECG signal, the features are different wave amplitudes, durations and interwave intervals, used the slope, the amplitude and time-Duration of ECG Sinal.

• The Korean Journal of Applied Statistics
• /
• v.24 no.5
• /
• pp.759-768
• /
• 2011

Tree algorithms have been widely developed for regression problems. One of the good features of a regression tree is the flexibility of fitting because it can correctly capture the nonlinearity of data well. Especially, data with sudden structural breaks such as the price of oil and exchange rates could be fitted well with a simple mixture of a few piecewise linear regression models. Now that split points are determined by chi-squared statistics related with residuals from fitting piecewise linear models and the split variable is chosen by an objective criterion, we can get a quite reasonable fitting result which goes in line with the visual interpretation of data. The piecewise linear regression by a regression tree can be used as a good fitting method, and can be applied to a dataset with much fluctuation.