• 말소리와 음성과학
• /
• 제7권4호
• /
• 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
• /
• 제18권5호
• /
• 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
• /
• 제5권1호
• /
• 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.

• 한국운동역학회지
• /
• 제22권1호
• /
• 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.

• 한국의류학회지
• /
• 제47권2호
• /
• 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.

• 패션비즈니스
• /
• 제13권6호
• /
• 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'.

• 한국빅데이터학회지
• /
• 제4권2호
• /
• pp.35-45
• /
• 2019

욕설과 비속어를 포함한 악성 댓글에 대한 피해는 최근 언론에 나오는 연애인의 자살뿐만 아니라 사회 전반에서 다양한 형태로 증가하고 있다. 이 논문에서는 양방향 장단기 메모리 신경망 모델을 이용하여 욕설을 검출하는 기법을 제시하였다. 웹 크룰러를 통해 웹상의 댓글을 수집하고, 영어나 특수문자 등의 사용하지 않은 글에 대해 불용어 처리를 하였다. 불용어 처리된 댓글에 대해 문장의 전·후 관계를 고려한 양방향 장단기 메모리 신경망 모델을 적용하여 욕설 여부를 판단하고 검출하였다. 양방향 장단기 메모리 신경망을 사용하기 위해 검출된 댓글에 대해 형태소 분석과 벡터화 과정을 거쳤으며 각 단어들에 욕설 해당 여부를 라벨링하여 진행하였다. 실험 결과 정제하고 수집된 총 9,288개의 댓글에 대해 88.79%의 성능을 나타내었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권4호
• /
• 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
• /
• 제13권1호
• /
• pp.9-14
• /
• 2009

T1, T2강조영상, FLAIR (fluid attenuated inversion recovery) 영상기법은 뇌 MRI의 가장 기본적인 영상기법들이다. T1강조영상은 짧은 TR과 짧은 TE를 이용한 스핀에코 기법으로서 조직의 T1이완시간의 차이를 신호 차이로 반영하는 기법이다. 짧은 TR을 사용하면 조직 간에 종축 자기화의 회복 정도가 크게 차이나게 되며 이를 신호에 반영하는 것이다. T2강조영상은 긴 TR과 긴 TE를 이용한 스핀에코 기법으로서 조직의 T2이완시간의 차이를 신호 차이로 반영하는 기법이다. 긴 TE을 사용하면 조직 간에 횡축 자기화의 붕괴가 크게 차이나게 되며 이를 신호에 반영하는 것이다. FLAIR는 180도 반전펄스를 먼저 가하는 반전회복 (inversion recovery) 기법의 일종으로서 뇌척수액의 신호를 억제하기 위하여 2500 msec 정도의 반전시간을 적용한다.

• ETRI Journal
• /
• 제44권4호
• /
• 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.