To address the challenge of catastrophic forgetting in synthetic aperture radar (SAR) image recognition caused by viewpoint-sensitive, high-interference samples encountered in dynamic environments, we propose a lightweight and efficient online class-incremental learning (OCI) framework named Interference-Aware Replay with Dynamic Review for SAR Target Recognition (IAR-DR). Based on the experience replay (ER) mechanism, a Maximally Interfered Retrieval (MIR) strategy is designed to prioritize the replay of high-interference samples by measuring loss changes before and after model updates, thereby preserving decision boundaries under viewpoint variation. A Review Trick (RT) mechanism is further introduced to periodically revisit all buffered samples with a low learning rate, which complements MIR by reinforcing global feature retention and enhancing long-term memory stability. The combination of MIR and RT achieves a synergistic balance between local discrimination and global generalization, mitigating the forgetting effect while maintaining the efficiency. Extensive experiments conducted on the MSTAR and Bistatic MiniSAR datasets demonstrate that the proposed IAR-DR framework maintains high recognition accuracy while achieving a forgetting rate as low as 6.92% in ablation studies, and improving retention by 4.7% over recent SAR class-incremental methods.

Visible light and thermal infrared tracking combines the characteristics of visible light and thermal infrared modalities to achieve robust target tracking in all-weather and all-day scenarios. However, most existing visible light and thermal infrared tracking methods rely on either full fine-tuning or attention mechanisms, which introduce a large number of parameters and are predominantly influenced by the visible modality. This results in challenges such as high computational complexity, slower processing speeds, and limited exploitation of multimodal information. To address these issues, this paper proposes a lightweight multimodal tracking model based on feature fusion and enhancement. The model consists of a feature fusion adapter and a joint enhancement adapter, designed to integrate and refine information across modalities. It employs a dual-stream transformer encoder with shared parameters across modality branches, utilizing a frozen pre-trained foundation model to independently extract features from visible light and thermal infrared inputs. The lightweight fusion adapter combines modality-specific information, while the joint enhancement adapter refines unimodal features, introducing only 0.23M trainable parameters. Experimental results on the LasHeR benchmark demonstrate that the proposed method outperforms prompt learning and other adapter-based methods, achieving a 4.4% improvement in PR and a 3.3% increase in SR while maintaining computational efficiency. With a real-time inference speed of 28.60 FPS, the proposed method balances accuracy and efficiency effectively. The source code will be available at https://github.com/huxue/MFJA.

Hyperspectral anomaly detection is a crucial technique for recognizing abnormal pixels in hyperspectral images (HSIs), that is, those with distinct spectral characteristics from those of the surrounding background. Traditional methods always fall short in effectively leveraging the information regarding the spectral and spatial aspects of the dataset simultaneously, limiting their detection performances. This article proposes a novel framework using U-Net, termed hybrid convolution and transformer-based U-Net (HCT-Unet), which integrates convolution with a multihead attention mechanism in Transformer for enhanced hyperspectral anomaly detection. To ensure a more comprehensive understanding of spatial and spectral interactions, the HCT-Unet architecture capitalizes on the strengths of local feature extraction of convolutional layers and the capabilities of the long-range dependency modeling of Transformers. A key innovation of this framework is an error attention mechanism, which facilitates adaptive multiscale feature fusion and enhances the feature representation capacity. Furthermore, a new anomaly score calculation method is proposed, which combines reconstruction error with the pixelwise structural similarity index (SSIM) to determine pixel anomaly from both local structural preservation and global spectral consistency perspectives. Experiments carried out on seven different hyperspectral datasets reveal that the proposed method consistently outperforms the widely accepted state-of-the-art methods in hyperspectral anomaly detection.

Convolutional neural networks (CNNs) have demonstrated strong performance in image processing tasks. However, as the complexity of the image scene increases, their ability to efficiently extract meaningful features diminishes. Quantum computing is increasingly recognized for its potential to address this limitation. We propose Scalable Quantum Feature Extraction (SQFE), a novel quantum feature extraction model designed as a variational quantum circuit (VQC) that mimics convolutional behavior while leveraging quantum principles. Unlike prior quantum feature extraction models that discard spatial features, use fixed quantum filters, or prevent joint optimization, SQFE supports full end-to-end training through backpropagation and is compatible with deep neural networks. SQFE is integrated into a ResNet-18 network to form the hybrid model QuRes. We evaluate multiple QuRes variants on a real-world dataset and demonstrate that QuRes models achieved test accuracies between 86.15% and 87.82%, outperforming the classical ResNet-18 with 84.84% accuracy. In terms of model complexity, QuRes reduced total parameter counts by 65%. These results highlight the potential of hybrid quantum-classical models to improve efficiency, scalability, and learning capacity in machine learning applications.

This paper presents a novel lightweight and robust object detection framework tailored for UAV-based applications. The core of the proposed method is the Dynamic Content-Augmented Feature Pyramid Network (DCA-FPN), which integrates a Global Content Extraction Module (GCEM), an Adaptive Branching Network (ABN), and a Linear Transformer (LT) to enhance multi-scale feature representation and contextual understanding. These components collectively improve detection performance for small and occluded objects while addressing the misalignment issues inherent in traditional feature pyramids. Built on a MobileNet backbone with depthwise separable convolutions, the framework offers low computational complexity and real-time readiness for edge devices. Experimental results on the Vis-Drone dataset show a state-of-the-art mean Average Precision (mAP) of 42.50%, while additional evaluations on the MS COCO benchmark confirm competitive performance across diverse object scales. Furthermore, testing on the GDIT Aerial Airport dataset demonstrates the model’s applicability in infrastructure monitoring tasks, particularly in detecting airplanes across varied sizes and conditions. These results highlight the robustness, efficiency, and deployment potential of the proposed framework in real-world, resource-constrained UAV scenarios.

The conventional direction-of-arrival (DoA) estimation approaches are effective only when the line-of-sight (LoS) link is available. In non-line-of-sight (NLoS) scenarios, it is challenging to effectively obtain the directional information of targets due to the uncontrollability of signal reflections from NLoS links. To handle this issue, a novel reconfigurable intelligent surface (RIS)-enabled gridless DoA estimation system for NLoS scenarios is proposed, where the RIS establishes a virtual LoS link between the base station and targets. First, considering the minable statistics of the signal, the RIS-enabled signal model in the covariance domain with a limited number of receiving antennas is proposed to help reduce resource consumption. Next, we estimate the noise variance by constraining the Frobenius norm of the measurement error matrix to enhance the robustness to noise. Then, we reconstruct the Hermitian Toeplitz matrix by addressing the atom norm minimization (ANM) problem on the covariance-noiseless matrix. To reduce the computation, an efficient iterative approach is designed via the alternating direction method of multipliers . Furthermore, this system’s Cramér–Rao lower bound is derived, which is further exploited as the DoA estimation’s reference bound. Numerical experiments validate the superiority of the proposed system over the benchmark in terms of computational efficiency and estimation precision.

An accurate prediction of energy production and consumption is a prerequisite for realizing reasonable energy scheduling in process industry. However, under the conditions of production-energy coupling, the energy operating status is highly related to production rhythm. Many prediction methods are unable to consider the impact of multi-production process correlation and planning constraints on energy data fluctuations. To tackle this problem, an industrial energy prediction method integrating plan and multi-dimensional data correlation is proposed. A data augmentation method based on wavelet matching is developed to extract specific features of the energy data and obtain augmented samples. To capture the alternating operation characteristics of different production processes, a contrastive learning (CL) method with probability jumping is developed that takes the process uncertainty into consideration. On this basis, the planning information is represented by a novel form of partial differential equations (PDEs), so that the global production information can be embedded as a priori knowledge within a physics-informed neural network (PINN) to achieve dynamic energy prediction. In order to validate the effectiveness of the proposed method, experiments are conducted using energy data from a steel company and compared with a variety of state-of-the-art methods. The results verify that the proposed method achieves better prediction results in complex industrial scenarios containing process coupling and planning constraints.

Deceptive jamming against synthetic aperture radar (SAR) is significant in defending against hostile reconnaissance and securing the region. Traditional jamming approaches primarily aim at single-imagery SAR, signal waveform type, multichannel, array, and degree of freedom. Since the video SAR (VideoSAR) system can enhance reconnaissance capability in detection, recognition, and perception in dynamic region of interest (DROI), it is imperative to devote to the relevant jamming discipline. To the best of our knowledge, it is the first time that a novel deceptive jamming perspective against VideoSAR system is proposed with simultaneously single-channel, single-band, and single-pass configurations. Frame-dependent principle of deceptive modulation against VideoSAR is derived from the video polar format algorithm (PFA). To obtain the VideoSAR deceptive jamming templates with diverse scattering features and high fidelity, a nonsubsampled Shearlet transform scattering characterization controlling approach is proposed for depicting the multidimensional intrinsic correlations of electromagnetic (EM) scattering behaviors. Three high-resolution airborne VideoSAR datasets are employed to confirm the effectiveness of the proposed deceptive jamming in anisotropy scenarios.

Operation optimization of industrial energy systems (IES) can effectively improve energy utilization efficiency and reduce carbon emissions. Learning-based optimization models such as reinforcement learning (RL) have been widely applied in dynamic scheduling of energy systems. However, they are usually time-driven periodic optimization that require the state variables having obvious time distribution rules, without considering the event-triggered characteristics of IES, and the uncertainty in state distribution caused by production-energy coupling. Thus, an event-driven neural Kalman state representation and dual-scale strategy learning framework is proposed in this study. To implement latent state construction with time distribution characteristics, an improved proximal policy optimization with neural Kalman state representation is developed to formulate time-driven scheduling policies, where the Kalman filter and RL parameters are trained in cascade to achieve an end-to-end learning process. In order to realize an event-driven policy learning, a state transition matrix connecting approach is proposed for collaborative calculation of time-event dual-scale policies. To verify the effectiveness of the proposed method, real data from a domestic steel company are employed for experiments. Commonly used and state-of-the-art approaches are selected for comparisons. The results validate the advantages of the proposed approach in terms of scheduling frequency, cost-effectiveness, and adaptation to industrial uncertain environments.

Multispectral image (MS) and panchromatic image (PAN) fusion, which is also named as multispectral pansharpening, aims to obtain MS with high spatial resolution and high spectral resolution. However, due to the usual neglect of noise and blur generated in the imaging and transmission phases of data during training, many deep learning (DL) pansharpening methods fail to perform on the dataset containing noise and blur. To tackle this problem, a variational optimization-guided two-stage network (VOGTNet) for multispectral pansharpening is proposed in this work, and the performance of variational optimization (VO)-based pansharpening methods relies on prior information and estimates of spatial-spectral degradation from the target image to other two original images. Concretely, we propose a dual-branch fusion network (DBFN) based on supervised learning and train it by using the datasets containing noise and blur to generate the prior fusion result as the prior information that can remove noise and blur in the initial stage. Subsequently, we exploit the estimated spectral response function (SRF) and point spread function (PSF) to simulate the process of spatial-spectral degradation, respectively, thereby making the prior fusion result and the adaptive recovery model (ARM) jointly perform unsupervised learning on the original dataset to restore more image details and results in the generation of the high-resolution MSs in the second stage. Experimental results indicate that the proposed VOGTNet improves pansharpening performance and shows strong robustness against noise and blur. Furthermore, the proposed VOGTNet can be extended to be a general pansharpening framework, which can improve the ability to resist noise and blur of other supervised learning-based pansharpening methods. The source code is available at https://github.com/HZC-1998/VOGTNet.

Diabetes mellitus is one of the fastest growing chronic health conditions worldwide, projected to affect 643 million people by 2030. Despite 100 years since insulin's discovery, diabetes remains a leading cause of death globally, responsible for about 5 % of fatalities. Traditional invasive glucose monitoring methods, such as blood pricks and implantable sensors, face challenges like patient discomfort and frequent replacement due to biofouling. In this research, we propose a low-cost DIY (do-it-yourself) electrochemical sweat glucose sensor using a fabric-based three-electrode system. The sensor integrates the enzyme Glucose Oxidase (GOx) with commercially available conductive fabrics, allowing non-invasive glucose detection without complex laboratory infrastructure. Fabrication techniques using household devices like Cricut and steam irons were employed for their affordability and ease of use. The sensor's performance was validated through Cyclic Voltammetry (CV) and Electrochemical Impedance Spectroscopy (EIS). Differential Pulse Voltammetry (DPV) was used to detect glucose achieving a sensitivity of 0.16 μA μM-1. To evaluate the stability of the sensors, the prepared patch was subjected to repeated DPV measurements using a specific glucose concentration over a period of 48 hours. The Relative Standard Deviation (RSD) was calculated to be 2.59 %. Notably, sweat glucose levels have shown a significant correlation with blood glucose levels, enhancing the potential of our approach for diabetes management. This method demonstrates significant potential for advancing medical diagnostics and developing multifunctional, smart wearable devices.

Due to the characteristics of light weight, low cost, and high resolution, millimeter wave (MMW) multiple-input multiple-output (MIMO) radars are widely applied in remote sensing and automotive systems. The MMW MIMO radar orthogonal waveform design is a key issue based on dechirp-on-receive technique to acquire high degree of freedom (DOF). In this paper, we propose an optimized interleaved orthogonal frequency division multiplexing (I-OFDM) chirp waveform design scheme using unequal sub-chirp duration and sparse sub-band constraint to further reduce the mutual interference (MI) between waveforms, and analyze the orthogonality of the original and optimized I-OFDM chirp waveform for MMW MIMO radar based on dechirp processing from various aspects. The simulation results show the effectiveness of the proposed method.

Hyperspectral (HS) and multispectral (MS) images’ fusion aims to improve their spatial resolutions and circumvent the main limitation of HS sensors. However, existing HS–MS fusion methods account for spectral variability fail to consider the global spectral correlation. To overcome this problem, this letter presents a novel joint weighted Schatten-p norm and spatial smoothness regularization for HS–MS fusion account for both spatial and spectral changes. First, the relationship between the spectral variability and the spectral signatures is formulated as an explicit parametric model. Second, to preserve the inherent correlation among the bands, we design a weighted Schatten-p ($ 0\lt p\lt 1 $) norm regularization method, which considers the importance of different components. Third, a spatial smoothness regularization term is exploited to reconstruct the spatial details. Finally, an iterative procedure based on the framework of alternating direction method of multipliers (ADMM) is designed to solve the resulting optimization problem. Extensive experiments on both synthetic and real datasets demonstrate that the proposed method outperforms six state-of-the-art methods from visual and quantitative assessments. The datasets and results are released inhttp://github.com/phan1007/WSGS.

A distributed multi-sensor control method is presented for multi-target tracking. The problem is formulated as auctioned partially observed Markov decision processes (auctioned POMDPs), which is a tractable approach to approximate the solutions in a distributed manner. To ensure adequate coverage of the multi-sensor system, a sparsity-promoting objective function is also designed to reduce overlapping sensing areas, balancing a tradeoff between the control reward and sensor coverage. Simulation results demonstrate that the proposed distributed method achieves comparable tracking performance to the state-of-art centralized approach. Furthermore, the proposed sparsity-promoting objective function outperforms the conventional Cauchy-Schwarz divergence (CSD) in discovery performance.

Deformable image registration is a process to determine the non-linear spatial correspondence among deformed image pairs. Generative registration network is a novel structure involving a generative registration network and a discriminative network that encourages the former to generate better results. We propose an Attention Residual UNet (AR-UNet) to estimate the complicated deformation field. The model is trained using perceptual cyclic constraints. As an unsupervised method, we require labelling for training and use virtual data augmentation to improve the robustness of the proposed model. We also introduce comprehensive metrics for image registration comparison. Experimental results show quantitative evidence that the method can predict reliable deformation field at a reasonable speed and outperform conventional learning based and non-learning based deformable image registration methods.

This paper presents a novel single-image object counting method based on block co-saliency density map estimation, called free-to-count everything network (F2CENet). Image block co-saliency attention is introduced to promote density estimation adaptation, allowing to input any image with arbitrary size for accurate counting using the learned model without requiring manually labeled few shots. The proposed network also outperforms existing crowd counting methods based on geometry-adaptive kernels in complex scenes. A novel module generates multilevel & scale block correlation maps to guide the co-saliency density map estimation. Co-saliency attention maps are then fused for accurately locating block-wise salient objects under guidance of the initial cues. Hence, accurate density maps are generated via comprehensive learning of internal relations in block co-salient features and progressive optimization of local details with saliency-oriented scene understanding. Results from extensive experiments on existing density map estimation datasets with arbitrary challenges verify the effectiveness of the proposed F2CENet and show that it outperforms various state-of-the-art few-shot and crowd counting methods. Mean Absolute Error (MAE) and Root Mean Square Error (RMSE) are used as evaluation metrics to measure the accuracy which are commonly used metrics for counting task. The average predicted MAE and RMSE are 10.88% and 8.44% less compared with the state-of-the-art evaluated on dataset contains sufficiently large and diverse categories used for few-shot and crowd counting.

An optimal energy scheduling strategy for integrated energy systems (IESs) can effectively improve the energy utilization efficiency and reduce carbon emissions. Due to the large-scale state space of IES caused by uncertain factors, it would be beneficial for the model training process to formulate a reasonable state-space representation. Thus, a condition knowledge representation and feedback learning framework based on contrastive reinforcement learning is designed in this study. Considering that different state conditions would bring inconsistent daily economic costs, a dynamic optimization model based on deterministic deep policy gradient is established, so that the condition samples can be partitioned according to the preoptimized daily costs. In order to represent the overall conditions on a daily basis and constrain the uncertain states in the IES environment, the state-space representation is constructed by a contrastive network considering the time dependence of variables. A Monte-Carlo policy gradient-based learning architecture is further proposed to optimize the condition partition and improve the policy learning performance. To verify the effectiveness of the proposed method, typical load operation scenarios of an IES are used in our simulations. The human experience strategies and state-of-the-art approaches are selected for comparisons. The results validate the advantages of the proposed approach in terms of cost effectiveness and ability to adapt in uncertain environments.

Pansharpening refers to the fusion between a multispectral (MS) image with abundant spectral information and a panchromatic (PAN) image with high spatial resolution to obtain a high spatial resolution multispectral (HRMS) image. The traditional pansharpening methods often ignore the effect of path-radiation caused by scattering from different atmospheric components, and the few methods that introduce haze correction only calibrate each band of the MS image individually, without exploring the intrinsic correlation among different bands. To address this problem, low rank tensor completion pansharpening based on haze correction (LRTCP) is proposed. The haze-line prior is first introduced into the joint haze correction of MS and PAN images, and obtain the pre-modulated images with the help of the improved high-pass modulation (HPM) injection scheme. We then use tensor completion to simulate the degradation problem by applying low-tubal-rank tensor complementation to the process of reconstructing HRMS images, thus constructing a low rank tensor completion pansharpening model based on haze correction. Finally, the alternating direction multiplier (ADMM) is employed to find the solution of the proposed approach, producing the final fusion result. Comprehensive qualitative and quantitative assessment of reduced- and full-resolution datasets from different satellites shows that the proposed method outperforms the state-of-the-art methods.

With the development of miniaturized millimeter wave (MMW) frequency-modulated continuous-wave (FMCW) radar, the dechirp-on-receive technique has been widely used. Due to the limitations of highly integrated radar hardware, it is difficult to further increase the bandwidth of the transmitted signal. Therefore, enhanced range resolution in MMW synthetic aperture radar (SAR) imaging can be achieved only thanks to suitable post-processing. In this paper, we propose a method for range resolution enhancement based on the principle of wavenumber shift with application to cross-track miniature MMW multiple-input and multiple-output (MIMO)-SAR systems. An improved orthogonal waveform design scheme of multi-subband chirp waveforms with chirp rate changes between waveforms is proposed, which is suitable for dechirp processing. In addition, given the constraint of the position of the equivalent SAR platform of MIMO-SAR, which leads to the lack of range-dimensional spectrum, a spectral data interpolation method based on autoregressive (AR) modeling in the time-frequency (TF) domain is proposed. The effectiveness of the proposed method is verified by numerical simulation and experimental data processing.

Machine learning-based automatic target detection in video synthetic aperture radar (VideoSAR) has great potential for raising the reconnaissance capability in dynamic region of interest (DROI). In this article, a novel systematic perspective, called low-rank plus sparse multiple-term decomposition (LRSMTD) for simultaneously single-channel, single-band, and single-pass (SCSBSP) VideoSAR configuration is proposed to track the ground defocusing targets. To address the target features of circular VideoSAR imaging, we extend the polar format algorithm (PFA) via exploiting a priori knowledge. In accordance with both the revealed imaging and imagery characteristics, we solve the systematic LRSMTD with proximal exchange-based alternating directions method of multipliers (PEADMM), which makes the process interpretable for defocusing target detection. Comprehensive circular SCSBSP airborne VideoSAR experiments reveal the superior detection performance of the systematic LRSMTD and its several subalgorithms with PEADMM, outperforming 11 state-of-the-art algorithms.

An off-grid direction-of-arrival (DOA) estimation method based on block sparse representation is proposed to localize the strictly noncircular (NC) sources utilizing an extended transformed nested array (ETNA). This novel off-grid DOA estimation algorithm effectively promotes spatial distribution information mining. Furthermore, it is conducive to providing stable signal recovery, which refines the DOA estimation precision with interpolation over a coarse grid. We then combine the above algorithm with the designed ETNA to improve the detection performance. The ETNA is an optimal displacement on the existing TNA, which enlarges the degree of freedom (DOF) and lengthens the maximum contiguous segment from the derived virtual array. Simulation results demonstrate its superiority in estimation performance and DOF.

Poisson noise is one of the significant sources of noise present in hyperspectral imagery (HSI). In most of the existing denoising methods, Poisson noise is first transformed into Gaussian noise through the Anscombe transform and then removed. However, the use of Anscombe transform can give rise to transform errors that affect the final denoising results. In addition, blurs often contaminate the HSI during the imaging procedure, which makes it more difficult to remove the Poisson noise. In view of the above problems, under the maximum a posteriori (MAP) model, we propose a Poissonian blurred HSI denoising based on variable splitting and penalty technique (named as VSPT) to directly remove the Poissonian blurred HSI noise without using the Anscombe transform. By finding the minimum value of the negative logarithmic Poisson log-likelihood combined with the total variation (TV), the proposed method transforms the problem into two subproblems, which are easier to solve: 1) a TV regularized deconvolution problem and 2) an ordinary convex optimization problem. The experimental results show that the proposed VSPT method can effectively remove Poisson noise in HSI contaminated by blurs during the imaging procedure.

Most pansharpening methods refer to the fusion of the original low-resolution multispectral (MS) and high-resolution panchromatic images (PAN) acquired simultaneously over the same area. Due to its good robustness, multiresolution analysis (MRA) has become one of the important categories of pansharpening methods. However, when only MS and PAN images acquired at different times can be provided, the fusion results from current MRA methods are often not ideal due to the failure to effectively analyze multitemporal misalignments between MS and PAN images from different times. To solve this issue, MRA pansharpening based on variation factor for MS and PAN images from different times is proposed. The multi-resolution analysis pansharpening based on dual-scale regression model is first established, and the variation factor is then introduced to effectively analyze the multitemporal misalignments by using alternating direction method of multipliers (ADMM), yielding the final fusion results. Experiments with synthetic and real datasets show that the proposed method exhibits significant performance improvement compared to the traditional pansharpening methods, as well as the state-of-the-art MRA methods. Visual comparisons demonstrate that the variation factor introduces encouraging improvements in the compensation of multi-temporal misalignments in ground objects and advances pansharpening applications for MS and PAN images acquired at different times.

The orthogonal waveform diversity design and efficient hardware implementation are important issues in miniature multiple-input multiple-output (MIMO) radars. The orthogonal frequency division multiplexing (OFDM) chirp waveform has received attention recently because of its large time-bandwidth product, constant modulus, no range-Doppler coupling, good orthogonality, and good Doppler tolerance. The dechirp-on-receive technique can reduce the amount of raw sampled data in near-field miniature millimeter-wave (mmW) MIMO radar detection and synthetic aperture radar (SAR) imaging. However, most of the current waveform diversity design methods are based on general matched filtering (MF). In this paper, the possibility of using the traditional OFDM chirp waveform for dechirp processing at the receiving end of MIMO radar is analyzed. Then, the results of different configurations of chirp rates within and between transmitted waveforms for different signal processing procedures are investigated. A novel dechirp-based OFDM chirp waveform diversity design method for MIMO radar is proposed, and the results of the waveform design are given. Numerical results, such as pulse compression (PC) results, dechirp ambiguity function (DAF), SAR imaging processing, etc., and experiments verify the effectiveness of the proposed methods.

While most existing transfer learning methods map the source domain and the target domain data into a common space by sharing the model, the specific knowledge with private properties may be lost. To address this problem, we propose a transfer learning model with shared and specific structures for synthetic aperture radar (SAR) target recognition in this paper. Firstly, we design a convolutional neural network model with the shared subnetwork and the specific subnetworks. The shared subnetwork transforms the common information of the source and the target domain data into a common subspace, while the specific subnetworks transform the private information into the specific subspaces separately. The proposed model does not only extract the similar structure of the different domains but also reserve their private properties. Secondly, by considering the different contributions of the common-subspace features and the specific-subspace features for the final classification, we design adaptive feature weights to compute the domain features. Lastly, in addition to the classification loss, the model is trained by reducing distribution discrepancy loss, which establishes a knowledge transfer bridge from the labeled source domain to the unlabeled target domain. The experimental results verify the effectiveness of the proposed method.

The orthogonal waveform design and good hardware realization of multiple-input–multiple-output (MIMO) radar have always been important research topics. The orthogonal frequency division multiplexing (OFDM) chirp waveform has received more attention because of its large time-bandwidth product, constant modulus, no range-Doppler coupling, good orthogonality, and good Doppler tolerance. Dechirp technique can reduce the amount of raw sampled data very well in near-field miniature lightweight MIMO radar detection and synthetic aperture radar (SAR) imaging. However, most of the current waveform analysis methods are based on matched filtering (MF). In this letter, an ambiguity function (AF) based on the dechirp signal processing approach to analyze the waveform performance is proposed, called dechirp ambiguity function (DAF). The pulse compression performance of the waveform itself and the level of mutual interference between the waveforms are described from the perspective of DAF. Numerical results validate reliability and effectiveness of the DAF.

This article introduces a novel consensus-based labeled multi-Bernoulli (LMB) filter to tackle multitarget tracking (MTT) in a distributed sensor network (DSN), whose sensor nodes have limited and different fields of view (FoVs). Although consensus-based algorithms are effective for distributed fusion and MTT, it may be problematic when distributed sensor nodes have different FoVs. To deal with this issue, the proposed method constructs an extended label space mapping to overcome the "label space mismatching" phenomenon; after that, the model of the undetected multitargets is established so that the tracks can be initialized outside the FoV of local sensors; finally and most important, weight selection and evolution mechanism are proposed such that the fusion weights are automatically tuned for each track at each time step and consensus step. The efficiency and robustness of the proposed algorithm are demonstrated in a distributed MTT scenario via numerical simulations.

This article proposes the problem of joint state estimation and correlation identification for data fusion with unknown and time-varying correlation under the Bayesian learning framework. The considered data correlation is represented by the randomly weighted sum of positive semi-definite matrices, where the random weights depict at least three kinds of unknown correlation across single-sensor measurement components, multisensor measurements, and local estimates. Based on the variational Bayesian mechanism, the joint posterior distribution of the state and weights is derived in a closed-form iterative manner, through minimizing the Kullback-Leibler divergence. The three-case simulation shows the superiority of the proposed method in the root-mean-square error of estimation and identification.

Pansharpening technique is used to merge the original multispectral image (MS) with a high spatial resolution panchromatic image (PAN). Due to its robustness, the multiresolution analysis (MRA) is an important part of pansharpening. The scale regression model is effective for improving MRA. However, the existing MRA based on scale regression results into single-scale regression information, thus affecting the final pansharpening result. To address this problem, in this work, we propose a dual-scale regression-based MRA for pansharpening. First, we establish a scale regression-based model. Then, this model is improved using a high-pass modulation (HPM) injection scheme. Finally, the dual-scale information is added to the scale regression to construct the dual-scale regression for obtaining the final pansharpening result. We perform experiments using five datasets. The results show that the proposed method obtains a better pansharpening result as compared to various state-of-the-art MRA methods. In addition, the quantitative and qualitative analysis of the results shows that the proposed method achieves appropriate spatial and spectral resolution fusion. Therefore, it has a great potential in pansharpening technique.

The integration of the communications network and the Internet of Things in today’s critical infrastructures facilitates intelligent and online monitoring of these systems. However, although critical infrastructure’s digitalization brings tremendous advantages and opportunities for remote access and control, it significantly increases cyber-attack’s vulnerability. Therefore, efficient and proper detection and localization of cyber-attack are paramount for the critical infrastructure’s reliable and secure operation. This article proposes a deep learning-based cyber-attack detection and location identification system for critical infrastructures by constructing new representations and model the system behavior using multilayer autoencoders. The results show that the new representations capture the physical relationships among the measurements and have more discriminant power in distinguishing the location of the attack. Furthermore, the proposed method has outperformed conventional machine learning models under various cyber-attack scenarios using real-world data from the gas pipeline and water distribution supervisory control and data acquisition systems.

This article presents integral-type edge event- and self-triggered policies for Lipschitz nonlinear multiagent systems, in which only edge states are employed by all controllers. An integral-type triggering function is designed to determine event instants, and the considered system can achieve Zeno-free triggering. An integral-type edge self-triggered policy is then designed to avoid sensors’ continuous measurements. Compared to traditional event-triggered schemes, the proposed strategies have relaxed triggering conditions and lowered the event frequencies. Also, the proposed edge self-triggered algorithm can avoid the requirement for continuous measurement error monitoring. Numerical simulations are given to demonstrate the effectiveness of the theoretical conclusions.

Video synthetic aperture radar (VideoSAR) possesses the capability of imaging and continuously monitoring the scenario from a wide-aspect interval for enhancing the performance of information interpretation. In this paper, we propose a complete imaging scheme to achieve the unified video coordinate system in high-resolution airborne VideoSAR configuration. Comprehensive postprocessing video imaging (PPVI) framework built on range Doppler algorithm and range migration algorithm is elaborated especially in terms of complex measured data, which is divided into three parts for ensuring the stability of video background: full-aperture imaging, 2-D autofocus technique, and Doppler spectrum segmentation. Experimental results utilizing the measured airborne data have demonstrated the effectiveness of PPVI scheme for sequential VideoSAR formation.

Numerous synthetic aperture radar-automatic target recognition (SAR-ATR) methods require a large amount of training data. However, collecting SAR data is both expensive and complicated in practical applications. Recognition with the limited training data has become a vital issue in SAR-ATR. To solve this problem, we propose a recognition model combining probabilistic inference with meta-learning to transfer prior knowledge from simulated to real SAR data. First, we use various recognition tasks drawn from the simulated data to learn the global parameters of the model. Second, we draw new tasks from the real data and use the amortized inference to model a posterior distribution over task-specific parameters. Finally, we produce a predictive distribution indicating the confidence of the target classes. The experimental results demonstrate the superiority of the model in recognition tasks with a small amount of training data. We also show that introducing probabilistic inference can improve the prediction accuracy and prediction uncertainty of the model.

A fast and precise interpretation of SAR images is an important and challenging research topic. Some progress has been made in optical image interpretation through decoupling analysis method, while research on decoupling components of SAR images is still in a blank stage. To make an initial exploration on the component interpretation of SAR target images, we propose a new network based on a deep generative model and a new decoupling method. Due to the lack of real training samples that meet the required condition, we use electromagnetic simulation software FEKO to construct the training data sets. In our proposed method, we use the tag information of training samples to constrain the hidden variable layer and improve the structure and loss function of the residual variation autoencoder (Res-VAE) network. By optimizing the newly defined loss function, the network can get the decipherable component features and achieve component interpretation of SAR images. Our experiments verify the feasibility and practicability of the proposed network through the simulation data sets and MSTAR data sets. The results show that the proposed method is effective in interpreting the target components of SAR images.

In this letter, a robust minimum error entropy based cubature information filter is proposed for state estimation in non-Gaussian measurement noise. A new combined optimization cost is defined based on the error entropy. Through cubature transform, a statistical linearization regression model is constructed, and a new information filter is then developed by minimizing the error entropy based cost. The fixed-point iteration approach is used to compute the state estimate. Further, the convergence of the proposed information filter is analyzed, and the convergence conditions are derived. Simulations are performed to demonstrate the effectiveness of the proposed algorithm. It is shown that the estimation performance of the proposed filter is more robust than that of traditional methods against the complicated non-Gaussian noises, such as outliers and noises from multimodal distributions.

Different image fusion systems have been developed to deal with the massive amounts of image data for different applications, such as remote sensing, computer vision, and environment monitoring. However, the generalizability and versatility of these fusion systems remain unknown. This article proposes an efficient regularization framework to achieve different kinds of fusion tasks accounting for the spatiospectral and spatiotemporal variabilities of the fusion process. A joint minimization functional is developed by taking an advantage of a composite regularizer for enforcing joint sparsity in the gradient domain and the frame domain. The proposed composite regularizer is composed of the Hessian Schatten-norm regularization and contourlet-based regularization terms. The resulting problems are solved by the alternating direction method of multipliers (ADMM). The effectiveness of the proposed method is validated in a variety of image fusion experiments: 1) hyperspectral (HS) and panchromatic image fusion; 2) HS and multispectral image fusion; 3) multitemporal image fusion (MIF); and 4) multi-image deblurring. Results show promising performance compared with state-of-the-art fusion methods.

Due to the influences of imaging conditions, spectral imagery can be coarse and contain a large number of mixed pixels. These mixed pixels can lead to inaccuracies in the land-cover class (LC) mapping. Super-resolution mapping (SRM) can be used to analyze such mixed pixels and obtain the LC mapping information at the subpixel level. However, traditional SRM methods mostly rely on spatial correlation based on linear distance, which ignores the influences of nonlinear imaging conditions. In addition, spectral unmixing errors affect the accuracy of utilized spectral properties. In order to overcome the influence of linear and nonlinear imaging conditions and utilize more accurate spectral properties, the SRM based on spatial-spectral correlation (SSC) is proposed in this work. Spatial correlation is obtained using the mixed spatial attraction model (MSAM) based on the linear Euclidean distance. Besides, a spectral correlation that utilizes spectral properties based on the nonlinear Kullback-Leibler distance (KLD) is proposed. Spatial and spectral correlations are combined to reduce the influences of linear and nonlinear imaging conditions, which results in an improved mapping result. The utilized spectral properties are extracted directly by spectral imagery, thus avoiding the spectral unmixing errors. Experimental results on the three spectral images show that the proposed SSC yields better mapping results than state-of-the-art methods.

More than 300 million people have been affected by depression all over the world. Due to the medical equipment and knowledge limitations, most of them are not diagnosed at the early stages. Recent work attempts to use social media to detect depression since the patterns of opinions and thoughts expression of the posted text and images, can reflect users' mental state to some extent. In this work, we design a system dubbed SenseMood to demonstrate that the users with depression can be efficiently detected and analyzed by using proposed system. A deep visual-textual multimodal learning approach has been proposed to reveal the psychological state of the users on social networks. The posted images and tweets data from users with/without depression on Twitter have been collected and used for depression detection. CNN-based classifier and Bert are applied to extract the deep features from the pictures and text posted by users respectively. Then visual and textual features are combined to reflect the emotional expression of users. Finally our system classifies the users with depression and normal users through a neural network and the analysis report is generated automatically.

It is recognized that system trustworthiness is a hyperstructure embodied by the structural, behavioral, and system dimensions with a set of coherent attributes. We explore a theoretical framework of tripartite trustworthiness that can be applied to real-world autonomous systems. We present a formal study of the essences and mathematical models of system trustworthiness and their quantitative measurements in the contexts of autonomous and mission-critical intelligent systems where humans and machines interact in a hybrid environment.

In this letter, a novel subpixel mapping (SPM) based on extended random walker (ERW) (SPMERW) is proposed. First, the resolution of the original coarse remote sensing image is upsampled by bicubic interpolation. Second, the class proportions of subpixel are produced by unmixing the upsampled image. Irregular objects are generated by adaptive segmentation of the first principal component of the upsampled image. Third, the class proportions of the object are derived by averaged fusion of the class proportions of subpixel belonging to each object in the segmentation image. Object spatial dependence including the spatial information among and within the objects is obtained by the ERW algorithm. Finally, a class allocation method based on units of the object is utilized to obtain the SPM result according to the object spatial dependence. Experimental results on two remote sensing data sets show that the proposed SPMERW outperforms the state-of-the-art SPM methods.

This paper is concerned with continuous direction-of-arrival (DOA) estimation, and focused on developing gridless sparse methods to colored noise environment. We propose a two-stage gridless model based on noise suppression and sparse representation. Then the atomic norm minimization method is applied to recover the fourth-order cumulant matrix. We further extend the gridless SPICE method to the reconstruction of fourth-order cumulant matrix. The unknown DOAs are retrieved from the recovered matrix and the source number can be obtained as a byproduct. Numerical simulations lastly validate the computational efficiency of the proposed algorithms.

Long-short-term-memory (LSTM) recurrent neural networks have difficulty in representing temporal and non-temporal inputs simultaneously, due to the sequential emphasis of the architecture. This limits the LSTM applicability in settings where multivariate data is difficult to align. In this paper, a modified hierarchical approach is proposed where a set of univariate LSTM's is trained for asynchronous temporal sequences. The resulting representation is jointly trained with an encoding of multivariate input for prediction. The approach is generalized to combine with non-sequential inputs. The proposed architecture is verified experimentally to improve prediction performance and convergence over conventional LSTM interpolation approaches on simulated Lorenz data and pipeline flow prediction.

Subpixel mapping based on the Hopfield neural network (HNN) is a technique to handle mixed pixels for obtaining the spatial distribution information of land cover. However, the original low-resolution remote sensing image may contain some uncertainties, such as the diversity of the land cover classes and the limitation of the resolution of the satellite sensor, the existing HNN is unable to fully utilize the prior information of the original image. In order to resolve this problem, an improved HNN (I-HNN) is proposed in this letter. In the proposed I-HNN, additional prior information of the original image is supplied by adding a new processing path to the existing HNN. To validate the effectiveness of the proposed method, two experiments are conducted on real hyperspectral images. The obtained results demonstrate that the proposed I-HNN outperforms the existing HNN. Moreover, the I-HNN does not require any auxiliary data.

Super-resolution mapping is an effective technique in mapping flood inundation for multispectral remote sensing image. However, the traditional super-resolution flood inundation mapping (SRFIM) is unable to fully utilize the spectral information from multispectral remote sensing image band. In order to resolve this problem, a novel SRFIM by supplying more spectral information (SRFIM-MSI) is proposed to improve mapping accuracy. In the proposed SRFIM-MSI, the spectral information from the multispectral band is calculated by the normalized difference water index (NDWI). A spectral term constituted by NDWI is added into the traditional SRFIM. The proposed method is evaluated by using two Landsat 8 OLI multispectral data from the study area in Cambodia. The obtained results demonstrate that the proposed SRFIM-MSI produces better results than the traditional SRFIM methods.

A variety of machine learning approaches have been applied to synthetic aperture radar (SAR) automatic target recognition. The performances of these approaches rely strongly on the quality and quantity of training data. In real-world applications, however, it is challenging to obtain sufficient data suitable for these approaches. To alleviate this problem, a novel deep generative model for SAR image generation is proposed, which is an extension of Wasserstein autoencoder. The network structure and reconstruction loss function of the model have been improved according to the characteristics of SAR images. The experimental results demonstrate that our model is superior to other classical generative models in SAR image generation. The generated images can be directly used as training samples, thereby extending the training data set and improving the recognition accuracy.

The traditional consensus-based filters are widely used in distributed sensor networks. However, they suffer from divergence when outliers occur. This paper proposes a robust consensus nonlinear information filter for distributed state estimation with measurement outliers. Unlike the Gaussian assumption in traditional consensus filers, the measurement of each sensor node is modeled here as a multivariate Student- t process with unknown parameters of the sufficient statistic. The variational Bayesian method is employed to jointly estimate the state and the parameters. As the state and parameters are coupled, the updated equation can be solved by fixed point iteration. The centralized outliers robust information filter is first derived for multiple sensors. It is then extended to a distributed version to fuse information from multiple interconnected local estimators. The integral of the consensus-based nonlinear filter is approximated by Gaussian approximation under the framework of the information filter. The consensuses are based on both likelihoods and prior probability distributions. The consensus and convergence of the proposed method are also analyzed. Simulation results show that the proposed approach is effective in dealing with outliers.

In previous work on joint multiple point sets registration, the multiple point sets are often formulated by a Gaussian mixture model (GMM) and the registration is then cast to a clustering problem, which aims to exploit global relationships on the multiple point sets. However, local relationships on the multiple point sets are ignored in the state-of-the-art joint multiple point sets registration techniques. In this paper, the multiple point sets are assumed to be generated from a GMM. Local features of the multiple point sets, such as shape context, are proposed to infer the membership probabilities of the GMM. The problem of joint multiple point sets registration can be performed by maximum likelihood of the GMM. The parameters of GMM and registration are estimated by an expectation maximization algorithm. Comprehensive experiments demonstrate that our proposed method has better performance than the state-of-the-art methods.

The most challenging problem of these days is dealing with the high dimensionality and any progress in this area is very welcomed. This paper is an attempt to propose a new optimization algorithm that performs well in problems with high dimensions. As the result, a new optimization algorithm based on the behavior of a special flower named as Brunsvigia is proposed. The distinguishing property of this algorithm is its simplicity as well as efficiency in angular movement. The special seeding behavior of this flower has been simulated to propose a search algorithm named as Brunsvigia Optimization Algorithm (BVOA) which has two major phases as information sharing through pollination and solution movement based on the head tumbling behavior of the flower in nature. The performance of the proposed algorithm is evaluated on some test functions used in CEC2005 and the results are compared with four other optimization algorithms. The results show that the proposed algorithm has a better performance in high dimensions.

In large-scale mobile networks, energy minimization problem pertaining to base station (BS) switching is known to require high computational complexity. In this paper, we propose a data-driven energy-saving (DDE) framework which partitions the networks into communities. Each community can separately make decisions with low computational cost. We introduce a novel metric to measure the collaborative relationship among BSs. Then, the mobile networks are partitioned via a multiscale community detection method. To improve the cell zooming performance, we estimate the aggregate traffic demands of the communities based on the historical traffic profile. A heuristic switch-off strategy is proposed to maximize the energy savings while guaranteeing minimal service requirements. Experiments with two real regional cellular network datasets show that the proposed DDE framework can conserve a significant amount of energy and leverage the tradeoff between energy savings and the blockage ratio.

Possible drug side-effects (SEs) are usually verified by many years of repeated clinical trials. Despite the effort, some drugs are still expected to cause adverse reactions in some patients. To better predict drug SEs without having to go through the laborious processes of testing and re-testing, machine learning (ML) techniques are more and more used to uncovered patterns in drug data for such purpose. Most existing such techniques are black-box techniques. Since correlations between sub-structures involving multiple variables may exist, these techniques may not always work well. For ML techniques to be effective, they should be accurate, efficient and the patterns they discover should be interpretable. Towards these goals, we have developed a second-order association discovering (SOAD) algorithm for SE prediction. Given a set of drug data for training, the SOAD algorithm can discover SO associations between multiple drug sub-structures and multiple SEs in drug data for the purpose of predicting the SEs. SOAD performs its tasks by first making use of a residual measure to test the significance of occurrence of a chemical sub-structure within a drug and the SE of the drug. Once an association is established between a sub-structure and a SE, we test if two or more such sub-structures are significantly associated with a SE. Based on such second-order associations, we derive from them a set of “informative” SO patterns so that the SEs of new unseen drugs can be predicted based on the frequency of appearance of such patterns. To ensure interpretability of the SE discovery process, we make use of the Bayesian to predict if certain SO relationship in a drug may be related to a certain side-effect. Based on the experimental results, SOAD is found to be very promising.

Registration of images from different modalities in the presence of intra-image fluctuation and noise contamination is a challenging task. The accuracy and robustness of the deformable registration largely depend on the definition of appropriate objective function, measuring the similarity between the images. Among them the multi-dimensional modality independent neighbourhood descriptor (MIND) is a promising method, yet its ability is limited by non-uniform bias fields and image noise, etc. Motivated by the fact that Log-Euclidean metric has promising invariance properties such as inversion invariant and similarity invariant, this paper introduces an objective function that embeds Log-Euclidean similarity metric between patches to form a multi-dimensional descriptor. The Gaussian-like penalty function consisting of the log-Euclidean metric between images to be registered is incorporated to better reflect the degree of preserving feature discriminability and structure ordering. Experimental results show the advantages of the proposed method over state-of-the-art techniques both quantitatively and qualitatively.

Since the significant intensity variations existed between different modal images, the deformable registration is still very challenging. In this paper, in order to alleviate the variations deficiency and attain robust alignment, we propose a multi-dimensional tensor based modality independent neighbourhood descriptor (tMIND) to measure the similarity between the images. The tMIND compares the neighboring tensors which consisting of multi-filters induced features. In this work we learn these filters via PCA network (PCANet). We additionally describe the scheme of incorporating these filters into the tMIND. Experimental evaluations demonstrate its promise and effectiveness over the current state-of-the-art approaches.

Synthesis learning and analysis learning, with sparse coding (SC) and Markov random fields (MRFs) as two representative types of models, are two complementary tools to describe the image manifolds. SC has strengths in representing the regular features/explicit visual manifolds while its effectiveness depends on the training dataset. While MRFs have great potentials to characterize the stochastic textures/implicit visual manifolds but at the cost of high training complexity. In this paper, by means of the convolutional operator, a unified synthesis and analysis deconvolutional network (SADN) is presented. It not only requires the generative coding coefficients to be sparse, but also enforces the convolution between the filter and trained images to be sparse. The proposed model incorporates the strengths of both SC and MRFs, which enables it to represent general images with both generative and discriminative abilities. The resulting minimization is tackled by the combination of alternating optimization and Iterative Re-weighted Least Square (IRLS). Experiments conducted on compressed sensing (CS) application show its great potentials both quantitatively and qualitatively.

The rapid development of techniques results in a growing diversity of social network data which require for analysis. Therefore, the deeper understanding of latent knowledge representing the social network data needs learning by combining the insights obtained from multiple, diverse networks carrying heterogeneous information featuring the interrelationship between vertices. In this manuscript, we propose a novel deepmodel- based approach to learn latent structural representation from multi-domain social network data. The algorithm, which we call Deep Multiple Networks Fusion (DMNF), is able to discover an aggregated deep representation, by taking into consideration multiple networks, which represent heterogeneous information carried by the social network data. To perform the task, DMNF first constructs a network representing the total degree of interrelationship between pairwise vertices by utilizing a fusion method to compute such degree taking into consideration heterogeneous information embedded in the network data, e.g., node connection, and attribute relativity. Given the fused network data, DMNF attempts to learn the latent network representation making use of a deep neural network model. Such learned representation is able to reveal the latent structure, e.g., social communities, and clusters in the social network. DMNF has been tested with two sets of real social network data and compared with several prevalent approaches to network community detection. The experimental results show that the latent representation found by DMNF may match well with the ground-truth communities and DMNF is able to outperform the state-of-the-art approaches to detecting social network communities.

This paper proposes a novel method for fire and smoke detection using video images. The ViBe method is used to extract a background from the whole video and to update the exact motion areas using frame-by-frame differences. Dynamic and static features extraction are combined to recognize the fire and smoke areas. For static features, we use deep learning to detect most of fire and smoke areas based on a Caffemodel. Another static feature is the degree of irregularity of fire and smoke. An adaptive weighted direction algorithm is further introduced to this paper. To further reduce the false alarm rate and locate the original fire position, every frame image of video is divided into 16×16 grids and the times of smoke and fire occurrences of each part is recorded. All clues are combined to reach a final detection result. Experimental results show that the proposed method in this paper can efficiently detect fire and smoke and reduce the loss and false detection rates.

In this letter, we propose a probabilistic method, called the coherent point drift (CPD) algorithm, to address track-to-track association with sensor bias. In the CPD method for a pair of sensors, the local tracks of one sensor are represented by Gaussian mixture model centroids, and the local tracks of the other sensor are fitted to those of the first sensor by maximizing the likelihood. An expectation-maximization algorithm is proposed to find the correspondence matrix between the local tracks. Experiments illustrate the effectiveness of our method.

While the RGB2GRAY conversion with fixed parameters is a classical and widely used tool for image decolorization, recent studies showed that adapting weighting parameters in a two-order multivariance polynomial model has great potential to improve the conversion ability. In this paper, by viewing the two-order model as the sum of three subspaces, it is observed that the first subspace in the two-order model has the dominating importance and the second and the third subspace can be seen as refinement. Therefore, we present a semiparametric strategy to take advantage of both the RGB2GRAY and the two-order models. In the proposed method, the RGB2GRAY result on the first subspace is treated as an immediate grayed image, and then the parameters in the second and the third subspace are optimized. Experimental results show that the proposed approach is comparable to other state-of-the-art algorithms in both quantitative evaluation and visual quality, especially for images with abundant colors and patterns. This algorithm also exhibits good resistance to noise. In addition, instead of the color contrast preserving ratio using the first-order gradient for decolorization quality metric, the color contrast correlation preserving ratio utilizing the second-order gradient is calculated as a new perceptual quality metric.

In cognitive radio networks, self-interested secondary users (SUs) desire to maximize their own throughput. They compete with each other for transmit time once the absence of primary users (PUs) is detected. To satisfy the requirement of PU protection, on the other hand, they have to form some coalitions and cooperate to conduct spectrum sensing. Such dilemma of SUs between competition and cooperation motivates us to study two interesting issues: 1) how to appropriately form some coalitions for cooperative spectrum sensing (CSS) and 2) how to share transmit time among SUs. We jointly consider these two issues, and propose a noncooperative game model with 2-D strategies. The first dimension determines coalition formation, and the second indicates transmit time allocation. Considering the complexity of solving this game, we decompose the game into two more tractable ones: one deals with the formation of CSS coalitions, and the other focuses on the allocation of transmit time. We characterize the Nash equilibria (NEs) of both games, and show that the combination of these two NEs corresponds to the NE of the original game. We also develop a distributed algorithm to achieve a desirable NE of the original game. When this NE is achieved, the SUs obtain a Dhp-stable coalition structure and a fair transmit time allocation. Numerical results verify our analyses, and demonstrate the effectiveness of our algorithm.

This paper presents a novel Log-Euclidean metric inspired color-to-gray conversion model for faithfully preserving the contrast details of color image, which differs from the traditional Euclidean metric approaches. In the proposed model, motivated by the fact that Log-Euclidean metric has promising invariance properties such as inversion invariant and similarity invariant, we present a Log-Euclidean metric-based maximum function to model the decolorization procedure. The Gaussian-like penalty function consisting of the Log-Euclidean metric between gradients of the input color image and transformed grayscale image is incorporated to better reflect the degree of preserving feature discriminability and color ordering in color-to-gray conversion. A discrete searching algorithm is employed to solve the proposed model with linear parametric and non-negative constraints. Extensive evaluation experiments show that the proposed method outperforms the state-of-the-art methods both quantitatively and qualitatively.

This paper presents a comprehensive literature review on environment perception for intelligent vehicles. The state-of-the-art algorithms and modeling methods for intelligent vehicles are given, with a summary of their pros and cons. A special attention is paid to methods for lane and road detection, traffic sign recognition, vehicle tracking, behavior analysis, and scene understanding. In addition, we provide information about datasets, common performance analysis, and perspectives on future research directions in this area.

One of the biggest challenges that consumers and service providers have is connecting a wide range of consumer electronics in a smart home environment. Resource planning and bandwidth allocation for these networks in the license free Industrial Scientific Medical (ISM) frequency band can not be guaranteed. In this paper, we propose improvements for ZigBee physical layer in order to cope with coexistence issue. A detailed MATLAB/Simulink simulator is developed to achieve our objective. In order to balance the trade-off between multipath effects and receiver complexity, the spreading gain of the conventional Direct Sequence Spread Spectrum (DSSS) scheme is limited to 9dB. Unfortunately, this reduces the interference suppression capability of spread spectrum schemes. Here, we propose a low complex spread spectrum scheme for the ZigBee physical layer. The proposed scheme is shown to be robust against multipath fading and interference with a low complexity.

In linear cooperative spectrum sensing, the weights of secondary users and detection threshold should be optimally chosen to minimize missed detection probability and to maximize secondary network throughput. Since these two objectives are not completely compatible, we study this problem from the viewpoint of multiple-objective optimization. We aim to obtain a set of evenly distributed Pareto solutions. To this end, here, we introduce the normal constraint (NC) method to transform the problem into a set of single-objective optimization (SOO) problems. Each SOO problem usually results in a Pareto solution. However, NC does not provide any solution method to these SOO problems, nor any indication on the optimal number of Pareto solutions. Furthermore, NC has no preference over all Pareto solutions, while a designer may be only interested in some of them. In this paper, we employ a stochastic global optimization algorithm to solve the SOO problems, and then propose a simple method to determine the optimal number of Pareto solutions under a computational complexity constraint. In addition, we extend NC to refine the Pareto solutions and select the ones of interest. Finally, we verify the effectiveness and efficiency of the proposed methods through computer simulations.

In biped walking, swing-leg retraction can reduce the energy loss at heel-strike by reducing the foot speed relative to the ground at touch-down. However, it also takes extra effort to brake and then accelerate the swing leg in the rearward direction. This energetic trade-off of retraction is influenced by the mechanical coupling with the stance leg preemptive push-off, and changes with different step lengths and speeds. Previously it has not been clear under which circumstances a retracting hip torque has a net energetic benefit (if ever). Here, using a simple biped model probed with numerical and analytic methods, we show how the effectiveness of leg retraction is influenced by actuator efficiencies for positive and negative work. As the efficiency of negative work decreases, the energetic advantage of retracting hip torque is found (mainly) for longer steps, whereas at shorter steps the hip joint extends (not retracts) prior to heel-strike. For fast walking, however, a braking hip torque is still required at the end of swing phase to ensure heel-strike.

In this paper, a multi-objective directional sensor placement problem for wireless sensor networks is considered. The goal of the multi-objective optimization problem is to obtain sensor placement solutions with reasonable trade-offs between two conflicting objectives, namely energy consumption and detection capability. An adaptive normalized normal constraint method is proposed to solve such optimization problem. Simulation results show that, when comparing with a conventional normalized normal constraint method and NSGA-II, the proposed method is more capable of finding extreme solutions on an approximated Pareto frontier.

This paper presents a novel SLAM method based on the filter that fuses EM algorithm in EKF. Due to the visual SLAM mostly depends on the sensor information that is hard to be obtained in high-level accuracy, the proposed filter is designed to deal with this problem since it can estimate the unknown parameter from the known information in every frame. Realtime experimental results also prove the advantages of SLAM method based on the proposed filter. Compared to the regular EKF, SLAM based on EM-EKF is suggested to have up to 60 percent improvement in the accuracy. It also shows the advantage in the convergence speed and the stability of the system.

With the wide spread of user-friendly mobile devices and applications, the broadband cellular network experiences a pronounced growth of traffic volume, and consumes a large amount of energy. To cope with these two challenges, it is important to understand the resource usage of base stations, which is the first step to manage the radio spectrum resources and network infrastructure efficiently. In this paper, we first use the Pearson's correlation to measure the dependency between base stations on the time variance of traffic load, which is the most direct pattern of resource usage in the cellular data network. By concentrating the analysis on relatively higher linear dependency between base stations, we construct a network in which the vertex and edge represents the base station and significant correlation of traffic dynamic between base stations, respectively. We characterize it in a way of weighted network, and considering the spatial deployment of base stations as well. Our findings are interesting and valuable. Specifically, such a network shows a “long tail” degree distribution, “small world” phenomenon and low modularity. And the spatial deployment of base stations has significant impact to the edge weight, rather than the topology.

Automatic Relevance Determination (ARD) priors have been widely used to induce sparse reconstructions in Bayesian compressive sensing approaches. In this paper, we propose a new sparsity-promoting prior coined as Double Lomax prior. Its connection with the generalized inverse Gaussian distribution and Rayleigh distribution leads to a tractable full Variational Bayesian (VB) inference procedure here. It is shown that the proposed update procedure includes the canonical ARD update procedure as a special case, but provides a better global convergence performance and results in improved signal reconstructions.

Swing leg retraction, the backward rotation of the swing leg prior to heel-strike, is known to have several advantages in legged locomotion. To achieve this motion, a hip torque is required at the end of the swing phase to brake the forward rotation of the leg and/or accelerate its backward motion. In walking, pre-emptive push-off of the stance leg also occurs at the end of the swing, so its relative timing with late-swing retracting torque influences gait energetics. To find the best relative timing between the stance leg's push-off force and the swing leg retraction torque, we calculate their work-based energetics in a simple bipedal model using impulsive approximations and with the aid of the so-called overlap parameter that quantifies the relative order and the percentage overlap of the push-off and retraction impulses. By minimizing the energetic cost of the gait, we found that it is energetically favorable to start with the push-off force, and postpone braking the leg swing until completely after the push-off (impulsive force/torque). The implication for the more realistic non-impulsive cases is to apply the retraction torque at the very end of the push-off before heel-strike. We show that the results are valid for many other bipedal models, for both periodic and aperiodic gaits, and regardless of the actuator efficiencies for positive and negative work.

In this paper, the problem of state estimation of complex dynamical network with unknown noisy transmission channel is considered. A likelihood function of the complex network is formulated. An expectation maximum (EM) algorithm is proposed to estimate the complex network's state and the noise parameter simultaneously. The proposed method can obtain suboptimal estimate of the state and noise parameter. At each iteration of the EM algorithm, the complex network's state is estimated by extend Kalman filter in the E-step, while the noise parameter is updated in the M-step. Computer simulation results verify the effectiveness of the proposed method.

Echo state networks (ESNs), that exhibit good performance for modeling a nonlinear or non-Gaussian dynamic system, have been widely used for time series prediction. However, estimating the output weights of the ESNs remains intractable. Extended Kalman filter (EKF) is an effective estimate method, but its computational cost is relatively high. In this study, a MapReduce framework based parallelized EKF is proposed to learn the parameters of the network, in which two MapReduce based models are designed, and each of them is composed of a set of mapper and reducer functions. The mapper receives a training sample and generates the updates of the internal states or the output weights, while the reducer merges all updates associated with the same key to produce an average value. To verify the effectiveness and the efficiency of the proposed method, an industrial data prediction problem coming from the blast furnace gas (BFG) system in steel industry is employed for the validation experiments, and the experimental results demonstrate that the proposed parallelized EKF can efficiently estimate the parameters of the ESN with good performance and computing time.

Navigation goal detection in complex real world scenarios is challenging for autonomous mobile robots due to the uncertainty and ambiguity of their environments. This paper proposes a fuzzy cognitive map (FCM) based situation assessment framework (SAF) for mobile robot navigation goal detection. A given navigation goal is described with several sub-goals using prior knowledge. Based upon these sub-goals, the proposed SAF operates recursively on the navigation goal to verify it. The decision fusion system combines sensory information from multiple sensors to verify the sub-goals. The FCM, which is realized using fuzzy gamma fusion, is used as a high level reasoning engine. The navigation goals are verified based on the rules which connect sub-goals together and the goal assertion confidence of sub-goals which is decided using FCM inference. Experimental results demonstrate that the proposed framework can accurately decide the navigation goals in unknown environments based on the sensory information and expert knowledge.

The paper proposes a scheme for achieving steganography with multiple encrypted monochromatic images with keys obtained from a synchronized system of semiconductor lasers. The key selection scheme for steganography determines the robustness of the application. It is in this area that steganography may benefit from the properties of chaos synchronization. The encryption principle of the new algorithm is analyzed quantitatively by various statistical tests. The cover image used in the technique is also obtained from the visual representation of the chaotic sequences. This new scheme enjoys the benefit of added security, high key space, high embedding capacity, imperceptibility and robustness of the hidden information in conjunction with Least Significant Bit (LSB) based substitution. The result is important from the perspective of introducing a mechanism to multiplex and simultaneously transmit multiple images.

A higher order statistics (HOS)-based method is proposed in this letter to estimate the nonlinear amplitude-to-phase (AM/PM) conversion function of power amplifiers (PAs) in communications systems. By utilizing the symmetry property of the modulated signal, the proposed method estimates the AM/PM conversion function using only the PA output signal, from which the phase predistorter (PD) function can be derived. Simulation results show that the HOS-based method can accurately determine the phase PD function required to compensate for the AM/PM distortion in the PA, yielding a linearization performance close to that of non-blind methods in terms of adjacent channel power ratio and error vector magnitude.

Prediction intervals that provide estimated values as well as the corresponding reliability are applied to nonlinear time series forecast. However, constructing reliable prediction intervals for noisy time series is still a challenge. In this paper, a bootstrapping reservoir computing network ensemble (BRCNE) is proposed and a simultaneous training method based on Bayesian linear regression is developed. In addition, the structural parameters of the BRCNE, that is, the number of reservoir computing networks and the reservoir dimension, are determined off-line by the 0.632 bootstrap cross-validation. To verify the effectiveness of the proposed method, two kinds of time series data, including the multisuperimposed oscillator problem with additive noises and a practical gas flow in steel industry are employed here. The experimental results indicate that the proposed approach has a satisfactory performance on prediction intervals for practical applications.

Analog and radio frequency (RF) front-end circuit impairments such as mismatches between in-phase (I) and quadrature (Q) branches can severely degrade performance of wireless communications systems. In this paper, we propose a technique to compensate for both frequency-independent and frequency-dependent impairments in direct conversion transmitters (DCTs). The technique employs a recursive algorithm to estimate the impairments from instantaneous power of the transmitted RF signal, and it jointly mitigates the mismatches/imbalances between the I and Q branches and the distortions in each of the I and Q branches. It is applicable to wireless communications systems that employ different modulation techniques. Theoretical analyses are presented for identifiability and convergence properties of the technique. Effects of imperfect measurement are discussed. Both computer simulation and prototype experimentation are carried out to demonstrate that the proposed technique accurately determines and compensates for the DCT impairment, and improves the transmitted signal quality.

In this paper, a minimum nonlinear prediction error (MNPE) based channel equalization and timing recovery technique is proposed for chaotic communications systems. This blind technique utilizes the short-term predictability of a chaotic signal to estimate the equalizer coefficients and the timing delay without any training signals. Both computer simulation and experimental setup are carried out to validate the proposed technique. Compared with the constant modulus algorithm (CMA) and higher-order statistics (HOS) based inverse filter techniques, which are commonly used in the conventional communications systems, the proposed MNPE technique can achieve better demodulation performance.

In a cluster-based wireless sensor network, to shorten the duration of a data aggregation process, wireless sensor nodes in different clusters may be required to perform concurrent transmissions. Inter-cluster interferences are usually resolved by using different channels among clusters. Since channel resource is limited, for large-scale networks, co-channel interferences are unavoidable. The problem becomes more severe when TDMA-based MAC protocols are employed. Such problem can be alleviated by controlling the transmission power levels of the concurrent users. In this paper, a transmission power control problem in wireless sensor networks is considered. The objective is to find optimum transmission power levels, which can obtain efficient trade-offs between energy consumption and the number of retransmissions. Different optimization schemes are investigated and analyzed using the concept of Pareto optimality.

This work applies nonlinear dynamics to model the encoded time series describing human activities performed in the spatio-temporal domain. We augment the concepts of symbolic dynamics and formal language theory to pattern recognition in generating probabilistic feature extraction which are used to drive a Bayesian classifier for behavior recognition. Our motivation for using stochastic context-free grammar (SCGF) is to aggregate low-level events detected so that we can construct higher-level models of interaction. This is a novel attempt in coupling symbolic dynamics with a stochastic model to construct a spatio-temporal ordered SCFG. Extended statistical tests and comparative analysis with Bayesian classification and k-nearest neighbour (K-NN) classification of time series sequences demonstrate a superiority of the proposed method of gesture recognition using concepts from nonlinear dynamics.

In this letter, we propose a novel approach of simultaneous feature and model selection for continuous hidden Markov model (CHMM). In our method, a set of real valued quantities, defined as feature saliencies, are proposed for feature selection. A variational Bayesian (VB) framework is applied to infer the feature saliencies, the number of hidden states, and the parameters of the CHMM simultaneously. Experiments based on synthetic and real data demonstrate the effectiveness of the proposed method.

In this paper, we propose a novel tracking algorithm that combines complementary tracking modules with a new object representation model to balance between stability and adaptivity. To reduce the update error of online tracking, we present three complementary modules (a stable module, a soft stable module, and an adaptive module) and fuse them by using a biased multiplicative criterion. The combination of those modules not only facilitates the accurate location of the tracked object but also makes our tracker adaptive to appearance change. For objection representation, we present an appearance model named pixel-wise spatial pyramid (PSP), which employs pixel feature vector to combine several pixel characteristics. During the updating process, we update the codebook by using the reserved pixel feature vectors that are selected by a distance-based scheme. Then, we generate an evolving target representation by using a hybrid feature map that consists of the reserved pixel vectors and antipart of the previous hybrid feature map. Numerous experiments on various challenging image sequences demonstrate that the proposed algorithm performs favorably against several state-of-the-art algorithms, especially for drastic appearance change.

Path planning can be viewed as an optimization process in which an optimum path between two points is to be found under some predefined constraints. Some typical constraints are path length, fuel consumption, and path safety factor. Exact algorithms such as linear programming (LP) and dynamic programming (DP) are widely adopted in vehicle maneuvering systems. However, as the problem domain scales up, exact algorithms suffer from high computational complexity. In contrast, metaheuristic algorithms such as evolutionary algorithms (EA) and genetic algorithms (GA) can provide suboptimum solutions without the full understanding of the problem domain. Metaheuristic algorithms are capable of providing decent solutions within a finite period of time, even for large-scaled problems. In this paper, a GA-inspired unmanned underwater vehicle (UUV) path planner based on DP is proposed. Simulation results show that the proposed algorithm can outperform a GA-based UUV path planner in terms of speed and solution quality.

In cognitive radio networks (CRNs), cooperative spectrum sensing (CSS) is usually performed periodically due to the uncertain activity of primary users (PUs). Considering the overhead in performing CSS, a selfish secondary user (SU) may not always participate in CSS. Instead, it elaborately selects a frequency (or number of times) for CSS participation to maximize its interest. A fusion center then schedules it to conduct CSS in appropriate periods. This paper investigates the interactive decision on the CSS participation frequency under sensing performance and quality of service (QoS) requirements. The problem is formulated as a noncooperative game, where Nash Equilibrium (NE) corresponds to the desired frequency selection outcome. Since the strategy sets of SUs are coupled, obtaining directly the NE requires explicit coordination among SUs, which is unrealistic in practice. Alternatively, we decompose the game into a lower-level uncoupled game and a higher-level optimization problem. A distributed hierarchical iterative algorithm (DHIA) is then proposed to obtain the desired frequency selection outcome without requiring explicit coordination. Furthermore, the uncertain sensing performance of SUs and the fairness issue are also considered. Finally, numerical results validate the effectiveness of the proposed scheme.

Camera networks are widely applied in surveillance and monitoring applications. Unlike other omni-directional sensors, cameras are directional sensors with limited field of views (FoVs). Such characteristics impose extra challenges in camera networks design. Comparing with ordinary sensors, cameras are relatively expensive. It is impractical to fully cover a space by using a large number of static cameras. The sensing coverage of a camera can be largely extended by mounting the camera on a rotator. However, such attempt is compromising the detection ability of a network as an attacker may breach the network by determining the rotating patterns of the cameras. A random-like rotating pattern can protect a camera network from such attack. In this paper, a chaotic motion controller for camera networks is proposed. The controller introduces random-like chaotic patterns to cooperate multiple cameras. Simulation results show that networks governed by the proposed motion controller can obtain higher coverage rate and coverage ratio than networks with random-based controller. Further improvement can be achieved by turning some parameters.

Game theoretic adaptive algorithms can be successfully applied for distributed intelligent Cognitive Wireless Sensor Networks (CWSNs). The use of these algorithms avoids weaknesses of centralized CWSNs. In this paper, a noncooperative spectrum sharing game theoretic approach for CWSNs is proposed to determine the optimum spectrum demand. The main objectives of this approach are improving the flexibility, efficiency and fairness in spectrum allocation with guaranteed sum data rates. We introduce a rewarding scheme in this approach to promote the communication of the sensor nodes that have good channel qualities and residual power levels. Then we analyze the existence and the uniqueness of the Nash Equilibrium. The simulation results show that the energy efficiency of our method is higher than the traditional uniform Time Division Multiplexing (TDMA - Uniform) approach and traditional TDMA approach that depends on channel (TDMA - Channel Based).

In sensor networks, depending on the user-defined goal and the number of objects-of-interest within the common sensor coverage area, multiple sensors generate multiple sources of information. Combining this information is essential and in this paper we propose a fuzzy outranking approach to combining information at the decision level, therefore leading to a collaborative decision making framework. Decision level information is represented through graphical models which helps in enhancing quantifiable system performance by processing information at a higher level and the second advantage is the ability to implement an adaptive framework for decision making. When used with dynamic belief update and an integrated database, a fuzzy outranking approach can be implemented with the ability to adapt to new sensor information and combined various local sensor decisions.

We consider the problem of assigning single-band thermal night vision image with natural day-time color appearance automatically. We present an approach in which supervised learning is first used to estimate colors of monochromic images. Modeling color distribution of thermal imagery is a challenging problem, since there are insufficient local features for estimating the chromatic value at a point. Our model uses a statistical learning algorithm that incorporates multi-scale and spatially arranged image features, and it can be trained on a data set that contains thermal image and registered day-time color image pairs. Experimental results show that our approach leads to relatively accurate description of the desired color distribution and results in thermal images that appear smooth and natural color details, so that the overall scene recognition and situational awareness can be improved.

Path planning is an optimization process in which a path between two points is to be found that results in a user-defined optimum satisfaction of a given set of requirements. For small scale path planning, exact algorithms such as linear programming and dynamic programming are usually adopted which are able to give optimum solutions in short time. However, due to their memory intensive nature and computational complexity, exact algorithms are not applicable for medium to large scale path planning. Meta-heuristic algorithms such as evolutionary algorithms can provide sub-optimum solution without the full understanding of the search space and are widely used in large-scaled path planning. However, extra precautions are needed to avoid meta-heuristic algorithms from being trapped in local optimum points. In this paper, a path planner combining genetic algorithms (GA) with dynamic programming (DP) is proposed to solve an autonomous under-water vehicles (AUVs) path planning problem. The proposed path planner inherits the speed of exact algorithms and the scalable nature of meta-heuristic algorithms. Simulation results show that when comparing with conventional GA-based path planners, the proposed path planner can greatly improve the convergence rate and solution quality.

Surveillance typically involves monitoring humans, buildings, and other mobile objects to detect abnormal behavior; primarily to sense and detect any anomalies in real time. Conventionally this has been done manually, but with a growing demand for day-to-day surveillance and the need for intense monitoring; decision support has proven to improve the overall system performance. Decision support also called situation assessment from a surveillance perspective, takes form of a higher order pattern recognition problem involving complex reasoning and inference. A distributed approach to knowledge modeling and inference is proposed here for effective representation of the domain knowledge. In addition optimal local and global rules to combine situation level information have been developed.

In this paper, stochastic delay differential equation (SDDE) and its application on communications are discussed. Based on SDDE, a novel communication scheme-delay time modulation (DTM) is proposed. In this modulation scheme, the information signal is conveyed by the delay time of a delayed linear Langevin equation, which exhibits a linear relationship with the variance of the SDDE system output. The information signal can be retrieved at the receiving end by estimating the variance of the received signal. To evaluate the performance of DTM scheme, normalized mean square error (NMSE) in additive white Gaussian channel is derived for analog information transmission, as well as BER (bit error rate) for binary information communications. Both analytical and simulation results demonstrate the feasibility and robustness of the proposed scheme.

Based on separation of the sum of chaotic signals, this paper proposes a novel spread spectrum modulation scheme-initial condition modulation (ICM), which is suitable for high data rate communications. The success of signal separation makes it possible to transmit multiple information streams through single channel. This technique significantly improves data transmission rate and implies good information security. Our theoretical analysis shows that this approach can also cleanse the additive white Gaussian noise imposed by communication channel. Computer simulations confirm that the proposed method has a good noise performance.

In this article, we consider the bias issue in a passive tracking system which utilizes a mobile passive sensor network, where bearing-only sensors such as Inferred or ESM are used. Biases due to nonlinear transformations have already been recognized, but have not been studied for this particular case of converted pseudo measurements in a mobile passive sensor network. Based on the Taylor series, the bias equations for a network of two passive sensors are derived. Monte Carlo simulation is used for analysis. There are two other non-linear transformations which are related to this study: 1. range/azimuth to X/Y; 2. range/azimuth to latitude/longitude. Insightful studies with explicit expressions are available for the first nonlinear transformation, but not for the second and the new nonlinear transformations. This article will provide an approximate solution and simulation study for the new nonlinear transformation.

Unmanned aerial vehicles (UAVs) are remote controlled or autonomous air vehicles. An UAV can be equipped with various types of sensors to perform life rescue missions or it can be armed with weapons to carry out stealthy attack missions. With the unmanned nature of UAVs, a mission can be taken in any hostile environment without risking the life of pilots. Among life rescue missions, the common objective is often defined as maximizing the total coverage area of the UAVs with the limited resources. When the number of UAVs increases, coordination among these UAVs becomes very complicated even for experienced pilots. In this paper, a cooperative path planner for UAVs is proposed. The path of each UAV is represented by a B-spline curve with a number of control points. The positions of these control points are optimized using an ant colony optimization algorithm (ACO) such that the total coverage of the UAVs is maximized.

The most often used operator to aggregate criteria in decision making problems is the classical weighted sum model or weighted sum model. However, in many problems, the criteria considered interact and a substitute to the weighted sum model has to be adopted. Multi-criteria decision making (MCDM) problems involve the ranking of a finite set of alternatives in terms of a finite number of decision criteria. Usually such criteria may be in conflict with each other. A typical problem in MCDA is concerned with the task of ranking a finite number of decision alternatives, each of which is explicitly described in terms of different characteristics often called decision criteria or objectives. This research applies an integrated multi-criteria decision making approach to design an optimal UAV resource management. In this approach, the ant colony optimization (ACO) is used firstly to obtain optimal solutions satisfying some path planning criteria, then, fuzzy analytic hierarchy process (AHP) is formulated to select the best set of UAVs. Due to vagueness and uncertainty, fuzzy set theory based AHP is employed in the decision making judgments, because it can handle uncertainty easily. The proposed method can be extended to any sensor network resource management problem.

This paper presents a new automated approach for the mine detection and classification (MDC) problem based on change detection techniques using sidescan sonar images. Adopting change detection techniques benefits this approach to recognize mine targets without training data or prior assumption required in traditional detection methods. In this approach, post-classification comparison is designed to detect the changes and the statistical information of pixel distribution is employed for change decision analysis. Specifically, because of the special characteristics of shadows in sonar images, shape and coarseness features are taken into account and play an important role in this method. This approach was successfully applied to two sets of bi-temporal sidescan sonar images and the results are presented in this paper. The results prove the applicability of this approach for mine detection.

The highly error-prone nature of wireless environments and limited computational power of mobile devices necessitates the implementation of robust yet simple error concealment in H.264/AVC. In this paper, we propose to use data hiding to facilitate the error concealment on intra-coded frames that utilizes the temporal redundancy in a wireless video bitstream. At the encoder side, the motion vector of a macroblock (MB) is encoded and imperceptibly embedded into other MB within the same intra-frame. If an MB is found missing at the decoder, the embedded information will be retrieved from the corresponding MB for the recovery of the lost MB. In order to isolate erroneous MBs caused by packet loss, a block shuffling scheme is applied. It is shown that the proposed method is able to shift the computation burden from decoder to encoder, and reduce the computation complexity of conventional error concealment methods. In addition, due to the use of real motion vectors for temporal concealment, the proposed method provides improved picture quality over the reference methods in H.264/AVC.

In this paper, we propose to apply a novel chaos-based ultra-wide band (UWB) radar for through-the-wall imaging. The proposed chaos modulation offers superior resolution compared to conventional UWB radars when applied for through-the-wall imaging. A noncoherent receiver is designed based on expectation maximization (EM) algorithm. The theoretical detection performance is derived for through-the-wall detection in the presence and absence of room reverberations as a function of dielectric properties of walls, targets, and their geometry illustrating the robustness of the proposed modulation against room reverberations. The resolution of the proposed modulation is analyzed theoretically and verified through simulations for different wall materials. Numerical electromagnetic simulations using finite difference time domain (FDTD) method are performed to confirm the obtained theoretical results. From the theoretical and simulation analysis, we find that the proposed chaos-based pulse amplitude modulated ultra-wide band (CPAM-UWB) radar has better detection performance, penetrating ability and imaging performance compared to other conventional through-the-wall imaging radars.

This paper presents a graphical model approach that fuses thermal infrared (IR) and visible spectrum video for human tracking. The proposed model uses unobserved variables to describe the data in terms of the process that generates them. It is thus able to capture and exploit the statistical structure of the IR and the visible data separately, as well as their mutual dependencies. Model parameters are learned form data using the expectation maximization (EM) algorithm. Automatic calibration is performed as part of this procedure. Tracking is done by Bayesian inference of the object location from the observed data. The effectiveness of the proposed method is demonstrated by the experimental results on the video clips captured in real world scenarios.

This paper describes the use of a fuzzy cognitive map (FCM) to model disaster reconstruction, based on data collected from the cities of BAM and Baravat. The extended fuzzy cognitive map augmented with an unsupervised learning algorithm has been used transform the associated data into a graphical model. Further to which, a modular approach based on efficient clustering of correlated variables has been adopted to model the sparse data. Discussion and justification of the results is also presented.

The problem of spatial-temporal signal processing and modeling has been of great interest in recent years. A new spatial-temporal prediction method is presented in this paper. An optimal fusion scheme based on fourth-order statistic is first employed to combine the received signals at different spatial domains. The fused signal is then used to construct a spatial-temporal predictor by a support vector machine. It is shown theoretically that the proposed method has an improved performance even in non-Gaussian environments. To demonstrate the practicality of this spatial-temporal predictor, we apply it to model real-life radar sea scattered signals. Experimental results show that the proposed method can provide a more accurate model for sea clutter than the conventional methods.

In this paper, we address the problem of parameter estimation of systems driven by chaotic signal We propose an expectation maximization (EM) based unscented Kalman smoother (UKS) to simultaneously estimate parameters of system along with the equalized chaotic signal. The proposed method can be applied to both linear and nonlinear systems driven by chaotic signals. The performance of the proposed estimator is evaluated for identification of systems that occur frequently in communication systems. The estimation performance of the proposed algorithm is evaluated using computer simulations and shown to be better than conventional nonlinear system identification algorithms.

In this letter, we present a novel chaos-based imaging technique. The proposed technique has good range-Doppler resolution and excellent side lobe suppression characteristics that promise immense potential for high-resolution imaging applications. We derive the range and Doppler resolution functions of the proposed technique and compare it with that of conventional time modulation-based imaging. Additionally, the noise performance of the proposed scheme is derived to show the improvement compared to the conventional amplitude and time modulation schemes. The proposed imaging technique is applied to through-the-wall radar imaging. Numerical electromagnetic simulations are performed to illustrate the effectiveness of the proposed technique.

This paper presents a novel technique for image watermarking based on chaos theory. Chaotic parameter modulation (CPM) is employed to modulate the copyright information into the bifurcating parameter of a chaotic system. The system output is a wideband signal and is used as a watermark to be inserted into the host image. In the detection, a novel method based on the ergodic property of chaotic signal is developed to demodulate the embedded copyright information. Compared to previous works on blind watermarking, the proposed technique can effectively remove the interference from the host image and, thus, improve the detection performance dramatically. Simulation results show that the ergodic CPM approach is effective for image watermarking in terms of noise performance, robustness against attacks, and payload. In addition, its implementation is very simple and the computation speed is fast. Compared to holographic transform domain method and the conventional spread spectrum watermarking scheme, the proposed technique is shown to be superior.

Registration of multidate or multisensor images is an essential process in many image processing applications including remote sensing, medical image analysis, and computer vision. Control point (CP) and intensity are the two basic features used separately for image registration in the literature. In this paper, an exact maximum likelihood (EML) registration method, which combines both CP and intensity, is proposed for image alignment. The EML registration method maximizes the likelihood function based CP and intensity to estimate the registration parameters, including affine transformation and CP coordinates. The explicit formulas of the Cramer-Rao bound (CRB) are also derived for the proposed EML and conventional image registration algorithms. The performances of these image registration techniques are evaluated with the CRBs.

Accurate modeling of sea clutter is an important problem in remote sensing and radar signal processing applications. Due to a recent discovery that sea clutter, the electromagnetic wave backscatter from a sea surface, is chaotic rather than purely random, computational intelligence techniques such as neural networks have been applied to develop new models for sea clutter. In this paper, we propose using the multiple neural network model approach to construct a predictive model for sea clutter. The motivation comes from the observation that the sea usually has some unpredictable motions that result in impulsive events such as sea spikes. Although a single nonlinear model could describe the Bragg scattering reasonably as shown in the literature, it is usually incapable of capturing sea spikes motions. Therefore, target detection performance might be degraded when such a clutter model is employed. Using a multiple radial basis function (RBF) net predictor, we found that a sea clutter signal with different underlying dynamics from sea spikes to normal motions can be modeled accurately. The multiple model (MM) approach automatically assigns different RBF predictors to model sea spikes and other mechanisms like Bragg scattering. The proposed multiple RBF neural network uses the expectation-maximization algorithm and multistep prediction for training, and hence it is suitable for real-time signal processing. Using real-life radar clutter data collected at the east coast of Canada, the proposed MM approach is shown to be effective in isolating and characterizing various components of sea clutter and, therefore, provides a promising model for clutter suppression in radar detection.

Many real-life time series cannot be accurately described by using a single dynamic model. A large amount of real world time series are composed of more than one underlying regimes switching along the time scale. In this paper, we propose using multiple nonlinear models for prediction. Based on a hidden Markov process, the proposed multiple model (MM) is able to capture the temporal relationship among the underlying regimes. A genetic algorithm (GA) is employed to train the multiple model and to obtain an optimal segmentation of the time series. Using real-life sea clutter data, this named GA MM predictor is shown to provide an accurate model for sea clutter in various sea state conditions.

A texture model for synthetic aperture radar (SAR) images is presented. Specifically, a sea surface in satellite images is modeled using the two-dimensional (2-D) fractionally integrated autoregressive-moving average (FARIMA) process with a non-Gaussian white driving sequence. The FARIMA process is an ARMA type model which is asymptotically self-similar. It captures the long-range as well as short-range spatial dependence structure of an image with a small number of parameters. To estimate these parameters, an efficient estimation procedure based on a spectral fit is presented. Real-life ocean surveillance radar images collected by the RADARSAT sensor are used to evaluate the practicality of this FARIMA approach. Using the radial power spectral density, the new model is shown to provide a more accurate description of the SAR images than the conventional moving-average (MA), autoregressive (AR), and fractionally differenced (FD) models.

Radar target tracking involves predicting the future trajectory of a target based on its past positions. This problem has been dealt with using trackers developed under various assumptions about statistical models of process and measurement noise and about target dynamics. Due to these assumptions, existing trackers are not very effective when executed in a stressful environment in which a target may maneuver, accelerate, or decelerate and its positions be inaccurately detected or missing completely from successive scans. To deal with target tracking in such an environment, recent efforts have developed fuzzy logic-based trackers. These have been shown to perform better as compared to traditional trackers. Unfortunately, however, their design may not be easier. For these trackers to perform effectively, a set of carefully chosen fuzzy rules are required. These rules are currently obtained from human experts through a time-consuming knowledge acquisition process of iterative interviewing, verifying, validating, and revalidating. To facilitate the knowledge acquisition process and ensure that the best possible set of rules be found, we propose to use an automatic rule generator that was developed based on the use of a genetic algorithm (GA). This genetic algorithm adopts a steady-state reproductive scheme and is referred to as the steady-state genetic algorithm (SSGA) in this paper. To generate fuzzy rules, we encode different rule sets in different chromosomes. Chromosome fitness is then determined according to a fitness function defined in terms of the number of track losses and the prediction accuracy when the set of rules it encodes is tested against training data. The rules encoded in the fittest chromosome at the end of the evolutionary process are taken to be the best possible set of fuzzy rules.

We present a fuzzy-gain filter for target tracking in a stressful environment where a target may accelerate at nonuniform rates and may also complete sharp turns within a short time period. Furthermore, the target may be missing from successive scans even during the turns, and its positions may be detected erroneously. The proposed tracker incorporates fuzzy logic in a conventional /spl alpha/-/spl beta/ filter by the use of a set of fuzzy if-then rules. Given the error and change of error in the last prediction, these rules are used to determine the magnitude of /spl alpha/ and /spl beta/. The proposed tracker has the advantage that it does not require any assumption of statistical models of process and measurement noise and of target dynamics. Furthermore, it does not need a maneuver detector even when tracking maneuvering targets. The performance of the fuzzy tracker is evaluated using real radar tracking data generated from F-18 and other fighters, collected jointly by the defense departments of Canada and the United States. When compared against that of a conventional tracking algorithm based on a two-stage Kalman filter, its performance is found to be better both in terms of prediction accuracy and the ability to minimize the number of track losses.