Search

Wireless sensor networks (WSNs), integral components underpinning the infrastructure of the internet of things (IoT), confront escalating threats originating from attempts at malicious jamming. Nevertheless, the limited nature of the hardware resources in distributed, low-cost WSNs, such as those for computing power and storage, poses a challenge when implementing complex and intelligent anti-jamming algorithms like deep reinforcement learning (DRL). Hence, in this paper a rapid anti-jamming method is proposed based on imitation learning in order to address this issue. First, on-network nodes obtain expert anti-jamming trajectories using heuristic algorithms, taking historical experiences into account. Second, an RNN neural network that can be used for anti-jamming decision making is trained by mimicking these expert trajectories. Finally, the late-access network nodes receive anti-jamming network parameters from the existing nodes, allowing them to obtain a policy network directly applicable to anti-jamming decision making and thus avoiding redundant learning. Experimental results demonstrate that, compared with traditional Q-learning and random frequency-hopping (RFH) algorithms, the imitation learning-based algorithm empowers late-access network nodes to swiftly acquire anti-jamming strategies that perform on par with expert strategies.

In this paper, in order to solve the problem of wireless sensor networks’ reliable transmission in intelligent malicious jamming, we propose a Distributed Anti-Jamming Algorithm (DAJA) based on an actor–critic algorithm for a multi-agent system. The Multi-Agent Markov Decision Process (MAMPD) is introduced to model the progress of wireless sensor networks’ anti-jamming communication, and the multi-agent system learns the intelligent jamming from the external environment by using an actor–critic algorithm. On the basis of coping with the influence of external and internal factors effectively, each sensor in networks selects the appropriate channels for transmission and finally realizes the optimal transmission of the system overall in a unit time period. In the environment of probabilistic intelligent jamming with tracking properties set in this paper, the simulation shows that the algorithm proposed can outperform the algorithm based on joint Q-learning and the conventional scheme based on orthogonal frequency hopping in terms of transmission. In addition, the proposed algorithm completes two updates of strategy evaluation and action selection in one iteration, which means that the system has higher efficiency of action selection and better adaptability to the environment through the interaction with the external environment, resulting in the better performance of transmission and convergence.

A rapid and nondestructive method is greatly important for the classification of aflatoxin B1 (AFB1) concentration of single maize kernel to satisfy the ever-growing needs of consumers for food safety. A novel method for classification of AFB1 concentration of single maize kernel was developed on the basis of the near-infrared (NIR) hyperspectral imaging (1100–2000 nm). Four groups of AFB1 samples with different concentrations (10, 20, 50, and 100 ppb) and one group of control samples were prepared, which were preprocessed with Savitzky–Golay (SG) smoothing and first derivative (FD) algorithms for their raw NIR spectra. A key wavelength selection method, combining the variance and order of average spectral intensity, was proposed on the basis of pretreated spectra. Moreover, principal component analysis (PCA) was conducted to reduce the dimensionality of hyperspectral data. Finally, a classification model for AFB1 concentrations was developed through linear discriminant analysis (LDA), combined with five key wavelengths and the first three PCs. The results show that the proposed method achieved an ideal performance for classifying AFB1 concentrations in a single maize kernel with overall accuracy, with an F1-score and Kappa values of 95.56%, 0.9554, and 0.9444, respectively, as well as the test accuracy yield of 88.67% for independent validation samples. The combinations of variance and order of average spectral intensity can be used for key wavelength selection which, combined with PCA, can achieve an ideal dimensionality reduction effect for model development. The findings of this study have positive significance for the classification of AFB1 concentration of maize kernels.

In many medical image classification tasks, there is insufficient image data for deep convolutional neural networks (CNNs) to overcome the over-fitting problem. The light-weighted CNNs are easy to train but they usually have relatively poor classification performance. To improve the classification ability of light-weighted CNN models, we have proposed a novel batch similarity-based triplet loss to guide the CNNs to learn the weights. The proposed loss utilizes the similarity among multiple samples in the input batches to evaluate the distribution of training data. Reducing the proposed loss can increase the similarity among images of the same category and reduce the similarity among images of different categories. Besides this, it can be easily assembled into regular CNNs. To appreciate the performance of the proposed loss, some experiments have been done on chest X-ray images and skin rash images to compare it with several losses based on such popular light-weighted CNN models as EfficientNet, MobileNet, ShuffleNet and PeleeNet. The results demonstrate the applicability and effectiveness of our method in terms of classification accuracy, sensitivity and specificity.

This paper proposed a local active control method for the reduction of road noise inside a vehicle cabin. A multichannel simplified hybrid active noise control (sHANC) system was first developed and applied to the rear left seat of a large sport utility vehicle (SUV). The attenuation capability of the sHANC system was investigated through simulations, using reference signals provided by accelerometers on the suspensions and bodywork of the vehicle and microphones on the floor of cabin, respectively. It was shown that compared to the traditional feedforward system, the sHANC system using either vibrational or acoustical reference signals can produce a significant suppression of the narrowband peak noise between 75 and 80 Hz, but the system lost the control capability in a range of 100–500 Hz when the acoustic signals were used as references. To reduce the practical implementation costs while maintaining excellent reduction performance, a modified simplified hybrid ANC (msHANC) system was further proposed, in which combined vibrational and acoustical signals were used as reference signals. The off-line analyses showed that four reference accelerometers can be substituted by ten microphones without compromising attenuation performance, with 3.7 dBA overall noise reduction being achieved. The effect of delays on the reduction performance of msHANC system was also investigated. The result showed that the msHANC system was more sensitive to the delays compared to the sHANC system if using only vibrational reference signals.

Image deblurring has been a challenging ill-posed problem in computer vision. Gaussian blur is a common model for image and signal degradation. The deep learning-based deblurring methods have attracted much attention due to their advantages over the traditional methods relying on hand-designed features. However, the existing deep learning-based deblurring techniques still cannot perform well in restoring the fine details and reconstructing the sharp edges. To address this issue, we have designed an effective end-to-end deep learning-based non-blind image deblurring algorithm. In the proposed method, a multi-stream bottom-top-bottom attention network (MBANet) with the encoder-to-decoder structure is designed to integrate low-level cues and high-level semantic information, which can facilitate extracting image features more effectively and improve the computational efficiency of the network. Moreover, the MBANet adopts a coarse-to-fine multi-scale strategy to process the input images to improve image deblurring performance. Furthermore, the global information-based fusion and reconstruction network is proposed to fuse multi-scale output maps to improve the global spatial information and recurrently refine the output deblurred image. The experiments were done on the public GoPro dataset and the realistic and dynamic scenes (REDS) dataset to evaluate the effectiveness and robustness of the proposed method. The experimental results show that the proposed method generally outperforms some traditional deburring methods and deep learning-based state-of-the-art deblurring methods such as scale-recurrent network (SRN) and denoising prior driven deep neural network (DPDNN) in terms of such quantitative indexes as peak signal-to-noise ratio (PSNR) and structural similarity (SSIM) and human vision.

The adsorption types of ten kinds of gas molecules (O2, NH3, SO2, CH4, NO, H2S, H2, CO, CO2, and NO2) on the surface of SiSe monolayer are analyzed by the density-functional theory (DFT) calculation based on adsorption energy, charge density difference (CDD), electron localization function (ELF), and band structure. It shows high selective adsorption on SiSe monolayer that some gas molecules like SO2, NO, and NO2 are chemically adsorbed, while the NH3 molecule is physically adsorbed, the rest of the molecules are weakly adsorbed. Moreover, stress is applied to the SiSe monolayer to improve the adsorption strength of NH3. It has a tendency of increment with the increase of compressive stress. The strongest physical adsorption energy (−0.426 eV) is obtained when 2% compressive stress is added to the substrate in zigzag direction. The simple desorption is realized by decreasing the stress. Furthermore, based on the similar adsorption energy between SO2 and NH3 molecules, the co-adsorption of these two gases are studied. The results show that SO2 will promote the detection of NH3 in the case of SO2-NH3/SiSe configuration. Therefore, SiSe monolayer is a good candidate for NH3 sensing with strain engineering.

Currently, in the modern power industry, it is still a great challenge to achieve high sensitivity and uninterrupted-online measurement of large current on the high voltage gridlines. At present, the fiber grating current sensors based on giant magnetostrictive material used in the modern power industry to achieve uninterrupted-online measurement of large currents on high voltage grid lines is a better method, but the sensitivity of this current sensor is relatively low, therefore, it is key to improve the sensitivity of this current sensor. Here we show a sensitivity-enhanced fiber grating current sensor based on giant magnetostrictive material (in the following, simply referred to as the sensitivity-enhanced fiber grating current sensor) that is able to achieve high sensitivity and uninterrupted-online measurement of large currents by means of pressurizing the giant magnetostrictive material. Sampling the power frequency sinusoidal alternating current signals with the amplitudes of 107, 157 and 262 A respectively, based on realistic factors, for the sensitivity-enhanced current sensor, the sensitivities, compared with that of the traditional fiber grating current sensor based on giant magnetostrictive material (in the following, simply referred to as the traditional fiber grating current sensor), were respectively enhanced by 268.96%, 135.72% and 71.57%. Thus the sensitivity-enhanced fiber grating current sensor allows us to solve the issue of high sensitivity and uninterrupted-online measurement of large currents that have been plaguing the power industry in a very simple and low-cost way.

Human action recognition is an increasingly important research topic in the fields of video sensing, analysis and understanding. Caused by unconstrained sensing conditions, there exist large intra-class variations and inter-class ambiguities in realistic videos, which hinder the improvement of recognition performance for recent vision-based action recognition systems. In this paper, we propose a generalized pyramid matching kernel (GPMK) for recognizing human actions in realistic videos, based on a multi-channel “bag of words” representation constructed from local spatial-temporal features of video clips. As an extension to the spatial-temporal pyramid matching (STPM) kernel, the GPMK leverages heterogeneous visual cues in multiple feature descriptor types and spatial-temporal grid granularity levels, to build a valid similarity metric between two video clips for kernel-based classification. Instead of the predefined and fixed weights used in STPM, we present a simple, yet effective, method to compute adaptive channel weights of GPMK based on the kernel target alignment from training data. It incorporates prior knowledge and the data-driven information of different channels in a principled way. The experimental results on three challenging video datasets (i.e., Hollywood2, Youtube and HMDB51) validate the superiority of our GPMK w.r.t. the traditional STPM kernel for realistic human action recognition and outperform the state-of-the-art results in the literature.

Indoor space subdivision is an important aspect of scene analysis that provides essential information for many applications, such as indoor navigation and evacuation route planning. Until now, most proposed scene understanding algorithms have been based on whole point clouds, which has led to complicated operations, high computational loads and low processing speed. This paper presents novel methods to efficiently extract the location of openings (e.g., doors and windows) and to subdivide space by analyzing scanlines. An opening detection method is demonstrated that analyses the local geometric regularity in scanlines to refine the extracted opening. Moreover, a space subdivision method based on the extracted openings and the scanning system trajectory is described. Finally, the opening detection and space subdivision results are saved as point cloud labels which will be used for further investigations. The method has been tested on a real dataset collected by ZEB-REVO. The experimental results validate the completeness and correctness of the proposed method for different indoor environment and scanning paths.

Direction of arrival (DOA) estimation using a uniform linear array (ULA) is a classical problem in array signal processing. In this paper, we focus on DOA estimation based on the maximum likelihood (ML) criterion, transform the estimation problem into a novel formulation, named as sum-of-squares (SOS), and then solve it using semidefinite programming (SDP). We first derive the SOS and SDP method for DOA estimation in the scenario of a single source and then extend it under the framework of alternating projection for multiple DOA estimation. The simulations demonstrate that the SOS- and SDP-based algorithms can provide stable and accurate DOA estimation when the number of snapshots is small and the signal-to-noise ratio (SNR) is low. Moveover, it has a higher spatial resolution compared to existing methods based on the ML criterion.

With the increasing demands for better transmission speed and robust quality of service (QoS), the capacity constrained backhaul gradually becomes a bottleneck in cooperative wireless networks, e.g., in the Internet of Things (IoT) scenario in joint processing mode of LTE-Advanced Pro. This paper focuses on resource allocation within capacity constrained backhaul in uplink cooperative wireless networks, where two base stations (BSs) equipped with single antennae serve multiple single-antennae users via multi-carrier transmission mode. In this work, we propose a novel cooperative transmission scheme based on compress-and-forward with user pairing to solve the joint mixed integer programming problem. To maximize the system capacity under the limited backhaul, we formulate the joint optimization problem of user sorting, subcarrier mapping and backhaul resource sharing among different pairs (subcarriers for users). A novel robust and efficient centralized algorithm based on alternating optimization strategy and perfect mapping is proposed. Simulations show that our novel method can improve the system capacity significantly under the constraint of the backhaul resource compared with the blind alternatives.