• Journal of Broadcast Engineering
• /
• v.9 no.1
• /
• pp.2-7
• /
• 2004

In this paper, we proposed the content-based music information retrieval technique using some MPEG-7 low-level descriptors. Especially, pitch information and timbral features can be applied in music genre classification, music retrieval, or QBH(Query By Humming) because these can be modeling the stochasticpattern or timbral information of music signal. In this work, we restricted the music domain as O.S.T of movie or soap opera to apply broadcasting system. That is, the user can retrievalthe information of the unknown music using only an audio clip with a few seconds extracted from video content when background music sound greeted user's ear. We proposed the audio feature set organized by MPEG-7 descriptors and distance function by vector distance or ratio computation. Thus, we observed that the feature set organized by pitch information is superior to timbral spectral feature set and IFCR(Intra-Feature Component Ratio) is better than ED(Euclidean Distance) as a vector distance function. To evaluate music recognition, k-NN is used as a classifier

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.41-44
• /
• 1997

This paper is to provide an integration approach between design and process planning for mechanical parts, using feature recognition. We develop a method to extract each individual feature of an object from 3D modeling data using face-edge graph based algorithm and then propose an approach to recognize the volumic form features using heuristic rules. we demonstrate the proposed approaches are effective for such basic shapes as pocket, slot, through hole, etc.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.11
• /
• pp.4556-4572
• /
• 2015

Dynamic texture (DT) recognition is a challenging problem in numerous applications. In this study, we propose a new algorithm for DT recognition based on group sparsity structure in conjunction with chaotic feature vector. Bag-of-words model is used to represent each video as a histogram of the chaotic feature vector, which is proposed to capture self-similarity property of the pixel intensity series. The recognition problem is then cast to a group sparsity model, which can be efficiently optimized through alternating direction method of multiplier algorithm. Experimental results show that the proposed method exhibited the best performance among several well-known DT modeling techniques.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.5 no.10
• /
• pp.1751-1768
• /
• 2011

Falls are one of the most concerned accidents for elderly people and often result in serious physical and psychological consequences. Many researchers have studied fall detection techniques in various domain, however none released to a commercial product satisfying user requirements. We present a systematic modeling and evaluating procedure for best classification performance and then do experiments for comparing the performance of six procedures to get a statistical classifier based wrist-type fall detector to prevent dangerous consequences from falls. Even though the wrist may be the most difficult measurement location on the body to discern a fall event, the proposed feature deduction process and fall classification procedures shows positive results by using data sets of fall and general activity as two classes.

• 한국지구물리탐사학회:학술대회논문집
• /
• 2003.11a
• /
• pp.684-689
• /
• 2003

One field identified by an inverse method is one of multiple candidate solutions those are independently obtained through a specific estimation technique. While averaging of optimized fields can provide a better description of the spatial feature of an unknown field, it deteriorates the flow and transport characteristics of the optimized fields. As a result, the averaged field is not suited for modeling aquifer performances. Based on genetic algorithm, an optimal field synthesis technique is developed, which combines diversely optimized fields into a refined group of fields. Each field in the population is paired, and a sub-region of each field is exchanged by crossover operation to create a group of synthesized fields of enhanced modeling capability. The population of the fields is evolved till the synthesized fields become sufficiently similar. Applications of the optimal field synthesis to synthetic cases indicate that the objective functions of the fields assessing the modeling capabilities are further reduced after the optimal field synthesis. The identified fields from various inverse techniques may yield a range of modeling results under varied flow situations. The uncertainty is narrowed down through the optimal field synthesis and the associated modeling results converge on that of the reference field. The developed inverse modeling facilitates the construction of a reliable simulation model and hence trustworthy predictions of the future performances.

• MALSORI
• /
• no.51
• /
• pp.151-165
• /
• 2004

For educational and research purposes, a Korean speech recognition platform is designed. It is based on an object-oriented architecture and can be easily modified so that researchers can readily evaluate the performance of a recognition algorithm of interest. This platform will save development time for many who are interested in speech recognition. The platform includes the following modules: Noise reduction, end-point detection, met-frequency cepstral coefficient (MFCC) and perceptually linear prediction (PLP)-based feature extraction, hidden Markov model (HMM)-based acoustic modeling, n-gram language modeling, n-best search, and Korean language processing. The decoder of the platform can handle both lexical search trees for large vocabulary speech recognition and finite-state networks for small-to-medium vocabulary speech recognition. It performs word-dependent n-best search algorithm with a bigram language model in the first forward search stage and then extracts a word lattice and restores each lattice path with a trigram language model in the second stage.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.377-380
• /
• 2022

An application called an app can be downloaded and used on mobile devices. Among them, Android-based apps have the disadvantage of being implemented on an open source basis and can be exploited by anyone, but unlike iOS, which discloses only a small part of the source code, Android is implemented as an open source, so it can analyze the code. However, since anyone can participate in changing the source code of open source-based Android apps, the number of malicious codes increases and types are bound to vary. Malicious codes that increase exponentially in a short period of time are difficult for humans to detect one by one, so it is efficient to use a technique to detect malicious codes using AI. Most of the existing malicious app detection methods are to extract Features and detect malicious apps. Therefore, three ways to select the optimal feature to be used for learning after feature extraction are proposed. Finally, in the step of modeling with optimal features, ensemble techniques are used in addition to a single model. Ensemble techniques have already shown results beyond the performance of a single model, as has been shown in several studies. Therefore, this paper presents a plan to select the optimal feature and implement a learning model for Android app-based malicious code detection.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.4
• /
• pp.51-58
• /
• 2008

In this paper, we propose a place modeling based on the distribution of scale-invariant features, and a place recognition method that recognizes places by comparing the place model in a database with the extracted features from input data. The proposed method is based on the assumption that every place can be represented by unique feature distributions that are distinguishable from others. The proposed method uses global information of each place where one place is represented by one distribution model. Therefore, the main contribution of the proposed method is that the time cost corresponding to the increase of the number of places grows linearly without increasing exponentially. For the performance evaluation of the proposed method, the different number of frames and the different number of features are used, respectively. Empirical results illustrate that our approach achieves better performance in space and time cost comparing to other approaches. We expect that the Proposed method is applicable to many ubiquitous systems such as robot navigation, vision system for blind people, wearable computing, and so on.

• The Transactions of the Korea Information Processing Society
• /
• v.6 no.12
• /
• pp.3514-3522
• /
• 1999

While the method of information collection and visual interface technique have been researched actively on web information retrieval, a study on structured modeling for effective classification of a wide collective information leaves to be desired. In this paper, we represent information feature based on structured information model. It aims at carrying out effectively the user's retrieval environment through visualization technique with analyzing the information feature. We propose a information classification method using Facet units and we construct the object model, table model, SQL code to define the relation of the information, and represent the information feature based on a wide range of views. After users gain a better global understanding of the information feature, retrieve more easily through their information. Conventional information retrieval is user-oriented to be what user want, but proposed technique it data-oriented which helps users to understand what exist in database by showing information feature.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.11 no.11
• /
• pp.4473-4482
• /
• 2010

The examination of pulse, which is a typical palpation technique in the oriental medicine, has been used conventional analog system for discrimination of 28 pulses. However, the clipping phenomenon in the pulses, which used same feature extraction technique with ECG signals, has been occurred in analog system due to feature extraction method and over amplification from the input signals. It caused inaccurate to analyze the pulse signals. In this paper, we propose a digital filter design technique based on Prony's method for signal modeling and C-spline interpolation for feature extraction from pulse signal to compensate analog pulse detection system. In addition, we suggest a compensated electronic pulse detection system comprising new pulse analyzing algorithm and shape analysis technique for pulses, which were difficult to use in analog system. The feasibility for new proposed system has been confirmed comparing output signals between electronic pulse detection system having proposed filter design techniques with pulse analyzing algorithm and conventional analog system.