• Journal of Information Processing Systems
• /
• v.20 no.3
• /
• pp.360-374
• /
• 2024

A personalized course recommendation algorithm based on deep learning in an online education cloud platform is proposed to address the challenges associated with effective information extraction and insufficient feature extraction. First, the user potential preferences are obtained through the course summary, course review information, user course history, and other data. Second, by embedding, the word vector is turned into a low-dimensional and dense real-valued vector, which is then fed into the compressed interaction network-deep neural network model. Finally, considering that learners and different interactive courses play different roles in the final recommendation and prediction results, an attention mechanism is introduced. The accuracy, recall rate, and F1 value of the proposed method are 0.851, 0.856, and 0.853, respectively, when the length of the recommendation list K is 35. Consequently, the proposed strategy outperforms the comparison model in terms of recommending customized course resources.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.12
• /
• pp.2291-2297
• /
• 2017

This paper describe to extract speech measure algorithm for evaluating a speech database, and presents generating method of a speech quality measure using DNN(Deep Neural Network). In our previous study, to produce an effective speech quality measure, we propose a combination of various speech measures which are highly correlated with WER(Word Error Rate). The new combination of various types of speech quality measures in this study is more effective to predict the speech recognition performance compared to each speech measure alone. In this paper, we describe the method of extracting measure using DNN, and we change one of the combined measure from GMM(Gaussican Mixture Model) score used in the previous study to DNN score. The combination with DNN score shows a higher correlation with WER compared to the combination with GMM score.

• Journal of Korean Medical classics
• /
• v.32 no.2
• /
• pp.17-31
• /
• 2019

Objectives : Understanding the Ten Stems and Twelve Branches is necessary to grasp the laws of change in Heaven and Earth. Methods : Based on relevant contents in East Asian classics, the Yin Yang, Sibling Wuxing, Husband-Wife Wuxing combinations as well as Mutual Collision and Zangfu combination were examined. Results & Conclusion : Yin Yang combination of the Ten Stems are divided according to odd/evenness. The Sibling Wuxing combination is categorized according to one life cycle of vegetation, resulting in Jia Yi Wood, Bing Ding Fire, Wu Ji Earth, Geng Xin Metal, Ren Gui Water. The Husband-Wife Wuxing combination of the Ten Stems are Jia Ji Earth, Yi Geng Metal, Bing Xin Water, Ding Ren Wood, Wu Gui Fire, which corresponds to the principles of the Duihuazuoyong Theory. Within the Husband-Wife Wuxing combination lies three principles which are Yin Yang combination, Mutual Restraining combination, and the Yang Stem restraining the Yin Stem. The Mutual Collision of the Ten Stems are Jia and Geng, Yi and Xin, Ren and Bing, Gui and Ding against each other. In matching Zangfu to the Ten Stems, Jia matches with Gallbladder, Yi matches with Liver; Bing matches with Small Intestine, Ding matches with Heart; Wu matches with Stomach, Ji matches with Spleen; Geng matches with Large Intestine, Xin matches with Lung; Ren matches with Bladder, Gui matches with Kidney. : When the adjacent vectors are extracted, the count-based word embedding method derives the main herbs that are frequently used in conjunction with each other. On the other hand, in the prediction-based word embedding method, the synonyms of the herbs were derived.

• Asia Marketing Journal
• /
• v.13 no.3
• /
• pp.209-231
• /
• 2011

Internet is having strong impact on the consumer's decision making process. Information search has been done actively through internet today. The online reviews can be crucial information cue to evaluate the alternarive products. The online WOM(Word-Of-Mouth) effect depends on the characteristics of information sender, receiver, and WOM. This study is to examine the influence of the online word of mouth on the consumer purchase intention and the moderating role of product involvement, consumer regulatory focus and self-efficacy. Positive customer reviews on the products influence the purchase intention positively and negative customer reviews influence it negatively. Moderating role of involvement in the causal relation between the valence of online reviews and purchase intention is tested. In case of positive WOM, it is predicted that purchase intention for high involvement products is higher than that of low involvement. In case of negative WOM, purchase intention for high involvement product is lower than that of low involvement product. And this study invetigate the moderating role of regulatory focus. In case of positive WOM, it is predicted that promotion focus oriented consumers have higher purchase intention than prevention focus oriented consumers. In case of negative WOM, prediction is that prevention focus oriented consumers have lower purchase intention than promotion focus oriented consumers. Then we examine the moderating role of self efficacy in the causal relation between the valence of online reviews and purchase intention. In case of positive WOM, it is predicted that consumers with low self efficacy have higher purchase intention than consumers with high self efficacy. In case of negative WOM, it is predicted that consumers with low self efficacy have lower purchase intention than consumers with high self efficacy. Emprical results support our prediction and four hypotheses derived from our conceptual framework are all accepted. This study suggest that the level of product involvement, consumer regulatory focus and the level of self-efficacy influence the consumer responses of the valence of online reviews. Therefore marketers need to manage online reviews based on the level of product involvement, regulatory focus orientation and the level of self-efficacy of target consumers.

• Information Systems Review
• /
• v.24 no.1
• /
• pp.21-37
• /
• 2022

Drug repositioning, one of the methods of developing new drugs, is a useful way to discover new indications by allowing drugs that have already been approved for use in people to be used for other purposes. Recently, with the development of machine learning technology, the case of analyzing vast amounts of biological information and using it to develop new drugs is increasing. The use of machine learning technology to drug repositioning will help quickly find effective treatments. Currently, the world is having a difficult time due to a new disease caused by coronavirus (COVID-19), a severe acute respiratory syndrome. Drug repositioning that repurposes drugsthat have already been clinically approved could be an alternative to therapeutics to treat COVID-19 patients. This study intends to examine research trends in the field of drug repositioning using machine learning techniques. In Pub Med, a total of 4,821 papers were collected with the keyword 'Drug Repositioning'using the web scraping technique. After data preprocessing, frequency analysis, LDA-based topic modeling, random forest classification analysis, and prediction performance evaluation were performed on 4,419 papers. Associated words were analyzed based on the Word2vec model, and after reducing the PCA dimension, K-Means clustered to generate labels, and then the structured organization of the literature was visualized using the t-SNE algorithm. Hierarchical clustering was applied to the LDA results and visualized as a heat map. This study identified the research topics related to drug repositioning, and presented a method to derive and visualize meaningful topics from a large amount of literature using a machine learning algorithm. It is expected that it will help to be used as basic data for establishing research or development strategies in the field of drug repositioning in the future.

• The Journal of the Acoustical Society of Korea
• /
• v.15 no.5
• /
• pp.38-43
• /
• 1996

This paper compares the recognition performances of feature vectors known to be robust to the environmental noise. And, the speech subtraction technique is combined with the noise robust feature to get more performance enhancement. The experiments using SMC(Short time Modified Coherence) analysis, root cepstral analysis, LDA(Linear Discriminant Analysis), PLP(Perceptual Linear Prediction), RASTA(RelAtive SpecTrAl) processing are carried out. An isolated word recognition system is composed using semi-continuous HMM. Noisy environment experiments usign two types of noises:exhibition hall, computer room are carried out at 0, 10, 20dB SNRs. The experimental result shows that SMC and root based mel cepstrum(root_mel cepstrum) show 9.86% and 12.68% recognition enhancement at 10dB in compare to the LPCC(Linear Prediction Cepstral Coefficient). And when combined with spectral subtraction, mel cepstrum and root_mel cepstrum show 16.7% and 8.4% enhanced recognition rate of 94.91% and 94.28% at 10dB.

• Journal of the Korea Convergence Society
• /
• v.12 no.10
• /
• pp.365-372
• /
• 2021

The purpose of this study was to examine the statements characteristics of the pressure ulcer nursing record by natural langage processing and assess the prediction accuracy for each pressure ulcer stage. Nursing records related to pressure ulcer were analyzed using descriptive statistics, and word cloud generators (http://wordcloud.kr) were used to examine the characteristics of words in the pressure ulcer prevention nursing records. The accuracy ratio for the pressure ulcer stage was calculated using deep learning. As a result of the study, the second stage and the deep tissue injury suspected were 23.1% and 23.0%, respectively, and the most frequent key words were erythema, blisters, bark, area, and size. The stages with high prediction accuracy were in the order of stage 0, deep tissue injury suspected, and stage 2. These results suggest that it can be developed as a clinical decision support system available to practice for nurses at the pressure ulcer prevention care.

• Journal of the Korean Society for Precision Engineering
• /
• v.32 no.4
• /
• pp.353-358
• /
• 2015

Energy consumption reduction has become an important key word in manufacturing that can be achieved through the efficient and optimal use of raw materials and natural resources, and minimization of the harmful effects on nature or human society. The successful implementation of this concept can only be possible by considering a product's entire life cycle and even its disposal from the early design stage. To accomplish this idea with milling, minimum quantity lubrication (MQL) strategies and cutting conditions are analyzed through process modeling and experiments. In this study, a model to predict the cutting energy in the milling process is used to find the cutting conditions, which minimize the cutting energy through a Kriging meta-modeling process. The MQL scheme is developed first to reduce the amount of cutting oil and costs used in the cutting process, which is then employed for the entire modeling and experiments.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.17 no.6
• /
• pp.1336-1341
• /
• 2013

Through reviewing the characteristics of digital TVs, which have emerged in CES since 2005, in the view of technology growth and substitution curves, this paper is to provide a prediction on the next generation's multi-media on smart environment. As a result, digital TV has been developed on the flow of its technology growth curve from the early version in 2005 to smart digital TV in 2013, which emphasizes the key word "connected", and it has already come to the market puberty.

• Journal of Distribution Science
• /
• v.15 no.9
• /
• pp.85-93
• /
• 2017

Purpose - The volume and valence of online word-of-mouth(eWOM) have become an important part of the retailer's market success for a wide range of products. This study aims to investigate how the growth of eWOM has generated the product's final financial outcomes in the introductory period influences. Research design, data, and methodology - This study uses weekly box office performance for 117 movies released in the South Korea from July 2015 to June 2016 using Korean Film Council(KOFIC) database. 292,371 posted online review messages were collected from NAVER movie review bulletin board. Using regression analysis, we test whether eWOM incurred during the opening week is valuable to explain the last of box office performance. Three major eWOM metrics were considered after controlling for the major distributional factors. Results - Results support that major eWOM variables play a significant role in box-office outcome prediction. Especially, the growth rate of the positive eWOM volume has a significant effect on the growth potential in sales. Conclusions - The findings highlight that the speed of eWOM growth has an informational value to understand the market reaction to a new product beyond valence and volume. Movie distributors need to take positive online eWOM growth into account to make optimal screen allocation decisions after release.