• Korean Journal of Cognitive Science
• /
• v.19 no.3
• /
• pp.283-295
• /
• 2008

With increasing usages of a messenger and a SMS, many young people are habitually using a new-style of sentences with intentionally disjoint Korean syllables. To develop a natural language interface system in these environments, we should first develop a technique that converts a sequence of disjoint Korean syllables to a correct sentence. Therefore, we propose a method to assemble a sequence of disjoint Korean syllables into a correct sentence by using two-step rules. In the first step, the proposed method assembles CVC (consonant-vowel-consonant) forms of simple-disjoint Korean syllables by using manual heuristic rules. In the second step, the proposed method assembles CCVCC forms of double-disjoint Korean syllables by using a mapping table and a transformation-based learning technique. In the experiment, the proposed method showed the perfect precision of 100% in assembling simple-disjoint Korean syllables and the high precision of 99.98% in assembling double-disjoint Korean syllables.

• The Journal of the Korea Contents Association
• /
• v.10 no.10
• /
• pp.237-245
• /
• 2010

Nerve conduction studies (NCS) are the most objective measure of nerve function and essential for the diagnosis of sub-clinical neuropathy in diabetes mellitus and diabetic polyneuropathy (DPN). This study evaluates the characteristic of electrophysiological abnormalities in DPN. Electrodiagnostic data from 120 patients with diabetic polyneuropathies and 77 control subjects were reviewed. Motor nerve conduction velocities (MNCV), distal motor latencies (DML), compound muscle action potential (CMAP) amplitudes, No potential frequency and conduction block were analyzed. Data were normalized based on normative reference values, and the proportion of nerves with abnormal values in the lower and upper limbs were evaluated. DPN was systemic demyelinating peripheral polyneuropathy and more severe abnormal nerve conduction was found in lower limbs than in upper limbs. The abnormal degree was more severe in peroneal nerve. It was no statistically significant difference of conduction block in control and DPN group. Our findings suggest that DPN had more common and severe peroneal nerve involvement in the motor nerve conduction studies (MNCS). These findings have important implications for the electrophysiological evaluation of DPN.

• Ocean and Polar Research
• /
• v.30 no.3
• /
• pp.351-359
• /
• 2008

In an effort to develop high-resolution sea surface temperature (SST) proxies for mid-latitude regions, two massive reef-building coral species, Alveopora and Favia, were collected from Jeju and Tsushima Islands, respectively. Their skeletons were subsequently analyzed for annual growth banding, Sr/Ca and Mg/Ca ratios. Hermatypic corals are thinly distributed in the waters of Jeju Island, where Alveopora japonica was the only dominant coral species. A higher diversity of hermatypic corals were observed in the waters of Tsushima Island, where Favia sp. was the most common coral species and even forming an about 6-m-high reef structure. Both Alveopora and Favia showed annual growth layers consisting of couplets of high- and low-density bands. Sr/Ca ratio of both species and Mg/Ca ratio of Alveopora also showed seasonal variation, likely reflecting SST variation. These results suggest the possibility that Alveopora and Favia species can be used as potential SST proxies. However, this study also highlights the potential growth disturbance of middle latitude corals due to high rainfall during monsoon and low SST during winter. This possibility should be taken into account in the investigation of Sr/Ca(Mg/Ca)-SST relationships.

• Proceedings of the Korea Contents Association Conference
• /
• 2009.05a
• /
• pp.1092-1096
• /
• 2009

While Korean allows the same consonants at the coda of the preceding syllable and at the onset of the following syllable, English does not allow the geminate consonant in the same position. Due to this difference between Korean and English, Korean learners of English tend to incorrectly produce geminate consonants for English geminate graphemes as in summer. Based on this observation, a pilot study was designed to investigate how Korean learners of English perceive and produce English doubleton graphemes and singleton graphemes. Twenty Korean college students were asked to perform a forced-choice perception test as well as a production test for the 36 real word stimuli which consist of near minimal pairs of singleton and doubleton graphemes. The result showed that the accuracy rates for the word with singleton graphemes were relatively high both in perception and production (78.6% and 76.1%, respectively), while those for the word with doubleton graphemes were low both in perception and production (55.3% and 61.7%, respectively). Also, spectrographic analyses were provided where more production errors were witnessed in doubleton grapheme words than singleton grapheme words.

• The Transactions of the Korea Information Processing Society
• /
• v.3 no.5
• /
• pp.1281-1293
• /
• 1996

In this paper, we propose a novel recognition model of on-line cursive Korean characters using HMM(Hidden Markov Model) and level building algorithm. The model is constructed as a form of recognition network with HMM for graphemes and Korean combination rules. Though the network is so flexible as to accomodate variability of input patterns, it has a problem of recognition speed caused by 11, 172 search paths. To settle the problem, we modify the level building algorithm to be adapted directly to the Korean combination rules and apply it to the model. The modified algorithm is efficient network search procedure time complexity of which depends on the number of HMMs for each grapheme, not the number of paths in the extensive recognition network. A test with 15, 000 hand written characters shows recognition rat 90% and speed of 0.72 second per character.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.3
• /
• pp.47-56
• /
• 1999

Various phonological alteration occurs when we pronounce continuously in korean. This phonological alteration is one of the major reasons which make the speech recognition of korean difficult. This paper presents a rule-based system which converts a speech recognition character string to a text-based character string. The recovery results are morphologically analyzed and only a correct text string is generated. Recovery is executed according to four kinds of rules, i.e., a syllable boundary final-consonant initial-consonant recovery rule, a vowel-process recovery rule, a last syllable final-consonant recovery rule and a monosyllable process rule. We use a x-clustering information for an efficient recovery and use a postfix-syllable frequency information for restricting recovery candidates to enter morphological analyzer. Because this system is a rule-based system, it doesn't necessitate a large pronouncing dictionary or a phoneme dictionary and the advantage of this system is that we can use the being text based morphological analyzer.

• Phonetics and Speech Sciences
• /
• v.11 no.4
• /
• pp.19-33
• /
• 2019

This paper examines the perception of Korean phonemes by Egyptian learners of Korean and presents the learnability gradient of Korean consonants and vowels through High Variability Phonetic Training (HVPT). 50 Egyptian learners of Korean (27 low proficiency learners and 23 high proficiency learners) participated in 10 sessions of HVPT for Korean vowels, word initial and final consonants. Participants were tested on their identification ability of Korean vowels, word initial consonants, and syllable codas before and after the training. The results showed that both low and high proficiency groups did benefit from the training. Low proficiency learners showed a higher improvement rate than high proficiency learners. Based on the HVPT results, a learnability gradient was established to give insights into priorities in teaching Korean sounds to Egyptian learners.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.6
• /
• pp.561-566
• /
• 2019

In the Internet space, integrity and security must be maintained for secure and confidential communication, which ensures reliability between sender and receiver. Cryptography is an important factor in maintaining robustness against external attacks. For this purpose, encryption and steganography methods are used. Steganography is a method of hiding confidential information without making statistically significant changes to digital media. I propose a method of transforming the Hangul-Jamo consisting of choseong, jungseong and jongseong, and inserting them into RGB pixel values of the cover image. In order to improve security, a new blending method was used to hide the altered information in the lowest region. In this case, a mixture of LSB and LDR techniques was applied. PSNR was calculated for image quality. The PSNR of the proposed method is 43.225dB, which satisfies the lowest level.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.3
• /
• pp.5-13
• /
• 1992

Taking devantage of the property that Korean digit is a mono-syllable word, we proposed a spoken Korean-digit recognition scheme using the multi-layer perceptron. The spoken Korean-digit is divided into three segments (initial sound, medial vowel, and final consonant) based on the voice starting / ending points and a peak point in the middle of vowel sound. The feature vectors such as cepstrum, reflection coefficients, ${\Delta}$cepstrum and ${\Delta}$energy are extracted from each segment. It has been shown that cepstrum, as an input vector to the neural network, gives higher recognition rate than reflection coefficients. Regression coefficients of cepstrum did not affect as much as we expected on the recognition rate. That is because, it is believed, we extracted features from the selected stationary segments of the input speech signal. With 150 ceptral coefficients obtained from each spoken digit, we achieved correct recognition rate of 97.8%.

• The Korean Journal of Food And Nutrition
• /
• v.14 no.2
• /
• pp.113-119
• /
• 2001

The purpose of this study was to compare to the effects of regular exercise on body fat contents and plasma lipid composition of college women. This study was conducted from May to August in 2000. The subjects selected for the experiment were composed sixty three female college students. The basal anthropometric measurements were performed. The levels of total cholesterol, HDL-cholesterol, triglyceride and fatty acid composition of plasma were determined. And plasma glucose concentrations was also assayed. The results obtained are summerized as follows : Average height and weight of E(exercise) group were found to be slightly higher than NE(non exercise) group. The percent of body fat and body fat mass (kg) in E group was slightly lowered than that of NE group. There was decreased on the levels of plasma total cholesterol, triglyceride by regular exercise. HDL-cholesterol level was not significantly different between two groups, but LDL-cholesterol level in E group was significantly lowered than that of NE group. Therefore, plasma total cholesterol and LDL cholesterol levels was significantly decreased by regular exercise.