• Journal of KIISE:Databases
• /
• v.34 no.4
• /
• pp.283-303
• /
• 2007

Recently, the study of efficient way to store and retrieve enormous music data is becoming the one of important issues in the multimedia database. Most general method of MIR (Music Information Retrieval) includes a text-based approach using text information to search a desired music. However, if users did not remember the keyword about the music, it can not give them correct answers. Moreover, since these types of systems are implemented only for exact matching between the query and music data, it can not mine any information on similar music data. Thus, these systems are inappropriate to achieve similarity matching of music data. In order to solve the problem, we propose an Efficient Query-By-Humming System (EQBHS) with a content-based indexing method that efficiently retrieve and store music when a user inquires with his incorrect humming. For the purpose of accelerating query processing in EQBHS, we design indices for significant melodies, which are 1) frequent melodies occurring many times in a single music, on the assumption that users are to hum what they can easily remember and 2) melodies partitioned by rests. In addition, we propose an error tolerated mapping method from a note to a character to make searching efficient, and the frequent melody extraction algorithm. We verified the assumption for frequent melodies by making up questions and compared the performance of the proposed EQBHS with N-gram by executing various experiments with a number of music data.

• Nuclear Engineering and Technology
• /
• v.54 no.1
• /
• pp.193-206
• /
• 2022

Several algorithms for nuclear power plant (NPP) break event detection, isolation, localization, and size estimation are proposed. A break event can be promptly detected and isolated after its occurrence by simultaneously monitoring changes in the sensing readings and by employing an interquartile range-based isolation scheme. By considering the multi-sensor data block of a break to be rank-one, it can be located as the position whose lead field vector is most orthogonal to the noise subspace of that data block using the Multiple Signal Classification (MUSIC) algorithm. Owing to the flexibility of deep neural networks in selecting the best regression model for the available data, we can estimate the break size using multiple-sensor recordings of the break regardless of the sensor types. The efficacy of the proposed algorithms was evaluated using the data generated by Maanshan NPP simulator. The experimental results demonstrated that the MUSIC method could distinguish two near breaks. However, if the two breaks were close and of small sizes, the MUSIC method might wrongly locate them. The break sizes estimated by the proposed deep learning model were close to their actual values, but relative errors of more than 8% were seen while estimating small breaks' sizes.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.5
• /
• pp.471-476
• /
• 2009

In this paper, we apply a discriminative weight training to a support vector machine (SVM) based speech/music classification for the selectable mode vocoder (SMV) of 3GPP2. In our approach, the speech/music decision rule is expressed as the SVM discriminant function by incorporating optimally weighted features of the SMV based on a minimum classification error (MCE) method which is different from the previous work in that different weights are assigned to each the feature of SMV. The performance of the proposed approach is evaluated under various conditions and yields better results compared with the conventional scheme in the SVM.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.9 no.4
• /
• pp.330-336
• /
• 2016

In this paper, we studied for modified bartlett method to estimate desired information signal. Constrained length of bartlett method is assigned as one, and estimate desired information signal to compensate for delay time. Modified bartlett method is an optimum direction-of-arrival (DoA) estimation algorithm to apply delay time compensation to update optimum weight. The optimum weight is used linear constrained minimum variance method(LCMV). Through simulation, we are comparative analysis proposed algorithm and general Bartlett and MUSIC method. In desired signal estimation, condition simulation is an array antenna element numbers 6 or 9 and desired information signals number 3. We show the superior performance of the proposed algorithm relative to the existing method in estimation of desired information signal.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.48-59
• /
• 2000

Eigendecomposition based direction-of-arrival(DOA) estimation algorithm such as MUSIC(multiple signal classification) is known to perform well and provide high resolution in white noise environment. However, its performance degrades severely when the noise process is not white. In this paper we consider the DOA estimation problem in a colored noise environment as a problem of extracting periodic signals from noise, and we take the problem to the wavelet domain. Covariance matrix of multiscale components which are obtained by taking wavelet decomposition on the noise has a special structure which can be approximated with a banded sparse matrix. Compared with noise the correlation between multiscale components of narrowband signal decays slowly, hence the covariance matrix does not have a banded structure. Based on this fact we propose a DOA estimation algorithm that transforms the covariance matrix into wavelet domain and removes noise components located in specific bands. Simulations have been carried out to analyze the proposed algorithm in colored noise processes with various correlation properties.

• The Journal of the Acoustical Society of Korea
• /
• v.24 no.5
• /
• pp.294-300
• /
• 2005

Generally, traditional approaches to track the target position are to estimate ranges and bearings by 2-D MUSIC (MUltiple 519na1 Classification) method. and to associate estimates of 2-D MUSIC made at different time points with the right targets by JPDA (Joint Probabilistic Data Association) filter in the near field. However, the disadvantages of these approaches are that these have the data association Problem in tracking multiple targets. and that these require the heavy computational load in estimating a 2-D range/bearing spectrum. In case multiple targets are adjacent. the tracking performance degrades seriously because the estimate of each target's Position has a large error. In this paper, we proposed a new tracking algorithm using Position innovations extracted from the senor output covariance matrix in the near field. The proposed algorithm is demonstrated by the computer simulations dealing with the tracking of multiple closing and crossing targets.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.41 no.1
• /
• pp.12-22
• /
• 2016

Convenience and safety are the key words for the automotive driving and various sensor technologies have been studied for enhanced perception of driving environments. In frequency modulated continuous wave (FMCW) radar systems, single antenna is enough for range and velocity detection of multiple targets. Multiple array antenna is needed for estimating direction of arrival(DoA). Using DoA estimation algorithm in time domain as in the conventional systems, it is difficult to distinguish vehicles lie in the same angle. In order to facilitate the enhanced angle estimation, DoA estimation algorithm is applied in frequency domain. In this paper, the method for applying multiple signal classification(MUSIC) algorithm in frequency domain is suggested and the performance is analyzed.

• Journal of Digital Contents Society
• /
• v.19 no.4
• /
• pp.829-836
• /
• 2018

Sheet music is one of the inevitable elements for successful melody interpretation, playing or rendering, and performance, most of performing artists usually utilize a paper sheet music in the cases. However, the paper sheet music can be a one of the reason to degrade the concentration of audiences and artists or entire performing flows. In addition, it might be a weakness to use a paper sheet music in an outside performing place. We propose an electronic sheet music page tuner application, which can overcome these problems, based on a Tablet PC. The proposed page tuner application, which uses the OpenCV to adapt an eye tracking and behavior recognition, can provide an automatical page pass function to the performing artists. We will expect that the proposed application can highly decrease the weakness of paper sheet music.

• The KIPS Transactions:PartD
• /
• v.10D no.3
• /
• pp.547-558
• /
• 2003

From the viewpoint of that music melody has the similar features to time-series data, music melody is transformed to a time-series data with normalization and corrections and the similarity between melodies is defined as the Euclidean distance between the transformed time-series data. Then, based the similarity between melodies of a music object, melodies are clustered and the representative of each cluster is extracted as one of theme melodies for the music. To construct the theme melody index, a theme melody is represented as a point of the multidimensional metric space of M-tree. For retrieval of user's query melody, the query melody is also transformed into a time-series data by the same way of indexing phase. To retrieve the similar melodies to the query melody given by user from the theme melody index the range query search algorithm is used. By the implementation of the prototype system using the proposed theme melody index we show the effectiveness of the proposed methods.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.27-32
• /
• 2019

Research that implements the classification process through Deep Learning algorithm, one of the outstanding human abilities, includes a unimodal model, a multi-modal model, and a multi-modal method using music videos. In this study, the results were better by suggesting a system to analyze each song's spectrum into short samples and vote for the results. Among Deep Learning algorithms, CNN showed superior performance in the category of music genre compared to RNN, and improved performance when CNN and RNN were applied together. The system of voting for each CNN result by Deep Learning a short sample of music showed better results than the previous model and the model with Softmax layer added to the model performed best. The need for the explosive growth of digital media and the automatic classification of music genres in numerous streaming services is increasing. Future research will need to reduce the proportion of undifferentiated songs and develop algorithms for the last category classification of undivided songs.