• Journal of Korea Multimedia Society
• /
• v.17 no.10
• /
• pp.1239-1252
• /
• 2014

The OST (Original Sound Track) in the film plays a vital role in increasing consensus and concentration to the storyline. The selected 4 animations are classified into 17 Narrative Processes (NP) by using NP Classification Model [1]. For the NPs each having OSTs, the authors have investigated 6 kinds of objective musical elements of the OST such as sound (speech, music, effect), tonality, tempo, range, intensity, and instrumentation. It is found that there are 33.3% common musical elements among all of them for the NPs with OSTs commonly. Among them, it is also found that there are 71.9% of common properties of the musical element. This research is meaningful by firstly showing that there are common properties of objective musical elements in each NP and the corresponding OST.

• The Journal of the Acoustical Society of Korea
• /
• v.19 no.3
• /
• pp.77-85
• /
• 2000

Laboratory determinations of acoustic and physical properties in Korea Strait sediment were carried out. Sediment sound velocimeter(SSV) was employed to measure the sound velocity of sandy sediment. Distribution patterns of the acoustic and physical properties are controlled by sediment texture. The study area is divided into three provinces(mid-shelf, shelf margin and enough) based on the acoustic and physical properties. This classification matches well with the previous result[14] based on the systems tracks and depositional systems. We suggest a geoacoustic model of the Korea Strait that replacing the old model of Briggs and Fisher[5].

• Smart Structures and Systems
• /
• v.29 no.3
• /
• pp.475-484
• /
• 2022

The loss of cable tension for civil infrastructure reduces structural bearing capacity and causes harmful deformation of structures. Currently, most of the structural health monitoring (SHM) approaches for cables rely on contact transducers. This paper proposes a cable tension identification technology using percussion sound, which provides a fast determination of steel cable tension without physical contact between cables and sensors. Notably, inspired by the concept of tensioning strings for piano tuning, this proposed technology predicts cable tension value by deep learning assisted classification of "percussion" sound from tapping a steel cable. To simulate the non-linear mapping of human ears to sound and to better quantify the minor changes in the high-frequency bands of the sound spectrum generated by percussions, Mel-frequency cepstral coefficients (MFCCs) were extracted as acoustic features to train the deep learning network. A convolutional neural network (CNN) with four convolutional layers and two global pooling layers was employed to identify the cable tension in a certain designed range. Moreover, theoretical and finite element methods (FEM) were conducted to prove the feasibility of the proposed technology. Finally, the identification performance of the proposed technology was experimentally investigated. Overall, results show that the proposed percussion-based technology has great potentials for estimating cable tension for in-situ structural safety assessment.

• Proceedings of the KIEE Conference
• /
• 2006.10c
• /
• pp.419-421
• /
• 2006

The importance of automatic discrimination image data has evolved as a research topic over recent years. We have used forward neural network as a classifier using sound data features within image data, our initial tests have shown encouraging results that indicate the viability of our approach.

• The Journal of the Acoustical Society of Korea
• /
• v.37 no.1
• /
• pp.60-65
• /
• 2018

In this paper, a covariance matrix and modulogram are proposed for realizing amphibian sound classification using CNN (Convolutional Neural Network). First of all, a database is established by collecting amphibians sounds including endangered species in natural environment. In order to apply the database to CNN, it is necessary to standardize acoustic signals with different lengths. To standardize the acoustic signals, covariance matrix that gives distribution information and modulogram that contains the information about change over time are extracted and used as input to CNN. The experiment is conducted by varying the number of a convolutional layer and a fully-connected layer. For performance assessment, several conventional methods are considered representing various feature extraction and classification approaches. From the results, it is confirmed that convolutional layer has a greater impact on performance than the fully-connected layer. Also, the performance based on CNN shows attaining the highest recognition rate with 99.07 % among the considered methods.

• 제어로봇시스템학회:학술대회논문집
• /
• 1997.10a
• /
• pp.1738-1741
• /
• 1997

This paper addresses the issue fo target classification and localization with a SONAR for mobiler robot indoor navigation. In particular, multiple refetions of SONAR sound are used actively and interntionally. As for the SONAR sensor, the multiple reflection has been generally considered as one of the noisy phenomena, which is inevitable in the indoor environments. However, these multiple reflections can be a clue for classifying and localizing targets in the indoor environment if those can be controlled and used well. This paper develops a new SONAR sensor module with a reflection plane which can actively create the multiple refection. This paper also intends to suggest a new target classification emthod which uses the multiple refectiions. We approximate the world as being two dimensional and assume that the targets consisting of the indoor environment are pland, corner, and edge. Multiple reflection paths of an acoustic bean by a SONAR are analyzed, by simulations and the patterns of the TOPs (Time Of Flight) and angles of multiple reflections from each target are also analyzed. In addition, a new algorithm for target classification and localization is proposed.

• Journal of the Korea Convergence Society
• /
• v.5 no.1
• /
• pp.35-41
• /
• 2014

An automatic speech recognition system is one of the popular research problems. There are many research groups working in this field for different language including Japanese. Japanese vowel recognition is one of important parts in the Japanese speech recognition system. The vowel classification system with the Mamdani fuzzy inference system was developed in this research. We tested our system on the blind test data set collected from one male native Japanese speaker and four male non-native Japanese speakers. All subjects in the blind test data set were not the same subjects in the training data set. We found out that the classification rate from the training data set is 95.0 %. In the speaker-independent experiments, the classification rate from the native speaker is around 70.0 %, whereas that from the non-native speakers is around 80.5 %.

• Journal of the Korean Society of Costume
• /
• v.64 no.5
• /
• pp.76-90
• /
• 2014

The Design Protection Act of Korea classifies industrial designs into examined-based and unexamined-based articles. For design application and registration under the DPA, applicable product for the design needs to be chosen in order for it to be registered. Clothing and personal belongings under class B in the classification list are subject to unexamined-based articles. A sound and logical classification system will lead to higher administrative efficiency as well as assurance of more convenience for the system users. This paper examines the suitability of the design classification for clothing and personal belongings and purposes to suggest improvements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.30 no.5C
• /
• pp.305-312
• /
• 2005

Three classification algorithms are tested using musical instruments. Several classification algorithms are introduced and among them, Bayes rule, NN and k-NN performances evaluated. ZCR, mean, variance and average peak level feature vectors are extracted from instruments sample file and used as data set to classification system. Used musical instruments are Violin, baroque violin and baroque cello. Results of experiment show that the performance of NN algorithm excels other algorithms in musical instruments classification.

• Journal of Sasang Constitutional Medicine
• /
• v.10 no.1
• /
• pp.65-80
• /
• 1998

Proceeding an objective Study of sasang constitution diagnosis by Sound Analysis which uses Computed Sound lab(CSL), we verified the confidence level of Questionnaire of Sasang Constitution classification II(QSCC II) and the first results of Sound Analysis for verifying correlation between the physical character and Sound character are as follows. 1. The confidence level of QSCC II is 70.8% to Soeumin, 60.8% to Soyangin, 74.5% to Taeumin, and 70.08% in total. But, the actual results of verifying the confidence level after making 100 persons an object of study, are that the confidence level of that is 55.10% to Soeumin, 30.77% to Soyangin, 80.00% to Taeumin, and 55.29% in total. So it doesn't coincide with the confidence lecel of QSCC II 70.8%. 2. The results of verifying the confidence level about other 134 persons after enough explanation before the constitutional diagnosis by QSCC II are that the confidence of that is 71.08 to Soeumin, 54.76% to Soyangin 81.82% to Taeumin, and 69.22% in total. 3. The results of verifying the correlation between B.M.I. and Sasang Costitution are that there are significant differences below P<0.001 between Taeumin and Soeumin, and between Taeumin and Soyangin. 4. Height and Weight influence on a fundamental frequency and formant frequency. 5. There are differences for every constitutions in a amplitude when we nave a Sound analysis. As aboves, it is considered that we can find the differences among the constitutional groups, if we have a Sound analysis of the constitutional Sound characters.