Search

This paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (MPVs). Using time domain and frequency domain features in combination with three common classification algorithms in pattern recognition, we develop a novel feature extraction method for vehicle classification. These three common classification algorithms are the k-nearest neighbor, the support vector machine, and the back-propagation neural network. Nevertheless, a problem remains with the original vehicle magnetic dataset collected being imbalanced, and may lead to inaccurate classification results. With this in mind, we propose an approach called SMOTE, which can further boost the performance of classifiers. Experimental results show that the k-nearest neighbor (KNN) classifier with the SMOTE algorithm can reach a classification accuracy of 95.46%, thus minimizing the effect of the imbalance.

Expression, occlusion, and pose variations are three main challenges for 3D face recognition. A novel method is presented to address 3D face recognition using scale-invariant feature transform (SIFT) features on 3D meshes. After preprocessing, shape index extrema on the 3D facial surface are selected as keypoints in the difference scale space and the unstable keypoints are removed after two screening steps. Then, a local coordinate system for each keypoint is established by principal component analysis (PCA). Next, two local geometric features are extracted around each keypoint through the local coordinate system. Additionally, the features are augmented by the symmetrization according to the approximate left-right symmetry in human face. The proposed method is evaluated on the Bosphorus, BU-3DFE, and Gavab databases, respectively. Good results are achieved on these three datasets. As a result, the proposed method proves robust to facial expression variations, partial external occlusions and large pose changes.

With the rapid growth of cloud computing services, there is an increasing need to expand applications across data centers. In these paradigms, common information exchange between two data centers can be assisted via one or more substrate nodes, which correspond to bidirectional relaying communication. In this paper, we investigate the performance of time division broadcast TDBC protocol in bidirectional cloud networks in the presence of channel estimation errors CEEs. The tight asymptotic expressions for individual and system outage probabilities are first presented in closed-form. It is shown that CEE causes outage probability to remain fixed even if the channel is noiseless. Then, the symbol error rate performance for TDBC protocol with M-ary Phase Shift Keying and M-ary quadrature amplitude modulation signals is analyzed. Simulation results validate the accuracy of our analytical results. Furthermore, comparison of signal-to-noise ratio gap ratio shows that TDBC protocol is less sensitive to the effect of CEE than analog network coding protocol. Copyright © 2014 John Wiley & Sons, Ltd.

This paper presents a novel method for 3D face recognition under expression and occlusion variations. It is based on the combination of the matching results from matching multiple partial regions on the 3D face. Spin image features are used for comparison between faces. Meanwhile, an efficient approach is proposed to detect nose tip and the nose tip determines the location of each candidate region. To fuse the contribution of each region, score-based and rank-based fusion scheme are performed and compared. The proposed method is evaluated on the Bosphorus database and achieves good results. It obtains 96.68% recognition rate in the presence of expression and occlusion variations.

This paper proposes a novel technique to detect the main moving trajectory of indoor pedestrians. Based on Long Short- Term Memory(LSTM) Network, this deep learning network is capable of learning the trajectory of human beings using indoor Wi-Fi positioning data. The data is collected by Wi-Fi detectors densely installed in a public building in the urban area, which can ensure the detection of any portable devices as long as the Wi-Fi module is turned on. Then the model works in the form of sequence modeling to learn the trajectory of the main stream extracted from massive pedestrian positioning data. In compare with methods like Recurrent Neural Network (RNN) and Gated Recurrent Unit(GRU), there is an obvious performance improvement of this method.

The Khatri-Rao (KR) subspace method is a high resolution method for direction-of-arrival (DOA) estimation. Combined with 2q level nested array, the KR subspace method can detect O(N2q) sources with N sensors. However, the method cannot be applicable to Gaussian sources when q is equal to or greater than 2 since it needs to use 2q-th order cumulants. In this work, a novel approach is presented to conduct DOA estimation by constructing a fourth order difference co-array. Unlike the existing DOA estimation method based on the KR product and 2q level nested array, the proposed method only uses second order statistics, so it can be employed to Gaussian sources as well as non-Gaussian sources. By exploiting a four-level nested array with N elements, our method can also identify O(N4) sources. In order to estimate the wideband signals, the proposed method is extended to the wideband scenarios. Simulation results demonstrate that, compared to the state of the art KR subspace based methods, the new method achieves higher resolution.

In this study, the authors address the problem of tracking a single target in a calibrated multi-camera surveillance system with information on its location in the first frame of each view. Recently, tracking with online multiple instance learning (OMIL) has been shown to give promising tracking results. However, it may fail in a real surveillance system because of problems arising from target orientation, scale or illumination changes. In this study, the authors show that fusing target information from multiple views can avoid these problems and lead to a more robust tracker. At each camera node, an efficient OMIL algorithm is used to model target appearance. To update the OMIL-based classifier in one view, a co-training strategy is applied to generate a representative set of training bags from all views. Bags extracted from each view hold a unique weight depending on similarity of target appearance between the current view and the view which contains the classifier that needs to be updated. In addition, target motion on a camera's image plane is modelled by a modified particle filter guided by the corresponding object two-dimensional (2D) location and fused 3D location. Experimental results demonstrate that the proposed algorithm is robust for human tracking in challenging scenes.

Based on the asymptotic analysis in spatially correlated Rician fading channel, the precoders for space-time block-coded multiple-input multiple-output system at high and low signal-to-noise ratios (SNRs) are, respectively, designed to minimise the system bit error rate (BER). The precoding for high SNR provides closed-form positive power allocation by using the Langrage optimisation method, and has the BER performance close to that of the optimal scheme, especially at high SNR. The Langrage multiplier does exist and is unique, and practical Newton's method is proposed to find its optimal value. Moreover, it has a closed-form solution for some special cases. Thus, it avoids the iterative calculation of some existing precoding schemes. The precoding for low SNR has a closed-form solution similar to onedirectional (1-D) beamforming, and can obtain the performance very close to that of the optimal scheme at low SNR. By combining the above two schemes, a simple and effective suboptimal precoding scheme can be achieved for different SNRs. Simulation results show that the proposed scheme derived from the integration of high and low SNR can provide BER lower than the equal power precoding, and obtain the BER performance close to that of the existing optimal scheme with low complexity.

Quasi-cyclic low-density parity-check (QC-LDPC) codes are known to have algebraic structure, which suits hardware implementation. However, low girth makes their performances worse than random structured LDPC codes. Based on independent row-column mapping sequence, this work proposed a generalized method of constructing QC-LDPC codes with girth eight, which enlarges the class of girth eight QC-LDPC codes to a fairly general series. Simulation results show that the bit error rate of the constructed codes is close to that of progressive edge growth (PEG) based QC-LDPC codes under iterative decoding.

This paper proposes an explicit adaptive algorithm to solve the problem of heterogeneous dynamic synchronization of multi-agent uncertain systems. Different from the existing works, the proposed algorithm depends on less control parameters and achieves zero synchronization error between the agents of heterogeneous uncertain dynamic networks and virtual target. By introducing appropriate assumptions, a class of explicit adaptive synchronization protocols is designed based on a combination of the virtual target's states, distributed feedback gain, and the limited neighboring agents' information. By using Lyapunov function approach, it is proved that the explicit adaptive synchronization problem of closed-loop multi-agent uncertain systems with heterogeneous dynamic networks can be solved, if the control parameters of the explicit adaptive synchronization algorithm are suitably selected. Finally, an example is given to demonstrate the proposed theory.

Acquisition is a key technology in DSSS system. The differential correlation is usually employed to eliminate the effect of frequency deviation. However, as the length of pseudo-code grows and the decrease of the SNR, the traditional differential acquisition algorithms will result in great loss of SNR. This paper presents an improved differential acquisition method, named as M-orders Auto-Correlation based on Differential correlation (MAC-DF). In the proposed method, the input signal is multiplied by the complex conjugate of the pseudo-code to eliminate its effect. After that, the product is applied to the M-orders Auto-Correlation to compensate the SNR loss caused by the differential process. By means of mathematical model to analyze its acquisition performance. We compare MAC-DF acquisition algorithm with the differential coherent and non-coherent acquisition algorithms through simulation. The simulation results indicate that this algorithm is approximately 5–6dB superior to the traditional differential acquisition algorithms in improving acquisition sensitivity and more adaptive to work under low SNR.

A compressive sensing joint sparse representation direction of arrival estimation (CSJSR-DoA) approach is proposed for wireless sensor array networks (WSAN). By exploiting the joint spatial and spectral correlations of acoustic sensor array data, the CSJSR-DoA approach provides reliable DoA estimation using randomly-sampled acoustic sensor data. Since random sampling is performed at remote sensor arrays, less data need to be transmitted over lossy wireless channels to the fusion center (FC), and the expensive source coding operation at sensor nodes can be avoided. To investigate the spatial sparsity, an upper bound of the coherence of incoming sensor signals is derived assuming a linear sensor array configuration. This bound provides a theoretical constraint on the angular separation of acoustic sources to ensure the spatial sparsity of the received acoustic sensor array signals. The Cram e ´ r–Rao bound of the CSJSR-DoA estimator that quantifies the theoretical DoA estimation performance is also derived. The potential performance of the CSJSR-DoA approach is validated using both simulations and field experiments on a prototype WSAN platform. Compared to existing compressive sensing-based DoA estimation methods, the CSJSR-DoA approach shows significant performance improvement.

In cognitive radio (CR) networks, unlicensed secondary users need to conduct spectrum sensing to gain access to a licensed spectrum band. And cooperation among CR users will solve the problems caused by multipath fading and shadowing. In this paper, we propose a multi-threshold method at local nodes to cope with noises of great uncertainty. Functions of distance between bodies of evidence are used at fusion centre to make synthetic judgment. To guarantee security which is an essential component for basic network functions, we will take selfish nodes into account which try to occupy channels exclusively. The proposed technique has shown better performance than conventional algorithms without increase the system overhead.

In this paper, the energy efficiency (EE) of distributed antenna system (DAS) with multiple receive antennas is investigated over composite fading channel that takes the path loss, shadow fading and Rayleigh fading into account. Our aim is to maximize EE which is defined as the ratio of the transmission rate to the total consumed power under the constraints of maximum transmit power of each remote antenna. According to the definition of EE and using the upper bound of average EE, the optimized objective function is provided. Based on this, utilizing Karush-Kuhn-Tucker (KKT) conditions and mathematical derivation, a suboptimal energy efficient power allocation (PA) scheme is developed, and closed-form expression of PA coefficients is achieved. The developed scheme can obtain the EE close to the existing optimal scheme due to better approximation, especially for larger receive antenna number. Moreover, it has lower calculation complexity than the existing optimal scheme because only the statistic channel information is needed. Simulation results verify the effectiveness of the developed scheme.

Mobile localization is a significant issue for wireless sensor networks (WSNs). However, it is a problem for the indoor localization using received signal strength (RSS) measurements that the signal is contaminated by the anisotropy fading and interference due to walls and furniture. Standard schemes such as Kalman filter are inadequate as the random transition of line-of-sight (LOS)/non-line-of-sight (NLOS) conditions occurs frequently. This paper proposes an indoor mobile localization scheme with RSS measurements in a mixed LOS and NLOS environment. First, a new efficient composite measurement model is induced and validated, which approximates the complex effects of LOS and NLOS channels. Second, a greedy anchor sensor selection strategy is adopted to break through the constraints of hardware consistency and the multipath interference. Third, for the Markov transition between LOS and NLOS conditions, an effective unscented Kalman filter (UKF) based interactive multiple model (IMM) is proposed to estimate not only the posterior model probabilities but also a weighted-sum position estimation with the aid of likelihood function. To evaluate the proposed algorithm, a complete hardware and software platform for mobile localization has been constructed. The numerical study, relying on the actual experiments, illustrates that the proposed UKF based IMM achieves a substantial gain in precision and robustness, compared with other works.