• Journal of the Korea Society of Computer and Information
• /
• v.22 no.12
• /
• pp.55-61
• /
• 2017

In this paper, we propose a novel tracking method using target separation and detection that are based on discriminative correlation filter (DCF), which is studied a lot recently. 'Retainability' is one of the most important factor of tracking. There are some factors making retainability of tracking worse. Especially, fast movement and occlusion of a target frequently occur in image data, and when it happens, it would make target lost. As a result, the tracking cannot be retained. For maintaining a robust tracking, in this paper, separation of a target is used so that normal tracking is maintained even though some part of a target is occluded. The detection algorithm is executed and find new location of the target when the target gets out of tracking range due to occlusion of whole part of a target or fast movement speed of a target. A variety of experiments with various image data sets are conducted. The algorithm proposed in this paper showed better performance than other conventional algorithms when fast movement and occlusion of a target occur.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.5
• /
• pp.807-812
• /
• 2020

This paper proposes a blind speech source separation algorithm using a microphone to separate only the target speech source signal in an environment in which various speech source signals are mixed. The proposed algorithm is a model of frequency domain representation based on independent component analysis method. Accordingly, for the purpose of verifying the validity of independent component analysis in the frequency domain for two speech sources, the proposed algorithm is executed by changing the type of speech sources to perform speech sources separation to verify the improvement effect. It was clarified from the experimental results by the waveform of this experiment that the two-channel speech source signals can be clearly separated compared to the original waveform. In addition, in this experiments, the proposed algorithm improves the speech source separation performance compared to the existing algorithms, from the experimental results using the target signal to interference energy ratio.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.4
• /
• pp.261-266
• /
• 2017

In this paper, we propose a vocal and nonvocal separation method which uses a combination of kernel model and LSTM (Long-Short Term Memory) networks. Conventional vocal and nonvocal separation methods estimate the vocal component even in sections where only non-vocal components exist. This causes a problem of the source estimation error. Therefore we combine the existing kernel based separation method with the vocal/nonvocal classification based on LSTM networks in order to overcome the limitation of the existing separation methods. We propose a parallel combined separation algorithm and series combined separation algorithm as combination structures. The experimental results verify that the proposed method achieves better separation performance than the conventional approaches.

• The KIPS Transactions:PartB
• /
• v.10B no.4
• /
• pp.397-402
• /
• 2003

This paper proposes an efficient fixed-point (FP) algorithm for improving performances of the independent component analysis (ICA) based on neural networks. The proposed algorithm is the FP algorithm based on Newton method for ICA using the adaptive learning parameters. The purpose of this algorithm is to improve the separation speed and performance by using the learning parameters in Newton method, which is based on the first order differential computation of entropy optimization function. The learning rate and the moment are adaptively adjusted according to an updating state of inverse mixing matrix. The proposed algorithm has been applied to the fingerprints and the images generated by random mixing matrix in the 8 fingerprints of 256${\times}$256-pixel and the 10 images of 512$\times$512-pixel, respectively. The simulation results show that the proposed algorithm has the separation speed and performance better than those using the conventional FP algorithm based on Newton method. Especially, the proposed algorithm gives relatively larger improvement degree as the problem size increases.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.7
• /
• pp.618-627
• /
• 1990

In this paper a new algorithm for separation of contacting subpattern and connective feature extraction of strokes is proposed. This algorithm is able to classification of the type of contacting parts, connective feature extreaction of strokes, separate the phoneme of contacting parts between strokes, classify the character types by feature classification of connecting parts and analysis of connecting attribute. Also, shape normalize into formal patterns and decide on the input pattern from position value of bending feature of this normalized shape and make an recognition experiment by neural network using BEP learining algorithm. This algorithm represents the good achievement ratio by separation of phoneme, classification of character type, connective feature extraction of stroke and recognition experiment.

• Journal of Biomedical Engineering Research
• /
• v.17 no.3
• /
• pp.319-326
• /
• 1996

Clinical myography(EMG) is a technique for diagnosing neuromuscular disorders by analyzing the electrical signal that can be records by needle electrode during a muscular contraction. The EMG signal arises from electrical discharges that accompany the generation of force by groups of muscular fiber, and the analysis of EMG signal provides symptoms that can distinguish disorder of mLecle from disor- ders of nerve. One of the methods for analysis of EMG signal is to separate the individual discharge-the motor unit action potentials(MVAPS) - from EMG signal. But we can only observe the EMG signal that is a superimposed version of time delayed MUAPS. To obtain the information about MUAP(, i.e., position, firing number, magnitude etc), first of all, a method that can separate each MUAP from the EMG signal must be developed Although the methods for MUAP separation have been proposed by many researcherl they have required heavy computational burden. In this paper, we proposed a new method that has less computational burden and performs more reliable separation of superimposed EMG signal using wavelet filter which has multiresolution analysis as major property. As a result, we develope the separation algorithm of superimposed EMG signal which has less computational burden than any other researchers and exacutes exact separation process. The performance of this method has been discussed in the automatic resolving procedure which is neccessary to identify every firing of every motor unit from the EMG pattern.

• Journal of Korean Society of Transportation
• /
• v.12 no.3
• /
• pp.15-27
• /
• 1994

A mathematical model and its solution algorithm are proposed for computing the capacity of terminal control area. The model is built based on dynamics of aircraft flying on pre-established approach path and its solution algorithm employs a numerical method. The model computes the minimum separation of two aircraft at the entry fix of the terminal control area, which assures that air traffic separation rules are not violated during the approach phase, thereby computes the capacity. The model might be applied for designing approach paths for a new airport, for rearranging paths of an existing airport or establishing approach control procedures.

• Advances in nano research
• /
• v.3 no.3
• /
• pp.143-168
• /
• 2015

Initiation of crack and its growth simulation requires accurate model of traction - separation law. Accurate modeling of traction-separation law remains always a great challenge. Atomistic simulations based prediction has great potential in arriving at accurate traction-separation law. The present paper is aimed at establishing a method to address the above problem. A method for traction-separation law prediction via utilizing atomistic simulations data has been proposed. In this direction, firstly, a simpler approach of common neighbor analysis (CNA) for the prediction of crack growth has been proposed and results have been compared with previously used approach of threshold potential energy. Next, a scheme for prediction of crack speed has been demonstrated based on the stable crack growth criteria. Also, an algorithm has been proposed that utilizes a variable relaxation time period for the computation of crack growth, accurate stress behavior, and traction-separation atomistic law. An understanding has been established for the generation of smoother traction-separation law (including the effect of free surface) from a huge amount of raw atomistic data. A new curve fit has also been proposed for predicting traction-separation data generated from the molecular dynamics simulations. The proposed traction-separation law has also been compared with the polynomial and exponential model used earlier for the prediction of traction-separation law for the bulk materials.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.294-299
• /
• 2005

This paper presents the separation performance of the linearly mixed image signals with additive noises by using an independent component analyses(ICAs) of the fixed-point(FP) algorithm based on Newton and secant method, respectively. The Newton's FP-ICA uses the slope of objective function, and the secant's FP-ICA also uses the tangent line of objective function. The 2 kinds of ICA have been applied to the 2 dimensional 2-image with $512\times512$ pixels. Then Gaussian noise and Laplacian noise are added to the mixed images, respectively. The experimental results show that the Newton's FP-ICA has better the separation speed than secant FP-ICA and the secant's FP-ICA has also the better separation rate than Newton's FP-ICA. Especially, the Newton and secant method gives relatively larger improvement degree in separation speed and rate as the noise increases.

• Proceedings of the IEEK Conference
• /
• 2001.09a
• /
• pp.85-88
• /
• 2001

In this paper we consider a problem of blind co-channel signal separation, the goal of which is to estimate multiple co-channel digitally modulated signals using an antenna array. We employ the joint maximum likelihood estimation and present a sequential algorithm, which is referred to as sequential joint maximum likelihood (SJML) algorithm. It separates multiple co-channel signal on-line and converges fast in overdetermined noisy communication environment. And the computational complexity of SJML for M-QAM (M=8, 16, 64,...) signals is less expensive compared to the SLSP. Useful behavior of this algorithm are confirmed by simulations.