• Proceedings of KOSOMES biannual meeting
• /
• 2018.06a
• /
• pp.55-55
• /
• 2018

• Journal of Web Engineering
• /
• v.21 no.2
• /
• pp.497-522
• /
• 2021

Audio event classification refers to the detection and classification of non-verbal signals, such as dog and horn sounds included in audio data, by a computer. Recently, deep neural network technology has been applied to audio event classification, exhibiting higher performance when compared to existing models. Among them, a convolutional neural network (CNN)-based training method that receives audio in the form of a spectrogram, which is a two-dimensional image, has been widely used. However, audio event classification has poor performance on test data when it is recorded by a device (unknown device) different from that used to record training data (known device). This is because the frequency range emphasized is different for each device used during recording, and the shapes of the resulting spectrograms generated by known devices and those generated by unknown devices differ. In this study, to improve the performance of the event classification system, a CNN based on the log mel-spectrogram separation technique was applied to the event classification system, and the performance of unknown devices was evaluated. The system can classify 16 types of audio signals. It receives audio data at 0.4-s length, and measures the accuracy of test data generated from unknown devices with a model trained via training data generated from known devices. The experiment showed that the performance compared to the baseline exhibited a relative improvement of up to 37.33%, from 63.63% to 73.33% based on Google Pixel, and from 47.42% to 65.12% based on the LG V50.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.21 no.4
• /
• pp.67-80
• /
• 2010

The output and usage rate of audio-visual materials have sharply increased as the information industry advances and diverse archives became available. However, the awareness of the audio-visual archives are more of a separate record with collateral value. The organizations that hold these materials have very weak system of the various areas such as the categories and archiving methods. Moreover, the management system varies among the organizations, so the users face difficulty retrieving and utilizing the audio-visual materials. Thus, this study examined the feasibility of the synchronized management of audio-visual archives by comparing the descriptive elements of the audio-visual archives in internal key agencies. The study thereby examines the feasibility of the metadata element of the organizations and that of synchronized management to propose the effect of the use of management, retrieval and service of efficient AV materials. The study also proposes the improvement of descriptive element of metadata.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.357-360
• /
• 2011

On the matter in line with NCW(Network Centric Warfare) and information age, the military is on an efficient-expanding trend as sharing with status and information promptly through the various and complex exchange of messages and the phone communication between operators, using a highly efficient operating console. The recording devices that record an operational situation to plan a new operation through the mission analysis and result reviews after finishing military operation or training are developed and operated. Recording method is classified into two groups. one is the recording of display shots, another is the recording of an exchange of messages. This study proposes the new data-oriented recording method to reduce the readiness time of replay and the improvement scheme.

• Journal of Korean Academy of Nursing
• /
• v.33 no.6
• /
• pp.802-811
• /
• 2003

Purpose: The purpose of this study was to compare the nursing activities delineated by interview of nurses with those on nursing notes. Method: The participants of interview were 18 nurses working in medical and surgical units of a large hospital in Seoul. Each nurse was asked to choose one patient who demand most nursing care among her patients. The nurse was then interviewed to describe what her nursing activities for the patient was that day. The audio-taped interview was transcribed and the content was analyzed by researchers. Nursing notes of each nurses' patients were copied and the content analyzed by researchers. Finally, themes from the interview data and those from nursing notes were compared. Result: Activities related to emotional or psychological nursing, education for patient and families, and problem solving related to treatment or nursing procedure were most often omitted in nursing notes. Most of the documentation in nursing notes were related to physical condition of patients or physician's orders. Nurses described that they will do better recording if they were given less patient care responsibility, had better nursing knowledge, had better recording system, and received more training on nursing record. Conclusion: Nursing notes did not reflect nursing activities properly. Few independent nursing roles were documented in the nursing notes. Development of nursing education program and nursing record system is needed for improvement of nursing record.

• Economic and Environmental Geology
• /
• v.21 no.2
• /
• pp.185-191
• /
• 1988

A two channel seismic recorder suitable for long-term observation of microearthquakes is developed. The direct analogue recording on cassette tape is adopted in the recorder whose circuits of amplifier and mortor units of an audio cassette recorder are modified. The recorder provides contineous record of 10 days with DC 12V battery (100AH) and with standard cassette tape of 60 minute use. The binary coded time signals of date, hour, and minute are generated once a minute by the timing system and absolute time input using radio to measure the time drift is also possible. For the seismic signal processing, the analogue signals from audio cassette player pass A/D converter and digitized data are stored in personal computer. Then visual records can be obtained using computer graphic mode. Basic programs "ADCONVO" and "DRAWO" to accomplish A/D conversions, the creation of data files and visualization of signals were written. Some sample signals reproduced from the recorded tape are presented.

• Journal of IKEEE
• /
• v.23 no.1
• /
• pp.249-253
• /
• 2019

Most of music-transcription systems that have been commercialized operate based on audio information. However, these conventional systems have disadvantages of environmental dependency, equipment dependency, and time latency. This paper studied a vision-based music-transcription system that utilizes video information rather than audio information, which is a traditional method of music-transcription programs. Computer vision technology is widely used as a field for analyzing and applying information from equipment such as cameras. In this paper, we created a program to generate MIDI file which is electronic music notes by using smart-phone cameras to record the play of piano.

• The Korean Journal of Archival Studies
• /
• no.79
• /
• pp.343-387
• /
• 2024

Electronic records, characterized by their inherent volatility and instability, necessitate sustainable preservation measures to ensure their long-term accessibility. The National Archives of Korea has instituted a selection system for preservation formats tailored predominantly for document-type electronic records. However, this system falls short in accommodating other record types such as audiovisual records. This study endeavors to broaden the applicability of the existing system, with a concentrated focus on image-type electronic records, and to formulate foundational guidelines for their long-term preservation. In South Korea, image-type electronic records rank as the second most prevalent category following document-type. The image-type electronic records are the most basic form of audio-visual records, and research on this lays the foundation for future discussions on other audio-visual records. Consequently, this research has led to the development of a selection system for preservation formats specifically for image-type electronic records. This system is designed to facilitate the prompt and efficient evaluation of preservation format suitability, even in the context of emerging image formats. The efficacy of this system was validated through its application to extant image formats, resulting in the selection of TIFF, JFIF, and PNG as the optimal preservation formats. The outcomes of this study offer valuable insights and practical reference points for future preservation format evaluations within the field of electronic record management.

• Journal of Korean Society of Archives and Records Management
• /
• v.22 no.4
• /
• pp.129-149
• /
• 2022

Records have temporal characteristics, including the past and present; linguistic characteristics not limited to a specific language; and various types categorized in a complex way. Processing records such as text, video, and audio in the life cycle of records' creation, preservation, and utilization entails exhaustive effort and cost. Primary natural language processing (NLP) technologies, such as machine translation, document summarization, named-entity recognition, and image recognition, can be widely applied to electronic records and analog digitization. In particular, Korean deep learning-based NLP technologies effectively recognize various record types and generate record management metadata. This paper provides an overview of Korean NLP technologies and discusses considerations for applying NLP technology in records management. The process of using NLP technologies, such as machine translation and optical character recognition for digital conversion of records, is introduced as an example implemented in the Python environment. In contrast, a plan to improve environmental factors and record digitization guidelines for applying NLP technology in the records management field is proposed for utilizing NLP technology.

• 대한공업교육학회지
• /
• v.30 no.1
• /
• pp.120-132
• /
• 2005

The major purpose of this study was to provide a basic model of mobile guide system for visitor's individual learning, self-regulated learning in a museum. System model realized by this study was as follows; 1) This system distributed exhibit information to tourists in place of existing audio guides or curators. Using wireless communications, the PDA automatically delivered information about the exhibit. The artistic and visual displays maximized effective and quick transmission of information to the user. 2) It made visiting a museum fun, exciting and entertaining. With the PDA guide the museum visitor can interact with detailed descriptions of exhibits, videos and images. The museum visitor, can also play a quiz game, take photos, record voices and send e-mail.