• Journal of Broadcast Engineering
• /
• v.17 no.6
• /
• pp.954-963
• /
• 2012

As a greedy algorithm reconstructing the sparse signal from underdetermined system, orthogonal matching pursuit (OMP) algorithm has received much attention. In this paper, we multiple candidate matching pursuit (MuCaMP), which builds up candidate support set in every iteration and uses the minimum residual at last iteration. Using the restricted isometry property (RIP), we derive the sufficient condition for MuCaMP to recover the sparse signal exactly. The MuCaMP guarantees to reconstruct the K-sparse signal when the sensing matrix satisfies the RIP constant ${\delta}_{N+K}<\frac{\sqrt{N}}{\sqrt{K}+3\sqrt{N}}$. In addition, we show a recovery performance both noiseless and noisy measurements.

• Journal of Information Processing Systems
• /
• v.10 no.3
• /
• pp.471-482
• /
• 2014

Influence maximization is an important problem of finding a small subset of nodes in a social network, such that by targeting this set, one will maximize the expected spread of influence in the network. To improve the efficiency of algorithm KK_Greedy proposed by Kempe et al., we propose two improved algorithms, Lv_NewGreedy and Lv_CELF. By combining all of advantages of these two algorithms, we propose a mixed algorithm Lv_MixedGreedy. We conducted experiments on two synthetically datasets and show that our improved algorithms have a matching influence with their benchmark algorithms, while being faster than them.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.49 no.2
• /
• pp.122-129
• /
• 2012

As a greedy algorithm reconstructing the sparse signal from underdetermined system, orthogonal matching pursuit (OMP) algorithm has received much attention in recent years. In this paper, we present an extension of OMP for pursuing efficiency of the index selection. Our approach, referred to as generalized OMP (gOMP), is literally a generalization of the OMP in the sense that multiple (N) columns are identified per step. Using the restricted isometry property (RIP), we derive the condition for gOMP to recover the sparse signal exactly. The gOMP guarantees to reconstruct sparse signal when the sensing matrix satisfies the RIP constant ${\delta}_{NK}$ < $\frac{\sqrt{N}}{\sqrt{K}+2\sqrt{N}}$. In addition, we show recovery performance and the reduced number of iteration required to recover the sparse signal.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39A no.12
• /
• pp.756-763
• /
• 2014

In this paper, we introduce a new sparse signal recovery algorithm referred to as the matching pursuit with greedy tree search (GTMP). The tree search in our proposed method is implemented to minimize the cost function to improve the recovery performance of sparse signals. In addition, a pruning strategy is employed to each node of the tree for efficient implementation. In our performance guarantee analysis, we provide the condition that ensures the exact identification of the nonzero locations. Through empirical simulations, we show that GTMP is effective for sparse signal reconstruction and outperforms conventional sparse recovery algorithms.

• Journal of Communications and Networks
• /
• v.18 no.5
• /
• pp.699-712
• /
• 2016

Recently, greedy algorithm has received much attention as a cost-effective means to reconstruct the sparse signals from compressed measurements. Much of previous work has focused on the investigation of a single candidate to identify the support (index set of nonzero elements) of the sparse signals. Well-known drawback of the greedy approach is that the chosen candidate is often not the optimal solution due to the myopic decision in each iteration. In this paper, we propose a tree search based sparse signal recovery algorithm referred to as the tree search matching pursuit (TSMP). Two key ingredients of the proposed TSMP algorithm to control the computational complexity are the pre-selection to put a restriction on columns of the sensing matrix to be investigated and the tree pruning to eliminate unpromising paths from the search tree. In numerical simulations of Internet of Things (IoT) environments, it is shown that TSMP outperforms conventional schemes by a large margin.

• Proceedings of the Korean Information Science Society Conference
• /
• 2008.06c
• /
• pp.555-560
• /
• 2008

두 장의 2차원 영상을 가지고 3차원을 재구성하기 위해서는 스테레오 정합을 이용한다. 이러한 이유로 그 동안에 많은 스테레오 정합에 대한 연구가 진행되었다. 스테레오 정합은 컴퓨터 기술의 발전과 더불어 좀 더 빠르고 높은 정확성을 보이고 있다. 하지만 속도와 정확성을 동시에 만족시키면서 대형영상에서도 동작할 수 있게 메모리을 적게 사용하는 방법은 많지가 않다. 본 논문에서는 이런 요구 조건을 만족시키기 위하여 새로운 스테레오 정합방법을 제시한다. 우리가 제시하는 새로운 방법은 다중 방향성 Greedy 알고리즘과 RANSAC을 반복적으로 사용하여 영상전체에 대한 스테레오 정합을 시도하는 방법이다. 우선 Greedy 알고리즘을 이용하여 여러 방향의 scan-line을 따라 깊이값 영상을 구한다. 그리고 이 여러 장의 깊이값 영상들의 분포를 RANSAC을 이용하여 신뢰영역을 찾아낸다. 구해진 신뢰영역을 바탕으로 Greedy 알고리즘과 RANSAC을 수 차례 반복하여 신뢰영역을 확장해 나가면 최종 깊이값 영상을 얻는다. 우리가 제안하는 알고리즘은 적은 메모리로도 큰 영상의 정합이 가능하고, 속도와 정확도 측면에서도 우수한 결과를 보인다.

• Journal of IKEEE
• /
• v.17 no.3
• /
• pp.339-345
• /
• 2013

In this paper, the probabilistic exclusion based orthogonal matching pursuit (PEOMP) algorithm for the sparse signal reconstruction is proposed. Some of recent greedy algorithms such as CoSaMP, gOMP, BAOMP improved the reconstruction performance by deleting unsuitable atoms at each iteration. They still often fail to converge to the solution because the support set could not escape from a local minimum. PEOMP helps to escape by excluding a random atom in the support set according to a well-chosen probability function. Experimental results show that PEOMP outperforms several OMP based algorithms and the $l_1$ optimization method in terms of exact reconstruction probability.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.9
• /
• pp.2087-2093
• /
• 2014

In this paper, an orthogonal matching pursuit (OMP) method combined with genetic algorithm (GA), named GAOMP, is proposed for sparse signal recovery. Some recent greedy algorithms such as SP, CoSaMP, and gOMP improved the reconstruction performance by deleting unsuitable atoms at each iteration. However they still often fail to converge to the solution because the support set could not avoid the local minimum during the iterations. Mutating the candidate support set chosen by the OMP algorithm, GAOMP is able to escape from the local minimum and hence recovers the sparse signal. Experimental results show that GAOMP outperforms several OMP based algorithms and the $l_1$ optimization method in terms of exact reconstruction probability.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.230-234
• /
• 1997

The matching pursuit (MP) algorithm developed by S. Mallat and Z. Zhang is applied to magnetic resonance (MR) imaging. Since matching pursuit is a greedy algorithm to find waveforms which are the best match for an object-signal, the signal can be decomposed with a few iterations. In this paper, we propose an application of the MP algorithm to the MR imaging to reduce imaging time. Inner products of residual signals and selected waveforms in the MP algorithm are derived from the MR signals by excitation of RF pulses which are fourier transforms of selected waveforms. Results from computer simulations demonstrate that the imaging time is reduced by using the MP algorithm and further a progressive reconstruction can be achieved.

• Proceedings of the KSRS Conference
• /
• 2003.11a
• /
• pp.1332-1333
• /
• 2003