In recent years, unsupervised feature learning based on a neural network architecture has become a hot new topic for research [1]-[4]. The revival of interest in such deep networks can be attributed to the development of efficient optimization skills, by which the model parameters can be optimally estimated [5]. The milestone work done by Hinton and Salakhutdinov [6] proposes to initialize the weights that allow deep autoencoder networks to learn low-dimensional codes. The encoding trick introduced works much better than principal component analysis (PCA) in terms of dimension reduction.

In this paper, two optimal resource allocation schemes are developed for asynchronous multiple targets tracking (MTT) in heterogeneous radar network. The key idea of the heterogeneous resource allocation (HRA) schemes is to coordinate the heterogeneous transmit resource (transmit power, dwell time, etc.) of different types of radars for better resource utilization efficiency. We use the Bayesian Cramr-Rao lower bound (BCRLB) as a metric function to quantify the target tracking performance, and build the following two HRA schemes: For given system resource budget, (1) Minimize the total resource consumption for given BCRLB requirements on multiple targets; (2) Maximize the overall MTT accuracy. Instead of updating the state of each target recursively at different measurement arrival times, we combine multiple asynchronous measurements into a single composite measurement, and use it as an input of the tracking filter for state estimation. In such a case, target tracking BCRLB no longer needs to be recursively calculated, and thus we can formulate the HRA schemes as two convex optimization problems. We subsequently design two efficient methods to solve these problems by exploring their unique structures. Simulation results demonstrate that the HRA processes can either provide smaller overall MTT BCRLB for given resource budgets, or require less resource to establish the same tracking performance for multiple targets.

Due to hardware limitations of the imaging sensors, it is challenging to acquire images of high resolution in both spatial and spectral domains. Fusing a low-resolution hyperspectral image (LR-HSI) and a high-resolution multispectral image (HRMSI) to obtain an HR-HSI in an unsupervised manner has drawn considerable attention. Though effective, most existing fusion methods are limited due to the use of linear parametric modeling for the spectral mixture process, and even the deep learning-based methods only focus on deterministic fully-connected networks without exploiting the spatial correlation and local spectral structures of the images. In this paper, we propose a novel variational probabilistic autoencoder framework implemented by convolutional neural networks, in order to fuse the spatial and spectral information contained in the LR-HSI and HRMSI, called FusionNet. The FusionNet consists of a spectral generative network, a spatial-dependent prior network, and a spatial-spectral variational inference network, which are jointly optimized in an unsupervised manner, leading to an end-toend fusion system. Further, for fast adaptation to different observation scenes, we give a meta-learning explanation to the fusion problem, and combine the FusionNet with meta-learning in a synergistic manner. Effectiveness and efficiency of the proposed method are evaluated based on several publicly available datasets, demonstrating that the proposed FusionNet outperforms the state-of-the-art fusion methods.

Multiple unmanned aerial vehicle (Multi-UAV) cooperative area search is an important and effective means of intelligence acquisition and disaster rescue. Search path planning is a critical factor to improve multi-UAV search performance. Aiming at the search inefficiency resulting from insufficient cooperation between UAVs in existing researches, we present a novel distributed real-time search path planning method based on distributed model predictive control (DMPC) framework. Firstly, we formulate the overall search objective function in finite time domain, considering not only repeated searches, but also maintenance of connectivity and collision avoidance between UAVs. Secondly, we decompose the overall search objective function to establish a distributed constrained optimization problem (DCOP) model, so that all UAVs optimize the overall search objective by interacting with neighbors. Thirdly, aiming at the problem of falling into the local optima in existing algorithms, distributed stochastic algorithm based on enhanced genetic algorithm (DSA-EGA) is proposed to solve the established DCOP model. We design a point crossover operator and introduce anytime local search (ALS) framework that stores the global optimal solution explored. Finally, the simulation results of different benchmark problems demonstrate that the proposed DSA-EGA outperforms other state-of-the-art algorithms in terms of the quality of solution. The simulation results of cooperative area search problems illustrate that the established DCOP model improves the search efficiency by 7.7 $\%$ , and DSA-EGA improves the search efficiency by 4.3 $\%$ at least. In addition, we also verify that our method has high scalability.

Unmanned aerial vehicle (UAV) swarms-enabled mobile edge computing (MEC) system can be deployed in critical industrial zones for monitoring. Meanwhile, its malicious use may bring great threat to the security, and the accurate detection and localization are important. UAV swarms show characteristics of the high density, small radar cross section (RCS), far range and time-varying motion, and have posed formidable challenges to the accurate detection and localization. In this paper, the accurate detection and localization of UAV swarms are investigated and an effective method is proposed based on the Dechirp-keystone transform (KT) and frequency-selective reweighted trace minimization (FS-RWTM). It inherits high robustness of the long-time integration (LTI) technique and super resolution of the gridless sparse technique. Mathematical analyses and numerical simulations validate its superiorities in accurate detection and localization of UAV swarms.