Search

A novel hybrid network was synthesized in two steps: the first step involved the attachment of glycidyl methacrylate (GMA) to octa(aminophenyl) silsesquioxane (OAPS) through a ring‐opening reaction, forming a hybrid dendrimer structure, and the second step involved the cross‐linking of hybrid dendrimer using an azobisisobutyronitrile initiator to create the final hybrid network of OAPS‐GMA. The synthesized hybrid material was comprehensively characterized using fourier transform infrared Spectroscopy (FTIR), nuclear magnetic resonance ((1H, 13C, and 29Si NMR) spectroscopy, thermogravimetric Analysis (TGA), and scanning electron microscopy (SEM). The BET surface area was found to be 25.44 m2/g, and significant 2.341 cm3/g of total pore volume was observed. The TGA analysis shows that the material is highly stable up to 450 °C. The synthesized network demonstrated remarkable adsorption capacities for iodine and dyes. It exhibited an iodine adsorption capacity of 3.4 g/g from vapors and 874 mg/g from solution. Additionally, it showed significant adsorption capacities for Rhodamine B and Congo red, with values of 762 mg/g and 517 mg/g, respectively. This study not only provides a novel method for preparing GMA‐functionalized silsesquioxane‐based porous hybrid polymers but also contributes to advancing solutions for environmental pollution issues. [ABSTRACT FROM AUTHOR]

Industrial safety applications using wireless sensor networks (WSN) require fast transmission of still images to identify urgent situation in the target field. However, it is quite challenging to transmit a large number of image packets reliably and quickly through wireless multihop. Thus, the current approaches employ slot scheduling and pipelined transmission, but suffer from many control messages. The proposed protocol exploits LoRa networks for reliable and fast image transmission on WSNs so that it can remove most of control messages related to topology management, slot scheduling, time synchronization, and retransmission. According to experimental results, the proposed protocol improves image transmission delay by 25% compared to the recent pipelined protocol by transmitting one image of 100 × 80 pixels in about 0.3 seconds, and also achieves an image transfer rate of 100% under 1 image packet loss tolerance at an 8-hop distance. [ABSTRACT FROM AUTHOR]

Skin cancer is a significant public health issue, making accurate and early diagnosis crucial. This study proposes a novel and efficient hybrid deep‐learning model for accurate skin cancer diagnosis. The model first employs DeepLabV3+ for precise segmentation of skin lesions in dermoscopic images. Feature extraction is then carried out using three pretrained models: MobileNetV2, EfficientNetB0, and DenseNet201 to ensure balanced performance and robust feature learning. These extracted features are then concatenated, and the ReliefF algorithm is employed to select the most relevant features. Finally, obtained features are classified into eight categories: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma, melanoma, melanocytic nevus, squamous cell carcinoma, and vascular lesion using the kNN algorithm. The proposed model achieves an F1 score of 93.49% and an accuracy of 94.42% on the ISIC‐2019 dataset, surpassing the best individual model, EfficientNetB0, by 1.20%. Furthermore, the evaluation of the PH2 dataset yielded an F1 score of 94.43% and an accuracy of 94.44%, confirming its generalizability. These findings signify the potential of the proposed model as an expedient, accurate, and valuable tool for early skin cancer detection. They also indicate combining different CNN models achieves superior results over the results obtained from individual models. [ABSTRACT FROM AUTHOR]

Integrating RGB and Event (RGBE) multi-domain information obtained by high-dynamic-range and temporal-resolution event cameras has been considered an effective scheme for robust object tracking. However, existing RGBE tracking methods have overlooked the unique spatio-temporal features over different domains, leading to object tracking failure and ineffeciency, especally for objects against complex backgrounds. To address this problem, we propose a novel tracker based on adaptive-time feature extraction hybrid networks, namely Siamese Event Frame Tracker (SiamEFT), which focuses on the effective representation and utilization of the diverse spatio-temporal features of RGBE. We first design an adaptive-time attention module to aggregate event data into frames based on adaptive-time weights to enhance information representation. Subsequently, the SiamEF module and cross-network fusion module combining artificial neural networks and spiking neural networks hybrid network are designed to effectively extract and fuse the spatio-temporal features of RGBE. Extensive experiments on two RGBE datasets (VisEvent and COESOT) show that the SiamEFT achieves a success rate of 0.456 and 0.574, outperforming the state-of-the-art competing methods and exhibiting a 2.3-fold enhancement in effeciency. These results validate the superior accuracy and effeciency of SiamEFT in diverse and challenging scenes. [ABSTRACT FROM AUTHOR]

In recent years, EEG-based emotion recognition technology has made progress, but there are still problems of low model efficiency and loss of emotional information, and there is still room for improvement in recognition accuracy. To fully utilize EEG's emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification and 97.69% and 98.05% in ternary classification, and on the SEED dataset, we achieved an accuracy of 98.63%, surpassing relevant algorithms. Additionally, the model's efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption. [ABSTRACT FROM AUTHOR]

The estimation of 3D interacting hand pose from a single RGB image is a challenging problem. The hands tend to occlude each other and are self-similar in two-handed interactions. In this study, a simple, accurate end-to-end framework called HybridPoseNet is proposed for estimating 3D interactive hand pose. The hybrid network employs an encoder-decoder architecture. More specifically, the feature encoder is a hybrid structure that combines a convolutional neural network (CNN) with a transformer to accomplish the feature encoding of hand information. An ordinary CNN is employed to extract the local detailed features of a given image, and a vision transformer is used to capture the long-distance spatial interactions between the cross-positional feature vectors. Moreover, the 3D pose decoder is based on left and right network branches, which are fused via a feature enhancement module (FEM). The FEM helps reduce the ambiguity in appearance caused by the self-similarity of the hands. The decoder elevates the 2D pose to the 3D pose by estimating two depth components. The ablation experiments demonstrate the effectiveness of each module in the network. In addition, comprehensive experiments on the InterHand2.6M dataset show that the proposed method outperforms previous state-of-the-art methods for estimating interactive hand pose. [ABSTRACT FROM AUTHOR]

Streamflow time series data typically exhibit nonlinear and nonstationary characteristics that complicate precise estimation. Recently, multifactorial machine learning (ML) models have been developed to enhance the performance of streamflow predictions. However, the lack of interpretability within these ML models raises concerns about their inner workings and reliability. This paper introduces an innovative hybrid architecture, the TCN-LSTM-Multihead-Attention model, which combines two layers of temporal convolutional networks (TCN) followed by one layer of long short-term memory (LSTM) units, integrated with a Multihead-Attention mechanism for predicting streamflow with streamflow causation–driven prediction samples (RCDP), employing local and global interpretability studies through Shapley values and partial dependency analysis. The find_peaks method was used to identify peak flow events in the test dataset, validating the model's generality and uncovering the physical causative patterns of streamflow. The results show that (1) compared to the LSTM model with the same hyperparameter settings, the proposed TCN-LSTM-Multihead-Attention hybrid model increased the R2 by 52.9%, 2.5%, 43.1%, and 10.7% respectively at four stations in the test set predictions using RCDP samples. Moreover, comparing the prediction results of the hybrid model under different samples in Hengshan station, the R2 for RCDP increased by 5.06% and 1.22% compared to streamflow autoregressive prediction samples (RAP) and meteorological-soil volumetric water content coupled autoregressive prediction samples (MCSAP) respectively. (2) Historical streamflow data from the preceding 3 days predominantly influences predictions due to strong autocorrelation, with flow quantity (Q) typically emerging as the most significant feature alongside precipitation (P), surface soil moisture (SSM), and adjacent station flow data. (3) During periods of low and normal flow, historical data remains the most crucial factor; however, during flood periods, the roles of upstream inflow and precipitation become significantly more pronounced. This model facilitates the identification and quantification of various hydrodynamic impacts on flow predictions, including upstream flood propagation, precipitation, and soil moisture conditions. It also elucidates the model's nonlinear relationships and threshold responses, thereby enhancing the interpretability and reliability of streamflow predictions. [ABSTRACT FROM AUTHOR]

A variable threshold voltage hybrid evaluation network based dynamic XOR/XNOR gate is presented to reduce the parameters leakage power dissipation, dynamic power, and layout area compared to existing dynamic gates under similar delay time conditions. This study explores the impacts of process, supply voltage, and temperature changes on leakage power dissipation and dynamic power using Monte Carlo simulation. The Monte Carlo analysis demonstrates that leakage power dissipation and dynamic power reduction have significantly improved. Furthermore, when compared to hybrid type dynamic XOR/XNOR (N-type XOR/XNOR), the proposed design reduces leakage power and dynamic power consumption by 6.1% (54.0%) and 18.75% (35.0%), respectively. While the proposed design has a slight layout area penalty compared to a hybrid type dynamic XOR/XNOR, it offers the same amount of the layout area as a traditional N-type XOR/XNOR. [ABSTRACT FROM AUTHOR]

BACKGROUND: The accurate classification of pulmonary nodules has great application value in assisting doctors in diagnosing conditions and meeting clinical needs. However, the complexity and heterogeneity of pulmonary nodules make it difficult to extract valuable characteristics of pulmonary nodules, so it is still challenging to achieve high-accuracy classification of pulmonary nodules. OBJECTIVE: In this paper, we propose a local-global hybrid network (LGHNet) to jointly model local and global information to improve the classification ability of benign and malignant pulmonary nodules. METHODS: First, we introduce the multi-scale local (MSL) block, which splits the input tensor into multiple channel groups, utilizing dilated convolutions with different dilation rates and efficient channel attention to extract fine-grained local information at different scales. Secondly, we design the hybrid attention (HA) block to capture long-range dependencies in spatial and channel dimensions to enhance the representation of global features. RESULTS: Experiments are carried out on the publicly available LIDC-IDRI and LUNGx datasets, and the accuracy, sensitivity, precision, specificity, and area under the curve (AUC) of the LIDC-IDRI dataset are 94.42%, 94.25%, 93.05%, 92.87%, and 97.26%, respectively. The AUC on the LUNGx dataset was 79.26%. CONCLUSION: The above classification results are superior to the state-of-the-art methods, indicating that the network has better classification performance and generalization ability. [ABSTRACT FROM AUTHOR]

Accurate prediction of the remaining useful life for the cutting tool is a key part of the predictive maintenance of computer numerical control machines. However, the wide variety of tools makes the process of modeling different tool wear regularities redundant and cumbersome. In addition, it is difficult to deal with the input characteristics of multi-sensor monitoring signals in a targeted manner. To solve the above problems, a hybrid predictive model with squeeze-and-excitation (SE) module is proposed. Combined with adaptive feature extraction based on convolutional neural network and observation based on bidirectional gated recurrent unit, accurate multivariate regression prediction is achieved. The SE module enhances the focus on crucial features. Finally, through the design of the tool wear experiment and the combination of the public dataset, the accuracy and generalization ability of the proposed model are verified under different tool types and different working conditions. [ABSTRACT FROM AUTHOR]

AbstractToday, the challenge of enhancing the strength and adhesion of the polyacrylamide hydrogel network is still a major concern in many applications. This study investigates the effect of silica nanoparticle concentration on the cross-linked polyacrylamide hydrogel’s gelation, viscoelastic, structural, and adhesion properties. The hybrid hydrogels were evaluated using DSC, XRD, SEM, and rheological analysis to determine their enthalpy of cross-linking, crystallinity, morphology, and elastic properties. The results of kinetic analysis confirmed the catalytic effect of silica nanoparticles on the gelation kinetics. A deviation from the elastic behavior of the unfilled hydrogel was found from the rheological studies. Using the Weibull Model to describe the creep test results showed a significant increase in retardation time with increasing silica nanoparticles content up to the percolation threshold of 0.24 wt.%. This confirmed the development of a more viscous behavior due to the formation of a physical network of nano-silica particles. Based on the DSC energy of hydrogels, both chemical and physical tie points (approximately 19 covalent crosslinking points) were calculated. The hydrogel containing 9 wt.% of silica nanoparticles demonstrated significant improvement in density, and adhesion to the metal surface by about 100% and 350%, respectively. As a result of this study, the hydrogel containing 9 wt% of silica nanoparticles (H9) is suggested for various field studies, such as oil well plugging industries. [ABSTRACT FROM AUTHOR]

Video semantic segmentation (VSS) plays a crucial role in various realistic applications, such as unmanned vehicles, autonomous robots, and augmented reality. Despite the significant progress achieved in this field, balancing accuracy and efficiency remains a significant challenge. This paper presents a novel dual-branch hybrid network of CNN and Transformer with adaptive keyframe scheduling (DHN–AKS) to achieve higher accuracy and faster inference times for VSS. One branch N e t T uses a hierarchical transformer to extract high-level features on keyframes beneficial for segmentation accuracy in consideration of transformer’s powerful ability of modeling global semantic information. The other branch N e t C uses a lightweight feature network (ResNet-18) to extract the low-level features on non-keyframes beneficial for segmentation efficiency. Moreover, we present a dynamically updating memory matrix that memorizes the significant semantic information of historical video frames, enabling the exploration of the temporal relevance of the current frame based on cross attention. Experiments on two benchmark data sets, Cityscapes and CamVid, demonstrate that our proposed framework achieves competitive performance in terms of accuracy and inference time against some previous state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In light of the satellite rejection environment and how aircraft can obtain high-precision positioning, this paper proposes a collaborative correction algorithm for aircraft based on the rank-defect network. Aiming at the problem of insufficient anchor points, which result in insufficient observations and the divergence of aircraft inertial navigation errors, this algorithm can effectively improve the navigation performance of cluster aircraft. On the basis of the observation information provided by the anchor aircraft, the observation information between aircraft is fully utilized to improve the observability of the aircraft cluster positioning method. At the same time, the pseudo-observation equation of heterogeneous aircraft cluster positioning is introduced, and the divergence of inertial navigation positioning errors caused by insufficient observations is suppressed by the pseudo-observation solution. On the basis of introducing the pseudo-observation equation, the inertial navigation error is solved and corrected by the Newton iterative method and the divergence of the inertial navigation position error is restrained. Compared with an aircraft cluster positioning method that does not use the inertial navigation error co-correction based on the pseudo-observation solution, this paper can achieve better overall cluster positioning accuracy when the available observations are insufficient, which is suitable for practical applications. [ABSTRACT FROM AUTHOR]

The increasing amount of massive data generated by commercial spacecraft in orbit puts forward higher and higher requirements for the stability, reliability, and computing power of computer systems for commercial aerospace data center. Data center computer systems are gradually transforming from X86 architecture and IP network model to a platform model with cloud computing and software-defined network (SDN) technology. This article proposes a new network architecture based on a unicast/multicast protocol for data interaction between the SDN and IP network. There are three main contributions of this article. The first is that the architecture proposed in this article aims to reduce end-to-end transmission latency and packet loss. The second is to improve the flexibility of system configuration and precise control when the SND controller state changes. The third is to verify the feasibility of deploying network architecture in a real data center environment.

【Objective】In recent years, data communication traffic has experienced explosive growth. To meet the demands for high-speed, high-capacity data transmission and the diverse network application scenarios, hybrid network beyond 100 Gbit/s (B100 Gbit/s) using Dense Wavelength Division Multiplexing (DWDM) has increasingly been recognized as an effective solution. This paper analyzes the requirements, key technologies, and practical case studies of such networks, providing technical support and guidance for building high-capacity and efficient communication networks.【Methods】This paper first outlines the requirements for developing B100 Gbit/s DWDM hybrid networks, including network capacity expansion and support for complex network architectures. Next, it details the key technologies for these networks, including constellation shaping, spectrum shaping, and flexible grid technologies. To support bitrate design in hybrid networking, a method for calculating Optical Signal-to-Noise Ratio (OSNR) in cascaded Erbium-Doped Fiber Amplifier (EDFA) communication systems is presented, using parameters such as channel configuration information, transmitted signal optical power, and EDFA gain and noise parameters, to calculate the output OSNR for each wavelength across the link. Finally, by integrating a foreign network case study and based on actual OSNR evaluation, a rational hybrid rate network design is performed, demonstrating the application effectiveness of B100 Gbit/s DWDM hybrid networking in engineering projects.【Results】Implementing B100 Gbit/s DWDM hybrid network, after flexibly configuring transmission rates and bandwidths based on OSNR evaluations, achieves hybrid rate networks deployment at 200, 600 and 800 Gbit/s. This approach fulfills the high-capacity requirements of core sites while accommodating the long-distance, extensive span requirements of edge sites. Furthermore, network upgrades and expansion are smoothly accomplished within a three-year period.【Conclusion】Practice demonstrates that B100 Gbit/s DWDM networking effectively enhances network capacity, flexibility, and spectrum resource utilization. It also provides room for the continuous network evolution, playing a crucial role in advancing the development of high-capacity optical transmission networks.

Ultrasound images are often affected by limited resolution, artifacts, and inherent speckle noise. To address these challenges, researchers have explored denoising approaches. Recently, deep learning methods have demonstrated distinct advantages in ultrasound image denoising. However, further improvements are needed to preserve structural details, such as boundaries, edges, and margins. This paper proposes a hybrid CNN-transformer network called HCTSpeckle, an encoder-decoder network with a fusion block designed to enhance ultrasound images. The fusion block combines swin transformers to capture global modeling relationships, and convolutional neural networks to extract local modeling details. It is integrated into the encoder-decoder structure, allowing the model to focus on both local and global texture structural information. An improved swin block is also introduced into the network to improve robustness by extracting more significant features. HCTSpeckle was evaluated both quantitatively and qualitatively with clinical objectives using two public and two private datasets. Both results showed that HCTSpeckle significantly enhanced the ultrasound image quality and outperformed state-of-the-art methods in noise reduction and structure preservation across all four datasets. Compared to existing denoising methods, HCTSpeckle achieved notably faster performance in terms of complexity comparison, such as parameter counts, gigaFLOPs, and inference time. Moreover, this study assessed the effectiveness of HCTSpeckle for alveolar bone segmentation using dental images, demonstrating that HCTSpeckle significantly improved segmentation performance. Furthermore, an experienced radiologist blindly rated the 250 dental US images on a scale of 1 to 5, with 5 being the highest image quality, showing that HCTSpeckle consistently produced higher-quality images.

The hybrid LiFi/WiFi communication networks have demonstrated their efficacy and advantages in terms of data transmission rates. Multiple difficulties were identified in these networks, including the access point assignment (APA) and the process of handover (HO). These troubles (criteria) are influenced by multiple elements, including optical gain at the recipient, mobility, distance, blockage, shadowing, and other variables. It is crucial to evaluate multiple criteria when making-decisions in order to attain more precise results. However, as far, limited studies employing the multicriteria decision-making (MCDM) technique for a hybrid LiFi/WiFi network has been discovered. Nevertheless, although the MCDM technique is highly accurate, it involves long process to achieve the optimal access point (AP). This results in heightened complexity of the system, leading to longer AP transfer times and higher HO rates. In order to address the aforementioned constraints, this paper introduces a novel approach termed as card-flipping decision making (CFDM). CFDM enables swift and precise decision-making while minimizing computational complexity. Additionally, it incorporates HO rates that involve bypassing HOs and selecting the most optimal AP. The analytic hierarchy process (AHP) is adopted to estimate the subjective weights of each criterion and establish their level of priority. The proposed method provided in this study is combined with the AHP, referred to as the merged AHP-CFDM. This integration is considered a new MCDM technique. The proposed method consists of an algorithm that performs i) criteria segmentation based on criteria values, ii) criteria sortation based on AHP results, and iii) criteria grouping based on network type. The classification of criteria is also taken into account including cost and benefit criteria. The proposed algorithm treats each criterion as a card, and each card is flipped (computed) when necessary. The outcome of the AHP-CFDM decisions are SKIP, FLIP, and ASSIGN. The proposed AHP-CFDM is a new MCDM technique and can be utilized in other networks and/or applications for decision-making. The investigation demonstrates improvements in total system efficiency in terms of computational complexity and HO rates when compared to both standard approaches and benchmark techniques. The simulation results demonstrate that the proposed strategy outperforms other methods significantly when compared to the most relevant studies.

Remote sensing image change detection (RSCD) based on deep learning technology has made remarkable achievements. Meanwhile, the enhancement of network architectures and advancements in optimization algorithms have pushed RSCD performance to a higher stage. However, the existing RSCD methods mainly focus on extracting differential information between pixel pairs from bitemporal images, while neglecting the importance of using complementary multiscale features to uncover hierarchical semantic change information. To address these issues, we propose a multiscale feature interaction hybrid network (MFIHNet), which aims to enhance feature discriminability by multiscale features interaction and fusion to enhance model RSCD performance. Specifically, we first design a cascaded convolutional neural networks (CNN)-Transformer feature extraction network to capture hierarchical features at different scales. This strategy enables the network to preserve detailed information in shallow layers while grasping more contextual information in high layers. Subsequently, based on the differences between hierarchical features, we design a novel edge enhancement module (EM) to adaptively focus on key areas under the guidance of edge information to make the changed information clearer. Furthermore, to ensure complementary advantages among different feature layers, we devise a novel cross-scale feature interaction module, which introduces a region-specific atrous convolution into the multiscale attention mechanism for improving feature coassistance capacity. In this way, the MFIHNet not only effectively obtains different types of fine-grained information but also reduces the loss incurred during the feature fusion process, thereby improving the performance of remote sensing RSCD tasks. Extensive experimental results on the challenging CDD and GZ-CD datasets, with mean F1 scores reaching 98.1% and 87.4%, respectively, demonstrate that the proposed method achieves competitive performance. Our source codes are available at https://github.com/qliu520/MFIHNet.

This study proposes a hybrid network model based on data enhancement to address the problem of low accuracy in photovoltaic (PV) power prediction that arises due to insufficient data samples for new PV plants. First, a time-series generative adversarial network (TimeGAN) is used to learn the distribution law of the original PV data samples and the temporal correlations between their features, and these are then used to generate new samples to enhance the training set. Subsequently, a hybrid network model that fuses bi-directional long-short term memory (BiLSTM) network with attention mechanism (AM) in the framework of deep & cross network (DCN) is constructed to effectively extract deep information from the original features while enhancing the impact of important information on the prediction results. Finally, the hyperparameters in the hybrid network model are optimized using the whale optimization algorithm (WOA), which prevents the network model from falling into a local optimum and gives the best prediction results. The simulation results show that after data enhancement by TimeGAN, the hybrid prediction model proposed in this paper can effectively improve the accuracy of short-term PV power prediction and has wide applicability.

Due to the remarkable ability to capture both spatial and angular information of the scene, light field imaging provides abundant cues and information. Over the last decade, various forms of data, such as the focal stack, all-in-focus image, depth map, sub-aperture image, center-view image, and micro-lens image array, have been exploited by different methods of light field salient object detection (SOD). In this study, we introduce a novel 3D–2D convolution hybrid network called HFSNet, which utilizes the focal stack as the only input to achieve SOD. The encoder network is constructed based on 3D convolution to extract and preserve the continuously changing focus cues within the focal stack. In order to reduce the computational burden of 3D convolution, we incorporate 3D max-pooling layers, channel reduction modules, and focal stack feature fusing modules to reduce the data dimension. The decoder network, on the other hand, is built on 2D convolution to generate coarse saliency maps, which are then refined using the refine module to obtain the final saliency map. We conduct experiments on five benchmark light field SOD datasets, and the results demonstrate that our method outperforms other models on DUTLF-V2 and DUTLF-FS, and achieves competitive outcomes on Lytro Illum, HFUT-Lytro, and LFSD. [ABSTRACT FROM AUTHOR]

Vision transformers (ViTs) are increasingly utilized for HSI classification due to their outstanding performance. However, ViTs encounter challenges in capturing global dependencies among objects of varying sizes, and fail to effectively exploit the spatial–spectral information inherent in HSI. In response to this limitation, we propose a novel solution: the multi-scale spatial–spectral transformer (MSST). Within the MSST framework, we introduce a spatial–spectral token generator (SSTG) and a token fusion self-attention (TFSA) module. Serving as the feature extractor for the MSST, the SSTG incorporates a dual-branch multi-dimensional convolutional structure, enabling the extraction of semantic characteristics that encompass spatial–spectral information from HSI and subsequently tokenizing them. TFSA is a multi-head attention module with the ability to encode attention to features across various scales. We integrated TFSA with cross-covariance attention (CCA) to construct the transformer encoder (TE) for the MSST. Utilizing this TE to perform attention modeling on tokens derived from the SSTG, the network effectively simulates global dependencies among multi-scale features in the data, concurrently making optimal use of spatial–spectral information in HSI. Finally, the output of the TE is fed into a linear mapping layer to obtain the classification results. Experiments conducted on three popular public datasets demonstrate that the MSST method achieved higher classification accuracy compared to state-of-the-art (SOTA) methods. [ABSTRACT FROM AUTHOR]

Copyright of Information & Control is the property of Gai Kan Bian Wei Hui and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Accurate estimating the state of health (SOH) of lithium-ion battery plays a significant role in the safe operation of electric vehicles. With the development of deep learning, neural network-based methods have attracted much attention from researchers. While most of the existing SOH estimation methods are built by a single network, failing to sufficiently extract data information, and thus leading to the limited accuracy and generality (i.e., such a single network makes it difficult to estimate the SOH of battery, with different types and working conditions). Towards this issue, a novel hybrid network, called HFCM (Hierarchical Feature Coupled Module)-LSTM (Long–short-term memory), is designed to fully extract the original data information, making it more accurate to estimate the SOH of battery, with different types and working conditions. Specifically, the proposed HFCM-LSTM mainly consists of two components, HCFM and LSTM. The HCFM is proposed to comprehensively extract the original data feature information from the original samples. On the other hand, following the HFCM, a LSTM module is employed to model time series information. Based on this HFCM-LSTM network, the data obtained directly from the battery are fed into the model as input, enabling an end-to-end SOH estimation of the battery. A series of experiments are conducted on both NASA dataset and Oxford dataset, the experimental results demonstrate that the proposed SOH estimation algorithm outperforms several existing state-of-the-art methods, in terms of accuracy and generality.

In recent years, EEG-based emotion recognition technology has made progress, but there are still problems of low model efficiency and loss of emotional information, and there is still room for improvement in recognition accuracy. To fully utilize EEG’s emotional information and improve recognition accuracy while reducing computational costs, this paper proposes a Convolutional-Recurrent Hybrid Network with a dual-stream adaptive approach and an attention mechanism (CSA-SA-CRTNN). Firstly, the model utilizes a CSAM module to assign corresponding weights to EEG channels. Then, an adaptive dual-stream convolutional-recurrent network (SA-CRNN and MHSA-CRNN) is applied to extract local spatial-temporal features. After that, the extracted local features are concatenated and fed into a temporal convolutional network with a multi-head self-attention mechanism (MHSA-TCN) to capture global information. Finally, the extracted EEG information is used for emotion classification. We conducted binary and ternary classification experiments on the DEAP dataset, achieving 99.26% and 99.15% accuracy for arousal and valence in binary classification and 97.69% and 98.05% in ternary classification, and on the SEED dataset, we achieved an accuracy of 98.63%, surpassing relevant algorithms. Additionally, the model’s efficiency is significantly higher than other models, achieving better accuracy with lower resource consumption.

With the progress of technology, inspection UAV clusters oriented to collaborative control are increasingly widely used in electric power inspection with the advantages of information sharing, task collaboration and multiplication of effectiveness. This paper proposes a hybrid cluster access selection algorithm for transmission line (QS) assurance of electric power business based on analyzing the differentiated needs of the electric power business. The entropy power method calculates objective weights for transmission line inspection, and the game theory is used to fuse the subjective and objective weights to determine the comprehensive weights. Secondly, the cooperative control rate is designed for the power inspection UAV cluster, and a set of cooperative control management systems for the power inspection UAV cluster is designed and implemented through detailed requirement analysis. The results show that the cooperative control of UAV cluster based on hybrid networking MAC protocol reduces the average time of path planning by 36.08s, increases the average path length by 7.30m, and reduces the average number of sampling points by 21.4% compared with RRT algorithm. The transmission line inspection UAV cluster cooperative control proposed in this paper can effectively and quickly detect faults on transmission lines and maximize the network utility function value, thus providing the optimal network access selection scheme for each power transmission.

This work is devoted to the development of epoxy-encapsulated zinc oxide-multiwalled carbon nanotubes (ZnO–MWCNT) hybrid nanostructured composites and the investigation of their thermoelectric performance in relation to the content of MWCNTs in the composite. For the preparation of nanocomposites, self-assembling Zn nanostructured networks were coated with a layer of dispersed MWCNTs and subjected to thermal oxidation. The resulting ZnO–MWCNT hybrid nanostructured networks were encapsulated in commercially available epoxy adhesive. It was found that encapsulation of ZnO–MWCNT hybrid networks in epoxy adhesive resulted in a simultaneous decrease in their electrical resistance by a factor of 20–60 and an increase in the Seebeck coefficient by a factor of 3–15, depending on the MWCNT content. As a result, the thermoelectric power factor of the epoxy-encapsulated ZnO–MWCNTs hybrid networks exceeded that of non-encapsulated networks by more than 3–4 orders of magnitude. This effect was attributed to the ZnO–epoxy interface's unique properties and to the MWCNTs' contribution. The processes underlying such a significant improvement of the properties of ZnO–MWCNT hybrid nanostructured networks after encapsulation in epoxy adhesive are discussed. In addition, a two-leg thermoelectric generator composed of epoxy-encapsulated ZnO–MWCNT hybrid nanocomposite as n-type leg and polydimethylsiloxane-encapsulated CuO–MWCNT hybrid nanocomposite as p-type leg characterized at room temperatures showed better performance at temperature difference 30 °C compared with the similar devices, thus proving the potential of the developed nanocomposites for applications in domestic waste heat conversion devices. [ABSTRACT FROM AUTHOR]

Cooperative intelligent transport systems (C-ITS) continue to be developed to enhance transportation safety and sustainability. However, the communication of vehicle-to-everything (V2X) systems is inherently open, leading to vulnerabilities that attackers can exploit. This represents a threat to all road users, as security failures can lead to privacy violations or even fatalities. Moreover, a high fatality rate is correlated with soft-mobility road users. Therefore, when developing C-ITS systems, it is important to broaden the focus beyond connected vehicles to include soft-mobility users and legacy vehicles. This work presents a new approach developed in the context of emerging hybrid networks, combining intelligent transport systems operating in 5.9 GHz (ITS-G5) and radio-mobile cellular technologies. Two protocols were implemented and evaluated to introduce security guarantees (such as privacy and integrity) in communications within the developed C-ITS hybrid environment. As a result, this work securely integrates G5-connected ITS stations and soft-mobility users through a smartphone application via cellular networks. Commercial equipment was used for this goal, including on-board and roadside units. Computational, transmission and end-to-end latency were used to assess the system's performance. Implemented protocols introduce an additional 11% end-to-end latency in hybrid communications. Moreover, workflows employing hybrid communications impose, on average, an extra 28.29 ms of end-to-end latency. The proposal shows promise, as it reaches end-to-end times below the latency requirements imposed in most C-ITS use cases. [ABSTRACT FROM AUTHOR]

In conjunction with the global concern regarding the spread of fake news on social media, there is a large flow of research to address this phenomenon. The wide growth in social media and online forums has made it easy for legitimate news to merge with comprehensive misleading news, negatively affecting people’s perceptions and misleading them. As such, this study aims to use deep learning, pre-trained models, and machine learning to predict Arabic and English fake news based on three public and available datasets: the Fake-or-Real dataset, the AraNews dataset, and the Sentimental LIAR dataset. Based on GloVe (Global Vectors) and FastText pre-trained models, A hybrid network has been proposed to improve the prediction of fake news. In this proposed network, CNN (Convolution Neural Network) was used to identify the most important features. In contrast, BiGRU (Bidirectional Gated Recurrent Unit) was used to measure the long-term dependency of sequences. Finally, multi-layer perceptron (MLP) is applied to classify the article news as fake or real. On the other hand, an Improved Random Forest Model is built based on the embedding values extracted from BERT (Bidirectional Encoder Representations from Transformers) pre-trained model and the relevant speaker-based features. These relevant features are identified by a fuzzy model based on feature selection methods. Accuracy was used as a measure of the quality of our proposed models, whereby the prediction accuracy reached 0.9935, 0.9473, and 0.7481 for the Fake-or-Real dataset, AraNews dataset, and Sentimental LAIR dataset respectively. The proposed models showed a significant improvement in the accuracy of predicting Arabic and English fake news compared to previous studies that used the same datasets.

In light of the satellite rejection environment and how aircraft can obtain high-precision positioning, this paper proposes a collaborative correction algorithm for aircraft based on the rank-defect network. Aiming at the problem of insufficient anchor points, which result in insufficient observations and the divergence of aircraft inertial navigation errors, this algorithm can effectively improve the navigation performance of cluster aircraft. On the basis of the observation information provided by the anchor aircraft, the observation information between aircraft is fully utilized to improve the observability of the aircraft cluster positioning method. At the same time, the pseudo-observation equation of heterogeneous aircraft cluster positioning is introduced, and the divergence of inertial navigation positioning errors caused by insufficient observations is suppressed by the pseudo-observation solution. On the basis of introducing the pseudo-observation equation, the inertial navigation error is solved and corrected by the Newton iterative method and the divergence of the inertial navigation position error is restrained. Compared with an aircraft cluster positioning method that does not use the inertial navigation error co-correction based on the pseudo-observation solution, this paper can achieve better overall cluster positioning accuracy when the available observations are insufficient, which is suitable for practical applications.

In the domain of network technologies, Local Area Networks (LANs) play a crucial role in enabling device connectivity and seamless communication. This research work presents a simulation study conducted using QUALNET, a robust network simulation tool, to explore the characteristics and performance of a hub-based LAN topology. Additionally, this research study explores the integration of a wireless network, reflecting diverse real-world scenarios encountered in modern network infrastructures. This research study involves a setup with a central hub connected to ten client devices via wired links, with the main server as a central node. Moreover, three client devices are incorporated into a wireless network, creating a hybrid networking environment. The proposed methodology entails extensive parameter configurations and simulated scenarios, aimed at evaluating the network's behaviour under varying conditions and loads. This research study serves as a practical guide for network simulation enthusiasts and showcases the evolving network topologies that are crucial in the current digital landscape. The proposed study underscores the importance of assessing the performance of hub-based LANs and their interplay with wireless networks, emphasizing the relevance of such studies in the context of network design and optimization. [ABSTRACT FROM AUTHOR]

In recent years, the development of super-resolution (SR) algorithms based on convolutional neural networks has become an important topic in enhancing the resolution of multi-channel remote sensing images. However, most of the existing SR models suffer from the insufficient utilization of spectral information, limiting their SR performance. Here, we derive a novel hybrid SR network (HSRN) which facilitates the acquisition of joint spatial–spectral information to enhance the spatial resolution of multi-channel remote sensing images. The main contributions of this paper are three-fold: (1) in order to sufficiently extract the spatial–spectral information of multi-channel remote sensing images, we designed a hybrid three-dimensional (3D) and two-dimensional (2D) convolution module which can distill the nonlinear spectral and spatial information simultaneously; (2) to enhance the discriminative learning ability, we designed the attention structure, including channel attention, before the upsampling block and spatial attention after the upsampling block, to weigh and rescale the spectral and spatial features; and (3) to acquire fine quality and clear texture for reconstructed SR images, we introduced a multi-scale structural similarity index into our loss function to constrain the HSRN model. The qualitative and quantitative comparisons were carried out in comparison with other SR methods on public remote sensing datasets. It is demonstrated that our HSRN outperforms state-of-the-art methods on multi-channel remote sensing images. [ABSTRACT FROM AUTHOR]

Convolutional neural networks (CNNs) have been widely used with its powerful discriminative ability in change detection (CD), but most CNN-based methods are still exploring ways to capture relatively long-range context in spatial-temporal domain. The recent vision transformer (ViT), which is based on the self-attention mechanism, has been applied in CD to model long-range dependencies. However, such transformer-based architectures do not fully consider the potential of interdependencies among the high-level semantic feature maps and easily overlook local detail features, resulting in a noncompact interior of the large-scale change area and missing small changes. Therefore, we propose a new transformer-based hybrid network called interact-feature transformer network with spatial detail enhancement module (IFTSDNet), which takes advantage of transformers to capture long-range context, and of CNNs to extract local information. We design an interact-feature transformer (IFT), which can not only obtain the global contextual information, but also achieve the interactions of high-level semantic feature maps. The spatial detail enhancement module (SDEM) with a group of various receptive fields is built to refine spatial features, which incorporates more discriminative feature representations. Comparative experiments prove the effectiveness of the proposed method, which shows better performance than four recent transformer-based methods. The code will be available at https://github.com/wanglinlin0219/IFTSDNet. [ABSTRACT FROM AUTHOR]

Recently, a hybrid network that combines radio frequency Wireless Gigabit Alliance (WiGig) networks with light fidelity (LiFi) networks has been proposed as the foundation for a high-speed wireless communication solution. A LiFi access point provides the service through the limited coverage area, LiFi attocell. Hence, LiFi networks could efficiently apply the frequency reuse concept to enhance spatial-spectral efficiency. Unfortunately, when the number of user equipment (UE) increases, new obstacles are added to those that the LiFi networks already face, such as light path obstruction, poorly aligned connections, and handover, in addition to uplink and mobility issues. To solve these issues and raise network quality of service (QoS), the hybrid LiFi/RF network has been suggested. In such networks, simultaneously and in a totally different frequency range, WiGig access points could provide tremendous data rates (gigabits per second) using the massive bandwidth of the Millimeter-Wave (mm-Wave) spectrum. Nevertheless, such hybrid networks need an effective load balancing (LB) strategy to assign the best access point (AP) and distribute enough resources for each UE depending on the location distributions of UEs (the channel between UEs and APs). The traditional LB approaches, however, use complex iterative computing procedures for each new distribution of UEs. Therefore, the Most-Correlated Distribution (MCD) Based Load Balancing Scheme is suggested in this work. The suggested method is clever enough to exploit the history of all prior load-balancing outcomes, recorded in a Distributions-Decisions Record (DDR), in order to identify appropriate allocations for the new UEs distribution, rather than going into repeated intensive complex calculations. The DDR is a list of the most common users’ distributions and the corresponding best AP allocation decisions which are calculated via the Consecutive Assign WiGig First SOA (CAWFS) LB Algorithm. The DDR record is created once, and off-line via the center processing unit (CPU). Each row in the DDR is composed of the supposed distribution and the corresponding decisions. Given the new mobile user distribution, the subset of the DDR records, that contains the most correlated distributions, is constructed. The current decisions are chosen depending on the previous decisions in the selected subset via the majority voting technique. In comparison to previous load-balancing algorithms, the proposed approach intends to provide equivalent attainable data rates and outage probability performances at lower complexity.

The object detection of unmanned aerial vehicle (UAV) images has widespread applications in numerous fields; however, the complex background, diverse scales, and uneven distribution of objects in UAV images make object detection a challenging task. This study proposes a convolution neural network transformer hybrid model to achieve efficient object detection in UAV images, which has three advantages that contribute to improving object detection performance. First, the efficient and effective cross-shaped window (CSWin) transformer can be used as a backbone to obtain image features at different levels, and the obtained features can be input into the feature pyramid network to achieve multiscale representation, which will contribute to multiscale object detection. Second, a hybrid patch embedding module is constructed to extract and utilize low-level information such as the edges and corners of the image. Finally, a slicing-based inference method is constructed to fuse the inference results of the original image and sliced images, which will improve the small object detection accuracy without modifying the original network. Experimental results on public datasets illustrate that the proposed method can improve performance more effectively than several popular and state-of-the-art object detection methods.

Introduction: This article proposes a novel hybrid network that combines the temporal signal of a spiking neural network (SNN) with the spatial signal of an artificial neural network (ANN), namely the Spatio-Temporal Combined Network (STNet). Methods: Inspired by the way the visual cortex in the human brain processes visual information, two versions of STNet are designed: a concatenated one (C-STNet) and a parallel one (P-STNet). In the C-STNet, the ANN, simulating the primary visual cortex, extracts the simple spatial information of objects first, and then the obtained spatial information is encoded as spiking time signals for transmission to the rear SNN which simulates the extrastriate visual cortex to process and classify the spikes. With the view that information from the primary visual cortex reaches the extrastriate visual cortex via ventral and dorsal streams, in P-STNet, the parallel combination of the ANN and the SNN is employed to extract the original spatio-temporal information from samples, and the extracted information is transferred to a posterior SNN for classification. Results: The experimental results of the two STNets obtained on six small and two large benchmark datasets were compared with eight commonly used approaches, demonstrating that the two STNets can achieve improved performance in terms of accuracy, generalization, stability, and convergence. Discussion: These prove that the idea of combining ANN and SNN is feasible and can greatly improve the performance of SNN. [ABSTRACT FROM AUTHOR]

Human lying is influenced by cognitive neural mechanisms in the brain, and conducting research on lie detection in speech can help to reveal the cognitive mechanisms of the human brain. Inappropriate deception detection features can easily lead to dimension disaster and make the generalization ability of the widely used semi-supervised speech deception detection model worse. Because of this, this paper proposes a semi-supervised speech deception detection algorithm combining acoustic statistical features and time-frequency two-dimensional features. Firstly, a hybrid semi-supervised neural network based on a semi-supervised autoencoder network (AE) and a mean-teacher network is established. Secondly, the static artificial statistical features are input into the semi-supervised AE to extract more robust advanced features, and the three-dimensional (3D) mel-spectrum features are input into the mean-teacher network to obtain features rich in time-frequency two-dimensional information. Finally, a consistency regularization method is introduced after feature fusion, effectively reducing the occurrence of over-fitting and improving the generalization ability of the model. This paper carries out experiments on the self-built corpus for deception detection. The experimental results show that the highest recognition accuracy of the algorithm proposed in this paper is 68.62% which is 1.2% higher than the baseline system and effectively improves the detection accuracy. [ABSTRACT FROM AUTHOR]

Given the growing number of devices and their need for internet access, researchers are focusing on integrating various network technologies. Concerning indoor wireless services, a promising approach in this regard is to combine light fidelity (LiFi) and wireless fidelity (WiFi) technologies into a hybrid LiFi and WiFi network (HLWNet). Such a network benefits from LiFi's distinct capability for high-speed data transmission and from the wide radio coverage offered by WiFi technologies. In this paper, we describe the framework for the HWLNet architecture, providing an overview of the handover methods used in HLWNets and presenting the basic architecture of hybrid LiFi/WiFi networks, optimization of cell deployment, relevant modulation schemes, illumination constraints, and backhaul device design. The survey also reviews the performance and recent achievements of HLWNets compared to legacy networks with an emphasis on signal to noise and interference ratio (SINR), spectral and power efficiency, and quality of service (QoS). In addition, user behaviour is discussed, considering interference in a LiFi channel is due to user movement, handover frequency, and load balancing. Furthermore, recent advances in indoor positioning and the security of hybrid networks are presented, and finally, directions of the hybrid network's evolution in the foreseeable future are discussed. [ABSTRACT FROM AUTHOR]