Search

Proxy Re-Encryption (PRE), a special cryptographic primitive, can efficiently perform ciphertext conversion on the cloud. To enable the data owner (i.e. delegator) to authorize a file access path according to the different priorities of the users (i.e. delegatees), autonomous path proxy re-encryption (AP-PRE) was proposed, where the delegator can generate a proxy re-encryption autonomous path in order of the delegatees’ priority. If one delegatee does not hold the decryption right, the ciphertext can be converted to a new ciphertext that can be decrypted by the next delegatee with lower priority in the path. Although AP-PRE enables the delegator to pre-define the whole decryption path, the access policy only supports a linked path and the data owner disallows the nodes in the proxy path to generate delegating branches to access its data. Such a linked path may be too long in practice, especially when the system scales up (i.e. the average complexity of encrypted data access is O(n) where ${n}$ denotes the number of delegatees). Hence, we propose a generalized autonomous path proxy re-encryption (APB-PRE) scheme for supporting branch functionality. Firstly, by setting the token and a carefully designed ciphertext structure, the branch functionality of the path delegation is realized. Specifically, we utilize the bilinearity of bilinear pairing to construct the token for the transition of the label embedded in the ciphertext in different paths, resulting in a far more flexible access structure with a tree-like topology. In APB-PRE, the delegatees with lower priority who need to share data can complete the decryption task earlier, without affecting the decryption of the high-priority delegatees. Finally, we prove that it achieves IND-HRA security under the Decisional Bilinear Diffie-Hellman (DBDH) assumption. Benefiting from the creation of branching paths, users on the branching path can get the re-encrypted ciphertext much earlier. Therefore, the average complexity of encrypted data access reduces to O(log n) compared to AP-PRE. The experimental results show that our proposal can extend the branching functionalities of AP-PRE with only moderate computational cost. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) contain many bands that can be used to obtain object material information for object tracking and remote sensing. Nevertheless, neighboring bands of HSIs are often highly correlated, and a large number of bands increase the complexity of model learning. This issue is worsened by the shortage of labeled hyperspectral videos (HSVs) for fine-tuning pretrained deep neural networks. To tackle these challenges, this letter introduces a novel background-aware band selection method to model spatial changes of an object and its corresponding local region, which is capable of selecting discriminative bands for object representation while reducing computational complexity. Specifically, the object and local regions of each band are compared with other bands to obtain their dissimilarity scores. Guided by these scores, the top three bands are selected and form a three-channel image. This image is then fed into an object tracker. Experimental results demonstrate the efficiency and effectiveness of the proposed method on a benchmark hyperspectral object-tracking dataset. [ABSTRACT FROM AUTHOR]

In the past few years, many convolutional neural networks (CNNs) have been applied to hyperspectral image (HSI) classification. However, many of them have the following drawbacks: they do not fully consider the abundant band spectral information and insufficiently extract the spatial information of HSI; all bands and neighboring pixels are treated equally, so CNNs may learn features from redundant or useless bands/pixels; and a significant amount of hidden semantic information is lost when a single-scale convolution kernel is used in CNNs. To alleviate these problems, we propose a spatial–spectral split attention residual networks (S $^{3}$ ARN) for HSI classification. In S $^{3}$ ARN, a split attention strategy is used to fuse the features extracted from multireceptive fields, in which both spectral and spatial split attention modules are composed of bottleneck residual blocks. Thanks to the bottleneck structure, the proposed method can effectively prevent overfitting, speeds up the model training, and reduces the network parameters. Moreover, the spectral and spatial attention residual branches aim to generate the attention masks, which can simultaneously emphasize useful bands and neighbor pixels and suppress useless ones. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed model for HSI classification. [ABSTRACT FROM AUTHOR]

The ECG classification processor is a key component in wearable intelligent ECG monitoring devices which monitor the ECG signals in real time and detect the abnormality automatically. The state-of-the-art ECG classification processors for wearable intelligent ECG monitoring devices are faced with two challenges, including ultra-low energy consumption demand and high classification accuracy demand against patient-to-patient variability. To address the above two challenges, in this work, an ultra-energy-efficient ECG classification processor with high classification accuracy is proposed. Several design techniques have been proposed, including a reconfigurable SNN/ANN inference architecture for reducing energy consumption while maintaining classification accuracy, a reconfigurable on-chip learning architecture for improving the classification accuracy against patent-to-patient variability, and a dual-purpose binary encoding scheme of ECG heartbeats for further reducing the energy consumption. Fabricated with a 28nm CMOS technology, the proposed design consumes extremely low classification energy (0.3μJ) while achieving high classification accuracy (97.36%) against patient-to-patient variability, outperforming several state-of-the-art designs. [ABSTRACT FROM AUTHOR]

Recently, convolutional neural networks (CNNs) have demonstrated impressive capabilities in the representation and classification of hyperspectral remote sensing images. Traditional CNNs require massive data to sufficiently train the network. To tackle this problem, graph convolutional network (GCN) has been introduced for hyperspectral image classification. GCN methods usually construct the graph from either spectral or spatial domain, which has not adequately explored the information in the joint spectral–spatial domain. In this article, we propose a superpixel spectral–spatial feature fusion graph convolution network for hyperspectral image classification (S3FGCN). S3FGCN can comprehensively use information in spectral, spatial, and spectral–spatial domains with limited data. Moreover, to enhance the performance, we explore a shared weights’ GCN in the spectral–spatial domain. To further improve the efficiency, superpixels are used to construct the adjacency matrix. Finally, dynamic sampling is adopted to make the model focus more on difficult samples. In the experiments on four datasets, S3FGCN demonstrates better accuracy compared with the state-of-the-art hyperspectral image classification methods. [ABSTRACT FROM AUTHOR]

Self-organizing vehicular social networks underpin many location-based services (LBS) such as those that collect and share environmental information (e.g., traffic and weather conditions) among vehicular users and the infrastructure. There are, however, security and privacy considerations in the sharing of such information, and one popular approach is to design lightweight authentication solutions for LBS. Existing approaches may suffer from limitations such as significant computational and/or storage overheads, latency and time delays, and consequently impractical for resource-constrained on-board units. In this paper, we propose an efficient privacy-preserving LBS bundle authentication scheme (hereafter referred to as SAVE) through secure redundancy filtering in self-organizing vehicular social networks. Firstly, an enhanced self-healing key distribution protocol with distributed revocation is proposed to reduce communication cost for retransmitting lost key material and resist free-riding attacks to enhance the authentication efficiency. Then, based on it, a generalized version of online/offline aggregate signature is proposed to achieve batch LBS bundle verification based on arbitrary one-way function holding the property of multiplicative homomorphism. Finally, an efficient zero-knowledge range proof based on lightweight one-way hash chain is designed to decide the redundancy of LBS bundles without disclosing vehicular users’ location privacy. Formal security proof and extensive simulation results demonstrate that our proposed SAVE achieves identity privacy, two levels of location privacy and the practicability in reality. [ABSTRACT FROM AUTHOR]

SMART (Single-cycle Multi-hop Asynchronous Repeated Traversal) Network-on-Chip (NoC), a recently proposed dynamically reconfigurable NoC, enables single-cycle long-distance communication by building single-bypass paths directly between distant communication pairs. However, such a single-cycle single-bypass path will be readily broken when contention occurs. Thus, packets will be buffered at intermediate routers with blocking latency from other contending packets, and extra router-stage latency to rebuild the remaining path when available, reducing the bypassing benefits that SMART NoC offers. In this article, we for the first time propose an effective contention-minimized routing algorithm to achieve maximal bypassing in SMART NoCs. Specifically, we identify two potential routes for packets: direct route, with which packets can reach the destination in a single bypass; and indirect route, with which packets can reach the destination in multiple bypasses via a (multiple) intermediate router(s). The novel feature of the proposed routing strategy is that, contrary to an intuitive approach, not the routes with minimal distance but the indirect routes via the arbitrary intermediate routers (even if they may be non-minimal) that avoid contentions yield the minimized end-to-end latency. Our new routing strategy can greatly enrich the path diversity, effectively minimize the conflicts between communication pairs, greatly balance the workloads and fully utilize bypass paths. Evaluation on realistic benchmarks demonstrates the effectiveness of the proposed routing strategy, which achieves average performance improvement by 35.48 percent in communication latency, 28.31 percent in application schedule length, and 37.59 percent in network throughput, compared with the current routing in SMART NoCs. [ABSTRACT FROM AUTHOR]

Image fusion effectively solves the trade-off among spatial resolution, temporal resolution, and spectral resolution of remote sensing sensors. However, most of existing methods focus on the fusion of two of the spatial, temporal, and spectral metrics of remote sensing images. The few spatial–temporal–spectral fusion (STSF) methods available are mainly for fusing Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat images, which are not suitable for the characteristics of the spaceborne hyperspectral images (HSIs) with low temporal resolution, such as Hyperion, ZY-1 02D, and PRISMA. For this purpose, we proposed a novel generalized linear spectral mixing model for STSF (GLMM-STSF). In the method, the GLMM is introduced into the STSF problem, and the temporal variations of images at different times are transferred to the endmember and abundance matrix variations of images for estimation. To the best of our knowledge, for the first time, the STSF task of remote sensing images is handled from the perspective of spectral unmixing. Compared with the existing STSF fusion methods, our method targets the task of fusing spaceborne HSI with low temporal and spatial resolutions with multispectral image (MSI) featured by high temporal and spatial resolutions. Taking the STSF of ZY-1 02D hyperspectral and Sentinel-2 multispectral real datasets as an example, comparisons with related state-of-the-art methods demonstrate that our proposed method achieves superior fusion performance. [ABSTRACT FROM AUTHOR]

Deep learning (DL) based hyperspectral images (HSIs) denoising approaches directly learn the nonlinear mapping between noisy and clean HSI pairs. They usually do not consider the physical characteristics of HSIs. This drawback makes the models lack interpretability that is key to understanding their denoising mechanism and limits their denoising ability. In this paper, we introduce a novel model-guided interpretable network for HSI denoising to tackle this problem. Fully considering the spatial redundancy, spectral low-rankness, and spectral-spatial correlations of HSIs, we first establish a subspace-based multidimensional sparse (SMDS) model under the umbrella of tensor notation. After that, the model is unfolded into an end-to-end network named SMDS-Net, whose fundamental modules are seamlessly connected with the denoising procedure and optimization of the SMDS model. This makes SMDS-Net convey clear physical meanings, i.e., learning the low-rankness and sparsity of HSIs. Finally, all key variables are obtained by discriminative training. Extensive experiments and comprehensive analysis on synthetic and real-world HSIs confirm the strong denoising ability, strong learning capability, promising generalization ability, and high interpretability of SMDS-Net against the state-of-the-art HSI denoising methods. The source code and data of this article will be made publicly available at https://github.com/bearshng/smds-net for reproducible research. [ABSTRACT FROM AUTHOR]

In this paper, we propose a novel method for boundary detection in close-range hyperspectral images. This method can effectively predict the boundaries of objects of similar colour but different materials. To effectively extract the material information in the image, the spatial distribution of the spectral responses of different materials or endmembers is first estimated by hyperspectral unmixing. The resulting abundance map represents the fraction of each endmember spectra at each pixel. The abundance map is used as a supportive feature such that the spectral signature and the abundance vector for each pixel are fused to form a new spectral feature vector. Then different spectral similarity measures are adopted to construct a sparse spectral-spatial affinity matrix that characterizes the similarity between the spectral feature vectors of neighbouring pixels within a local neighborhood. After that, a spectral clustering method is adopted to produce eigenimages. Finally, the boundary map is constructed from the most informative eigenimages. We created a new HSI dataset and use it to compare the proposed method with four alternative methods, one for hyperspectral image and three for RGB image. The results exhibit that our method outperforms the alternatives and can cope with several scenarios that methods based on colour images cannot handle. [ABSTRACT FROM AUTHOR]

The control bandwidth of the injection-locked system utilizing a DFB fiber laser and fiber ring cavity is analyzed to estimate system stability. Within the bandwidth of the injection lock, an electrical feedback control loop is adopted to better suppress the phase noise of the fiber ring cavity. The entire system operates in low noise conditions of lower than −60 dBc/Hz from 1 Hz to 100 kHz. The output power of the fiber ring cavity is amplified stably to 0.346 W with a polarization extinction ratio of 31 dB based on an all-polarization-maintaining ring structure. The output laser from the single-mode fiber has the near diffraction-limited beam quality for wide applications. [ABSTRACT FROM AUTHOR]

In order to overcome the demerits of traditional city air terminals (CAT), a brand-new service mode based on urban mobile stations (UMS) is introduced in this article for providing the luggage check-in service in urban area. Different from CAT, for each service time period, the UMSs are located based on the real-time passenger distributions. The objectives are to improve the service quality and enhance the competitiveness of air transportation. First, the system components and operation mode of UMS are described. Second, a mathematical model is set up for locating UMSs and assigning passengers to service stations. Three aspects, including the average path length from passengers to UMSs, the maximum acceptable path length for passengers, and the maximum service capacity of a station are considered. Third, to meet the strict time requirement of the UMS system, an effective evolutionary algorithm for optimizing UMS locations in real time is further developed. In the method, the ripple-spreading algorithm is applied for solving the many-to-many path optimization problem and a two-stage adaptive genetic algorithm is utilised for efficiently locating UMSs. Finally, a test case is set up based on the city centre of Tianjin, China, and passenger source locations are obtained by surveying passengers at Tianjin Airport. The reported method is then applied to dynamically locate UMSs in Tianjin urban area and it is compared to some other existing methods to show its effectiveness and efficiency. The service quality of UMS is compared to CAT in both cases with realistic data and randomly generated data to show its advantages. [ABSTRACT FROM AUTHOR]

The existing approach for evaluating the statistical characteristics of speckle intensity distribution is applicable only to completely decorrelated laser beams. In the current study, a theoretical method based on a coherent matrix is developed for evaluating the first-order speckle statistics of partially correlated beams. A rigorous analytical formula for the calculation of speckle contrast is obtained based on the proposed coherent matrix method. Subsequently, an approximate analysis model of the speckle intensity distribution in a laser spot illuminated by partially correlated beams is proposed. The simulation results show that the accuracy of the approximate analysis model increases with the number of beams and is acceptable for practical application, even for a small number of beams. Applications of the proposed method are presented for analyzing two different optical schemes for speckle suppression. It is shown that the developed theoretical method is straightforward and effective for the analysis of light intensity statistics of laser spots illuminated by partially correlated beams. Therefore, the developed method can be easily generalized to imaging systems with partially correlated laser beams for evaluating the speckle intensity statistics. [ABSTRACT FROM AUTHOR]

This study proposes a multi-method fusion algorithm to solve the problem of coupled traction resistance with the vehicle mass for distributed drive agricultural vehicles (DDAVs), because this coupling makes estimation measurements by agricultural vehicles difficult. Indeed, the proposed method decouples the vehicle mass and traction resistance. The vehicle mass was obtained using the recursive least square method and filtering the low-frequency parts of signals of driving force and longitudinal acceleration. After obtaining estimated vehicle mass, the dynamics method was coordinated and complemented with the kinematics method to observe the traction resistance. In the low-frequency load test, statistical performance criteria (SPCs) of the mass estimation were ${R} = 0.9985$ , root mean squared error (RMSE) = 0.0551 kg, and average of prediction accuracy (PA) = 98.02%. In addition, SPCs of the traction resistance estimation were ${R}=0.9655$ , RMSE = 23.0472 N, and average of PA = 99.28%. In the high-frequency load test, the maximum PA of the mass estimation reached 98.78%, and SPCs of the traction resistance estimation were ${R} = 0.9371$ , RMSE = 1266.3933 N, and average of PA = 85.62%. Experimental tests proved that the proposed method is robust and can accurately estimate the vehicle mass and traction resistance in real time. [ABSTRACT FROM AUTHOR]

SMART NoC, which transmits unconflicted flits to distant processing elements (PEs) in one cycle through the express bypass, is a high-performance NoC design proposed recently. However, if contention occurs, flits with low priority would not only be buffered but also could not fully utilize bypass. Although there exist several routing algorithms that decrease contentions by rounding busy routers and links, they cannot be directly applicable to SMART since it lacks the support for arbitrary-turn (i.e., the number and direction of turns are free of constraints) routing. Thus, in this article, to minimize contentions and further utilize bypass, we propose an improved SMART NoC, called ArSMART, in which the arbitrary-turn transmission is enabled. Specifically, ArSMART divides the whole NoC into multiple clusters where the route computation is conducted by the cluster controller and the data forwarding is performed by the bufferless reconfigurable router. Since the long-range transmission in SMART NoC needs to bypass the intermediate arbitration, to enable this feature, we directly configure the input and output ports connection rather than applying hop-by-hop table-based arbitration. To further explore the higher communication capabilities, effective adaptive routing algorithms that are compatible with ArSMART are proposed. The route computation overhead, one of the main concerns for adaptive routing algorithms, is hidden by our carefully designed control mechanism. Compared with the state-of-the-art SMART NoC, the experimental results demonstrate an average reduction of 40.7% in application schedule length and 29.7% in energy consumption. [ABSTRACT FROM AUTHOR]

The rapid development of remote sensing sensors makes the acquisition, analysis, and application of hyperspectral images (HSIs) more and more extensive. However, the limited sample sets, high-dimensional features, highly correlated bands, and mixing spectral information make the classification of HSIs a great challenge. In this article, an unsupervised multiscale and diverse feature learning (UMsDFL) method is proposed for HSI classification, which deeply considers the spatial–spectral features via convolutional neural networks (CNNs). Specifically, after employing the simple noniterative clustering (SNIC) algorithm with the heuristic calculation of superpixel size, the HSIs are segmented into superpixels for feature learning. The unsupervised network is designed with the convolutional encoder and decoder, the additional clustering branch, and the multilayer feature fusion to enhance the distinguishability of feature learning and the reusability of feature maps. Then, the spatial relationships and object attributes in large- and small-scale contexts are learned collaboratively through the unsupervised network to utilize the complementary multiscale characteristics. Moreover, the diverse features of hyperspectral information and nonsubsampled contourlet transform (NSCT) textures are learned simultaneously via the unsupervised network to alleviate the insufficiency of geometric representation. Finally, the random forest (RF) is adopted as the comprehensive classifier for land cover mapping based on the UMsDFL, and superpixel regularization is adopted to optimize the classification results. A series of experiments are performed on three real-world HSI datasets to demonstrate the effectiveness of our UMsDFL approach. The experimental results show that the proposed UMsDFL can achieve the overall accuracy of 79.23%, 96.49%, and 77.26% for Houston, Pavia, and Dioni datasets, respectively, when there are only five samples per class for training. [ABSTRACT FROM AUTHOR]

We investigate stimulated Brillouin scattering (SBS) suppressing capability of a piecewise parabolic waveform phase modulated fiber system by means of localized nonfluctuating source model. The optical spectra of piecewise parabolic phase modulated laser field are derived analytically. We prove that the parabolic phase modulated laser spectra have a discrete top-hat envelope, and the spectral linewidth can be changed by the product of modulation depth and chirp rate while the spectral line separation remains constant. Theoretically, we calculated the Brillouin gain spectra of piecewise parabolic phase modulation to visually characterize the SBS suppression capability. We define $L_{ch}$ as the characteristic fiber length. It is found that the Brillouin gain spectra broadened as fiber length $L$ increases for the case of $L < L_{ch}$ , while reach the widest linewidth and keep constant for the case of $L\geq L_{ch}$. We establish a piecewise parabolic phase modulation experimental setup to verify our simulation results. According to our model and experiments, we also made predictions for SBS suppression of GHz-level fiber system with several kilowatts output power and $\sim 10$ m fiber length. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) denoising is an ill-posed inverse problem. The underlying physical model is always important to tackle this problem, which is unfortunately ignored by most of the current deep learning (DL)-based methods, producing poor denoising performance. To address this issue, this article introduces an end-to-end model-aided nonlocal neural network (MAC-Net) which simultaneously takes the spectral low-rank model and spatial deep prior into account for HSI noise reduction. Specifically, motivated by the success of the spectral low-rank model in depicting the strong spectral correlations and the nonlocal similarity prior in capturing spatial long-range dependencies, we first build a spectral low-rank model and then integrate a nonlocal U-Net into the model. In this way, we obtain a hybrid model-based and DL-based HSI denoising method where the spatial local and nonlocal multi-scale and spectral low-rank structures are effectively exploited. After that, we cast the optimization and denoising procedure of the hybrid method as a forward process of a neural network and introduce a set of learnable modules to yield our MAC-Net. Compared with traditional model-based methods, our MAC-Net overcomes the difficulties of accurate modeling, thanks to the strong learning and representation ability of DL. Unlike most “black-box” DL-based methods, the spectral low-rank model is beneficial to increase the generalization ability of the network and decrease the requirement of training samples. Experimental results on the natural and remote-sensing HSIs show that MAC-Net achieves state-of-the-art performance over both model-based and DL-based methods. The source code and data of this article will be made publicly available at https://github.com/bearshng/mac-net for reproducible research. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) denoising is a crucial preprocessing task to improve the performance of the subsequent HSI interpretation and applications. With recent progress in deep learning, HSI denoising methods based on deep neural networks have attracted increasing interest and achieved the state-of-the-art performance. Nevertheless, most of these methods are based on network structures originally developed for grayscale and color images and require a change of network structure to be applicable to HSIs. The new network architectures often lead to complicated models and limited flexibility, which, in turn, result in difficulty in learning and demand of a large number of training samples. In this article, we propose an innovative two-stage learning method including pretraining and fine-tuning procedures. In the first stage, a denoising convolutional neural network can be pretrained with pairs of corrupted and clean images. In the second stage, the pretrained network is fine-tuned via a self-supervised learning strategy to capture the spectral correlation in HSIs. The training pairs in the second stage are constructed from the neighboring band images in the target noisy HSI, leading to a novel idea of embedding spectral information into denoiser through the target image, rather than the change of the network architecture. This model has strong adaptability such that many image denoising networks can be easily adopted for HSIs, while the external hyperspectral training set is optional but not mandatory. Experimental results show that our method has competitive performance compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing is recognized as an important tool to learn the constituent materials and corresponding distribution in a scene. The physical spectral mixture model is always important to tackle this problem because of its highly ill-posed nature. In this article, we introduce a linear spectral mixture model (LMM)-based end-to-end deep neural network named SNMF-Net for hyperspectral unmixing. SNMF-Net shares an alternating architecture and benefits from both model-based methods and learning-based methods. On the one hand, SNMF-Net is of high physical interpretability as it is built by unrolling $L_{p}$ sparsity constrained nonnegative matrix factorization ($L_{p}$ -NMF) model belonging to LMM families. On the other hand, all the parameters and submodules of SNMF-Net can be seamlessly linked with the alternating optimization algorithm of $L_{p}$ -NMF and unmixing problem. This enables us to reasonably integrate the prior knowledge on unmixing, the optimization algorithm, and the sparse representation theory into the network for robust learning, so as to improve unmixing. Experimental results on the synthetic and real-world data show the advantages of the proposed SNMF-Net over many state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Band selection is an effective means to alleviate the curse of dimensionality in hyperspectral data. Many methods select a compact and low redundant band subset, which is inadequate as it may degrade the classification performance. Instead, more emphasis shall be put on selecting representative bands. In this article, we propose a robust unsupervised band selection method to address this issue. Our method reveals bandwise representativeness based on the comprehensive interband neighborhood structure. It incorporates an interband neighborhood graph into a sparse self-contained regression model in order to provide a reasonable measure for bandwise representativeness. The derived coefficient matrix not only uncovers bandwise importance values but also is coherent to the generalized interband local neighborhood structure. For constructing the interband neighboring structural graph, an integrated multigraph model is employed to achieve better generalization performance. It combines the benefit of multiple graphs but is insusceptible to the defects of a single one. To enhance the reliability of this model, a joint trace minimum and nonnegative constraint is imposed on the coefficient matrix. Accordingly, a multigraph integrated embedding and robust self-contained regression model (MGRSR) is formulated. In addition, an iterative update algorithm is developed to solve the problem. Comparative experiments on three hyperspectral data sets illustrate that MGRSR is robust to various data and has superior performance compared with several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The convolutional neural network (CNN) is a feed-forward neural network with deep structure and convolution operation. In the hyperspectral image (HSI) classification, CNN has demonstrated excellent performance in extracting spectral and spatial information. However, the inherent complexity and high dimension of HSIs still limit the performance of most neural network models. The powerful feature extraction ability of CNN is normally achieved by dozens or more layers, which brings a series of problems such as gradient vanishing, overfitting, and slow training speed. In order to address these problems, this article presents a CNN architecture-based stochastic depth residual network (SDRN), which is specially designed for HSI data. This model takes the original 3-D cube as the input and 3-D convolution is used to extract abundant spectral and spatial features through corresponding residual blocks. In order to reduce the training time, we adopt a stochastic depth strategy. For each small batch, a sublayer is randomly discarded by an identity function. During the testing stage, the residual network with complete depth is used. Experiments on three datasets and a comparison of the state-of-art methods show that SDRN has great advantages in accuracy and training time compared with state-of-the-art HSI classification methods. [ABSTRACT FROM AUTHOR]

ECG classification is a key technology in intelligent electrocardiogram (ECG) monitoring. In the past, traditional machine learning methods such as support vector machine (SVM) and K-nearest neighbor (KNN) have been used for ECG classification, but with limited classification accuracy. Recently, the end-to-end neural network has been used for ECG classification and shows high classification accuracy. However, the end-to-end neural network has large computational complexity including a large number of parameters and operations. Although dedicated hardware such as field-programmable gate array (FPGA) and application-specific integrated circuit (ASIC) can be developed to accelerate the neural network, they result in large power consumption, large design cost, or limited flexibility. In this work, we have proposed an ultra-lightweight end-to-end ECG classification neural network that has extremely low computational complexity (∼8.2k parameters & ∼227k multiplication/addition operations) and can be squeezed into a low-cost microcontroller (MCU) such as MSP432 while achieving 99.1% overall classification accuracy. This outperforms the state-of-the-art ECG classification neural network. Implemented on MSP432, the proposed design consumes only 0.4 mJ and 3.1 mJ per heartbeat classification for normal and abnormal heartbeats respectively for real-time ECG classification. [ABSTRACT FROM AUTHOR]

Point cloud processing is rapidly expanding the applicable scenarios in the industry. The surface normal is a fundamental feature for various point cloud processing tasks. Recently, deep supervised normal estimators outperform traditional normal estimation methods by adapting to dataset statistics. However, existing normal estimation methods mainly adopt hand-crafted features or complicated networks borrowed from other tasks and make less effort to design network models specifically for the problem. Instead of regressing the normal vector directly, we propose a simple deep network to estimate the normal vector based on a latent tangent space representation learned in the network. We call the network tangent represent learning network (TRNet). For each query point, the tangent space representation is a set of latent points spanning the tangent plane of it. The representation is generated using only the coordinates of its neighbors and regularized by a differentiable random sample consensus like component, which makes TRNet more compact and effective for normal estimation. We also design a compact multiscale network, denoted by multiresolution tangent representation learning network (MTRNet), to boost estimations from multiple TRNet trained with different fixed neighborhood size. Our TRNet and MTRNet perform favorably against state-of-the-art methods on synthesized data and real scenarios with far smaller model size. [ABSTRACT FROM AUTHOR]

Low noise synchronization of the frequency and phase of a DFB fiber laser and two fiber ring cavities was achieved based on a two-channel optical injection lock and phase lock loop. Two-channel modulation signals of different frequencies were adopted to extract the phase noise signals of the two fiber ring cavities. Finally, the lasers from the two fiber ring cavities were coherently combined in the closed loop of the control system owing to the synchronous frequency and phase. The power stability and polarization stability of the combined laser was improved under the optical injection lock and phase lock loop. The phase noise of the two cavities was $6.56 \times 10^{-7}$ rad/Hz1/2 and $1.34 \times 10^{-6}$ rad/Hz1/2 at 10 Hz; and $7.77 \times 10^{-8}$ rad/Hz1/2 and $1.35 \times 10^{-7}$ rad/Hz1/2 at 10 kHz. The total combined power was ~580 mW in the closed loop, and the entire system oscillated under a single frequency, providing excellent power scaling ability. [ABSTRACT FROM AUTHOR]

We describe stimulated Brillouin scattering process in a fiber system with light field phase modulated by lowpass filtered and amplified pseudo random bit sequence (PRBS) using localized nonfluctuating source model. The effective Brillouin gain spectra and the ratio of normalized Stimulated Brillouin Scattering (SBS) threshold to RMS optical linewidth is used to characterize the SBS suppression capability of the PRBS phase modulation. The normalized effective Brillouin gain spectra for different modulation parameters are calculated to exhibit the Brillouin gain broadening process. Based on the theoretical model, we find that the SBS threshold reaches a maximum for the ratio of cutoff frequency to clock rate rc = 0.53 and RMS modulation depth krms = 0.55 π for PRBS9. An effective Brillouin gain spectrum measurement setup is established, and the theoretical predictions are verified by the experiment. [ABSTRACT FROM AUTHOR]

Hyperspectral images encompass abundant information and provide unique characteristics for material classification. However, the labeling of training samples can be challenging in hyperspectral image classification. To address this problem, this study proposes a framework named flexible Gabor-based superpixel-level unsupervised linear discriminant analysis (FG-Su ULDA) to extract the most informative and discriminating features for classification. First, a number of 3-D flexible Gabor filters are rigorously designed using an asymmetric sinusoidal wave to sufficiently characterize the spatial–spectral structure in hyperspectral images. Then, an unsupervised linear discriminant analysis strategy guided by the entropy rate superpixel (ERS) segmentation algorithm, called Su ULDA, is skillfully introduced to reduce the extracted large amount of FG features. The Su ULDA method not only boosts the classification capability but also increases the peculiarity of features, with the aid of superpixel information. Finally, the achieved features are imported to the popular support vector machine classifier. The proposed FG-Su ULDA framework is applied to four real hyperspectral image data sets, and the experiments constantly prove that our FG-Su ULDA is superior to several state-of-the-art methods in both classification performance and computational efficiency, especially with scarce training samples. The codes of this work are available at http://jiasen.tech/papers/ for the sake of reproducibility. [ABSTRACT FROM AUTHOR]

In recent years, due to increased attention of individual physical health condition, the demand on portable multi-vital signs monitoring devices has shown an explosive growth. This work designed a portable, multi-vital signs monitoring system, consisting of chest unit and wrist unit, with size of 32 mm $\times32$ mm and diameter of 30 mm, respectively. The designed system is capable of transmitting measured electrocardiograph (ECG), pulse wave and body temperature signal to the mobile devices wirelessly by Bluetooth low energy (BLE) technique. The heart rate, pulse oximetry (SpO2) and respiratory rate are extracted through time domain algorithm. The chest and wrist units can continuously monitor body vital signs for more than 12 and 24 hours, respectively. Besides, the experiment results reveal that the chest unit is able to monitor patients with heart rate abnormalities such as atrial fibrillation and premature beats. The typical heart diseases can be detected in real-time. Meanwhile, the wrist unit clearly detects the changes of the physical parameters of the subjects under different physiological conditions. The accuracy of the designed system is consistent with that of the commercial medical instrument counterpart, with further advantages of compact, portable and patient-friendly natures. [ABSTRACT FROM AUTHOR]

Due to the importance in many military and civilian applications, hyperspectral anomaly detection has attracted remarkable interest. Low-rank representation (LRR)-based anomaly detectors use the low-rank property to represent background pixels, and pixels that cannot be well represented are detected as anomalies. The ability of an LRR-based detector to separate background pixels and anomalous pixels depends on the dictionary representation ability, which usually can be enhanced by designing a proper prior for dictionary representation coefficients and constructing a better dictionary. However, it is not easy to handcraft effective and meaningful regularizers for dictionary coefficients. In this article, we propose a novel anomaly detection algorithm that uses a plug-and-play prior for representation coefficients and constructs a new dictionary based on clustering. Instead of cumbersomely handcrafting a regularizer for representation coefficients, we propose solving the anomaly detection problem using the plug-and-play framework, which enables us to plug state-of-the-art priors for representation coefficients. An effective convolutional neural network (CNN) denoiser is plugged into our framework to fully exploit the spatial correlation of representation coefficients. We also propose a modified background dictionary construction method, which carefully includes background pixels and excludes anomalous pixels from clustering results. We refer to the proposed anomaly detection method as plug-and-play denoising CNN regularized anomaly detection (DeCNN-AD) method. Extensive experiments were performed on five data sets in a comparison with eight state-of-the-art anomaly detection methods. The experimental results suggest that the proposed method is effective in anomaly detection and can produce better anomaly detection results than that of the comparison methods. The codes of this work will be available at https://github.com/FxyPd for the sake of reproducibility. [ABSTRACT FROM AUTHOR]

Reported here are disk-integrated Moon surface microwave brightness temperature ($Tb$) retrievals covering the frequency range of 23–183 GHz. Full Moon observations obtained from the advanced technology microwave sounder (ATMS) onboard the NOAA-20 satellite during a special spacecraft pitch–maneuver operation forms the basis of the retrievals. Instrument nonlinearity, Earth sidelobe contamination, cosmic background radiation, and reflector thermal emission corrections are applied to the observations to obtain accurate values of the Moon’s $Tb$ at all frequencies. The measured full Moon $Tb$ ranges from ~240 to 293 K with frequency increases from 23 to 183 GHz. A clear frequency trend is detected when the brightness temperature increases. [ABSTRACT FROM AUTHOR]

Deep learning approaches have significantly contributed to recent progress in stereo matching. These deep stereo matching methods are usually based on supervised training, which requires a large amount of high-quality ground-truth depth map annotations that are expensive to collect. Furthermore, only a limited quantity of stereo vision training data are currently available, obtained either by active sensors (Lidar and ToF cameras) or through computer graphics simulations and not meeting requirements for deep supervised training. Here, we propose a novel deep stereo approach called the “self-supervised multiscale adversarial regression network (SMAR-Net),” which relaxes the need for ground-truth depth maps for training. Specifically, we design a two-stage network. The first stage is a disparity regressor, in which a regression network estimates disparity values from stacked stereo image pairs. Stereo image stacking method is a novel contribution as it not only contains the spatial appearances of stereo images but also implies matching correspondences with different disparity values. In the second stage, a synthetic left image is generated based on the left–right consistency assumption. Our network is trained by minimizing a hybrid loss function composed of a content loss and an adversarial loss. The content loss minimizes the average warping error between the synthetic images and the real ones. In contrast to the generative adversarial loss, our proposed adversarial loss penalizes mismatches using multiscale features. This constrains the synthetic image and real image as being pixelwise identical instead of just belonging to the same distribution. Furthermore, the combined utilization of multiscale feature extraction in both the content loss and adversarial loss further improves the adaptability of SMAR-Net in ill-posed regions. Experiments on multiple benchmark datasets show that SMAR-Net outperforms the current state-of-the-art self-supervised methods and achieves comparable outcomes to supervised methods. The source code can be accessed at: https://github.com/Dawnstar8411/SMAR-Net. [ABSTRACT FROM AUTHOR]

Medical hyperspectral imagery has recentlyattracted considerable attention. However, for identification tasks, the high dimensionality of hyperspectral images usually leads to poor performance. Thus, dimensionality reduction (DR) is crucial in hyperspectral image analysis. Motivated by exploiting the underlying structure information of medical hyperspectral images and enhancing the discriminant ability of features, a discriminant tensor-based manifold embedding (DTME) is proposed for discriminant analysis of medical hyperspectral images. Based on the idea of manifold learning, a new discriminant similarity metric is designed, which takes into account the tensor representation, sparsity, low-rank and distribution characteristics. Then, an inter-class tensor graph and an intra-class tensor graph are constructed using the new similarity metric to reveal intrinsic manifold of hyperspectral data. Dimensionality reduction is achieved by embedding this supervised tensor graphs into the low-dimensional tensor subspace. Experimental results on membranous nephropathy and white bloodcells identification tasks demonstrate the potential clinical value of the proposed DTME. [ABSTRACT FROM AUTHOR]

This article investigates spectral chromatic and spatial defocus aberration in a monocular hyperspectral image (HSI) and proposes methods on how these cues can be utilized for relative depth estimation. The main aim of this work is to develop a framework by exploring intrinsic and extrinsic reflectance properties in HSI that can be useful for depth estimation. Depth estimation from a monocular image is a challenging task. An additional level of difficulty is added due to low resolution and noises in hyperspectral data. Our contribution to handling depth estimation in HSI is threefold. Firstly, we propose that change in focus across band images of HSI due to chromatic aberration and band-wise defocus blur can be integrated for depth estimation. Novel methods are developed to estimate sparse depth maps based on different integration models. Secondly, by adopting manifold learning, an effective objective function is developed to combine all sparse depth maps into a final optimized sparse depth map. Lastly, a new dense depth map generation approach is proposed, which extrapolate sparse depth cues by using material-based properties on graph Laplacian. Experimental results show that our methods successfully exploit HSI properties to generate depth cues. We also compare our method with state-of-the-art RGB image-based approaches, which shows that our methods produce better sparse and dense depth maps than those from the benchmark methods. [ABSTRACT FROM AUTHOR]

In the hyperspectral image, each pixel corresponds to a small area on the Earth’s surface and represents the intrinsic characteristic of objects, which can be applied for recognition of land covers. Nevertheless, hyperspectral image processing should face some critical issues, and a small sample set problem may be the most challenging one in the research. Deep learning (DL), which has successfully been applied in many fields, has also been introduced for hyperspectral image classification. However, the large gap between the massive parameters to be tuned and limited labeled samples can lead to overfitting scenario, inevitably deteriorating the generalization ability of the DL model. In this article, a lightweight convolutional neural network (LWCNN) is proposed for hyperspectral image classification to mainly tackle the small sample set problem. Especially, spatial–spectral Schroedinger eigenmaps (SSSE) feature extraction is first adopted to obtain the joint spatial–spectral information, and the compressed dimensionality could significantly reduce the number of parameters in the following DL model. Second, a dual-scale convolution (DSC) module is carefully designed to address the SSSE features from a 1-D vector viewpoint (the number of parameters is further decreased), and the DSC procedure is successively employed to obtain the hierarchical structure description that could represent data distribution from different aspects. Subsequently, the feature vectors from all DSC layers are separately filtered by a new bichannel fusion (BCF) module, which could well encode both the intrinsic and contextual information inside DSC features. Finally, the filtered features are concatenated together and imported into a global average pooling classifier to achieve the predicted probability of each category. Experimental results on three famous hyperspectral image data sets illustrate that the developed LWCNN approach is advantageous in both the efficiency and robustness sides for hyperspectral image classification tasks and outperforms other state-of-the-art methods (both traditional-based and DL-based) with very limited labeled samples. [ABSTRACT FROM AUTHOR]

Flexible tactile sensors have become one of the most attractive research areas because of its great application prospect in electronic skin, healthcare monitoring and artificial intelligence. However, there are still great challenges in mimicking the human skin’s strong ability of tactile perception to the changes of external physical information. Nowadays, in addition to flexible polymers and conductive materials, the microstructure of sensing units is a key factor to improve the performance of tactile sensors such as sensitivity, fast response and robustness. In recent years, a variety of novel microstructure designs have been applied to applications of tactile information perception and numerous corresponding processing methods have also been developed, which provides a wealth of enlightening solutions for the production of electronic skins. Herein, a large number of research results of tactile sensor devices are systematically reviewed according to different three-dimensional geometric shapes of the microstructures which are grouped into several categories. At the same time, relevant processing technologies employed, working principles and chief performance characteristics are also briefly described. Relative merits of different types of microstructure applications are clearly elaborated through the classification and comparison of multiple microstructure geometries in this paper to provide valuable reference for sensing microstructure design and fabrication of tactile sensors in corresponding engineering applications. Moreover, current difficulties and challenges in fabrication of flexible microstructures and future investigative directions pertaining to this field have been discussed. [ABSTRACT FROM AUTHOR]

We demonstrated a mode-controllable fiber laser system with output power of 1.4 kW level. The system consists of a kilowatt-scale master oscillator power amplifier and an active feedback control system based on the stochastic parallel-gradient descent algorithm. We can convert the LP01 and LP11 modes by performing an extremum search for power in the bucket of the output beam. Under the same pump power, we obtain the mode conversion of LP11 to LP01, and the efficiency is as high as 99.5%. The maximum output power of LP11 and LP01 mode are 1396 W and 1389 W, respectively, with corresponding slope efficiencies of 85.8% and 84.1%. [ABSTRACT FROM AUTHOR]

The rapid increase in the number of remote sensing sensors makes it possible to develop multisource feature extraction and fusion techniques to improve the classification accuracy of surface materials. It has been reported that light detection and ranging (LiDAR) data can contribute complementary information to hyperspectral images (HSIs). In this article, a multiple feature-based superpixel-level decision fusion (MFSuDF) method is proposed for HSIs and LiDAR data classification. Specifically, superpixel-guided kernel principal component analysis (KPCA) is first designed and applied to HSIs to both reduce the dimensions and compress the noise impact. Next, 2-D and 3-D Gabor filters are, respectively, employed on the KPCA-reduced HSIs and LiDAR data to obtain discriminative Gabor features, and the magnitude and phase information are both taken into account. Three different modules, including the raw data-based feature cube (concatenated KPCA-reduced HSIs and LiDAR data), the Gabor magnitude feature cube, and the Gabor phase feature cube (concatenation of the corresponding Gabor features extracted from the KPCA-reduced HSIs and LiDAR data), can be, thus, achieved. After that, random forest (RF) classifier and quadrant bit coding (QBC) are introduced to separately accomplish the classification task on the aforementioned three extracted feature cubes. Alternatively, two superpixel maps are generated by utilizing the multichannel simple noniterative clustering (SNIC) and entropy rate superpixel segmentation (ERS) algorithms on the combined HSIs and LiDAR data, which are then used to regularize the three classification maps. Finally, a weighted majority voting-based decision fusion strategy is incorporated to effectively enhance the joint use of the multisource data. The proposed approach is, thus, named MFSuDF. A series of experiments are conducted on three real-world data sets to demonstrate the effectiveness of the proposed MFSuDF approach. The experimental results show that our MFSuDF can achieve the overall accuracy of 73.64%, 93.88%, and 74.11% for Houston, Trento, and Missouri University and University of Florida (MUUFL) Gulport data sets, respectively, when there are only three samples per class for training. [ABSTRACT FROM AUTHOR]

Point-of-care testing (POCT) is characterized by fast detection, simple use, and cost efficiency. As the focus of healthcare shifts to precision medicine, population health, and chronic disease management, the potential impact of POCT has increased significantly in the past decade. Immunochromatographic test strips (ICTSs) are currently the most promising POCT diagnostic format due to the advantages of fast detection, simple operation and cost-effective. The lateral flow immune analyzer (LFIA) system that uses magnetic resistance (MR) sensors as readers and magnetic nanoparticle labeling materials has attracted wide attention due to its high sensitivity and specificity. This paper designs a quantitative lateral flow immunoassay instrument for MR sensors using InSb single crystals as magnetoresistive elements. MR sensors detect samples of ICTSs labeled with superparamagnetic nanoparticles (SMNPs). The collected weak magnetic signal is processed by the designed amplifying circuit and software algorithm. As a result, the MR system can quantitatively detect the concentration of morphine (MOP), and has good repeatability. Compared with other optical detection instruments, the system has good specificity because there is very low background noise in the detection sample. The size of the whole system is 98 mm × 62 mm × 78 mm, and it has the characteristics of compactness and fast detection. [ABSTRACT FROM AUTHOR]

In many statistical hyperspectral unmixing approaches, the unmixing task is essentially an optimization problem given a defined linear or nonlinear spectral mixture model. However, most of the model inference algorithms require a time-consuming iterative procedure. On the other hand, neural networks have been recently used to estimate abundances given some training samples, or directly estimate endmembers and abundances simultaneously in an unsupervised setting. However, their disadvantages are clear: lack of interpretability and reliance on the large training set. Model-inspired neural networks are constructed by the problem model and its corresponding inference algorithm. It incorporates the prior knowledge of physical model and algorithm into network architecture, combining the advantages of model-based and learning-based methods. This article deeply unfolds the linear mixture model and the corresponding iterative shrinkage-thresholding algorithm (ISTA) to build two unmixing network architectures. The first assumes that the set of endmembers are known, and the deep unfolded ISTA model is only for abundance estimation; and the second is used for blind unmixing to estimate both endmembers and abundances at the same time. The networks can be trained by supervised and unsupervised schemes, respectively, with a small-size training set, and then, unmixing becomes a feedforward process, which is very fast since no iteration is required. The experimental results show their competitive performance compared with the state-of-the-art unmixing approaches. [ABSTRACT FROM AUTHOR]

With the emergence of next-generation fiber materials and the development of sensors and wearable technologies, new breakthroughs also emerge in the field of wearable fabrics. By combining wearable fabrics with sensors, artificial intelligence and other technologies, the new intelligent fabrics create an intelligent, flexible and adaptive performance, thus meeting people's needs better and becoming more acceptable to users than traditional fabrics. Nevertheless, present intelligent fabrics have some shortcomings, such as insufficient interactive ability, the narrow scope of applications, and poor ability in synchronizing physical and psychological health data. Therefore, in this article, we propose the Living with I-Fabric system, which represents smart living powered by intelligent fabric and deep analytics. The proposed system is capable of solving problems that are beyond the scope of existing fabrics and further improve the user's experience. Combining multiple smart accessories and cognitive devices, together with smartphones and multi-level clouds, the proposed system builds a comprehensive and sustainable health monitoring and guidance ecosystem. Through AI algorithms on the edge and remote clouds, the user's historical data is analyzed in depth, and additional valued function services can be provided for users. [ABSTRACT FROM AUTHOR]

Frequency-tunable gyrotron is a promising terahertz (THz) radiation source for many modern applications. Actually, a resonator-based gyrotron oscillator can play dual functions: gyromonotron and reflected-type gyro-backward-wave oscillator (BWO) corresponding to the forward-wave and backward-wave operation. The performances of the gyromonotron and the reflected-type gyro-BWO for a 0.5-THz frequency-tunable gyrotron have been theoretically investigated in detail. The calculated results indicate that the frequency tunability, the field profile of the axial mode, and the beam–wave interaction efficiency of the gyromonotron and the reflected-type gyro-BWO are dramatically different from each other. The gyromonotron state can switch to the reflected-type gyro-BWO state by means of increasing the operating magnetic field. In addition, we have systematically investigated the characteristics of the 0.5-THz frequency-tunable gyrotron with different beam–wave interaction structures, especially for the reflected-type gyro-BWO. It is found that the tapered angle of the output section has a significant effect on the frequency tunability of the reflected-type gyro-BWO, and the multisection cavity can improve the performance of the reflected-type gyro-BWO. The results of this study may be beneficial for getting a deeper insight into the physics of the forward-wave and backward-wave operation of a frequency-tunable gyrotron. [ABSTRACT FROM AUTHOR]

Although object detection techniques have been widely employed in various practical applications, automatic tree detection is still a difficult challenge, especially for street-view images. In this article, we propose a unified end-to-end trainable network for automatic street tree detection based on a state-of-the-art deep learning-based object detector. We tackle low illumination and heavy occlusion conditions in tree detection, which have not been extensively studied until now, due to clear challenges. Existing generic object detectors cannot be directly applied to this task due to aforementioned challenges. To address these issues, we first present a simple, yet effective image brightness adjustment method to handle low illuminance cases. Moreover, we propose a novel loss and a tree part-attention module to reduce false detections caused by heavy occlusion, inspired by the previously proposed occlusion-aware region-convolutional neural network (R-CNN) work. We train and evaluate several versions of the proposed network and validate the importance of each component. It is demonstrated that the resulting framework, part attention network for tree detection (PANTD), can efficiently detect trees in street-view images. The experimental results show that our approach achieves high accuracy and robustness under various conditions. [ABSTRACT FROM AUTHOR]

Traditional color images only depict color intensities in red, green and blue channels, often making object trackers fail in challenging scenarios, e.g., background clutter and rapid changes of target appearance. Alternatively, material information of targets contained in large amount of bands of hyperspectral images (HSI) is more robust to these difficult conditions. In this paper, we conduct a comprehensive study on how material information can be utilized to boost object tracking from three aspects: dataset, material feature representation and material based tracking. In terms of dataset, we construct a dataset of fully-annotated videos, which contain both hyperspectral and color sequences of the same scene. Material information is represented by spectral-spatial histogram of multidimensional gradients, which describes the 3D local spectral-spatial structure in an HSI, and fractional abundances of constituted material components which encode the underlying material distribution. These two types of features are embedded into correlation filters, yielding material based tracking. Experimental results on the collected dataset show the potentials and advantages of material based object tracking. [ABSTRACT FROM AUTHOR]

As a typical graph-based semisupervised learning technique, the label propagation (LP) approach has gained much attention in recent years. The key to LP algorithms is the propagation capability and efficiency of the similarity matrix, which describes the similarity between two data points. Concerning hyperspectral image which often contains hundreds of thousands of pixels, the corresponding similarity matrix is particularly huge and thus the LP procedure is intractable. Fortunately, superpixel, which can effectively characterize the spatial semantic information of surface objects, provides a reasonable way to solve this problem. In this article, we propose an elaborate superpixel-based weighted LP approach, abbreviated as SuWLP, for hyperspectral image classification. First, the hyperspectral image is oversegmented by the entropy rate segmentation (ERS) method, and the internal consistency of each superpixel can be achieved. Second, a new similarity measure is designed to estimate the similarity between two superpixels, and a superpixel-based similarity matrix can be thus established. Third, after the training samples have been expanded based on the superpixel distribution, a weighted LP technique is designed to propagate the sample label at the superpixel level without any parameter tuning. Finally, the label of each superpixel maps back to the contained pixels. We compared our proposed SuWLP method with several state-of-the-art ones, and experimental results on three real hyperspectral data sets certify the effectiveness and efficiency of the superpixel-level LP strategy. [ABSTRACT FROM AUTHOR]

Location-based service (LBS) in vehicular ad hoc networks (VANETs) has significantly benefited information acquisition from geographically-based social networking. Authentication guarantees the unforgeability and the effectiveness of the LBS information. Unfortunately, owing to a large quantity of redundant or useless LBS messages disseminated in VANETs, the heavy authentication overhead of the existing work adopting a periodically released authentication key, filtering with message identifiers or exploiting public key (fully) homomorphic encryption (FHE), is either intolerable by resource-constrained on-board units (OBUs) or inappropriate to the realtime controlling requirement for VANETs. In this paper, an efficient multi-key secure outsourced computation scheme MSOC without exploiting public key FHE is first proposed, in the setting of two non-colluding servers, namely the cloud and the cryptographic service provider (CSP). Then, based on MSOC, an efficient and secure comparison protocol LSCP is devised, without the interaction between the server and the users. Furthermore, a lightweight privacy-preserving authentication protocol LPPA for LBS in VANETs is proposed, by eliminating duplicate and useless encrypted LBS messages before authentication is executed, through a newly devised efficient privacy-preserving information filtering system. Both user’s location privacy and interest privacy are well protected against even the collusion between the roadside units (RSUs) serving as the cloud (or CSP) and malicious users. Especially, the property of ciphertext re-encryption of our proposed MSOC also guarantees the interest pattern privacy whether two users accept the same LBS information. Finally, formal security proof and extensive simulation results verify the effectiveness and practicability of our proposed LPPA. [ABSTRACT FROM AUTHOR]

map matching has played a crucial role in technologies related to indoor positioning. Conventional map matching algorithms based on particle filter (PF) have some limitations, such as the limited use of map information, poor generalization and low precision. To solve these problems, we propose an adaptable particle filter network (AdaPFnet), a novel map matching technique that integrates particle filter algorithm into a neural network. AdaPFnet uses local views of particles to represent particles so that the map information about location can be learned sufficiently through a neural network. To demonstrate the performance of the model, it has conducted extensive experiments using 1540 real-world data. The results show that AdaPFnet outperforms PF by up to 21% and remains a strong adaptability for different environments. [ABSTRACT FROM AUTHOR]

Power girds in different countries face different types of threats and in China the threats severely affecting grid reliability were in the past large power outage accidents caused by pollution flashovers. First records of pollution flashover accidents in China can be traced back to 1950s in industrial areas in Northeast and East China. Thereafter, such accidents occurred occasionally, but after 1970s they started to expand and were recorded in most of the country's provinces. The very first large area outage accident caused by pollution flashover happened in early 1974 in Northeast China around the local largest cities Shenyang and Fushun. Between 1971 and 1994, 3542 pollution-caused line trip-outs (several trip-outs on one overhead line (OHL) happening the same day is counted in China as a single event) were recorded on 35–500 kV OHLs and 1768 substation trip-outs. A total of 44 large area outage accidents caused by pollution flashovers took place during the 30 year period before 2007, as shown in Figure 1, while the outages recorded between 1981 and 2001 accounted for 43% of the total number. Among them, outages of super large character occurred every 5–6 years, e.g., in 1990 in North China and Northeast China, in 1996–1997 in East China and Central China, 2001 in North China and Northeast China [1–3]. Here we refer to the large area outage accidents as flashover events on several main transmission overhead lines and substations, appearing during one or several consequent severe meteorological events and continuing for several days. They affect several big cities within one province and stretch over an area of less than 100 thousand km2. For super large area outage accident, we refer to the accidents stretching across several provinces over the area of 200–300 thousand km2 and resulting in hundreds of pollution flashover events. [ABSTRACT FROM AUTHOR]

Indoor pedestrian positioning has been widely used in applications such as fire rescue and indoor navigation. Compared with other indoor positioning technologies such as Wi-Fi and UWB, inertial measurement unit (IMU) based indoor positioning does not require external facilities and has lower cost. However, the major issue of IMU-based indoor positioning is that the inertial sensors exhibit errors and the errors accumulates, which affects the positioning precision. Existing IMU-based indoor positioning techniques have reduced the accumulated error, but still face several issues in positioning precision and system cost. In this paper, we propose a new IMU-based indoor pedestrian positioning technique. It adopts motion speed based adaptive error compensation and step detection based up/downstairs tracking to improve the positioning precision without using additional sensors. Compared with the existing techniques, the proposed technique achieves higher positioning precision (down to 0.11% for the closed error, 0.15% for the distance error and 0.52% for the height error) with less number of sensors (only accelerator and gyroscope) to lower the cost. [ABSTRACT FROM AUTHOR]

This article investigates the relationship between the tracking performance and coupling effect for attitude tracking issue of hypersonic reentry vehicle (HRV), and proposes a performance-involved coupling effect-triggered robust control scheme. The main feature of the article lies in that the influence of the coupling effect on the performance is discussed via a defined performance-involved coupling effect indicator. Consequently, the proposed control ensures the transient performance within the prescribed limitation in all phases, and the better transient performance is achieved with the help of the sliding mode control and disturbance observer technique enhancing the robustness. Comparison simulations and Monte Carlo tests under coefficients perturbation on the HRV system demonstrate the effectiveness of the proposed control strategy. [ABSTRACT FROM AUTHOR]

The irreversible electroporation with microsecond electric pulses is a new ablation technique adopted in the tumor therapy worldwide. On the other hand, the nsPEF (nanosecond pulsed electric field) has been proved to provide a means to induce immunogenic cell death and elicits antitumor immunity, which is under intensive in-vitro and in-vivo studies and in clinical trials. Normally, one needs two different types of electric pulse generators for producing the pulses in the ranges of nanosecond and microsecond, respectively. In order to realize these two types of tumor treatments in complementary and optimize electrical pulse parameters, we have developed a compact high-voltage pulse generator with a wide pulse width tuning range, based on a capacitor discharging configuration digitally controlled by a silicon carbide MOSFET switching array through a pair of optic-coupler drivers. The developed digital pulse generator is capable of adjusting: pulse width over 100–100 μs, voltage over 0–2 kV and repetition rate up to 1.2 kHz. The pulse generator is designed in simulation, implemented and verified in experiments. The pulse generator is shown to deliver a complementary treatment on Murine melanoma B16 cell lines, i.e., triggering the cell early apoptosis under the 300 ns pulse stimulation while a complete killing under the 100 ns pulses. The pulse generator is further demonstrated to induce antitumor immunity in a preliminary in vivo study on the mice model. [ABSTRACT FROM AUTHOR]