• The Journal of the Acoustical Society of Korea
• /
• v.35 no.2
• /
• pp.143-148
• /
• 2016

Deep neural network that effectively capture the characteristics of data has been widely used in various applications. However, the amount of sound database is often insufficient for learning the deep neural network properly, so resulting in overfitting problems. In this paper, we propose a transfer learning framework that can effectively train the deep neural network even with insufficient sound event data by employing rich speech or music data. A series of experimental results verify that proposed method performs significantly better than the baseline deep neural network that was trained only with small sound event data.

• The KIPS Transactions:PartD
• /
• v.14D no.7
• /
• pp.727-732
• /
• 2007

Most of previous work on indexing and searching time series focused on the similarity matching and retrieval of one-attribute time series. However, multimedia databases such as music, video need to handle the similarity search in multi-attribute time series. The limitation of the current similarity models for multi-attribute sequences is that there is no consideration for attributes' sequences. The multi-attribute sequences are composed of several attributes' sequences. Since the users may want to find the similar patterns considering attributes's sequences, it is more appropriate to consider the similarity between two multi-attribute sequences in the viewpoint of attributes' sequences. In this paper, we propose the similarity search method based on attributes's sequences in multi-attribute time series databases. The proposed method can efficiently reduce the search space and guarantees no false dismissals. In addition, we give preliminary experimental results to show the effectiveness of the proposed method.

• Journal of Korean Clinical Health Science
• /
• v.10 no.2
• /
• pp.1600-1606
• /
• 2022

Objective: This study was to compares and analyzes programs applied to improve cognitive function in patients with mild cognitive impairment and early dementia in the community to find out their effectiveness. Methods: In this study, 12 papers were finalized by searching for "elderly", "cognitive", "community", and "program" using the database of the Research Information System (RISS), National Assembly Library, and Korean Studies Information (KISS). Results: Programs for cognitive function were in the order of cognitive stimulation program, arts and crafts, and exercise program. In the program, rather than applying the cognitive stimulation program alone, the program was operated by combining leisure or exercise, music, art, and handicraft. The time was shown to be 30 minutes. The most frequently used evaluation tool was MMSE, followed by GDS and BBS. By cognitive domain, cognitive stimulation program and memory, satisfaction in psychology, and balance ability in exercise were evaluated the most. In the cognitive area, various cognitive stimulation areas were included, and in the exercise area, basic exercise, muscle strength exercise, joint exercise, and balance exercise were applied. Conclusion: Therefore, developing a program to improve cognitive function for mild cognitive impairment, it will be possible to prepare guidelines to establish and development.

• Journal of Korea Society of Industrial Information Systems
• /
• v.15 no.5
• /
• pp.89-95
• /
• 2010

Currently memorandum have been a method to manage information easily by short writing. In particular, a electronic memorandum system has been efficiently used for business purpose, which is available in a computer widely used in our daily life. Considering the smart business environment, we propose a multi-functional electronic memorandum system in this paper, which is helpful to manage information intelligently in the smart business environment. The proposed system maintains the contents of memorandum in a database structure, so it is available without any restrictions in time and place. In addition, it also has additional functions of music playing, capturing working screens, and scheduling. The functions help for the proposed system to be widely used in the smart business environment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.6
• /
• pp.391-404
• /
• 2018

The purpose of this study was to determine the status of interventional studies to prevent falling in elderly with dementia and to determine the contents and effectiveness of intervention programs to prevent falling. Existing reports published between January 1, 2000 and December 31, 2016 were searched electronically using the RISS, National Library, KISS, PubMed, and CINAHL database with the keywords dementia, Alzheimer's or Alzheimer's disease, falling, and prevention of falling. After checking the original sources of the articles, 13 articles were included in the review. Therapeutic interventions used in the articles included exercise therapy (8, 61.5%), physiotherapy and occupational therapy (2, 15.4%), complementary therapies (2, 15.4%), and music therapy (1, 7.7%). As a result of the qualitative evaluation of the papers using a checklist of the Scottish Intercollegiate Guideline Network, two studies scored 9 out of 10 points, five studies scored 8 out of 10, and six studies scored 7 out of 10. Intervention sessions were conducted for 55 minutes, on average, for a total of 37 sessions. This study found that exercise, music therapy, physical and occupational therapy, and rhythmic motion therapy were effective in preventing falling in the elderly with dementia. In the future, these findings are expected to be used as a basis for the development of a preventive intervention program for nurses in a clinical setting.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.253-266
• /
• 2018

This paper proposes a methodology applying sequence tagging methodology to improve the performance of NER(Named Entity Recognition) used in QA system. In order to retrieve the correct answers stored in the database, it is necessary to switch the user's query into a language of the database such as SQL(Structured Query Language). Then, the computer can recognize the language of the user. This is the process of identifying the class or data name contained in the database. The method of retrieving the words contained in the query in the existing database and recognizing the object does not identify the homophone and the word phrases because it does not consider the context of the user's query. If there are multiple search results, all of them are returned as a result, so there can be many interpretations on the query and the time complexity for the calculation becomes large. To overcome these, this study aims to solve this problem by reflecting the contextual meaning of the query using Bidirectional LSTM-CRF. Also we tried to solve the disadvantages of the neural network model which can't identify the untrained words by using ontology knowledge based feature. Experiments were conducted on the ontology knowledge base of music domain and the performance was evaluated. In order to accurately evaluate the performance of the L-Bidirectional LSTM-CRF proposed in this study, we experimented with converting the words included in the learned query into untrained words in order to test whether the words were included in the database but correctly identified the untrained words. As a result, it was possible to recognize objects considering the context and can recognize the untrained words without re-training the L-Bidirectional LSTM-CRF mode, and it is confirmed that the performance of the object recognition as a whole is improved.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.8 no.6
• /
• pp.847-854
• /
• 2013

This paper implements a smartphone application for sound recording and player of mobile learning. Due to its ubiquitous nature, smartphones could be used anytime anywhere, and because they combine an audio and a microphone, the application for sound recording and player that this paper suggests can be easily and cost effectively developed without additional infrastructure. This paper also explains a technique which processes data of music lyrics. The technique is built on a database technology by using SQLite, a DBMS combined in a platform of android. Thus, as long as the smartphone application for sound recording and player is developed and the mobile phone has sound source files, learners could record their own voices to the sound. Therefore, we expect the learners without additional infrastructure to enable mobile learning.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.611-618
• /
• 2003

In this paper, we describe a fuzzy inference approach for detecting and classifying shot transitions in video sequences. Our approach basically extends FAM (Fuzzy Associative Memory) to detect and classify shot transitions, including cuts, fades and dissolves. We consider a set of feature values that characterize differences between two consecutive frames as input fuzzy sets, and the types of shot transitions as output fuzzy sets. The inference system proposed in this paper is mainly composed of a learning phase and an inferring phase. In the learning phase, the system initializes its basic structure by determining fuzzy membership functions and constructs fuzzy rules. In the inferring phase, the system conducts actual inference using the constructed fuzzy rules. In order to verify the performance of the proposed shot transition detection method experiments have been carried out with a video database that includes news, movies, advertisements, documentaries and music videos.

• Journal of KIISE:Computing Practices and Letters
• /
• v.12 no.1
• /
• pp.31-42
• /
• 2006

Context-awareness is a technology to facilitate information acquisition and execution by supporting interoperability between users and devices based on users' context. It is one of the most important technologies in ubiquitous computing. In this paper, we propose a middleware and a context server for dealing with context-awareness in ubiquitous Computing and implement an application system using them. The middleware proposed in our work plays an important role in recognizing a moving node with mobility by using a Bluetooth wireless communication technology as well as in executing an appropriate execution module according to the context acquired from a context server. In addition, the proposed context server functions as a manager that efficiently stores into a database server context information, such as user's current status, physical environment, and resources of a computing system. Finally, our application system implemented in our work one which provides a music playing service based on context information, and it verifies the usefulness of both the middleware and the context server developed in our work.

• Journal of KIISE:Computing Practices and Letters
• /
• v.15 no.8
• /
• pp.534-546
• /
• 2009

Query by humming is an effective and intuitive querying mechanism when a user wants to find a song without knowing lyrics. The query by humming system takes a user-hummed melody as input, compares it with melodies in a music database, and returns top-k similar melodies to the input. In this paper, we propose a novel algebra for query by humming, and design and implement a real query by humming system called HummingBase by exploiting the algebra. By analyzing existing similarity search techniques, we derive 10 core operators for the algebra. By using the well-defined algebra, we can easily implement such a system in a extensible and modular way. With two case studies, we show that the proposed algebra can easily represent the query processing processes of existing query-by-humming systems.