• Annual Conference on Human and Language Technology
• /
• 2017.10a
• /
• pp.163-166
• /
• 2017

딥러닝은 모델이 복잡해질수록 Train 시간이 오래 걸리는 작업이다. Layer Normalization은 Train 시간을 줄이고, layer를 정규화 함으로써 성능을 개선할 수 있는 방법이다. 본 논문에서는 한국어 의미역 결정을 위해 Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델을 제안한다. 실험 결과, Layer Normalization이 적용 된 Bidirectional LSTM CRF 모델은 한국어 의미역 결정 논항 인식 및 분류(AIC)에서 성능을 개선시켰다.

• Speech Sciences
• /
• v.11 no.1
• /
• pp.21-29
• /
• 2004

In this paper we examined the effect of normalization on discriminating the pathological voice into normal and abnormal classes using artificial neural network. Average values per each parameter were used to normalize each set of parameter values. Artificial neural networks were used as classifiers. And the effect of normalization was evaluated by comparing the discrimination results between original and normalized parameter sets.

• Journal of KIISE:Software and Applications
• /
• v.34 no.6
• /
• pp.503-518
• /
• 2007

Normalization transforms one parent genotype to be consistent with the other before crossover. In this paper, we explain how normalization alleviates the difficulties caused by non-synonymously redundant encodings in genetic algorithms. We define the encodings with maximally non-synonymous property and prove that the encodings induce uncorrelated search spaces. Extensive experiments for a number of problems show that normalization transforms the uncorrelated search spaces to correlated ones and leads to significant improvement in performance.

• Physical Therapy Korea
• /
• v.14 no.3
• /
• pp.32-40
• /
• 2007

Although many children with cerebral palsy have problems with their eye movements available data on its intervention is minimal. The purpose of the study was to determine the effectiveness of the postural movement normalization and eye movement program on the oculomotor ability of children with cerebral palsy. Twenty-four children with cerebral palsy (12 male and 12 female), aged between 10 and 12, were invited to partake in this study. The subjects were randomly allocated to two groups: an experimental group received the postural movement normalization and eye movement program and a control group which received conventional therapy without the eye movement program. Each subject received intervention three times a week for twelve weeks. The final measurement was the ocular motor computerized test before and after treatment sessions through an independent assessor. Differences between the experimental group and control group were determined by assessing changes in oculomotor ability using analysis of covariance (ANCOVA). The changes of visual fixation (p<.01), saccadic eye movement (p<.01) and pursuit eye movement (p<.01) were significantly higher in the experimental group than in the control group. These results show that the postural movement normalization and eye movement program may be helpful to treat children with cerebral palsy who lose normal physical and eye movement.

• Journal of IKEEE
• /
• v.26 no.2
• /
• pp.319-328
• /
• 2022

Bearing plays an important role in the operation of most machinery, Therefore, when a defect occurs in the bearing, a fatal defect throughout the machine is generated. In this reason, bearing defects should be detected early. In this paper, we describe a method using Convolutional Neural Networks (SN-CNNs) based on continuous wavelet transformations and Switchable normalization for bearing defect detection models. The accuracy of the model was measured using the Case Western Reserve University (CWRU) bearing dataset. In addition, batch normalization methods and spectrogram images are used to compare model performance. The proposed model achieved over 99% testing accuracy in CWRU dataset.

• Speech Sciences
• /
• v.13 no.1
• /
• pp.129-139
• /
• 2006

In this paper, we propose two effective energy feature normalization methods for robust speech recognition in noisy environments. In the first method, we estimate the noise energy and remove it from the noisy speech energy. In the second method, we propose a modified algorithm for the Log-energy Dynamic Range Normalization (ERN) method. In the ERN method, the log energy of the training data in a clean environment is transformed into the log energy in noisy environments. If the minimum log energy of the test data is outside of a pre-defined range, the log energy of the test data is also transformed. Since the ERN method has several weaknesses, we propose a modified transform scheme designed to reduce the residual mismatch that it produces. In the evaluation conducted on the Aurora2.0 database, we obtained a significant performance improvement.

• Smart Media Journal
• /
• v.8 no.4
• /
• pp.64-71
• /
• 2019

The performance of an OMR (Optical Music Recognition) system is usually determined by the characterizing features of the input music score images. Low resolution is one of the main factors leading to degraded image quality. In this paper, we handle the low-resolution problem using the super-resolution technique. We propose the use of a deep neural network with instance normalization to improve the quality of music score images. We apply instance normalization which has proven to be beneficial in single image enhancement. It works better than batch normalization, which shows the effectiveness of shifting the mean and variance of deep features at the instance level. The proposed method provides an end-to-end mapping technique between the high and low-resolution images respectively. New images are then created, in which the resolution is four times higher than the resolution of the original images. Our model has been evaluated with the dataset "DeepScores" and shows that it outperforms other existing methods.

• Communications for Statistical Applications and Methods
• /
• v.31 no.1
• /
• pp.105-127
• /
• 2024

We propose recurrent neural network (RNN) methods for forecasting realized volatility (RV). The data are RVs of ten major stock price indices, four from the US, and six from the EU. Forecasts are made for relative ratio of adjacent RVs instead of the RV itself in order to avoid the out-of-scale issue. Forecasts of RV ratios distribution are first constructed from which those of RVs are computed which are shown to be better than forecasts constructed directly from RV. The apparent asymmetry of RV ratio is addressed by the Piecewise Min-max (PM) normalization. The serial dependence of the ratio data renders us to consider two architectures, long short-term memory (LSTM) and gated recurrent unit (GRU). The hyperparameters of LSTM and GRU are tuned by the nested cross validation. The RNN forecast with the PM normalization and ratio transformation is shown to outperform other forecasts by other RNN models and by benchmarking models of the AR model, the support vector machine (SVM), the deep neural network (DNN), and the convolutional neural network (CNN).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.36 no.8C
• /
• pp.505-515
• /
• 2011

This paper describes a normalization method of Haar-like features used for object detection. Previous method which performs variance normalization on Haar-like features requires a lot of calculations, since it uses an additional integral image for calculating the standard deviation of intensities of pixels in a candidate window and increases possibility of false detection in the area where variance of brightness is small. The proposed normalization method can be performed much faster than the previous method by not using additional integral image and classifiers which are trained with the proposed normalization method show robust performance in various lighting conditions. Experimental result shows that the object detector which uses the proposed method is 26% faster than the one which uses the previous method. Detection rate is also improved by 5% without increasing false alarm rate and 45% for the samples whose brightness varies significantly.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.35 no.7C
• /
• pp.604-610
• /
• 2010

In this paper we proposed FSFN (Filter bank sub-band energy subtraction based CLSFN) method to improve the recognition performance of the existing CLSFN (Cepstral distance and Log-energy based Silence Feature Normalization). The proposed FSFN reduces the energy of noise components in filter bank sub-band domain when extracting the features from speech data. This leads to extract the enhanced cepstral features and thus improves the accuracy of speech/silence classification using the enhanced cepstral features. Therefore, it can be expected to get improved performance comparing with the existing CLSFN. Experimental results conducted on Aurora 2.0 DB showed that our proposed FSFN method improves the averaged word accuracy of 2% comparing with the conventional CLSFN method, and FSFN combined with CMVN (Cepstral Mean and Variance Normalization) also showed the best recognition performance comparing with others.