• Journal of KIISE:Software and Applications
• /
• v.29 no.9
• /
• pp.654-668
• /
• 2002

In this paper, we present an empirical study for improving the Korean text chunking based on machine learning and feature set selection approaches. We focus on two issues: the problem of selecting feature set for Korean chunking, and the problem of alleviating the data sparseness. To select a proper feature set, we use a heuristic method of searching through the space of feature sets using the estimated performance from a machine learning algorithm as a measure of "incremental usefulness" of a particular feature set. Besides, for smoothing the data sparseness, we suggest a method of using a general part-of-speech tag set and selective lexical information under the consideration of Korean language characteristics. Experimental results showed that chunk tags and lexical information within a given context window are important features and spacing unit information is less important than others, which are independent on the machine teaming techniques. Furthermore, using the selective lexical information gives not only a smoothing effect but also the reduction of the feature space than using all of lexical information. Korean text chunking based on the memory-based learning and the decision tree learning with the selected feature space showed the performance of precision/recall of 90.99%/92.52%, and 93.39%/93.41% respectively.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.1
• /
• pp.1-7
• /
• 2023

Convolutional neural networks have already been applied to various fields beyond human visual processing capabilities in the image processing area. However, they are exposed to a severe risk of deteriorating model performance due to the appearance of adversarial attacks. In addition, defense technology to respond to adversarial attacks is effective against the attack but is vulnerable to other types of attacks. Therefore, to respond to an adversarial attack, it is necessary to analyze how the performance of the adversarial attack deteriorates through the process inside the convolutional neural network. In this study, the adversarial attack of the Alexnet and VGG11 models was analyzed using the population sparseness index, a measure of neuronal activity in neurophysiology. Through the research, it was observed in each layer that the population sparsity index for adversarial examples showed differences from that of benign examples.

• ETRI Journal
• /
• v.39 no.4
• /
• pp.455-466
• /
• 2017

This study focuses on a method for sequential data augmentation in order to alleviate data sparseness problems. Specifically, we present corpus expansion techniques for enhancing the coverage of a language model. Recent recurrent neural network studies show that a seq2seq model can be applied for addressing language generation issues; it has the ability to generate new sentences from given input sentences. We present a method of corpus expansion using a sentence-chain based seq2seq model. For training the seq2seq model, sentence chains are used as triples. The first two sentences in a triple are used for the encoder of the seq2seq model, while the last sentence becomes a target sequence for the decoder. Using only internal resources, evaluation results show an improvement of approximately 7.6% relative perplexity over a baseline language model of Korean text. Additionally, from a comparison with a previous study, the sentence chain approach reduces the size of the training data by 38.4% while generating 1.4-times the number of n-grams with superior performance for English text.

• 한국HCI학회:학술대회논문집
• /
• 2008.02a
• /
• pp.569-572
• /
• 2008

The possibility to extent the solution in human detection problem for plug-in on vision-based Human Computer Interaction domain is very attractive, since the successful of the machine leaning theory and computer vision marriage. Bayesian logistic regression is a powerful classifier performing sparseness and high accuracy. The difficulties of finding people in an image will be conquered by implementing this Bavesian model as classifier. The comparison with other massive classifier e.g. SVM and RVM will introduce acceptance of this method for human detection problem. Our experimental results show the good performance of Bavesian logistic regression in human detection problem, both in trade-off curves (ROC, DET) and real-implementation compare to SVM and RVM.

• MALSORI
• /
• no.46
• /
• pp.51-64
• /
• 2003

In order to produce high quality synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model from texts using natural language processing. Robust preprocessing for non-Korean characters should also be required. In this paper, we analyzed Korean texts using a morphological analyzer, part-of-speech tagger and syntactic chunker. We present a new grapheme-to-phoneme conversion method for Korean using a hybrid method with a phonetic pattern dictionary and CCV (consonant vowel) LTS (letter to sound) rules, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method. The probabilistic method atone usually suffers from performance degradation due to inherent data sparseness problems. So we adopted tree-based error correction to overcome these training data limitations.

• Journal of applied mathematics & informatics
• /
• v.8 no.2
• /
• pp.361-370
• /
• 2001

Testing equality of covariance matrix of k populations has long been an interesting issue in statistical inference. To overcome the sparseness of data points in a high-dimensional space and deal with the general cases, we suggest several projection pursuit type statistics. Some results on the limiting distributions of the statistics are obtained. some properties of Bootstrap approximation are investigated. Furthermore, for computational reasons an approximation which is based on Number theoretic method for the statistics is adopted. Several simulation experiments are performed.

• Journal of the Korean Statistical Society
• /
• v.27 no.4
• /
• pp.515-529
• /
• 1998

Burman (1987) and Hall and Titterington (1987) studied kernel smoothing for sparse multinomial data in detail. Both of their estimators for cell probabilities are sparse asymptotic consistent under some restrictive conditions on the true cell probabilities. Dong and Simonoff (1994) adopted boundary kernels to relieve the restrictive conditions. We propose a local linear kernel estimator which is popular in nonparametric regression to estimate cell probabilities. No boundary adjustment is necessary for this estimator since it adapts automatically to estimation at the boundaries. It is shown that our estimator attains the optimal rate of convergence in mean sum of squared error under sparseness. Some simulation results and a real data application are presented to see the performance of the estimator.

• Journal of the Optical Society of Korea
• /
• v.20 no.2
• /
• pp.228-233
• /
• 2016

In this paper, we propose a nonlinear maximum average correlation height (MACH) filter for information authentication of photon counting double random phase encryption (DRPE). To enhance the security of DRPE, photon counting imaging can be applied because of its sparseness. However, under severely photon-starved conditions, information authentication of DRPE may not be implemented successfully. To visualize the photon counting DRPE, a three-dimensional imaging technique such as integral imaging can be used. In addition, a nonlinear MACH filter can be utilized for helping the information authentication. Therefore, in this paper, we use integral imaging and nonlinear MACH filter to implement the information authentication of photon counting DRPE. To verify our method, we implement optical experiments and computer simulation.

• Phonetics and Speech Sciences
• /
• v.5 no.4
• /
• pp.227-232
• /
• 2013

Since a reverberation filter is generally much shorter than the corresponding dereverberation filter, a single-channel speech dereverberation method based on reverberation filter estimation has been developed to improve its performance. Unfortunately, a typical reverberation filter still requires too many coefficients to be accurately estimated using limited speech observations. In order to exploit sparseness of reverberation filter coefficients, in this paper, we present an algorithm to impose a sparse prior to the process of reverberation filter estimation. Simulation results demonstrate that the sparse prior imposition further improves performance of the speech dereverberation method based on reverberation filter estimation.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.34C no.10
• /
• pp.43-50
• /
• 1997

In this paper, we present a method that can recognize face images by use of a sparse population code that is a learning model about a receptive fields of the simple cells in the primary visual cortex. Twenty front-view facial images form twenty persons were used for the training process, and 200 varied facial images, 20 per person, were used for test. The correct recognition rate was 100% for only the front-view test facial images, which include the images either with spectacles or of various expressions, while it was 90% in average for the total input images that include rotated faces. We analyzed the effect of nonlinear functon that determine the sparseness, and compared recognition rate using the sparese population code with that using eigenvectors (eigenfaces), which is compact code that makes contrast with the sparse population code.