• Proceedings of the Zoological Society Korea Conference
• /
• 1998.10b
• /
• pp.127.1-127
• /
• 1998

No Abstract, See Full Text

• Journal of Biomedical Engineering Research
• /
• v.36 no.4
• /
• pp.128-134
• /
• 2015

Recently, the structured data format in RDF/OWL has played an increasingly vital role in the semantic web. We converted pediatric and oncologic nuclear medicine imaging reports in free text into RDF/OWL format and evaluated the usefulness of nuclear medicine imaging reports in RDF/OWL by comparing SPARQL query results with the manually retrieved results by physicians from the reports in free text. SPARQL query showed 95% recall for simple queries and 91% recall for dedicated queries. In total, SPARQL query retrieved 93% (51 lesions of 55) recall and 100% precision for 20 clinical query items. All query results missed by SPARQL query were of some inference. Nuclear medicine imaging reports in the format of RDF/OWL were very useful for retrieving simple and dedicated query results using SPARQL query. Further study using more number of cases and knowledge for inference is warranted.

• Journal of Information Processing Systems
• /
• v.8 no.1
• /
• pp.67-84
• /
• 2012

An important amount of clinical data concerning the medical history of a patient is in the form of clinical reports that are written by doctors. They describe patients, their pathologies, their personal and medical histories, findings made during interviews or during procedures, and so forth. They represent a source of precious information that can be used in several applications such as research information to diagnose new patients, epidemiological studies, decision support, statistical analysis, and data mining. But this information is difficult to access, as it is often in unstructured text form. To make access to patient data easy, our research aims to develop a system for extracting information from unstructured text. In a previous work, a rule-based approach is applied to a clinical reports corpus of infectious diseases to extract structured data in the form of named entities and properties. In this paper, we propose the use of a Boolean inference engine, which is based on a cellular automaton, to do extraction. Our motivation to adopt this Boolean modeling approach is twofold: first optimize storage, and second reduce the response time of the entities extraction.

• International Journal of Computer Science & Network Security
• /
• v.22 no.8
• /
• pp.242-248
• /
• 2022

The article presents the analysis of modern methods of automatic comparison of original and unoriginal text to detect textual plagiarism. The study covers two types of plagiarism - literal, when plagiarists directly make exact copying of the text without changing anything, and intelligent, using more sophisticated techniques, which are harder to detect due to the text manipulation, like words and signs replacement. Standard techniques related to extrinsic detection are string-based, vector space and semantic-based. The first, most common and most successful target models for detecting literal plagiarism - N-gram and Vector Space are analyzed, and their advantages and disadvantages are evaluated. The most effective target models that allow detecting intelligent plagiarism, particularly identifying paraphrases by measuring the semantic similarity of short components of the text, are investigated. Models using neural network architecture and based on natural language sentence matching approaches such as Densely Interactive Inference Network (DIIN), Bilateral Multi-Perspective Matching (BiMPM) and Bidirectional Encoder Representations from Transformers (BERT) and its family of models are considered. The progress in improving plagiarism detection systems, techniques and related models is summarized. Relevant and urgent problems that remain unresolved in detecting intelligent plagiarism - effective recognition of unoriginal ideas and qualitatively paraphrased text - are outlined.

• Journal of Korea Multimedia Society
• /
• v.20 no.7
• /
• pp.1065-1072
• /
• 2017

As smart devices and social network services (SNSs) become increasingly pervasive, individuals produce large amounts of data in real time. Accordingly, studies on unstructured data analysis are actively being conducted to solve the resultant problem of information overload and to facilitate effective data processing. Many such studies are conducted for filtering inappropriate information. In this paper, a feature-weighting method considering SNS-message features is proposed for the classification of short text messages generated on SNSs, using Markov logic networks for category inference. The performance of the proposed method is verified through a comparison with an existing frequency-based classification methods.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.595-602
• /
• 2020

We propose a generative probabilistic model with Dirichlet prior distribution for topic modeling and text similarity analysis. It assigns a topic and calculates text correlation between documents within a corpus. It also provides posterior probabilities that are assigned to each topic of a document based on the prior distribution in the corpus. We then present a Gibbs sampling algorithm for inference about the posterior distribution and compute text correlation among 50 abstracts from the papers published by IEEE. We also conduct a supervised learning to set a benchmark that justifies the performance of the LDA (Latent Dirichlet Allocation). The experiments show that the accuracy for topic assignment to a certain document is 76% for LDA. The results for supervised learning show the accuracy of 61%, the precision of 93% and the f1-score of 96%. A discussion for experimental results indicates a thorough justification based on probabilities, distributions, evaluation metrics and correlation coefficients with respect to topic assignment.

• Genomics & Informatics
• /
• v.2 no.2
• /
• pp.99-106
• /
• 2004

In this paper we introduce PubMiner, an intelligent machine learning based text mining system for mining biological information from the literature. PubMiner employs natural language processing techniques and machine learning based data mining techniques for mining useful biological information such as protein­protein interaction from the massive literature. The system recognizes biological terms such as gene, protein, and enzymes and extracts their interactions described in the document through natural language processing. The extracted interactions are further analyzed with a set of features of each entity that were collected from the related public databases to infer more interactions from the original interactions. An inferred interaction from the interaction analysis and native interaction are provided to the user with the link of literature sources. The performance of entity and interaction extraction was tested with selected MEDLINE abstracts. The evaluation of inference proceeded using the protein interaction data of S. cerevisiae (bakers yeast) from MIPS and SGD.

• The Journal of the Convergence on Culture Technology
• /
• v.7 no.1
• /
• pp.640-645
• /
• 2021

The deep learning based end-to-end TTS system consists of Text2Mel module that generates spectrogram from text, and vocoder module that synthesizes speech signals from spectrogram. Recently, by applying deep learning technology to the TTS system the intelligibility and naturalness of the synthesized speech is as improved as human vocalization. However, it has the disadvantage that the inference speed for synthesizing speech is very slow compared to the conventional method. The inference speed can be improved by applying the non-autoregressive method which can generate speech samples in parallel independent of previously generated samples. In this paper, we introduce FastSpeech, FastSpeech 2, and FastPitch as Text2Mel technology, and Parallel WaveGAN, Multi-band MelGAN, and WaveGlow as vocoder technology applying non-autoregressive method. And we implement them to verify whether it can be processed in real time. Experimental results show that by the obtained RTF all the presented methods are sufficiently capable of real-time processing. And it can be seen that the size of the learned model is about tens to hundreds of megabytes except WaveGlow, and it can be applied to the embedded environment where the memory is limited.

• Journal of the Korean Society for information Management
• /
• v.26 no.4
• /
• pp.7-34
• /
• 2009

Structures of stories, paragraphs, and sentences and inferences applied to indexing and searching were studied to construct the full-text and sentence retrieval system for storytelling. The system designed the database of stories, paragraphs, and sentences and the knowledge-base of inference rules to aid to write the story. The Knowledge-base comprised the files of story frames, paragraph scripts, and sentence logics made by mark-up languages like SWRL etc. able to operate in semantic web. It is necessary to establish more precise indexing language represented the sentences and to create a mark-up languages able to construct more accurate inference rules.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.17-20
• /
• 2005

In this work, we compared several feature selection methods in the field of spam mail filtering. The proposed fuzzy inference method outperforms information gain and chi squared test methods as a feature selection method in terms of error rate. In the case of junk mails, since the mail body has little text information, it provides insufficient hints to distinguish spam mails from legitimate ones. To address this problem, we follow hyperlinks contained in the email body, fetch contents of a remote web page, and extract hints from both original email body and fetched web pages. A two-phase approach is applied to filter spam mails in which definite hint is used first, and then less definite textual information is used. In our experiment, the proposed two-phase method achieved an improvement of recall by 32.4% on the average over the $1^{st}$ phase or the $2^{nd}$ phase only works.