• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.11
• /
• pp.1397-1406
• /
• 2019

In everyday mobile phone calls between the disabled and non-disabled people due to neurological impairment, the communication accuracy is often hindered by combining the accuracy of pronunciation due to the neurological impairment and the pronunciation features of the disabled. In order to improve this problem, the limiting method is MEMS (micro electro mechanical systems), which includes an induction line that artificially corrects difficult vocalization according to the oral characteristics of the language impaired by improving the word of out of vocabulary. mechanical System) Microphone device improvement. S/W improvement is decision tree with invert function, and improved matrix-vector rnn method is proposed considering continuous word characteristics. Considering the characteristics of H/W and S/W, a similar dictionary was created, contributing to the improvement of speech intelligibility for smooth communication.

• The Journal of the Korea Contents Association
• /
• v.14 no.1
• /
• pp.66-75
• /
• 2014

The purpose of this study is to analyze and illustrate 'Rhizome', a postmodern speculation system based on de-subjectivity and decentralization, presented by Gilles Deleuze. He borrowed the word rhizome, an originally botanical term meaning a horizontal stem under the surface of the earth, to counteract the dominating system grounded on binary, root-tree structure. The study then criticizes the early movements of de-subjectivity with molecular-biological and evolutionary evidences, and proves that these evidences can only be characterized by chance and nomadism, which are the key elements that constitute Rhizome. As a practical example of Rhizome, the study analyzes the film by Gus Van Sant, and demonstrates that both his various cinematic experiments and the result bear the same characteristics as Rhizome.

• The Journal of the Korea Contents Association
• /
• v.10 no.2
• /
• pp.241-249
• /
• 2010

Companies and consumers are highly interested in online activities such as word-of-mouth(W.O.M) as marketing paradigm moved to online context. In this study, the research identified major variables affecting product review reference rate online and analyzed the difference based on those variables. According to the results, remarkable differences were discovered in four variable such as 'brand reference', 'review symbol', 'affirmation' and 'information offering'. In addition, the researcher found 'brand reference' and 'information offering' are most important factors deciding review reference rate using regression tree analysis method. Based on the results, the practical implications and further research directions for utilizing consumer online W.O.M were discussed.

• Journal of the Korean Institute of Traditional Landscape Architecture
• /
• v.32 no.4
• /
• pp.61-72
• /
• 2014

Throughout analyzing and construing the words, contexts, and expressive languages used for depicting the pine tree in the novel "Honbul" written by Choi, Myung-Hee the symbolism of the pine and folksy languages used for scenery can be condensed as written below: First, it is explicit that the scenery-words for illustrating the pine tree in "Honbul" are emerged through diverse means methods and expressions. Namely, the reference forms of the pine tree and the expressive means of utilizing words portrays the use of the pine are various and subdivided. Second, the scenery-words found in vocabularies and the contexts of "Honbul" imply various symbolic representation. They not only perform to describe inherent image and symbolism of the pine, but they work for reifying the image of "Honbul" in the narrative structure in "Honbul" as being intrinsic scenery-word. Third, the scenery-words used for expressing aesthetics emerge as synesthetic expressions through the linear beauty and the texture of the pine as well as through five-senses. Forth, on the basis of the inherent symbolism and the image of the pine, the landscape of the background described in "Honbul" deems as a symbolic backdrop. As with then narrative structure of the novel, the pine tree performs as a mediation of the heaven and the earth, god and man, as well as the sacred and the secular. Fifth, scenery-words used for depicting the pine tree are a symbol that represents the spirit and emotion of the character in the novel. Moreover, it is a tool for pursuing the personification of the nature, the deification of the object, and the cosmos of the space. It is also utilized as a device that definitize the ideational image applied to express the landscape of the background of the novel. As mentioned above, the expressions, vocabularies and textures about pine tree represented from "Honbul" are expected to be the beginning of understanding the landscape-images and landscape-languages of pine in not only the setting for this novels, Namwon but also the entire districts of Korea.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.4
• /
• pp.612-622
• /
• 2003

This paper studied and proposed a XML document storing-and-retrieval framework based on a variant k-ary complete tree and a RDF metadata, which is composed of an effective storing module to store xml documents, a retrieving module to retrieve xml documents, and a connecting module to make this system intemperate in the web environment. In this storing module, DTD independent DOM based decomposition model using a method of addressing unique ill using a variant k-ary complete tree is adopted and is implemented. Query Processing Module includes a XPath query process and a content based retrieval function using word index for content information. To retrieve more exactly data, a structural retrieval using RDF metadata is adopted and implemented. In order to implement effectively XML document storing and retrieval system in the web environment, API using XML-RPC, API using HTTP's GET, PUT, POST and API using SOAP have been adopted and implemented.

• Journal of Information Technology Services
• /
• v.19 no.1
• /
• pp.103-112
• /
• 2020

Job seekers are making various efforts to find a good company and companies attempt to recruit good people. Job search activities through self-introduction essay are nowadays one of the most active processes. Companies spend time and cost to reviewing all of the numerous self-introduction essays of job seekers. Job seekers are also worried about the possibility of acceptance of their self-introduction essays by companies. This research builds a classification model and conducted an experiments to classify self-introduction essays into pass or fail using deep learning and decision tree techniques. Real world data were classified using stratified sampling to alleviate the data imbalance problem between passed self-introduction essays and failed essays. Documents were embedded using Doc2Vec method developed from existing Word2Vec, and they were classified using logistic regression analysis. The decision tree model was chosen as a benchmark model, and K-fold cross-validation was conducted for the performance evaluation. As a result of several experiments, the area under curve (AUC) value of PV-DM results better than that of other models of Doc2Vec, i.e., PV-DBOW and Concatenate. Furthmore PV-DM classifies passed essays as well as failed essays, while PV_DBOW can not classify passed essays even though it classifies well failed essays. In addition, the classification performance of the logistic regression model embedded using the PV-DM model is better than the decision tree-based classification model. The implication of the experimental results is that company can reduce the cost of recruiting good d job seekers. In addition, our suggested model can help job candidates for pre-evaluating their self-introduction essays.

• Proceedings of the KSPS conference
• /
• 2003.10a
• /
• pp.175-179
• /
• 2003

In order to produce a high quality (intelligibility and naturalness) synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model. In this paper, we analyzed Chinese texts using a segmentation, POS tagging and unknown word recognition. We present a grapheme-to-phoneme conversion using a dictionary-based and rule-based method. We constructed a prosody model using a probabilistic method and a decision tree-based error correction method. According to the result from the above analysis, we can successfully select and concatenate exact synthesis unit of syllables from the Chinese Synthesis DB.

• The Korean Journal of Food And Nutrition
• /
• v.8 no.2
• /
• pp.128-134
• /
• 1995

God created the havens and earth and god gave man every seed-bearing plant and every tree that has fruit with seed in it. These food Is all vegetable food that don't take diseases of adult people. But God gave Noah the green plants. Everything that lives and moves will be food for Noah. Just as God gave man the green plants. And then man must not eat meat (animal protein food) that has its lifeblood still in it and God must not eat fat in it. The fat contains much fat (saturated fatty acids) and cholesterol that have susceptibility to disease of coronary heart, hypertension and atheriosclerosis etc. God must not eat these fat before we don't know that It have susceptibility to disease of adult people.

• Proceedings of the KSPS conference
• /
• 2003.05a
• /
• pp.219-222
• /
• 2003

In this paper, we study the usage of phoneme duration information for rejection garbage sentence. First, we build a phoneme duration modeling in a speech recognition system based on dicicion tree state tying, We assume that phone duration has a Gamma distribution. Next, we build a verification module in which word-level confidence measure is used. Finally, we make a comparative study on phoneme duration with speech DB obtained from the live system. This DB consistes of OOT(out-of-task) and ING(in-grammar) utterences. the usage of phone duration information yields that OOT recognition rate is improved by 46％ and that another 8.4％ error rate is reduced when combined with utterence verification module.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.337-338
• /
• 2009

블로그문서의 의견극성분류 연구는 주로 기계학습기법에 기반한 방법이었고, 이때 주로 활용된 자질은 명사, 동사 등의 품사정보와 의견어 어휘정보였다. 하지만 하나의 의견어 어휘만을 고려한다면 그 극성을 판별하는데 필요한 정보가 충분하지 않아 부정확한 결과를 도출하는 경우가 발생할 수 있다. 본 논문에서는 여러 어휘를 동시에 고려하였을 때 보다 정확한 의견분류를 수행할 수 있을 것이라는 가정을 세웠다. 본 논문에서는 효과적인 의견어휘자질의 추출을 위하여 의견이 내포될 가능성이 높은 의견어휘를 기반으로 의존구문분석을 통해 의존트리패턴을 추출하였고, 제안하는 PF-IDF가중치를 적용하여 지지벡터기계(SVM)와 다항시행접근 단순베이지안(MNNB)알고리즘으로 비교 실험을 수행하였다. 기준시스템인 TF-IDF가중치 기법에 비해 정확도(accuracy)가 지지벡터기계에서 5%, 다항시행접근 단순베이지안에서 8.9% 향상된 성능을 보였다.