• Phonetics and Speech Sciences
• /
• v.7 no.4
• /
• pp.131-138
• /
• 2015

The initial syllables of a pair of Sino-Korean words are generally differentiated in their meaning by either short or long durations. They are realized differently by the dialect and generation of speakers. Recent research has reported that the temporal distinction has gradually faded away. The aim of this study is to examine whether college students with Kyungsang dialect made the distinction temporally using a statistical method of Mixed Effects Model. Thirty students participated in the recording of five pairs of Korean words in clear or casual speaking styles. Then, the author measured the durations of the initial syllables of the words and made a descriptive analysis of the data followed by applying Mixed Effects Models to the data by setting gender, length, and style as fixed effects, and subject and syllable as random effects, and tested their effects on the initial syllable durations. Results showed that college students with Kyungsang dialect did not produce the long and short syllables distinctively with any statistically significant difference between them. Secondly, there was a significant difference in the duration of the initial syllables between male and female students. Thirdly, there was also a significant difference in the duration of the initial syllables produced in the clear or casual styles. The author concluded that college students with Kyungsang dialect do not produce long and short Sino-Korean syllables distinctively, and any statistical analysis on the temporal aspect should be carefully made considering both fixed and random effects. Further studies would be desirable to examine production and perception of the initial syllables by speakers with various dialect, generation, and age groups.

• Journal of Information Processing Systems
• /
• v.18 no.5
• /
• pp.614-627
• /
• 2022

Aspect-based sentiment analysis is to discover the sentiment polarity towards an aspect from user-generated natural language. So far, most of the methods only use the implicit position information of the aspect in the context, instead of directly utilizing the position relationship between the aspect and the sentiment terms. In fact, neighboring words of the aspect terms should be given more attention than other words in the context. This paper studies the influence of different position embedding methods on the sentimental polarities of given aspects, and proposes a position embedding interactive attention network based on a long short-term memory network. Firstly, it uses the position information of the context simultaneously in the input layer and the attention layer. Secondly, it mines the importance of different context words for the aspect with the interactive attention mechanism. Finally, it generates a valid representation of the aspect and the context for sentiment classification. The model which has been posed was evaluated on the datasets of the Semantic Evaluation 2014. Compared with other baseline models, the accuracy of our model increases by about 2% on the restaurant dataset and 1% on the laptop dataset.

• International Journal of Advanced Culture Technology
• /
• v.5 no.1
• /
• pp.83-89
• /
• 2017

In this paper, we propose an extended method of one-hot Long Short-Term Memory (LSTM) and evaluate the performance on spam filtering task. Most of traditional methods proposed for spam filtering task use word occurrences to represent spam or non-spam messages and all syntactic and semantic information are ignored. Major issue appears when both spam and non-spam messages share many common words and noise words. Therefore, it becomes challenging to the system to filter correct labels between spam and non-spam. Unlike previous studies on information filtering task, instead of using only word occurrence and word context as in probabilistic models, we apply a neural network-based approach to train the system filter for a better performance. In addition to one-hot representation, using term weight with attention mechanism allows classifier to focus on potential words which most likely appear in spam and non-spam collection. As a result, we obtained some improvement over the performances of the previous methods. We find out using region embedding and pooling features on the top of LSTM along with attention mechanism allows system to explore a better document representation for filtering task in general.

• Korean Journal of Applied Biomechanics
• /
• v.22 no.1
• /
• pp.9-16
• /
• 2012

The purpose of this study was to compare and analyze muscle function and EMG of the trunk and the lower extremity in short and long distance athletes and in order to determine difference in peak torque per unit weight, muscle power per unit weight, endurance ratio, and %MVIC classified by muscle. For that purpose, isokinetic muscle function tests for waist, knee, and ankle joints and EMG measurements for the trunk and the lower extremity muscle with running motion were conducted for 7 short and long distance high school athletes respectively. The study over muscle function of waist, knee, and ankle joints indicates that peak torque per unit weight of short distance athletes is higher than that of long distance athletes in extension and flexion of waist joint, plantar flexion of right ankle joint, and dorsi flexion of left ankle joint. In case of the muscle power per unit weight of short distance athletes is also higher than long distance athletes in waist, knee, and ankle joints. No difference in endurance ratio of waist, knee, and ankle joints between the two groups was founded. The results of the test over EMG of the trunk and the lower extremity show that %MVIC of erector spinae, rectus femoris, vastus medialis, vastus lateralis, and tibialis anterior is higher than that of long distance athletes in support phase. The above results proved to be the same in flight phase except for %MVIC of medial gastrocnemius. In other words, %MVIC of medial gastrocnemius for short distance athletes turned out to be higher than that of long distance athletes in flight phase.

• Journal of the Korean Society of Clothing and Textiles
• /
• v.47 no.2
• /
• pp.215-231
• /
• 2023

This study classifies short front long back skirts from the Joseon Dynasty by style type, identifies their formative characteristics based on their external morphological properties and internal composition, and examines their correlation with Korean thought. A literature review and empirical research were conducted for this study. The style of short front long back skirts is classified as inverted "b"-shaped, lower lip, wavy, trapezoid with a raised center hem, or half-circle. As such, this skirt possesses the formative properties of imbalance, variability of shape, intentional three-dimensionality, and confluence. In other words, with an imbalance resulting from the difference in length between the front and back, these skirts are characterized by variability in shape created by intentional three-dimensionality expressed as intentional three-dimensional beauty, the confluence of planes and dimensions, as well as of materials and colors. These properties are correlated with Korean ways of viewing the world. This study contributes to the development of Korean designs.

• Journal of Fashion Business
• /
• v.13 no.6
• /
• pp.137-146
• /
• 2009

This study analyzed hierarchy of image for visual evaluation of flare skirt. This study analyzed expression words about flare skirt with frequency data of image expression words with different length and volume of flare. Stimuli for the study were set to be 4 different volume of flare ($90^{\circ}$, $180^{\circ}$, $270^{\circ}$, $360^{\circ}$) and 3 different length of skirt(48cm, 58cm, 68cm). Stimuli were made by using I-Designer which is Virtual Sewing System. From simulation of flare skirt, the subjects were asked to write down suggested adjective freely and selected 210 adjectives. With this, we chose total 38 adjectives considering frequencies in the pre-study. And we analyzed the combination process of expression words according to construction factor of flare skirt and hierarchy of image from dendrogram which was resulted by hierarchical cluster analysis. 'Feminine' got high score in all 12 flare skirt. When the skirt was short, it was vivid, and as the skirt got longer, ordinary and pure image showed. Also, as the volume of flare got larger, the average of visual effect was higher than visual image. Visual hierarchy construction according to construction factors of flare skirt could be divided into visual image and visual effect, and visual image was shown to be form 'A type - large volume of flare and short skirt length', 'H type-small volume of flare and short skirt length' and 'X type - large volume of flare and long skirt length'.

• The Journal of Bigdata
• /
• v.4 no.2
• /
• pp.35-45
• /
• 2019

Recently, the damage with social cost of malicious comments is increasing. In addition to the news of talent committing suicide through the effects of malicious comments. The damage to malicious comments including abusive language and slang is increasing and spreading in various type and forms throughout society. In this paper, we propose a technique for detecting abusive language using a bi-directional long short-term memory neural network model. We collected comments on the web through the web crawler and processed the stopwords on unused words such as English Alphabet or special characters. For the stopwords processed comments, the bidirectional long short-term memory neural network model considering the front word and back word of sentences was used to determine and detect abusive language. In order to use the bi-directional long short-term memory neural network, the detected comments were subjected to morphological analysis and vectorization, and each word was labeled with abusive language. Experimental results showed a performance of 88.79% for a total of 9,288 comments screened and collected.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.4
• /
• pp.1400-1418
• /
• 2020

In the development of commercial promotion, chatbot is known as one of significant skill by application of natural language processing (NLP). Conventional design methods are using bag-of-words model (BOW) alone based on Google database and other online corpus. For one thing, in the bag-of-words model, the vectors are Irrelevant to one another. Even though this method is friendly to discrete features, it is not conducive to the machine to understand continuous statements due to the loss of the connection between words in the encoded word vector. For other thing, existing methods are used to test in state-of-the-art online corpus but it is hard to apply in real applications such as telemarketing data. In this paper, we propose an improved chatbot design way using hybrid bag-of-words model and skip-gram model based on the real telemarketing data. Specifically, we first collect the real data in the telemarketing field and perform data cleaning and data classification on the constructed corpus. Second, the word representation is adopted hybrid bag-of-words model and skip-gram model. The skip-gram model maps synonyms in the vicinity of vector space. The correlation between words is expressed, so the amount of information contained in the word vector is increased, making up for the shortcomings caused by using bag-of-words model alone. Third, we use the term frequency-inverse document frequency (TF-IDF) weighting method to improve the weight of key words, then output the final word expression. At last, the answer is produced using hybrid retrieval model and generate model. The retrieval model can accurately answer questions in the field. The generate model can supplement the question of answering the open domain, in which the answer to the final reply is completed by long-short term memory (LSTM) training and prediction. Experimental results show which the hybrid word vector expression model can improve the accuracy of the response and the whole system can communicate with humans.

• Investigative Magnetic Resonance Imaging
• /
• v.13 no.1
• /
• pp.9-14
• /
• 2009

T1-, and T2-weighted imagings and FLAIR (fluid attenuated inversion recovery) imaging are fundamental imaging methods in the brain. T1-weighted imaging is a spin-echo sequence with short TR and short TE and produces the tissue contrast by different T1 relaxation times. In other words, short TR maximizes the difference of the longituidinal magnetization recovery between the tissues. T2-weighted imaging is a spin-echo sequence with long TR and long TE and produces the tissue contrast by different T2 relaxation times. Long TE maximizes the difference of the transverse magnetization decay between the tissues. FLAIR is an inversion recovery sequence using 180 degree inversion pulse. 2500 msec of inversion time is applied to suppress the CSF signal.

• ETRI Journal
• /
• v.44 no.4
• /
• pp.672-685
• /
• 2022

This article proposes a subject-independent application of brain-computer interfacing (BCI). A 32-channel Electroencephalography (EEG) device is used to measure imagined speech (SI) of four words (sos, stop, medicine, washroom) and one phrase (come-here) across 13 subjects. A deep long short-term memory (LSTM) network has been adopted to recognize the above signals in seven EEG frequency bands individually in nine major regions of the brain. The results show a maximum accuracy of 73.56% and a network prediction time (NPT) of 0.14 s which are superior to other state-of-the-art techniques in the literature. Our analysis reveals that the alpha band can recognize SI better than other EEG frequencies. To reinforce our findings, the above work has been compared by models based on the gated recurrent unit (GRU), convolutional neural network (CNN), and six conventional classifiers. The results show that the LSTM model has 46.86% more average accuracy in the alpha band and 74.54% less average NPT than CNN. The maximum accuracy of GRU was 8.34% less than the LSTM network. Deep networks performed better than traditional classifiers.