• Journal of the Korea Society of Computer and Information
• /
• v.29 no.5
• /
• pp.177-187
• /
• 2024

177-Existing music recommendation systems do not sufficiently consider the discrepancy between the intended emotions conveyed by song lyrics and the actual emotions felt by users. In this study, we generate topic vectors for lyrics and user comments using the LDA model, and construct a user preference model by combining user behavior trajectories reflecting time decay effects and playback frequency, along with statistical characteristics. Empirical analysis shows that our proposed model recommends music with higher accuracy compared to existing models that rely solely on lyrics. This research presents a novel methodology for improving personalized music recommendation systems by integrating emotion recognition and user behavior analysis.

• Journal of the Korean Society for information Management
• /
• v.31 no.1
• /
• pp.163-187
• /
• 2014

The purpose of this study is to explain information usage behavior of researchers in the field of ocean science and technology. The study mainly collected primary data for advancement of special library services as well as establishment of personalized information services based on personal characteristics such as age, education level, and area of research. The data collection was conducted for two weeks during January 2014, through a web survey to 348 researchers in national ocean research institutions in South Korea. Total of 115 researchers replied. The analysis showed that the most preferred type of information medium was a scholarly journal. Researchers used more foreign published journals compared to Korean ones, while favoring digital formats rather than printed ones. The top channels for information collection were 'web search' and 'affiliated libraries.' Most pointed out difficulties of data collection were 'lack of variety of digital resources in affiliated libraries' and 'reluctance to use charged information.' Key elements for satisfactory user experience were ranked in the order of 'digital library system,' 'library staff,' and 'library collection' and so on;which proves the close relationship between library service and information usage service satisfaction. The result of an assessment for demands in special libraries showed that 'personalized information search service,' 'project support service,' and 'research direction analysis service' should be implemented in the future.

• Journal of KIISE:Software and Applications
• /
• v.31 no.4
• /
• pp.467-477
• /
• 2004

While recommender systems were used by a few E-commerce sites former days, they are now becoming serious business tools that are re-shaping the world of I-commerce. And collaborative filtering has been a very successful recommendation technique in both research and practice. But there are two problems in personalized recommender systems, it is First-Rating problem and Sparsity problem. In this paper, we solve these problems using the associative relation clustering and “Lift” of association rules. We produce “Lift” between items using user's rating data. And we apply Threshold by -cut to the association between items. To make an efficiency of associative relation cluster higher, we use not only the existing Hypergraph Clique Clustering algorithm but also the suggested Split Cluster method. If the cluster is completed, we calculate a similarity iten in each inner cluster. And the index is saved in the database for the fast access. We apply the creating index to predict the preference for new items. To estimate the Performance, the suggested method is compared with existing collaborative filtering techniques. As a result, the proposed method is efficient for improving the accuracy of prediction through solving problems of existing collaborative filtering techniques.

• Journal of Broadcast Engineering
• /
• v.9 no.4 s.25
• /
• pp.305-321
• /
• 2004

With the advent of the digital broadcasting, the audiences can access a large number of TV programs and their information through the multiple channels on various media devices. The access to a large number of TV programs can support a user for many chances with which he/she can sort and select the best one of them. However, the information overload on the user inevitably requires much effort with a lot of patience for finding his/her favorite programs. Therefore, it is useful to provide the persona1ized broadcasting service which assists the user to automatically find his/her favorite programs. As the growing requirements of the TV personalization, we introduce our automatic user preference learning algorithm which 1) analyzes a user's usage history on TV program contents: 2) extracts the user's watching pattern depending on a specific time and day and shows our automatic TV program recommendation system using MPEG-7 MDS (Multimedia Description Scheme: ISO/IEC 15938-5) and 3) automatically calculates the user's preference. For our experimental results, we have used TV audiences' watching history with the ages, genders and viewing times obtained from AC Nielson Korea. From our experimental results, we observed that our proposed algorithm of the automatic user preference learning algorithm based on the Bayesian network can effectively learn the user's preferences accordingly during the course of TV watching periods.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.89-103
• /
• 2023

Obstructive sleep apnea (OSA) is one of the most prevalent sleep disorders that can lead to serious consequences, including hypertension and/or cardiovascular diseases, if not treated promptly. Continuous positive airway pressure (CPAP) is widely recognized as the most effective treatment for OSA, which needs the proper titration of airway pressure to achieve the most effective treatment results. However, the process of CPAP titration can be time-consuming and cumbersome. There is a growing importance in predicting personalized CPAP pressure before CPAP treatment. The primary objective of this study was to optimize the CPAP titration process for obstructive sleep apnea patients through EEG feature engineering with machine learning techniques. We aimed to identify and utilize the most critical EEG features to forecast key OSA predictive indicators, ultimately facilitating more precise and personalized CPAP treatment strategies. Here, we analyzed 126 OSA patients' PSG datasets before and after the CPAP treatment. We extracted 29 EEG features to predict the features that have high importance on the OSA prediction index which are AHI and SpO2 by applying the Shapley Additive exPlanation (SHAP) method. Through extracted EEG features, we confirmed the six EEG features that had high importance in predicting AHI and SpO2 using XGBoost, Support Vector Machine regression, and Random Forest Regression. By utilizing the predictive capabilities of EEG-derived features for AHI and SpO2, we can better understand and evaluate the condition of patients undergoing CPAP treatment. The ability to predict these key indicators accurately provides more immediate insight into the patient's sleep quality and potential disturbances. This not only ensures the efficiency of the diagnostic process but also provides more tailored and effective treatment approach. Consequently, the integration of EEG analysis into the sleep study protocol has the potential to revolutionize sleep diagnostics, offering a time-saving, and ultimately more effective evaluation for patients with sleep-related disorders.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• The Journal of the Korea Contents Association
• /
• v.8 no.12
• /
• pp.20-27
• /
• 2008

Hospitals today use independent systems for each department and job such as Hospital Information Sytem(HIS), Picture Archiving Communications System(PACS), Ordering Communication System(OCS), Electronic Medical Record(EMR), Enterprise Resource Planning(ERP), etc and each system employs its own DB. So, it is impossible to integrate information within the institution and difficult to keep transparency and consistency of data. I in this study offered a data integration environment through flexible management linked with other systems, and by doing that, designed a medical CRM frame which offers the optimum service the customer wants at the optimum time. I designed 4 of medical CRM frame: customer relationship management, public relations/marketing, service management, and statistics/analysis by the customer relationship management process standardization and aimed to offer tailored mobile contents according to customer's characters and health situation on the basis of customer's data by securing mobile medical contents for personalized medical information service.

• 한국경영정보학회:학술대회논문집
• /
• 2008.06a
• /
• pp.1088-1095
• /
• 2008

The outpaced growth of online channel sales over the traditional retail sales is a result from superior shopping convenience that online stores offer to their customers. One major source of online shopping convenience is a personalized store that reduces customer's shopping time. personalization of an online store is accomplished by using various in-store shopping behavior data that the Internet and Web Technology provides. Brick-and-mortar retailers have not been able to make this type of data available for their stores until now. However, RFID technology has now opened a new possibility to personalization of traditional retail stores. In this paper, we propose BRIMPS (BRIck-and-Mortar Personalization System) as a system that brick-and-mortar retailers may use to personalize their business and become more competitive against online retailers.

• Journal of Intelligence and Information Systems
• /
• v.11 no.1
• /
• pp.107-121
• /
• 2005

Recently, many researches on recommendation systems and collaborative filtering have been proceeding in both research and practice. However, although product items may have multi-valued attributes, previous studies did not reflect the multi-valued attributes. To overcome this limitation, this paper proposes new methodology for recommendation system. The proposed methodology uses multi-valued attributes based on clustering technique for items and applies the collaborative filtering to provide accurate recommendations. In the proposed methodology, both user clustering-based CBR and item attribute clustering-based CBR technique have been applied to the collaborative filtering to consider correlation of item to item as well as correlation of user to user. By using multi-valued attribute-based clustering technique for items, characteristics of items are identified clearly. Extensive experiments have been performed with MovieLens data to validate the proposed methodology. The results of the experiment show that the proposed methodology outperforms the benchmarked methodologies: Case Based Reasoning Collaborative Filtering (CBR_CF) and User Clustering Case Based Reasoning Collaborative Filtering (UC_CBR_CF).

• Journal of Oriental Neuropsychiatry
• /
• v.18 no.1
• /
• pp.37-61
• /
• 2007

Objective : By examining EEG status in Korean Traditional Medicine (KTM) from the viewpoint of 'form-qi theory(形氣論)', We wish to prepare for the fundamentals of applicability of KTM diagnoses to EEG. In addition, through reinterpretation of existing Western Medicine reports from the viewpoint of KTM, We tried to find out interrelationship between them. Method : In this paper, a methodology applicable to KTM diagnoses of EEG is presented from the EEG features in waveform characteristics, personalized diversity, and cognitive activity reflection. Results : Frequency bands are assigned to corresponding one of the eight trigrams in terms of yin/yang balance, which is analogous with EEG spectrum analysis mostly used in EEG quantification. The amplitude ratio of each EEG for each frequency band gives meaningful index numbers which can be used in EEG data interpretation, and every index number is named after the sixty four hexagrams. These approaches are adopted through both '4-band classification system and '6-band classification system', and applied to pre-existing reported EEG data obtained from normal adults. These analyses show that changes and distribution pattern in the index numbers are observed as a whole on both left-right line and front-back line connecting EEG measurement cephalic electrodes. And differences in distribution pattern of three index numbers deduced from '6-band classification system' are discussed according to constitution. Conclusion : The index numbers introduced here, which are the spectral power ratio for each EEG, are based on KTM yin/yang balance. These index numbers vary according to cephalic location, so its application in terms of traditional meridian theory is strongly expected. The index number distribution also shows different patterns according to constitution.