Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 176 papers published in subject: > since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Masked Face Detection Using Deep Learning | |||
Li yichao,Qiting Ye,Zhao Luo,Shiming Ge | |||
Electrics, Communication and Autocontrol Technology 21 March 2016 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Face occlusion such as masked face is a challenge problem for most face detection algorithms due to a lack of discriminative information. In this paper, we proposed a novel method to address occluded face detection especially masked face detection. We built a masked face database whose images are collected from web images in the wild. The database includes more than 6000 images and more than 10000 masked faces. To perform masked face detection, we proposed a joint pre-detection and classification method, which learn a discriminative classifier based on deep learning to classify the face proposals which are generated by some weak face detectors. The classifier has higher discrimination power to masked face, unmasked face and non-face. Experimental comparisons with state-of-the-art face detection methods show that the proposed method can give better performance. . | |||
TO cite this article:Li yichao,Qiting Ye,Zhao Luo, et al. Masked Face Detection Using Deep Learning[OL].[21 March 2016] http://en.paper.edu.cn/en_releasepaper/content/4681179 |
2. Algebraic Connectivity Estimation Based On Decentralized Inverse Power Iteration | |||
Yue Wei, Hao Fang, Jie Chen, Bin Xin | |||
Electrics, Communication and Autocontrol Technology 29 December 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this work we propose a new scheme to estimate the algebraic connectivity of the Laplacian matrix associated with the graph describing the network topology of a multi-agent system. We consider network topologies modelled by undirected graphs. The main idea is to propose a new decentralized conjugate gradient algorithm and a decentralized compound inverse power iteration scheme is built, in which the matrix inversion computation is replaced by solving the non-homogeneous linear equations relying on the proposed decentralized conjugate gradient algorithm. With this scheme, we can achieve a fast convergence rate in algebraic connectivity estimation by setting the parameter $mu$ properly. Simulation results demonstrate the effectiveness of the proposed scheme. | |||
TO cite this article:Yue Wei, Hao Fang, Jie Chen, et al. Algebraic Connectivity Estimation Based On Decentralized Inverse Power Iteration[OL].[29 December 2015] http://en.paper.edu.cn/en_releasepaper/content/4673942 |
3. Design of LDPC Convolutional Codes with Improved Cycle Property | |||
ZHOU HUA,WENG SHAOHUI | |||
Electrics, Communication and Autocontrol Technology 21 December 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The cycles property of time-varying LDPC-CCs is superior to that of time-invariant LDPC-CCs. The concept of transformed LDPC-CCs, which can be considered as the time-varying version of the non-transformed one, is introduced. Based on the weight matrix of the transformed code, a family of LDPC-CCs with improved cycle properties is obtained. When the syndrome former memory is large, the enumerators for the short cycles of the designed LDPC-CCs are optimized, i.e., the number of short cycles is minimized. | |||
TO cite this article:ZHOU HUA,WENG SHAOHUI. Design of LDPC Convolutional Codes with Improved Cycle Property[OL].[21 December 2015] http://en.paper.edu.cn/en_releasepaper/content/4672185 |
4. A Novel Joint Block Diagonalization Algorithm for Convolutive BSS with Limited Constraint | |||
ZHANG Wei-Tao | |||
Electrics, Communication and Autocontrol Technology 08 December 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper, the convolutive blind source separation (CBSS) via joint block diagonalization (JBD) technique is revisited to reduce the rigorous constraint. As is known that the CBSS signal model under the JBD framework is equivalent to an instantaneous mixture model, where the mixing matrix is almost always non-square. This considerably restricts the applicability of existing JBD algorithms in CBSS problem for non-square mixing cases. In this paper the nonunitary JBD problem is reformulated as a multicriteria optimization model, where the mixing matrix can be non-square. Moreover, by optimizing the proposed model the resulting algorithm can eliminate the degenerate solutions in nonunitary JBD. The simulation results show that the proposed algorithm outperforms the existing JBD algorithms in terms of separation accuracy and stability. | |||
TO cite this article:ZHANG Wei-Tao. A Novel Joint Block Diagonalization Algorithm for Convolutive BSS with Limited Constraint[OL].[ 8 December 2015] http://en.paper.edu.cn/en_releasepaper/content/4670351 |
5. A new fusion algorithm with radar IR heterogeneous measurements for maneuvering target tracking | |||
LI Xingxiu,LIU Jiale | |||
Electrics, Communication and Autocontrol Technology 02 December 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents a interacting multiple model based on modified debiased converted measurement kalman filter (IMM-MDCMKF) for tracking a maneuvering target using radar/IR heterogeneous sensors. Under the architecture of the proposed algorithm, the interacting multiple model integrates different filter model to estimate target state, and the MDCMKF algorithm reduces the effect of measurement noise on the covariance effectively. Simulation results show the proposed algorithm is valid and feasible and has higher tracking accuracy than radar individual tracking. | |||
TO cite this article:LI Xingxiu,LIU Jiale. A new fusion algorithm with radar IR heterogeneous measurements for maneuvering target tracking[OL].[ 2 December 2015] http://en.paper.edu.cn/en_releasepaper/content/4668224 |
6. Learning-Based Compressed Sensing for Infrared Image Super Resolution | |||
Yao Zhao,Xiubao Sui,Qian Chen,Shaochi Wu | |||
Electrics, Communication and Autocontrol Technology 30 November 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents an infrared image super-resolution method based on compressed sensing (CS). First, the reconstruction model under the CS framework is established and a Toeplitz matrix is selected as the sensing matrix. Compared with traditional learning-based methods, the proposed method uses a set of sub-dictionaries instead of two coupled dictionaries to recover high resolution (HR) images. And Toeplitz sensing matrix allows the proposed method time-efficient. Second, all training samples are divided into several feature spaces by using the proposed adaptive k-means classification method, which is more accurate than the standard k-means method. On the basis of this approach, a complex nonlinear mapping from the HR space to low resolution (LR) space can be converted into several compact linear mappings. Finally, the relationships between HR and LR image patches can be obtained by multi-sub-dictionaries and HR infrared images are reconstructed by the input LR images and multi-sub-dictionaries. The experimental results show that the proposed method is quantitatively and qualitatively more effective than other state-of-the-art methods. | |||
TO cite this article:Yao Zhao,Xiubao Sui,Qian Chen, et al. Learning-Based Compressed Sensing for Infrared Image Super Resolution[OL].[30 November 2015] http://en.paper.edu.cn/en_releasepaper/content/4665509 |
7. Reconstruction of Sparse Signals in Heterogeneous Radar Sensor Network Based on Distributed Compressive Sensing | |||
MAO Cheng-chen,ZHU Fang-Qi,LIU Huai-Yuan,LIANG Jing | |||
Electrics, Communication and Autocontrol Technology 25 November 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper, we reconstruct signals in heterogeneous sensor network (HRSN) with distributed compressive sensing (DCS). Combining different types of measurement matrices and different numbers of measurements, we investigate three different scenarios in which HRSN is used to acquiring signals for the first time. In the first scenario, there are two different types of measurement matrices. One is Gaussian measurement and the other is Fourier measurement, and each sensor applies the same numbers of measurements. In the second scenario, all sensors use the same type of measurement matrices but the number of measurements are different each other. The third scenario combines different types of measurement matrix and distinct numbers of measurements. Our simulation results show that in Scenario I, when the common sparsity is considerable, the DCS scheme can reduce the number of measurements. In Scenario II, the reconstruction situation becomes better with the increase of the number of measurements. In both Scenario I and III, joint decoding that use different types of measurement matrices performs better than that of all-Gaussian measurement matrices, but it performs worse than that of all-Fourier measurement matrices. Therefore, DSC is a good compromise between reconstruction percentage and the number of measurements in HRSN. | |||
TO cite this article:MAO Cheng-chen,ZHU Fang-Qi,LIU Huai-Yuan, et al. Reconstruction of Sparse Signals in Heterogeneous Radar Sensor Network Based on Distributed Compressive Sensing[OL].[25 November 2015] http://en.paper.edu.cn/en_releasepaper/content/4665647 |
8. Cluster-head Election Algorithms in Fuzzy Logic Systems for Radar Sensor Networks | |||
HU Yao-Yue,LIU Huai-Yuan,LIANG Jing | |||
Electrics, Communication and Autocontrol Technology 25 November 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In this paper, we propose three cluster-head election schemes using fuzzy logic systems (FLSs) for clustered radar sensor networks. Three factors of a radar sensor (RS) are considered in our FLS design: its remaining energy (RE); the fading envelope of the signal transmitted by the RS to base station (FESTRBS); its distance to base station (DBS). The three cluster-head election schemes are named FF (FLS with two-antecedents & fuzzy-c means (FCM) ), FFSVD (FLS with two-antecedents, FCM, and singular value decomposition-QR (SVD-QR)), and FF3SVD (FLS with three-antecedent FLS, FCM and SVD-QR). Their clustering performances in terms of detection performances and networks' lifetime are compared and analyzed. Monte Carlo simulations show that among these three cluster-head election schemes, FF3SVD provides the lowest energy consumption and moderate probability of target detection (PD), and FFSVD offers moderate power loss and the highest PD, whereas FF has the worst clustering performances. | |||
TO cite this article:HU Yao-Yue,LIU Huai-Yuan,LIANG Jing. Cluster-head Election Algorithms in Fuzzy Logic Systems for Radar Sensor Networks[OL].[25 November 2015] http://en.paper.edu.cn/en_releasepaper/content/4665638 |
9. Multiple Sensors Joint Tracking of Maneuvering Target with Intermission Radar Measurement | |||
LI Xingxiu,LIU Jiale | |||
Electrics, Communication and Autocontrol Technology 22 November 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper presents a modified debiased converted measurement kalman filter based on interacting multiple model (IMM-MDCMKF) for tracking a maneuvering target using radar/infrared heterogeneous sensors. Under the architecture of the proposed algorithm, the interacting multiple model deals with the model switching, while a modified debiased converted measurement kalman filter (MDCMKF) is derived to account for non-linearity in the dynamic system models. The MDCMKF algorithm improves the converted error covariance matrix by introducing state estimate, and reduces the effect of measurement noise on the covariance effectively. The 3th order polynomial fitting is used to estimate the measurements when radar turns off. Simulation results show the proposed algorithm is valid and feasible in case of radar under intermittent working state, and has higher tracking accuracy than the traditional algorithms. | |||
TO cite this article:LI Xingxiu,LIU Jiale. Multiple Sensors Joint Tracking of Maneuvering Target with Intermission Radar Measurement[OL].[22 November 2015] http://en.paper.edu.cn/en_releasepaper/content/4664599 |
10. Proportional Fairness Optimization with Energy Efficiency guaranteed for FeICIC | |||
Tu Si-Jia,Niu Kai,Dong Chao | |||
Electrics, Communication and Autocontrol Technology 06 November 2015 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The paper has studied the user's proportional fairness and system energy efficiency under the joint cell range expansion(CRE) and Further enhanced Inter-Cell Interference Coordination(FeICIC) scheme of two-tier Heterogeneous networks(Het-net). Performances of downlink Het-net including the joint probability density function of signal-interference ratio(SIR), system energy efficiency(EE) and user's proportional fairness(PF) are analyzed. Paper also discusses the influence of CRE bias and power reduction ratio to the EE and PF. In the simulation section, numerical results of EE and PF are obtained. Using these numerical results, we lay a polynomial fitting of EE and PF to do the collaborative optimization. Our analysis shows the optimum parameters setting to obtain the maximum UE's proportional fairness with the energy efficiency guaranteed. | |||
TO cite this article:Tu Si-Jia,Niu Kai,Dong Chao. Proportional Fairness Optimization with Energy Efficiency guaranteed for FeICIC[OL].[ 6 November 2015] http://en.paper.edu.cn/en_releasepaper/content/4660430 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated