• Asian Journal for Public Opinion Research
• /
• v.5 no.4
• /
• pp.266-284
• /
• 2018

This paper adopts the big data research method, and draws 491 data from the Tianya Forum about the Simultaneous Renting and Purchasing policy of Guangzhou. The qualitative analysis software Nvivo11 is used to cluster the main questions about the Simultaneous Renting and Purchasing policy in the forum. The 36 high-frequency word frequencies are obtained through text clustering. Through rooted theory analysis, the main driving factors for summarizing people's doubts are 9 main categories, 3 core categories, and the model of driving factors for online forums is established. The study finds that resource factors are the most key factor, economic factors are the important drivers, and policy guiding factors are sub-important drivers.

• Journal of Information Processing Systems
• /
• v.3 no.2
• /
• pp.73-81
• /
• 2007

In this paper, we introduce a domain-independent classification framework based on both k-nearest neighbor and Naive Bayesian classification algorithms. The architecture of our system is simple and modularized in that each sub-module of the system could be changed or improved efficiently. Moreover, it provides various feature selection mechanisms to be applied to optimize the general-purpose classifiers for a specific domain. As for the enhanced classification performance, our system provides conditional probability boosting (CPB) mechanism which could be used in various domains. In the mood classification domain, our optimized framework using the CPB algorithm showed 1% of improvement in precision and 2% in recall compared with the baseline.

• Speech Sciences
• /
• v.2
• /
• pp.57-66
• /
• 1997

This paper studies the effects of the method, CMS(Cepstral Mean Subtraction), (which compensates for some of the speech distortion. caused by telephone channels), on the performance of the text-dependent speaker identification system. This system is based on the VQ(Vector Quantization) and HMM(Hidden Markov Model) method and chooses the LPC-Cepstrum and Mel-Cepstrum as the feature vectors extracted from the speech data transmitted through telephone channels. Accordingly, we can compare the correct recognition rates of the speaker identification system between the use of LPC-Cepstrum and Mel-Cepstrum. Finally, from the experiment results table, it is found that the Mel-Cepstrum parameter is proven to be superior to the LPC-Cepstrum and that recognition performance improves by about 10% when compensating for telephone channel using the CMS.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2003.05a
• /
• pp.99-102
• /
• 2003

본 논문에서는 JPEG 이미지파일을 효율적으로 검색하기 위해서 확장된 JPEG파일의 포맷을 제안하고자 한다. 확장된 JPEG 파일의 포맷 안에는 JPEG 파일을 검색할 때에 사용될 키워드에 대한 설명, 이미지가 만들어진 날짜, 만든 이, 해상도와 같은 이미지에 대한 정보가 들어가게 된다. 이렇게 확장된 포맷을 어떻게 검색에 이용하는지 보이기 위해서 검색 어플리케이션을 설계하였다. 이 어플리케이션은 사용자가 검색 시에 찾고자 하는 이미지의 정보 값들을 지정해 줌으로써 자시의 의도에 적합한 이미지를 보다 정확하게 찾을 수 있게 된다. 피리고 이렇게 찾아진 이미지들은 여러 이미지 정보값들에 따라 다양한 방식으로 정렬되어 보여 지도록 하였다. 또한 이렇게 확장된 JPEG 파일포맷에 사용자가 접근하여 정보를 변경하거나 추가할 수 있는 인터페이스도 제공하도록 하였다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.1287-1290
• /
• 2011

Because of the rapid development of internet, there are more and more documents stored by the XML-based format. When there is a great deal of XML documents, how to get the valuable Information is an important subject. This paper proposes an effective XML document search method to search text contents and structures of XML documents. We build the keyword matrix of text contexts and structure matrixes of structures in XML documents to improve the efficiency of query time. When there is a great deal of XML documents, the search method we propose can improve much efficiency of query time.

• Phonetics and Speech Sciences
• /
• v.15 no.2
• /
• pp.13-20
• /
• 2023

This study explores the potential of automated speech recognition (ASR) in assessing English learners' pronunciation. We employed ASR technology, acknowledged for its impartiality and consistent results, to analyze speech audio files, including synthesized speech, both native-like English and Korean-accented English, and speech recordings from a native English speaker. Through this analysis, we establish baseline values for the word error rate (WER). These were then compared with those obtained for human raters in perception experiments that assessed the speech productions of 30 first-year college students before and after taking a pronunciation course. Our sub-group analyses revealed positive training effects for Whisper, an ASR tool, and human raters, and identified distinct human rater strategies in different assessment aspects, such as proficiency, intelligibility, accuracy, and comprehensibility, that were not observed in ASR. Despite such challenges as recognizing accented speech traits, our findings suggest that digital tools such as ASR can streamline the pronunciation assessment process. With ongoing advancements in ASR technology, its potential as not only an assessment aid but also a self-directed learning tool for pronunciation feedback merits further exploration.

• Journal of Information Technology Services
• /
• v.19 no.3
• /
• pp.17-34
• /
• 2020

Recently, various attempts have been made to discover promising items and technologies. However, there are very few data-driven approaches to support business diversification by companies with specific technologies. Therefore, there is a need for a methodology that can detect items related to a specific technology and recommend highly marketable items among them as business diversification targets. In this paper, we devise Labeled Item Network for Business Diversification Consulting Support System. Our research is performed with three sub-studies. In Sub-study 1, we find the proper source documents to build the item network and construct item dictionary. In Sub-study 2, we derive the Labeled Item Network and devise four index for item evaluation. Finally, we introduce the application scenario of our methodology and describe the result of real-case analysis in Sub-study 3. The Labeled Item Network, one of the main outcome of this study, can identify the relationships between items as well as the meaning of the relationship. We expect that more specific business item diversification opportunities can be found with the Labeled Item Network. The proposed methodology can help many SMEs diversify their business on the basis of their technology.

• Imaging Science in Dentistry
• /
• v.51 no.4
• /
• pp.363-372
• /
• 2021

Purpose: This systematic review and meta-analysis assessed the diagnostic accuracy of imaging examinations for the detection of peri-implant bone defects and compared the diagnostic accuracy between titanium (Ti) and zirconium dioxide (ZrO₂) implants. Materials and Methods: Six online databases were searched, and studies were selected based on eligibility criteria. The studies included in the systematic review underwent bias and applicability assessment using the Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool and a random-effect meta-analysis. Summary receiver operating characteristic (sROC) curves were constructed to compare the effect of methodological differences in relation to the variables of each group. Results: The search strategy yielded 719 articles. Titles and abstracts were read and 61 studies were selected for full-text reading. Among them, 24 studies were included in this systematic review. Most included studies had a low risk of bias (QUADAS-2). Cone-beam computed tomography (CBCT) presented sufficient data for quantitative analysis in ZrO₂ and Ti implants. The meta-analysis revealed high levels of inconsistency in the latter group. Regarding sROC curves, the area under the curve (AUC) was larger for the overall Ti group (AUC=0.79) than for the overall ZrO₂ group (AUC=0.69), but without a statistically significant difference between them. In Ti implants, the AUCs for dehiscence defects(0.73) and fenestration defects(0.87) showed a statistically significant difference. Conclusion: The diagnostic accuracy of CBCT imaging in the assessment of peri-implant bone defects was similar between Ti and ZrO₂ implants, and fenestration was more accurately diagnosed than dehiscence in Ti implants.

• Journal of Digital Convergence
• /
• v.15 no.6
• /
• pp.399-406
• /
• 2017

Contrary to the fact that the old films contain artistic and include contemporary literature, religion, and philosophy, latest films are produced with focusing on external interesting composition and sensational scene. A good movie emotionally express the directors' topic message exuding from an interesting story, and empathize with the social agenda which shows a sharp look of the directors' on contemporary social aspect. In the movies of the Coen brothers, it seems like an entertainment movie as typical black comedy genre through irony and happening, but in fact, it inserts a lot of social problems in the film to show that they cynically express their social agenda from a contemplative view. In their movie "The Big Lebowski (1998)", it seems like they are creating comical content through the main characters' unaffected attitude. However, it is director's excellent director of the sub-text that expresses American social issues such as Vietnam war, post-modernism and an obscurantist policy and au fond the comedy about the historical facts of mass production of social maladjustment into black comedy. We expect to contribute to make a step forward in the Korea film industry by analyzing such movies that has the cultural power of influence.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1649-1659
• /
• 2004

Text Generation is a process of generating comprehensible texts in human languages from some underlying non-linguistic representation of information. Among several sub-processes for text generation to generate coherent texts, this paper concerns referring expression generation which produces different types of expressions to refer to previously-mentioned things in a discourse. Specifically, we focus on pronominalization by zero pronouns which frequently occur in Korean. To build a generation model of referring expressions for Korean, several features are identified based on grammatical information and cost-based centering model, which are applied to various machine learning techniques. We demonstrate that our proposed features are well defined to explain pronominalization, especially pronominalization by zero pronouns in Korean, through 95 texts from three genres - Descriptive texts, News, and Short Aesop's Fables. We also show that our model significantly outperforms previous ones with a 99.9% confidence level by a T-test.