• 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

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.383-388
• /
• 2005

Depth recovery in robot vision is an essential problem to infer the three dimensional geometry of scenes from a sequence of the two dimensional images. In the past, many studies have been proposed for the depth estimation such as stereopsis, motion parallax and blurring phenomena. Among cues for depth estimation, depth from lens translation is based on shape from motion by using feature points. This approach is derived from the correspondence of feature points detected in images and performs the depth estimation that uses information on the motion of feature points. The approaches using motion vectors suffer from the occlusion or missing part problem, and the image blur is ignored in the feature point detection. This paper presents a novel approach to the defocus technique based depth from lens translation using sequential SVD factorization. Solving such the problems requires modeling of mutual relationship between the light and optics until reaching the image plane. For this mutuality, we first discuss the optical properties of a camera system, because the image blur varies according to camera parameter settings. The camera system accounts for the camera model integrating a thin lens based camera model to explain the light and optical properties and a perspective projection camera model to explain the depth from lens translation. Then, depth from lens translation is proposed to use the feature points detected in edges of the image blur. The feature points contain the depth information derived from an amount of blur of width. The shape and motion can be estimated from the motion of feature points. This method uses the sequential SVD factorization to represent the orthogonal matrices that are singular value decomposition. Some experiments have been performed with a sequence of real and synthetic images comparing the presented method with the depth from lens translation. Experimental results have demonstrated the validity and shown the applicability of the proposed method to the depth estimation.

• Journal of the Korea Society for Simulation
• /
• v.30 no.1
• /
• pp.75-85
• /
• 2021

In this paper, we present a deep neural network-based prediction model that processes and analyzes the corporate credit and personal credit information of individual business owners as a new method to predict the default rate of individual business more accurately. In modeling research in various fields, feature selection techniques have been actively studied as a method for improving performance, especially in predictive models including many features. In this paper, after statistical verification of macroeconomic indicators (macro variables) and credit information (micro variables), which are input variables used in the default rate prediction model, additionally, through the credit information feature selection method, the final feature set that improves prediction performance was identified. The proposed credit information feature selection method as an iterative & hybrid method that combines the filter-based and wrapper-based method builds submodels, constructs subsets by extracting important variables of the maximum performance submodels, and determines the final feature set through prediction performance analysis of the subset and the subset combined set.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.9 no.7
• /
• pp.1513-1517
• /
• 2005

In this paper, I make use of a Multi-Channel skin color model with Hue, Cb, Cg using Red, Blue, Green channel altogether which remove bight component as being consider the characteristics of skin color to do modeling more effective to a facial skin color for extracting a facial area. 1 used efficient HOLA(Higher order local autocorrelation function) using 26 feature vectors to obtain both feature vectors of a facial area and the edge image extraction using Harr wavelet in image which split a facial area. Calculated feature vectors are used of date for the facial recognition through learning of neural network It demonstrate improvement in both the recognition rate and speed by proposed algorithm through simulation.

• Journal of the Semiconductor & Display Technology
• /
• v.15 no.2
• /
• pp.61-65
• /
• 2016

Facial feature detection is a fundamental function in the field of computer vision such as security, bio-metrics, 3D modeling, and face recognition. There are many algorithms for the function, active shape model is one of the most popular local texture models. This paper addresses issues related to face detection, and implements an efficient extraction algorithm for extracting the facial feature points to use on iOS platform. In this paper, we extend the original ASM algorithm to improve its performance by four modifications. First, to detect a face and to initialize the shape model, we apply a face detection API provided from iOS CoreImage framework. Second, we construct a weighted local structure model for landmarks to utilize the edge points of the face contour. Third, we build a modified model definition and fitting more landmarks than the classical ASM. And last, we extend and build two-dimensional profile model for detecting faces within input images. The proposed algorithm is evaluated on experimental test set containing over 500 face images, and found to successfully extract facial feature points, clearly outperforming the original ASM.

• International Journal of Computer Science & Network Security
• /
• v.23 no.7
• /
• pp.131-140
• /
• 2023

Network security situational awareness systems helps in better managing the security concerns of a network, by monitoring for any anomalies in the network connections and recommending remedial actions upon detecting an attack. An Intrusion Detection System helps in identifying the security concerns of a network, by monitoring for any anomalies in the network connections. We have proposed a CRF based IDS system using genetic search feature selection algorithm for network security situational awareness to detect any anomalies in the network. The conditional random fields being discriminative models are capable of directly modeling the conditional probabilities rather than joint probabilities there by achieving better classification accuracy. The genetic search feature selection algorithm is capable of identifying the optimal subset among the features based on the best population of features associated with the target class. The proposed system, when trained and tested on the bench mark NSL-KDD dataset exhibited higher accuracy in identifying an attack and also classifying the attack category.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.325-345
• /
• 2023

In the rapidly evolving domain of e-commerce, our study presents a cohesive approach to enhance customer satisfaction prediction from online reviews, aligning methodological innovation with practical insights. We integrate the RFE-SHAP feature selection with LDA topic modeling to streamline predictive analytics in e-commerce. This integration facilitates the identification of key features-specifically, narrowing down from an initial set of 28 to an optimal subset of 14 features for the Random Forest algorithm. Our approach strategically mitigates the common issue of overfitting in models with an excess of features, leading to an improved accuracy rate of 84% in our Random Forest model. Central to our analysis is the understanding that certain aspects in review content, such as quality, fit, and durability, play a pivotal role in influencing customer satisfaction, especially in the clothing sector. We delve into explaining how each of these selected features impacts customer satisfaction, providing a comprehensive view of the elements most appreciated by customers. Our research makes significant contributions in two key areas. First, it enhances predictive modeling within the realm of e-commerce analytics by introducing a streamlined, feature-centric approach. This refinement in methodology not only bolsters the accuracy of customer satisfaction predictions but also sets a new standard for handling feature selection in predictive models. Second, the study provides actionable insights for e-commerce platforms, especially those in the clothing sector. By highlighting which aspects of customer reviews-like quality, fit, and durability-most influence satisfaction, we offer a strategic direction for businesses to tailor their products and services.

• Journal of the Korean Society of Safety
• /
• v.16 no.1
• /
• pp.88-93
• /
• 2001

This study discusses frequency analysis based on autoregressive (AR) time series model, and process characterization in orthogonal cutting of a fiber-matrix composite materials. A sparsely distributed idealized composite material, namely a glass reinforced polyester (GFRP) was used as workpiece. Analysis method employs a force sensor and the signals from the sensor are processed using AR time series model. The resulting pattern vectors of AR coefficients are then passed to the feature extraction block. Inside the feature extraction block, only those features that are most sensitive to different types of cutting mechanisms are selected. The experimental correlations between the different chip formation mechanisms and AR model coefficients are established.

• Proceedings of the KSRS Conference
• /
• v.1
• /
• pp.98-101
• /
• 2006

In general, stereo images are widely used to remote sensing or photogrametric applications for the purpose of image understanding and feature extraction or cognition. However, the most cases of these stereo-based application deal with 2-D satellite images or the airborne photos so that its main targets are generation of small-scaled or large-scaled DEM(Digital Elevation Model) or DSM(Digital Surface Model), in the 2.5-D. Contrast to these previous approaches, the scope of this study is to investigate 3-D stereo processing and visualization of true geo-referenced 3-D features based on anaglyph technique, and the aim is at the prototype development for stereo visualization system of complex typed 3-D GIS features. As for complex typed 3-D features, the various kinds of urban landscape components are taken into account with their geometric characteristics and attributes. The main functions in this prototype are composed of 3-D feature authoring and modeling along with database schema, stereo matching, and volumetric visualization. Using these functions, several technical aspects for migration into actual 3-D GIS application are provided with experiment results. It is concluded that this result will contribute to more specialized and realistic applications by linking 3-D graphics with geo-spatial information.

• Health Policy and Management
• /
• v.16 no.4
• /
• pp.1-23
• /
• 2006

There is general consensus in the research literature that market orientation is related to organizational performance. The study examines this relationship in the Korean hospital industry. One feature of this study is to examine the differences between large and small hospitals in terms of their market orientation, performance and the relationship between these constructs. The other feature is that both market orientation and performance are conceptualized as being multi-dimensional constructs. Hence a structural equations modeling (SEM) technique is used to examine the dimensionality of market orientation and performance and to examine the nature of this relationship. Data for this study are collected using a questionnaire that is mailed to the top marketing-related managers of 1,048 hospitals. Usable responses are obtained from 230 hospitals for a response rate of 21.9%. The SEM results confirm the multi-dimensional nature of both market orientation and performance, and the strong relationships between the constructs. Interestingly, this relationship is found to be much stronger for smaller hospitals than for larger hospitals. For smaller hospitals, this study shows that market orientation has a tremendous influence on performance, with almost 73.9% of the variance in performance being attributed to market orientation.