• The Journal of the Acoustical Society of Korea
• /
• v.29 no.4
• /
• pp.243-250
• /
• 2010

This paper proposes a spectral modeling of Korean traditional instrument, Haegeum, using cepstral analysis to naturally describe Haegeum sounds varying with time. To get a precise result of cepstral analysis, we set the frame size to 3 periods of input signal and more cepstral coefficients are used to extract formants. The performance is enhanced by flexibly controlling the cutoff frequency of bandpass filter depending on the resonances in the synthesis process of sinusoidal components and the deleting peaks remained in the residual signal. To detect the change of pitch, we divide the input frames into silence, attack, and sustain region and determine which region the current frame is involved in. Then, the proposed method readjusts the frame size according to the fundamental frequency in the case of the current frame is in attack region and corrects the extraction errors of the fundamental frequency for the frames in sustain region. With these processes, the synthesized sounds are much more similar to the originals. The evaluation result through the listening test by a Haegeum player says that the synthesized sounds are almost similar to originals (96~100 % similar to the original sounds).

• Journal of Environmental Impact Assessment
• /
• v.24 no.1
• /
• pp.51-65
• /
• 2015

The flora distributed around Mt. Hwangseok were summarized as 495 taxa including 97 families, 295 genera, 394 species, 4 subspecies, 80 varieties and 17 forms. In the component ratio of taxa, pteridophyta was 4.2%, 1.2% of gymnospermae, 78.8% of dicotyledonae and 15.8% of monocotyledonae. The rare plants were 9 taxa including Aconitum chiisanense, Eranthis stellata, Aristolochia contorta, Viola albida and so forth. The Korean endemic plants were 13 taxa including Populus tomentiglandulos, Pseudostellaria coreana, Aconitum pseudolaeve, Thalictrum actaefolium var. brevistylum and so forth. The specific plants by floristic region were 16 taxa including Cimicifuga heracleifolia, Sanguisorba longifolia, Symplocarpus renifolius, Betula davurica and so forth. The plants adaptable to climate change were 11 taxa including Aconitum pseudolaeve, Ajuga spectabilis, Carex okamotoi, Rhynchosia volubilis and so forth. The naturalized plants were 20 taxa including Fallopia convolvulus, Rumex crispus, Phytolacca amrericana, Robinia pseudoacacia and so forth. The invasive alien plant was Aster pilosus. The emergence of local ecologically important species, set the correct range for the core and buffer zone, transition zone, coded will be necessary, the distribution of the specialty plant areas and rare plants, an area management plan should be organized by nature. In addition, a variety of assessment techniques and accurate data to establish the validity of the core area is also set to acquire.

• Journal of The Korean Association For Science Education
• /
• v.38 no.3
• /
• pp.393-405
• /
• 2018

In this study, we classified the group model construction types in the actual classroom situation implementing the instructional strategy mixed with individual model construction and group model construction types. The purpose of this study is to analyze the information flow and the individual construction types of each group model construction type to obtain implications for model co-construction in a real classroom environment. A two-session class on sound propagation was carried out for thirty-three 8th grade students in Seoul. A total of 65 individual model construction and 16 group model construction processes were collected and analyzed. The group model construction types were classified as unchanged, enumerated, and elaborated. The unchanged type was found in 8 groups, the enumerated type in 3 groups, and the elaborated type in 5 groups. The isolated individual and independent construction (i.I) were found mostly in the unchanged group construction type (50.0%) and enumerated group construction type (54.5%). In the unchanged type, the radial shape of flow in which one student's information is transmitted to all the members of the group appeared. In the enumerated type, the starting point of the information flow was observed from two individuals. In the elaborated type, linear information flow appeared and both the second dissemination and reflective construction (2d.R) contributed to the group model construction (58.3%). This study suggests a viewpoint that enables to understand the process of complex model construction in an actual classroom context rather than in an ideal situation. The result of this study suggests the necessity of a modeling strategy considering the characteristics of Korean small group culture. It is expected that the discussion will progress through further studies.

• Journal of Broadcast Engineering
• /
• v.22 no.6
• /
• pp.693-701
• /
• 2017

In this paper, we propose a new method for music genre classification using spikegram and deep neural network. The human auditory system encodes the input sound in the time and frequency domain in order to maximize the amount of sound information delivered to the brain using minimum energy and resource. Spikegram is a method of analyzing waveform based on the encoding function of auditory system. In the proposed method, we analyze the signal using spikegram and extract a feature vector composed of key information for the genre classification, which is to be used as the input to the neural network. We measure the performance of music genre classification using the GTZAN dataset consisting of 10 music genres, and confirm that the proposed method provides good performance using a low-dimensional feature vector, compared to the current state-of-the-art methods.

• Korean Journal of Environment and Ecology
• /
• v.18 no.4
• /
• pp.392-414
• /
• 2004

The flora of Sorok Island was investigated 8 times from January 2001 to November 2002. The vascular plants recorded as total 604 taxa, 13 forms, 65 varieties, 1 subspecies, 524 species, 397 genera, 128 families. The rare and endangered plants were recorded 1 taxa (Millettia japonica (Sieb. et Zucc.) A. Gray), 12 taxa (3 variety, 9 species, 10 genera, 10 families) as Korean endemic plants. The naturalized plants were 26 taxa, 1 variety, 25 species, 21 genera, 12 families, 4.30% and 9.15％ among the total naturalized plants and Urbanization Index in Korea. Visitor's numbers are expected to increase rapidly because nature views of Sorok Island are beautiful, which kind and number of naturalized plants are forecasted to be increased. Strong conservation policies should be considered.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.854-860
• /
• 2020

Deep neural networks have shown remarkable performance in various areas, including image classification and speech recognition. The variety of data generated by augmentation plays an important role in improving the performance of the neural network. The transformation of data in the augmentation process makes it possible for neural networks to be learned more generally through more diverse forms. In the traditional field of image process, not only new augmentation methods have been proposed for improving the performance, but also exploring methods for an optimal augmentation policy that can be changed according to the dataset and structure of networks. Inspired by the prior work, this paper aims to explore to search for an optimal augmentation policy in the field of sound data. We carried out many experiments randomly combining various augmentation methods such as adding noise, pitch shift, or time stretch to empirically search which combination is most effective. As a result, by applying the optimal data augmentation policy we achieve the improved classification accuracy on the environmental sound classification dataset (ESC-50).

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.4
• /
• pp.187-195
• /
• 2023

This study propose to develop artificial intelligence liberal arts courses for college students in the humanities and social sciences majors using the entry artificial intelligence model. A group of experts in computer, artificial intelligence, and pedagogy was formed, and the final artificial intelligence liberal arts course was developed using previous research analysis and Delphi techniques. As a result of the study, the educational topics were largely composed of four categories: image classification, image recognition, text classification, and sound classification. The training consisted of 1) Understanding the principles of artificial intelligence, 2) Practice using the entry artificial intelligence model, 3) Identifying the Ethical Impact, and 4) Based on learned, team idea meeting to solve real-life problems. Through this course, understanding the principles of the core technology of artificial intelligence can be directly implemented through the entry artificial intelligence model, and furthermore, based on the experience of solving various real-life problems with artificial intelligence, and it can be expected to contribute positively to understanding technology, exploring the ethics needed in the artificial intelligence era.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.7
• /
• pp.291-305
• /
• 2008

Previous study about Mobile Music Contents was mainly focused on Industry factors & enterprise factors like Technology. This study is not only focused on Technology factors, but also Customer & System factors like TAM of original, and also, this study first tried to find the Mobile Internet medium's customer purchase by each property's Mobile Music Contents from assorting the Mobile music Contents property and defining them. So to speak of this study have tried to concretely verify the factors of purchase. And also, I proposed an transformated model, and added independent variable factors, 'distinction', 'speed of system', 'speed of network', 'a career of use', 'amount of use', 'preservation', 'customization', 'information', 'confidence', 'omni presentation', 'potential possibility of reproduce'. By applying TAM this study has measured how the product property. user property, and system property causes effect to customer purchase of Mobile Music Contents. In results, First, success 8 factors were determined to be the purchase of 'Ringtone'. Second, 8 factors were determined to be the purchase of 'Ring-Back tone', but, 'The use of convenience' was not influenced 'Intention of Purchase'. Third, 6 factors were determined to be the purchase of 'Full Track Download of Music'. At the Conclusion this study presented a scheme that these study results could be applied in actual company and academic world.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.5
• /
• pp.193-204
• /
• 2019

The explosion of data due to the improvement of sensor technology and computing performance has become the basis for analyzing the situation in the industrial fields, and various attempts to detect events based on such data are increasing recently. In particular, sound signals collected from sensors are used as important information to classify events in various application fields as an advantage of efficiently collecting field information at a relatively low cost. However, the performance of sound-event classification in the field cannot be guaranteed if noise can not be removed. That is, in order to implement a system that can be practically applied, robust performance should be guaranteed even in various noise conditions. In this study, we propose a system that can classify the sound event after generating the enhanced sound signal based on the deep learning algorithm. Especially, to remove noise from the sound signal itself, the enhanced sound data against the noise is generated using SEGAN applied to the GAN with a VAE technique. Then, an end-to-end based sound-event classification system is designed to classify the sound events using the enhanced sound signal as input data of CNN structure without a data conversion process. The performance of the proposed method was verified experimentally using sound data obtained from the industrial field, and the f1 score of 99.29% (railway industry) and 97.80% (livestock industry) was confirmed.

• Korean Journal of Plant Resources
• /
• v.21 no.2
• /
• pp.162-170
• /
• 2008

The purpose of this study was to suggest the raw data on establishing the domestic wetland conservation plan. The results of this study were as follows. The vascular plants were summarized as 201 taxa in Ahnshim wetland; 57 families, 154 genera, 179 species and 22 varieties. The rare and endangered plant designated by Korea Forest Service was Hydorcharis dubia. In the wetland plants, the emerged plants were showed Typha angustata, Beckmannia syzigachne, Zizania latifolia, Phragmites communis, Persicaria thunbergii, Oenanthe javanica and Veronica undulata, and the submerged plants were Potamogeton crispus, Vallisneria asiatica, Hydrilla verticillata, Ceratophyllum demersum and Myriophyllum verticillatum. And the floating leaved plants were confirmed Potamogeton distinctus, Hydrocharis dubia, Nelumbo nucifera and Nymphoides peltata, and the floating plants were Salvinia natans, Spirodela polyrhiza and Lemna paucicostata. The naturalized plants were 33 taxa; Avena fatua, Dactylis glomerata, Rumex crispus, Rumex conglomeratus, Amaranthus retroflexus, Lepidium apetalum, Tlaspi arvense, Descurainia pinnata, Potentilla supina, Vicia villosa, Robinia pseruo-acacia, Amorpha fruticosa, Trifolium repens, Medicago sativa, Ailanthus altissima, Euphorbia supina, Oenothera lamarckiana, Quamoclit angulata, Ipomoea purpurea, Solanum nigrum, Veronica perisca, Helianthus tuberosus, Ambrosia artemisifolia var. elatior, Xanthium strumarium, Erigeron annuus, Erigeron canadensis, Conyza sumatrensis, Senecio vulgaris, Bidens frondosa, Tagetes minuta, Taraxacum officinale, Taraxacum laevigatum and Sonchus oleraceus.