• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1869-1886
• /
• 2018

This paper proposes a MIDI- and audio-based music genre classification method for Korean traditional music. There are many traditional instruments in Korea, and most of the traditional songs played using the instruments have similar patterns and rhythms. Although music information processing such as music genre classification and audio melody extraction have been studied, most studies have focused on pop, jazz, rock, and other universal genres. There are few studies on Korean traditional music because of the lack of datasets. This paper analyzes raw audio and MIDI phrases in Korean traditional music, performed using Korean traditional musical instruments. The classified samples and MIDI, based on our classification system, will be used to construct a database or to implement our Kontakt-based instrument library. Thus, we can construct a management system for a Korean traditional music library using this classification system. Appropriate feature sets for raw audio and MIDI phrases are proposed and the classification results-based on machine learning algorithms such as support vector machine, multi-layer perception, decision tree, and random forest-are outlined in this paper.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2012.04a
• /
• pp.658-664
• /
• 2012

This paper presents an investigation into driveline clonk noise of midi-bus. Test was performed for operational acceleration and pressure, torsional vibration of driveline and FRF to TPA. Wavelet analysis was used to study spectral-time characteristics to all measurement data and specially for torsional vibration, lash analysis was carried out. To investigate the path of the clonk in detail, time domain TPA was introduced. With time domain TPA, the contribution of each path for the clonk was estimated by both subjectively and objectively. As a result, Transmission mount part was came to light as the main contributor of issued clonk. This was verified by reinforcing the bracket of transmission side. And 1D torsional nvh performance simulation model was built with measured torsional vibration. The simulation tool was used for prediction of some clonk behavior in tip in-out transient condition.

• Journal of Music and Human Behavior
• /
• v.8 no.1
• /
• pp.1-16
• /
• 2011

This study was to investigate the influence of using Therapeutic Instrumental Music Performance (TIMP) in uninvolved hand function for children with spastic cerebral palsy. Participants were recruited from a welfare center for people with cerebral palsy(CP). Ages ranged from 11 to 12, and a total of 15 TIMP sessions were provided for 3 weeks. Hand function tests were used including Jebsen Hand Function Test for hand function, Box and Block Test for dexterity of uninvolved hand, and MIDI (Musical Instrument Digital Interface) evaluation for velocity of fingers. The TIMP program consisted of hand percussion playing and keyboard playing with changes of timbre and tempo. While the scores of Jebsen test and Box and Block test were improved for all participants, outcomes of MIDI analysis showed differences among participants. Overall, hand function improvements were observed after the completion of using the TIMP program, and the results implies that the TIMP program can be applied in upper extremity rehabilitation for children with CP.

• Annual Conference of KIPS
• /
• 2011.11a
• /
• pp.306-309
• /
• 2011

컴퓨터의 발전과 함께 음악 프로그램을 이용한 작곡 작업은 전문가부터 일반인에게 이르기까지 사용자의 폭을 넓혀왔다. 본 연구에서는 이러한 작곡 작업을 보다 효과적으로 하기 위하여 다양한 방안을 모색하였다. 단순한 텍스트 기반의 음악 검색이 아닌 미디(Midi) 분석엔진 기반의 다양한 검색방법을 설계하였으며 이를 기반으로 통합 음악제작/검색 솔루션을 구현하였다. 또한, 휴대성(Portability)을 위하여 MS 사의 WindowsPhone7 플랫폼 기반의 어플리케이션 구현을 통해 PC기반의 프로그램을 모바일 환경에서 작동 및 사용할 수 있도록 구현하였다.

• Microbiology and Biotechnology Letters
• /
• v.34 no.2
• /
• pp.101-108
• /
• 2006

YNB54 strain which shows inhibitory activities specific to the plant pathogenic Phytophthora sp. on potato dextrose agar medium was screened among lots of strains isolated from Korean soils. To identify taxonomy of the Phytophthora specific antagonistic bacteria YNB54, 165 rDNA sequence, MIDI fatty acid composition, DNA-DNA hybridization, GC content, and commercial multitest systems such as API 20E and Biolog GN were performed. Results of commercial kits including lots of biochemical and physiological reactions showed that this strain was closely related to taxa including Enterobacter cloacae and Enterobacter cancerogenus species than other genera(Citerobacter Klebsiella, Leclercia). Also, analysis of its MIDI, G+C contents, and DNA-DNA hybridization suggests that this strain was more similiar to the Genus Enterobacter than other genera (Citerobacter Klebsiella, Leclercia). This strain was potentially identified as Enterobacter sp. by these results. But our 16S ribosomal DNA sequences (rDNA) analysis confirmed that it was more closely related to the cluster of Citerobacter freundii ATCC 29935 than any other Enterobacter species. In the absence of defined phylogenetic critia for delineating genera, the results observed with Citrobacter and Enterobacter species suggest that further studies are needed to clarify their relationships. This investigation demonstrates that YNB54 strain is genetically diverse and potentially more taxonomically complex than hitherto realized. Further study is necessary to confirm their taxonomic positions.

• 한국HCI학회:학술대회논문집
• /
• 2007.02c
• /
• pp.176-182
• /
• 2007

본 연구에서는 사용자가 즉석에서 연주한 곡에 대응하는 춤 동작을 자동으로 생성하는 기술을 제안한다. 본 기법은 먼저 댄서로부터 모션 캡쳐 받은 춤 시퀀스를 분절화한 후 사용자가 신디사이저를 통해 직접 연주하여 얻은 MIDI 데이터를 분석해 음악에서의 특징점을 추출한다. 그리고 분절화 한 모션의 세그먼트들을 음악에 맞춰 다시 배열하여 새로운 춤 시퀀스를 생성함으로써 사용자가 연주한 음악과 어울리는 춤 동작을 자동으로 생성한다. 이를 위해 세 단계의 작업을 수행하게 되는데, 첫 번째 단계에서 모션 캡쳐를 통해 얻게 된 데이터에서 캐릭터의 위치와 자세를 기준으로 하여 긴 시퀀스를 의미 있는 작은 춤 동작으로 분절화한다. 두 번째 단계에서는 사용자의 연주를 통해 획득한 MIDI를 분석하여 특징점을 추출하고, 마지막 단계에서는 이를 바탕으로 음악에 기반한 음악과 동작을 합성한다. 본 연구는 음악과 댄스의 리듬감이 파괴되지 않도록 합성함으로써 우리의 연구는 기존 연구에 비해서 훨씬 자연스러운 춤 시퀀스를 결과물로 만들어 낸다.

• Korean Journal of Environmental Agriculture
• /
• v.23 no.1
• /
• pp.68-74
• /
• 2004

Miscanthus purpurascens Juice containing potassium (37,952 mg/L), nitrogen (14,000 mg/L), phosphorus (6,800 mg/L), magnesium (5,969 mg/L), calcium (5,910 mg/L), etc., was investigated to develop a novel meidum far the mass cultivation of useful microorganisms. For this research, we first isolated an antagonistic bacterium G-74 from soil, which showed strong growth inhibition against two phytopathogenic fungi, Rhizoctonia solani and Botrytis cinerea, and identified as Bacillus lentimorbus G-74 based on the morphological characteristics and MIDI analysis. Culture conditions for G-74 strain in the M. purpurascens juice medium were optimized. Dilution rate of the medium, temperature and initial pH for the optimum growth of G-74 strain were 30% (V/V), $35^{\circ}C$ and 5.0, respectively. It was found that additions of 2.0% (W/V) corn starch as a carbon source and 1.0% (W/V) yeast extract as a nitrogen source in this medium increased B. lentimorbus G-74 growth to 66% more efficient than Luria Bertani medium.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.48 no.2
• /
• pp.113-119
• /
• 2003

Soybean sprout pathogenic bacteria were isolated from the large, deep containers of a commercial factory. Over a period of one year, 40 pathogenic-like bacteria were isolated among a total of 732 isolates. In addition to bacteria previously reported to be associated with rotting, such as Pseudomonas putida and Erwinia carotovora, several other genera were also identified: Acinetobacter spp., Chryseobacterium spp., Klebsiella sp., Pantoea agglomerans, Bacillus sp. Fatty acid methyl ester (FAME) analysis using the Microbial ID (MIDI) system, and 16s rRNA sequence analysis, yielded identical results, confirming the identities of these microorganisms. Several types of selective media were not good for identification and determination of population structure in commercial environments, as colony type was not specific to the genus. There was no dominant bacterium, and we were not able to find the main bacterium responsible for soybean spout rot. Even though we did not identify a major target for controlling rot or screening for resistant cultivars, the results of this study indicated that bacterial rot of soybean sprout is endemic. In addition, it emerged that factory epidemics in summer are not caused by the bacteria isolated in this study.

• The Journal of the Korea Contents Association
• /
• v.16 no.8
• /
• pp.427-434
• /
• 2016

This paper focuses on a real-time hardware processing by implementing the ARM Cortex-M4 based embedded system, using a conversion algorithm from a muscular sense to both visual and auditory elements, which recognizes rotations of a human body, directional changes and motion amounts out of human senses. As an input method of muscular sense, AHRS(Attitude Heading Reference System) was used to acquire roll, pitch and yaw values in real time. These three input values were converted into three elements of HSI color model such as intensity, hue and saturation, respectively. Final color signals were acquired by converting HSI into RGB color model. In addition, Three input values of muscular sense were converted into three elements of sound such as octave, scale and velocity, which were synthesized to give an output sound using MIDI(Musical Instrument Digital Interface). The analysis results of both output color and sound signals revealed that input signals of muscular sense were correctly converted into both color and sound in real time by the proposed conversion method.

• Journal of KIISE:Software and Applications
• /
• v.34 no.12
• /
• pp.1037-1044
• /
• 2007

Recently, we extract the representative melody of the music and index the music to reduce searching time at the content-based music retrieval system. The existing study has used MIDI data to extract a representative melody but it has a weak point that can use only MIDI data. Therefore, this paper proposes a representative melody retrieval method that can be use at all audio file format and uses digital signal processing. First, we use Fast Fourier Transform (FFT) and find the tempo and node for the representative melody retrieval. And we measure the frequency of high value that appears from PCM Data of each node. The point which the high value is gathering most is the starting point of a representative melody and an eight node from the starting point is a representative melody section of the audio data. To verity the performance of the method, we chose a thousand of the song and did the experiment to extract a representative melody from the song. In result, the accuracy of the extractive representative melody was 79.5% among the 737 songs which was found tempo.