• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제13권3호
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권3호
• /
• pp.1047-1062
• /
• 2018

In this paper the problem of massive multiple input multiple output (MIMO) channel estimation with sparsity aware adaptive algorithms for $5^{th}$ generation mobile systems is investigated. These channels are shown to be non-stationary along with being sparse. Non-stationarity is a feature that implies channel taps change with time. Up until now most of the adaptive algorithms that have been presented for channel estimation, have only considered sparsity and very few of them have been tested in non-stationary conditions. Therefore we investigate the performance of several newly proposed sparsity aware algorithms in these conditions and finally propose an enhanced version of RZA-LMS/F algorithm with variable threshold namely VT-RZA-LMS/F. The results show that this algorithm has better performance than all other algorithms for the next generation channel estimation problems, especially when the non-stationarity gets high. Overall, in this paper for the first time, we estimate a non-stationary Rayleigh fading channel with sparsity aware algorithms and show that by increasing non-stationarity, the estimation performance declines.

• 정보처리학회논문지A
• /
• 제8A권4호
• /
• pp.439-446
• /
• 2001

현재 대부분의 병렬 알고리즘은 동기 알고리즘으로 올바른 계산을 위해서는 프로세서들의 동기화와 부하균형이 필수적이다. 만일 부하균형이 불가능하거나 이질적 클러스터처럼 각 프로세서의 성능이 다른 경우, 연산은 가장 느린 프로세서의 성능에 의해 결정된다. 비동기 반복법은 이런 문제를 해결하는 하나의 방안으로 각광받고 있으나, 현재까지의 연구는 비교적 구현이 쉬운 공유 메모리 시스템을 사용한 것이었다. 본 논문에서는 분산 메모리 환경에서 초대형 선형 시스템 문제를 풀기 위해, 빠른 프로세서의 유휴 시간을 최대한 줄임으로써 전체적으로 성능을 향상시키는 비동기 병렬 알고리즘을 제안하고 이를 클러스터에 구현하였다.

• IEIE Transactions on Smart Processing and Computing
• /
• 제2권5호
• /
• pp.277-281
• /
• 2013

Modern speaker verification systems based on support vector machines (SVMs) use Gaussian mixture model (GMM) supervectors as their input feature vectors, and the maximum a posteriori (MAP) adaptation is a conventional method for generating speaker-dependent GMMs by adapting a universal background model (UBM). MAP adaptation requires the appropriate amount of input utterance due to the number of model parameters to be estimated. On the other hand, with limited utterances, unreliable MAP adaptation can be performed, which causes adaptation noise even though the Bayesian priors used in the MAP adaptation smooth the movements between the UBM and speaker dependent GMMs. This paper proposes a sparse MAP adaptation method, which is known to perform well in the automatic speech recognition area. By introducing sparse MAP adaptation to the GMM-SVM-based speaker verification system, the adaptation noise can be mitigated effectively. The proposed method utilizes the L0 norm as a regularizer to induce sparsity. The experimental results on the TIMIT database showed that the sparse MAP-based GMM-SVM speaker verification system yields a 42.6% relative reduction in the equal error rate with few additional computations.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권3호
• /
• pp.1014-1034
• /
• 2015

Location information of sensor nodes plays a critical role in many wireless sensor network (WSN) applications and protocols. Although many localization algorithms have been proposed in recent years, they usually target at dense networks and perform poorly in sparse networks. In this paper, we propose two component-based localization algorithms that can localize many more nodes in sparse networks than the state-of-the-art solution. We first develop the Basic Common nodes-based Localization Algorithm, namely BCLA, which uses both common nodes and measured distances between adjacent components to merge components. BCLA outperforms CALL, the state-of-the-art component-based localization algorithm that uses only distance measurements to merge components. In order to further improve the performance of BCLA, we further exploit the angular information among nodes to merge components, and propose the Component-based Localization with Angle and Distance information algorithm, namely CLAD. We prove the merging conditions for BCLA and CLAD, and evaluate their performance through extensive simulations. Simulations results show that, CLAD can locate more than 90 percent of nodes in a sparse network with average node degree 7.5, while CALL can locate only 78 percent of nodes in the same scenario.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권5호
• /
• pp.2346-2362
• /
• 2016

As one of the most important issues in computer vision and image processing, online object tracking plays a key role in numerous areas of research and in many real applications. In this study, we present a novel tracking method based on the proposed structured sparse representation model, in which the tracked object is assumed to be sparsely represented by a set of object and background templates. The contributions of this work are threefold. First, the structure information of all the candidate samples is utilized by a joint sparse representation model, where the representation coefficients of these candidates are promoted to share the same sparse patterns. This representation model can be effectively solved by the simultaneous orthogonal matching pursuit method. In addition, we develop a tracking algorithm based on the proposed representation model, a discriminative candidate selection scheme, and a simple model updating method. Finally, we conduct numerous experiments on several challenging video clips to evaluate the proposed tracker in comparison with various state-of-the-art tracking algorithms. Both qualitative and quantitative evaluations on a number of challenging video clips show that our tracker achieves better performance than the other state-of-the-art methods.

• 지능정보연구
• /
• 제29권3호
• /
• pp.167-183
• /
• 2023

최근 추천시스템 분야에서는 희소한 데이터를 효과적으로 모델링하기 위한 다양한 연구가 진행되고 있다. GLocal-K(Global and Local Kernels for Recommender Systems)는 그중 하나의 연구로 전역 커널과 지역 커널을 결합하여 데이터의 전역적인 패턴과 개별 사용자의 특성을 모두 고려해 사용자 맞춤형 추천을 제공하는 모델이다. 하지만 GLocal-K는 커널 트릭을 사용하기 때문에 매우 희소한 데이터에서 성능이 떨어지고 부가 정보를 사용하지 않아 새로운 사용자나 아이템에 대한 추천을 제공하는 데 어려움이 있다. 본 논문에서는 이러한 GLocal-K의 단점을 극복하기 위해 EASE(Embarrassingly Shallow Autoencoders for Sparse Data) 모델과 부가 정보를 활용한 GEase-K(Global and EASE kernels for Recommender Systems) 모델을 제안한다. 우선 GLocal-K의 지역 커널 대신 EASE를 활용하여 매우 희소한 데이터에서 추천 성능을 높이고자 하였다. EASE는 단순한 선형 연산 구조로 이루어져 있지만, 규제화와 아이템 간 유사도 학습을 통해 매우 희소한 데이터에서 높은 성능을 내는 오토인코더이다. 다음으로 Cold Start 완화를 위해 부가 정보를 활용하였다. 학습 과정에서 부가 정보를 추가하기 위해 조건부 오토인코더 구조를 적용하였으며 이를 통해 사용자-아이템 간의 유사성을 더 잘 파악할 수 있도록 하였다. 결론적으로 GEase-K는 선형 구조와 비선형 구조의 결합, 부가 정보의 활용을 통해 매우 희소한 데이터와 Cold Start 상황에서 강건한 모습을 보인다. 실험 결과, GEase-K는 매우 희소한 GoodReads, ModCloth 데이터 세트에서 RMSE, MAE 평가 지표 기준 GLocal-K 보다 높은 성능을 보였다. 또한 GoodReads, ModCloth 데이터 세트를 4개의 집단으로 나누어 실험한 Cold Start 실험에서도 GLocal-K 대비 Cold Start 상황에서 좋은 성능을 보였다.

• KNOM Review
• /
• 제24권2호
• /
• pp.24-34
• /
• 2021

엣지 컴퓨팅을 사용하는 서비스 공급업체는 높은 수준의 서비스를 제공한다. 이에 따라 다양하고 중요한 정보들이 단말 장치에 저장되면서 탐지하기 더욱 어려운 최신 사이버 공격의 핵심 목표가 됐다. 보안을 위해 침입 탐지시스템과 같은 보안 시스템이 자주 활용되지만, 기존의 침입 탐지 시스템은 탐지 정확도가 낮은 문제점이 존재한다. 따라서 본 논문에서는 엣지 컴퓨팅에서 단말 장치의 더욱 정확한 침입 탐지를 위한 기계 학습 모델을 제안한다. 제안하는 모델은 희소성 제약을 사용하여 입력 데이터의 중요한 특징 벡터들을 추출하는 stacked sparse autoencoder (SSAE)와 convolutional neural network (CNN)를 결합한 하이브리드 모델이다. 최적의 모델을 찾기 위해 SSAE의 희소성 계수를 조절하면서 모델의 성능을 비교 및 분석했다. 그 결과 희소성 계수가 일 때 96.9%로 가장 높은 정확도를 보여주었다. 따라서 모델이 중요한 특징들만 학습할 경우 더 높은 성능을 얻을 수 있었다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권4호
• /
• pp.305-309
• /
• 2011

A sparse reconfigurable adaptive filter (SRAF) based on a photonic switch determines the appropriate time delays and weight values for an optical switch implementation of tapped-delay-line (TDL) systems. It is well known that the choice of switch delays is significantly important for efficiently implementing the SRAF. If the same values exist as calculating the sum of weight magnitudes for implementing the connection constraint required by the SRAF, conventional connection algorithm based on sequentially selection the maximum elements might not work perfectly. In an effort to increase the effectiveness of system identification, an upgraded connection algorithm used progressive calculation to obtain the better solution is considered in this paper. The performance of the proposed connection constraint algorithm is illustrated by computer simulation for a system identification application.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권5호
• /
• pp.2102-2123
• /
• 2016

This paper considers a channel estimation scheme for millimeter-wave multiuser multiple-input multiple-output systems. According to the proposed method, parts of the beams are selected and the channel parameters are estimated according to the sparsity of channels and the orthogonality of the beams. Since the beams for each channel become distinct and the signal power increases with the increased number of antennas, the proposed approach is able to achieve good estimation performance. As a result, the sum rate can be increased in comparison with traditional approaches, and channels can be estimated with fewer pilot symbols. Numerical results verify that the proposed approach outperforms traditional approaches in cases with large numbers of antennas.