• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.2162-2179
• /
• 2019

The performance of text classification is highly related to the feature selection methods. Usually, two tasks are performed when a feature selection method is applied to construct a feature set; 1) assign score to each feature and 2) select the top-N features. The selection of top-N features in the existing filter-based feature selection methods is biased by their discriminative power and the empirical process which is followed to determine the value of N. In order to improve the text classification performance by presenting a more illustrative feature set, we present an approach via a potent representation learning technique, namely DBN (Deep Belief Network). This algorithm learns via the semantic illustration of documents and uses feature vectors for their formulation. The nodes, iteration, and a number of hidden layers are the main parameters of DBN, which can tune to improve the classifier's performance. The results of experiments indicate the effectiveness of the proposed method to increase the classification performance and aid developers to make effective decisions in certain domains.

• Journal of Korean Biological Nursing Science
• /
• v.23 no.3
• /
• pp.170-179
• /
• 2021

Purpose: The aim of this study was to identify core keywords and topic groups in the 'Diabetes mellitus and mobile applications' field of research for better understanding research trends in the past 20 years. Methods: This study was a text-mining and topic modeling study including four steps such as 'collecting abstracts', 'extracting and cleaning semantic morphemes', 'building a co-occurrence matrix', and 'analyzing network features and clustering topic groups'. Results: A total of 789 papers published between 2002 and 2021 were found in databases (Springer). Among them, 435 words were extracted from 118 articles selected according to the conditions: 'analyzed by text network analysis and topic modeling'. The core keywords were 'self-management', 'intervention', 'health', 'support', 'technique' and 'system'. Through the topic modeling analysis, four themes were derived: 'intervention', 'blood glucose level control', 'self-management' and 'mobile health'. The main topic of this study was 'self-management'. Conclusion: While more recent work has investigated mobile applications, the highest feature was related to self-management in the diabetes care and prevention. Nursing interventions utilizing mobile application are expected to not only effective and powerful glycemic control and self-management tools, but can be also used for patient-driven lifestyle modification.

• Journal of Biomedical Engineering Research
• /
• v.43 no.2
• /
• pp.109-115
• /
• 2022

Purpose: Medical records classification using vectorization techniques plays an important role in natural language processing. The purpose of this study was to investigate proper vectorization techniques for electronic medical records classification. Material and methods: 403 electronic medical documents were extracted retrospectively and classified using the cosine similarity calculated by Scikit-learn (Python module for machine learning) in Jupyter Notebook. Vectors for medical documents were produced by three different vectorization techniques (TF-IDF, latent sematic analysis and Word2Vec) and the classification precisions for three vectorization techniques were evaluated. The Kruskal-Wallis test was used to determine if there was a significant difference among three vectorization techniques. Results: 403 medical documents were relevant to 41 different diseases and the average number of documents per diagnosis was 9.83 (standard deviation=3.46). The classification precisions for three vectorization techniques were 0.78 (TF-IDF), 0.87 (LSA) and 0.79 (Word2Vec). There was a statistically significant difference among three vectorization techniques. Conclusions: The results suggest that removing irrelevant information (LSA) is more efficient vectorization technique than modifying weights of vectorization models (TF-IDF, Word2Vec) for medical documents classification.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.535-548
• /
• 2022

Using a rich resource language to classify sentiments in a language with few resources is a popular subject of research in natural language processing. Burmese is a low-resource language. In light of the scarcity of labeled training data for sentiment classification in Burmese, in this study, we propose a method of transfer learning for sentiment analysis of a language that uses the feature transfer technique on sentiments in English. This method generates a cross-language word-embedding representation of Burmese vocabulary to map Burmese text to the semantic space of English text. A model to classify sentiments in English is then pre-trained using a convolutional neural network and an attention mechanism, where the network shares the model for sentiment analysis of English. The parameters of the network layer are used to learn the cross-language features of the sentiments, which are then transferred to the model to classify sentiments in Burmese. Finally, the model was tuned using the labeled Burmese data. The results of the experiments show that the proposed method can significantly improve the classification of sentiments in Burmese compared to a model trained using only a Burmese corpus.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.2
• /
• pp.49-57
• /
• 2010

This paper proposes a Korean document. categorization algorithm using Back Propagation Neural Network(BPNN) with Singular Value Decomposition(SVD). BPNN makes a network through its learning process and classifies documents using the network. The main difficulty in the application of BPNN to document categorization is high dimensionality of the feature space of the input documents. SVD projects the original high dimensional vector into low dimensional vector, makes the important associative relationship between terms and constructs the semantic vector space. The categorization algorithm is tested and compared on HKIB-20000/HKIB-40075 Korean Text Categorization Test Collections. Experimental results show that BPNN algorithm with SVD achieves high effectiveness for Korean document categorization.

• Women's Health Nursing
• /
• v.29 no.2
• /
• pp.128-136
• /
• 2023

Purpose: Topic modeling is a text mining technique that extracts concepts from textual data and uncovers semantic structures and potential knowledge frameworks within context. This study aimed to identify major keywords and network structures for each major topic to discern research trends in women's health nursing published in the Korean Journal of Women Health Nursing (KJWHN) using text network analysis and topic modeling. Methods: The study targeted papers with English abstracts among 373 articles published in KJWHN from January 2011 to December 2021. Text network analysis and topic modeling were employed, and the analysis consisted of five steps: (1) data collection, (2) word extraction and refinement, (3) extraction of keywords and creation of networks, (4) network centrality analysis and key topic selection, and (5) topic modeling. Results: Six major keywords, each corresponding to a topic, were extracted through topic modeling analysis: "gynecologic neoplasms," "menopausal health," "health behavior," "infertility," "women's health in transition," and "nursing education for women." Conclusion: The latent topics from the target studies primarily focused on the health of women across all age groups. Research related to women's health is evolving with changing times and warrants further progress in the future. Future research on women's health nursing should explore various topics that reflect changes in social trends, and research methods should be diversified accordingly.

• Journal of Information Processing Systems
• /
• v.19 no.3
• /
• pp.355-369
• /
• 2023

Since the widespread adoption of deep-learning and related distributed representation, there have been substantial advancements in part-of-speech (POS) tagging for many languages. When training word representations, morphology and shape are typically ignored, as these representations rely primarily on collecting syntactic and semantic aspects of words. However, for tasks like POS tagging, notably in morphologically rich and resource-limited language environments, the intra-word information is essential. In this study, we introduce a deep neural network (DNN) for POS tagging that learns character-level word representations and combines them with general word representations. Using the proposed approach and omitting hand-crafted features, we achieve 90.47%, 80.16%, and 79.32% accuracy on our own dataset for three morphologically rich languages: Uyghur, Uzbek, and Kyrgyz. The experimental results reveal that the presented character-based strategy greatly improves POS tagging performance for several morphologically rich languages (MRL) where character information is significant. Furthermore, when compared to the previously reported state-of-the-art POS tagging results for Turkish on the METU Turkish Treebank dataset, the proposed approach improved on the prior work slightly. As a result, the experimental results indicate that character-based representations outperform word-level representations for MRL performance. Our technique is also robust towards the-out-of-vocabulary issues and performs better on manually edited text.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1045-1055
• /
• 2007

Latent topic models are statistical models which automatically captures salient patterns or correlation among features underlying a data collection in a probabilistic way. They are gaining an increased popularity as an effective tool in the application of automatic semantic feature extraction from text corpus, multimedia data analysis including image data, and bioinformatics. Among the important issues for the effectiveness in the application of latent topic models to the massive data set is the efficient learning of the model. The paper proposes an accelerated learning technique for PLSA model, one of the popular latent topic models, by an incremental EM algorithm instead of conventional EM algorithm. The incremental EM algorithm can be characterized by the employment of a series of partial E-steps that are performed on the corresponding subsets of the entire data collection, unlike in the conventional EM algorithm where one batch E-step is done for the whole data set. By the replacement of a single batch E-M step with a series of partial E-steps and M-steps, the inference result for the previous data subset can be directly reflected to the next inference process, which can enhance the learning speed for the entire data set. The algorithm is advantageous also in that it is guaranteed to converge to a local maximum solution and can be easily implemented just with slight modification of the existing algorithm based on the conventional EM. We present the basic application of the incremental EM algorithm to the learning of PLSA and empirically evaluate the acceleration performance with several possible data partitioning methods for the practical application. The experimental results on a real-world news data set show that the proposed approach can accomplish a meaningful enhancement of the convergence rate in the learning of latent topic model. Additionally, we present an interesting result which supports a possible synergistic effect of the combination of incremental EM algorithm with parallel computing.

• Journal of KIISE:Software and Applications
• /
• v.29 no.10
• /
• pp.726-735
• /
• 2002

E-mail service has been a general method for communication as internet is widely used instead of post mails. Many companies have invested in e-mail advertisement as e-mail service is spread. E-mail advertisement has an advantage that it can consider personal characters. A lot of e-mail users have been given e-mails that they did not want to receive because their e-mail addresses were opened out to companies on internet. Therefore, they need junk mail checking systems and several e-mail service providers have supported junk mail filters. However, the junk mail filters can check the junk mail with constraint because they don't check the junk degree of mails by the contents of e-mail. This paper suggests a content-based junk mail checking model using fuzzy relational products. The process of the junk mail checking model using fuzzy relational products is as following: (1) analyzes semantic relation between junk words-base and e-mails, (2) checks the junk degree of the e-mail using the semantic relation, (3) checks the mails with SVJ(Standard Value of Junk) if those are junk mail or non-junk mail. The efficiency of the proposed technique is proved by comparing the junk degree of the e-mail and the number of junk mails that was checked by e-mail users and checked by the proposed junk mail checking model.

• Journal of KIISE:Databases
• /
• v.33 no.4
• /
• pp.372-383
• /
• 2006

Among the approaches to image database management, content-based image retrieval (CBIR) is viewed as having the best support for effective searching and browsing of large digital image libraries. Typical CBIR systems allow a user to provide a query image, from which low-level features are extracted and used to find 'similar' images in a database. However, there exists the semantic gap between human visual perception and low-level representations. An effective methodology for overcoming this semantic gap involves relevance feedback to perform feature re-weighting. Current approaches to feature re-weighting require the number of components for a feature representation to be the same for every image in consideration. Following this assumption, they map each component to an axis in the n-dimensional space, which we call the metric space; likewise the feature representation is stored in a fixed-length vector. However, with the emergence of features that do not have a fixed number of components in their representation, existing feature re-weighting approaches are invalidated. In this paper we propose a feature re-weighting technique that supports features regardless of whether or not they can be mapped into a metric space. Our approach analyses the feature distances calculated between the query image and the images in the database. Two-sided confidence intervals are used with the distances to obtain the information for feature re-weighting. There is no restriction on how the distances are calculated for each feature. This provides freedom for how feature representations are structured, i.e. there is no requirement for features to be represented in fixed-length vectors or metric space. Our experimental results show the effectiveness of our approach and in a comparison with other work, we can see how it outperforms previous work.