For WiFi indoor localization, collecting the data to construct the fingerprint dataset is a time-consuming and laborious job. In this paper, we propose to alleviate the time-intensive data-labeling by generating artificial fingerprint using a single AC-GAN. Compared to the existing multi-GAN approaches, we show that the use of a single AC-GAN could achieve the improved accuracy in localization, which is validated by extensive experiments. We also discuss its potential limit.

A new extreme learning machine (ELM) localization technique that uses received signal strength indicator fingerprints only is proposed for multifloor environments. This structured scheme forms multiple individual ELMs for the floors as well as for the geographically formed data clusters of each floor. Multifloor environments often have huge amount of training and online measurement data. To maximize efficiency, we develop a data preprocessing algorithm, aiming to: 1) efficiently extract out only the essential information from the vast amount of data sets and reduce the data dimension and 2) transform the floor-level data sets and positioning data sets of each floor into a proper structure that is suitable for the proposed ensemble ELM technique. The proposed solution is unique in that its offline phase exploits multiple individual ELMs for all floors to generate a set of floor-level classification functions with the preprocessed training data sets, and for each floor, it exploits multiple ELMs for the data clusters to generate a set of position regression functions. The online phase executes a coarse localization step to estimate the floor by using the floor-level classification functions and a refined step to estimate the position on the floor by using the position regression functions. The proposed algorithm and several existing algorithms are implemented to perform localization using the same measured datasets in a multistory building. For both floor estimation and localization on the floor, it outperforms existing schemes. For most cases, the performance gap is substantial.

Most localization methods for mixed far-field (FF) and near-field (NF) sources are based on uniform linear array (ULA) rather than sparse linear array (SLA). In this paper, we propose a localization method for mixed FF and NF sources based on the generalized symmetric linear arrays, which include ULAs, Cantor array, Fractal array and many other SLAs. Our method consists of two steps. In the first step, the high-order statistics of the array output is exploited to increase the degree of freedom. Then the direction-of-arrivals (DOAs) of the FF and NF sources are jointly estimated by using the recently proposed atomic norm minimization (ANM), which belongs to the gridless super-resolution method since the discretization of the parameter space is not required. In the second step, the ranges are given by MUSIC-like one-dimensional searching. Simulations results are provided to demonstrate the advantages of our method.

In this work, we find that radar signatures registered by wingbeats can work as a chronophotograph in radar version to record bird flight modes. When a bird flies, its wings and body compose a corner reflector, and the incident radiation upon either face of this wingbeat corner reflector impinges onto the other face and is reflected toward the illuminator, which enhances the bird signal intensity by 0-10 dB. When a bird flaps its wings, the corner works at a right angle, and the wingbeat corner reflector strongly modulates the radar signal; therefore, the contribution is strong and stably approaches 10 dB. During gliding, the wingbeat corner reflector fades away, the modulation effect significantly decreases, and the contribution approaches 0 dB. This difference can assist in classifying bird flight modes between flapping and gliding over a long sampling period. Both the Ku-band data from a duck in an anechoic chamber and the Ku-band radar data from a pigeon in an outside environment support the ability of this signature to classify gliding and flapping modes. We present flight mode transitions between flapping and gliding extracted from the radar echoes of small and large oncoming and outgoing birds.

Recent progress in deep convolutional neural networks has considerably changed the landscape of speech recognition, computer vision, natural language processing and so on. However, limited by the large number of parameters, the memory space and high computational complexity, it is a challenging task to deploy the deep neural network model in embedded system. To solve this problem, we propose Equal Trained Ternary Quantization (ETTQ), a ternary quantization method by improving Trained Ternary Quantization, which uses only a full-precision scaling coefficient for each layer, and quantize the weights to three levels. These positive and negative weights have same absolute values that are trainable parameters. Experiments show that the performance of ETTQ is only slightly worse than TTQ, but can converge faster and more stable during the training over CIFAR-10 and CIFAR-100 datasets.

Open set domain adaptation by back propagation (OSDA-BP) was recently proposed as a novel end-to-end training approach for tackling the open set scenario, where only a few categories of interest are shared between source and target data. This paper provides an insightful understanding of the binary cross entropy loss employed in OSDA-BP for picking up the potential unknown samples. With this new understanding, we propose to replace the binary cross entropy loss with a symmetrical Kullback Leibler(KL) distance based loss. This improved OSDA-BP method is extensively evaluated over Office-31 dataset and a considerable performance improvement is observed.

Pruning the parameters of basis filters can effectively eliminate the negative effect of redundant deep features in discriminative correlation filter based trackers. However, traditional methods often treat feature maps in Convolutional Neural Networks (CNN) as isolate observations, ignore the intrinsic correlation between partially attentional feature maps in multiple convolutional layers, when basis filter pruning is pursued. In this letter, we propose a multi-layer factorized discriminant correlation filter (MLF-DCF) for visual tracking. By integrating the multi-view discriminant learning and the discriminative correlation filter into a unified optimization problem, we can explore the correlation between different target sub-regions from multi-layer viewpoint, thus can effectively prune multi-layer basis filters. To enhance the efficiency of MLF-DCF in terms of speed and accuracy, we not only adopt alternating direction method of multipliers (ADMM) to solve the unified optimization, but also employ a mask estimation strategy to eliminate the background noise in deep features. A large number of experiments on challenging video sequences are given to illustrate the superiority of our tracking method.

Channel estimation is essential for precoding/combining in millimeter wave (mmWave) communications. However, accurate estimation is usually difficult because the receiver can only observe the low-dimensional projection of the received signals due to the hybrid architecture. We take the high speed scenario into consideration where the Doppler effect caused by fast-moving users can seriously deteriorate the channel estimation accuracy. In this paper, we propose to incorporate the nested array into analog array architecture by using RF switch networks with an objective of reducing the complexity and power consumption of the system. Based on the covariance fitting criterion, a joint Doppler and channel estimation method is proposed without need of discretizing the angle space, and thus the model mismatch effect can be totally eliminated. We also present an algorithmic implementation by solving the dual problem of the original one in order to reduce the computational complexity. Numerical simulations are provided to demonstrate the effectiveness and superiority of our proposed method.

The atomic norm minimization (ANM) has been successfully incorporated into the two-dimensional (2-D) direction-of-arrival (DOA) estimation problem for super-resolution. However, its computational workload might be unaffordable when the number of snapshots is large. In this paper, we propose two gridless methods for 2-D DOA estimation with L-shaped array based on the atomic norm to improve the computational efficiency. Firstly, by exploiting the cross-covariance matrix an ANM-based model has been proposed. We then prove that this model can be efficiently solved as a semi-definite programming (SDP). Secondly, a modified model has been presented to improve the estimation accuracy. It is shown that our proposed methods can be applied to both uniform and sparse L-shaped arrays and do not require any knowledge of the number of sources. Furthermore, since our methods greatly reduce the model size as compared to the conventional ANM method, and thus are much more efficient. Simulations results are provided to demonstrate the advantage of our methods.

Conventional reconstruction algorithms of compressed sensing suffer from serious performance degradation in impulsive noise environment. In this paper, we propose a modified Lorentzian greedy iterative algorithm to further improve the quality of the reconstructed sparse signals in such an adverse condition. By using bi-directional support estimation in conjunction with an iterative unconstrained Lorentzian norm optimization, we detect the impulse noise support first and then estimate the signal support to compute the values of sparse signals. Experimental results demonstrate that our proposed algorithm gives a higher average SNR and a lower computational cost than the conventional Lorentzian iterative thresholding algorithm does.

Existing indoor positioning methods for visible-light communication systems require large database, powerful signal processing units, additional sensors, such as gyroscopes, or the receiver placed toward a certain angle. These assumptions limit the applications of the indoor positioning systems in low-cost scenarios. In this paper, we propose a novel positioning framework based on the angle differences of arrival (ADOA) in 3-D coordinate systems, which can be used in receivers with image sensors or photodiodes. The proposed ADOA positioning does not require the receiver to be placed toward a certain angle and no additional sensor is required. Two positioning algorithms are proposed: one is based on the method of exhaustion (MEX), and the other is based on the least squares method (LSM). The MEX algorithm is analytically proved to be the optimal, while the LSM algorithm has much lower complexity. Both the upper and lower bounds are derived for the average discrepancy between the exact position and the estimated position. These performance bounds can facilitate the design of a light-emitting diode array. Experimental results show that the MEX algorithm can achieve an average error of 3.20 cm with a time cost of 0.36 s, and the LSM algorithm can achieve an average error of 14.66 cm with a time cost of 0.001 s.

Prior asymptotic performance analyses are based on the series expansion of the moment-generating function (MGF) or the probability density function (PDF) of channel coefficients. However, these techniques fail for lognormal fading channels because the Taylor series of the PDF of a lognormal random variable is zero at the origin and the MGF does not have an explicit form. Although lognormal fading model has been widely applied in wireless communications and free-space optical communications, few analytical tools are available to provide elegant performance expressions for correlated lognormal channels. In this paper, we propose a novel framework to analyze the asymptotic outage probabilities of selection combining (SC), equal-gain combining (EGC), and maximum-ratio combining (MRC) over equally correlated lognormal fading channels. Based on these closed-form results, we show: 1) the outage probability of EGC or MRC becomes an infinitely small quantity compared to that of SC at high signal-to-noise ratio (SNR); 2) channel correlation can cause an infinite performance loss at high SNR; and 3) negatively correlated lognormal channels can outperform the independent lognormal channels. The analyses reveal insights into the long-standing problem of asymptotic performance analyses over correlated lognormal channels, and circumvent the time-consuming Monte Carlo simulation and numerical integration.

Prior visible-light communication (VLC) positioning systems require the receiver to be placed towards a certain angle, or extra sensors like gyroscopes must be equipped to estimate the angle of the receiver. In this work, we propose a positioning scheme using cameras based on angle difference of arrival (ADOA). ADOA-based positioning does not need the receiver to know its tilting angle, and the position estimation is modeled as a three-variate optimization problem in a finite search region, which is tractable in most smart devices. Our experimental and numerical results show that the ADOA-based VLC positioning scheme achieves accuracy of centimeters and the average cost time is as low as 0.2 seconds.

In this paper, a new method for two-dimensional (2-D) direction-of-arrival (DOA) estimation is proposed. We first reconstruct the covariance matrix of the coarray with block-Toeplitz structure and then retrieve the DOAs. Our method is computationally efficient as supported by the derived closed-form expression for the estimated covariance matrix. Unlike other methods, which require fully loaded arrays, the proposed method can be applied in the case of common rectangular arrays with arbitrary geometries. The estimated azimuth and elevation angles are automatically paired. Moreover, our method is of high estimation accuracy and immune to the angle ambiguity effect. Numerical simulations are carried out to verify the effectiveness of the proposed method.

This paper addresses the issue of direction-of-arrival (DOA) estimation with an objective to eliminate the off-grid effect of the sparsity-based methods and enlarge the maximum number of distinguishable signals in the subspace-based methods. We first reconstruct the covariance matrix of the array output in the Toeplitz structure and then employ the reconstructed covariance matrix together with root-MUSIC to estimate the DOAs. The proposed covariance matrix reconstruction approach (CMRA) can be used for uniform and sparse linear arrays. It can also estimate the DOAs of multiple signals that are larger than the number of sensors by taking advantage of the array geometry. In contrast to the sparsity-based methods, CMRA is formulated in the continuous angle space rather than the discretized one, and hence it is immune to the off-grid effect. Simulations are carried out to verify the effectiveness of our method.

We propose a low-rate turbo-Hadamard coding approach for narrow-band interference (NBI) suppression. The proposed approach can be viewed as the employment of a coded spread-spectrum signalling with time-varying spreading sequences and the NBI suppression is naturally achieved in iterative decoding. Compared with the traditional code-aided NBI suppression with direct-sequence spread-spectrum (DS-SS) signalling, the spreading sequences for the turbo-Hadamard coding approach are non-constant in time and determined from the columns of a Hadamard matrix subject to the low-rate coding rule. The low-rate turbo-Hadamard coding approach is sharply compared with the code-aided DS-SS approach with convolutional coding. With a spreading sequence of length 32, it is shown that the proposed turbo-Hadamard approach outperforms the code-aided DS-SS approach even when its transmission information rate is about 5 times higher than that of the coded-aided DS-SS approach.

To improve the mean acquisition time performance of the zero-padding (ZP) method, we propose to fully exploit the computation capability of FFT by partially folding the local pseudo-noise (PN) code. The detection and mean acquisition time performance of the proposed method is analyzed and compared with that of the zero-padding method. It is shown that the proposed method can reduce the mean acquisition time significantly at the expense of less than 1.5 dB degradation in detection performance.

Owing to the characteristic of single frequency network (SFN) and non-line of sight (NLOS) environment, base station (BS) identification becomes a prominent problem in SFN positioning systems. In this work, a universal BS identification algorithm is proposed for any DTV standard. The basic idea is to formulate the base station identification problem as a data classification which is then solved by the least distance classifier. The state prediction model is utilized to estimate kinematics parameters and thus decrease the system hardware requirement. In order to obtain accurate state prediction for BS identification, an interacting multiple model (IMM) method is adopted to mitigate the NLOS effect for performance improvement. Because of close relation between the position estimation and BS identification, the proposed method is more effective as compared to some existing methods. Simulation results show that the proposed algorithm can perform well in both unfixed BS set and NLOS environments.

In this study, an efficient image fusion framework for multi‐focus images is proposed based on compressed sensing. The new fusion framework consists of three parts: image sampling, measurement fusion and image reconstruction. First, the dual‐channel pulse coupled neural network model is used in the image sampling part as an important weighting factor in the fusion scheme. Second, the result from the measurement fusion part is reconstructed through a new reconstruction algorithm called self‐adaptively modified Landwebber filter. Finally, computer simulation‐based experiment is conducted, showing that the novel fusion framework is capable of saving computational resource and enhancing the fusion result and is easy to implement.