• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2007.02a
• /
• pp.48-52
• /
• 2007

As huge amount of literature including biological data is being generated after post genome era, it becomes difficult for researcher to find useful knowledge from the biological databases. Bio-text mining and related natural language processing technique are the key issues in the intelligent knowledge retrieval from the biological databases. We propose a bio-text mining technique for the biologists who find Knowledge from the huge literature. At first, web robot is used to extract and transform related literature from remote databases. To improve retrieval speed, we generate an inverted file for keywords in the literature. Then, text mining system is used for extracting given knowledge patterns and keywords. Finally, we construct a grid computing environment to guarantee processing speed in the text mining even for huge literature databases. In the real experiment for 10,000 bio-literatures, the system shows 95% precision and 98% recall.

• The KIPS Transactions:PartB
• /
• v.15B no.6
• /
• pp.595-602
• /
• 2008

The focused word of each sentence is a help in recognizing and understanding spoken Korean. To find the method of focused word spotting at spoken speech signal, we made an analysis of the average and variance of Fundamental Frequency and the average energy extracted from a focused word and the other words in a sentence by experiments with the speech data from 100 spoken sentences. The result showed that focused words have either higher relative average F0 or higher relative variances of F0 than other words. Our findings are to make a contribution to getting prosodic characteristics of spoken Korean and keyword extraction based on natural language processing.

• Journal of Korea Multimedia Society
• /
• v.22 no.6
• /
• pp.695-705
• /
• 2019

The level of psychological damage caused by verbal abuse among cyberbully victims is very serious. It is going to introduce a system that determines the level of sanctions against chatting in real time using the automatic prohibited words filtering based on artificial neural network. In this paper, we propose a keyword filtering method that detects the modified prohibited words and determines whether the corresponding chat should be sanctioned in real time, and a real-time chatting screening system using it. The accuracy of filtering through machine learning was improved by processing data in advance through coding techniques that express consonants and vowels of similar pronunciation at close distances. After comparing and analyzing Mahalanobis-based clustering algorithms and artificial neural network-based algorithms, algorithms that utilize artificial neural networks showed high performance. If it is applied to Internet chatting, comments or online games, it is expected that it will be able to filter more effectively than the existing filtering method and that this will ease communication inconvenience due to existing indiscriminate filtering methods.

• International Journal of Computer Science & Network Security
• /
• v.21 no.6
• /
• pp.137-142
• /
• 2021

Machine-learning systems have proven their worth in various industries, including healthcare and banking, by assisting in the extraction of valuable inferences. Information in these crucial sectors is traditionally stored in databases distributed across multiple environments, making accessing and extracting data from them a tough job. To this issue, we must add that these data sources contain sensitive information, implying that the data cannot be shared outside of the head. Using cryptographic techniques, Privacy-Preserving Machine Learning (PPML) helps solve this challenge, enabling information discovery while maintaining data privacy. In this paper, we talk about how to keep your data mining private. Because Data mining has a wide variety of uses, including business intelligence, medical diagnostic systems, image processing, web search, and scientific discoveries, and we discuss privacy-preserving in deep learning because deep learning (DL) exhibits exceptional exactitude in picture detection, Speech recognition, and natural language processing recognition as when compared to other fields of machine learning so that it detects the existence of any error that may occur to the data or access to systems and add data by unauthorized persons.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.45-52
• /
• 2022

With the development of artificial intelligence analysis methods, especially machine learning, various fields are widely expanding their application ranges. However, in the case of classical music, there still remain some difficulties in applying machine learning techniques. Genre classification or music recommendation systems generated by deep learning algorithms are actively used in general music, but not in classical music. In this paper, we attempted to classify opera among classical music. To this end, an experiment was conducted to determine which criteria are most suitable among, composer, period of composition, and emotional atmosphere, which are the basic features of music. To generate emotional labels, we adopted zero-shot classification with four basic emotions, 'happiness', 'sadness', 'anger', and 'fear.' After embedding the opera libretto with the doc2vec processing model, the optimal number of clusters is computed based on the result of the elbow method. Decided four centroids are then adopted in k-means clustering to classify unsupervised libretto datasets. We were able to get optimized clustering based on the result of adjusted rand index scores. With these results, we compared them with notated variables of music. As a result, it was confirmed that the four clusterings calculated by machine after training were most similar to the grouping result by period. Additionally, we were able to verify that the emotional similarity between composer and period did not appear significantly. At the end of the study, by knowing the period is the right criteria, we hope that it makes easier for music listeners to find music that suits their tastes.

• 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.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.5
• /
• pp.203-210
• /
• 2022

As more and more research and companies use health care data, efforts are being made to vitalize health care data worldwide. However, the system and format used by each institution is different. Therefore, this research established a basic model to classify text data onto multiple institutions according to the type of the future by establishing a basic model to classify the types of medical records of the EEG Report. For EEG Report classification, four deep learning-based algorithms were compared. As a result of the experiment, the ANN model trained by vectorizing with One-Hot Encoding showed the highest performance with an accuracy of 71%.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.73-79
• /
• 2021

Recently, in the field of computer animation, a method for generating motion using deep learning has been studied away from conventional finite-state machines or graph-based methods. The expressiveness of the network required for learning motions is more influenced by the diversity of motion contained in it than by the simple length of motion to be learned. This study aims to find an efficient network structure when the types of motions to be learned are diverse. In this paper, we train and compare three types of networks: basic fully-connected structure, mixture of experts structure that uses multiple fully-connected layers in parallel, recurrent neural network which is widely used to deal with seq2seq, and transformer structure used for sequence-type data processing in the natural language processing field.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.93-100
• /
• 2022

Keyword-oriented search methods are mainly used as data search methods, but this is not suitable as a search method in the legal field where professional terms are widely used. In response, this paper proposes an effective data search method in the legal field. We describe embedding methods optimized for determining similarities between sentences in the field of natural language processing of legal domains. After embedding legal sentences based on keywords using TF-IDF or semantic embedding using Universal Sentence Encoder, we propose an optimal way to search for data by combining BERT models to check similarities between sentences in the legal field.

• The KIPS Transactions:PartD
• /
• v.18D no.1
• /
• pp.67-80
• /
• 2011

On an automated business document processing system maintaining financial data, errors on query based retrieval of numbers are critical to overall performance and usability of the system. Automatic spelling correction methods have been emerged and have played important role in development of information retrieval system. However scope of the methods was limited to the symbols, for example alphabetic letter strings, which can be reserved in the form of trainable templates or custom dictionary. On the other hand, numbers, a sequence of digits, are not the objects that can be reserved into a dictionary but a pure markov sequence. In this paper we proposed a new OCR model for spelling correction for numbers using the multiple streams and the context based correction on top of probabilistic information retrieval framework. We implemented the proposed error correction model as a sub-module and integrated into an existing automated invoice document processing system. We also presented the comparative test results that indicated significant enhancement of overall precision of the system by our model.