The highly dynamic nature,strong uncertainty,and coupled multiple safety constraints inherent in carrier aircraft recovery operations pose severe challenges for real-time decision-making.Addressing bolter scenarios,th...The highly dynamic nature,strong uncertainty,and coupled multiple safety constraints inherent in carrier aircraft recovery operations pose severe challenges for real-time decision-making.Addressing bolter scenarios,this study proposes an intelligent decision-making framework based on a deep long short-term memory Q-network.This framework transforms the real-time sequencing for bolter recovery problem into a partially observable Markov decision process.It employs a stacked long shortterm memory network to accurately capture the long-range temporal dependencies of bolter event chains and fuel consumption.Furthermore,it integrates a prioritized experience replay training mechanism to construct a safe and adaptive scheduling system capable of millisecond-level real-time decision-making.Experimental demonstrates that,within large-scale mass recovery scenarios,the framework achieves zero safety violations in static environments and maintains a fuel safety violation rate below 10%in dynamic scenarios,with single-step decision times at the millisecond level.The model exhibits strong generalization capability,effectively responding to unforeseen emergent situations—such as multiple bolters and fuel emergencies—without requiring retraining.This provides robust support for efficient carrier-based aircraft recovery operations.展开更多
As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic e...As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.展开更多
Single Image Super-Resolution(SISR)seeks to reconstruct high-resolution(HR)images from lowresolution(LR)inputs,thereby enhancing visual fidelity and the perception of fine details.While Transformer-based models—such ...Single Image Super-Resolution(SISR)seeks to reconstruct high-resolution(HR)images from lowresolution(LR)inputs,thereby enhancing visual fidelity and the perception of fine details.While Transformer-based models—such as SwinIR,Restormer,and HAT—have recently achieved impressive results in super-resolution tasks by capturing global contextual information,these methods often suffer from substantial computational and memory overhead,which limits their deployment on resource-constrained edge devices.To address these challenges,we propose a novel lightweight super-resolution network,termed Binary Attention-Guided Information Distillation(BAID),which integrates frequency-aware modeling with a binary attention mechanism to significantly reduce computational complexity and parameter count whilemaintaining strong reconstruction performance.The network combines a high–low frequency decoupling strategy with a local–global attention sharing mechanism,enabling efficient compression of redundant computations through binary attention guidance.At the core of the architecture lies the Attention-Guided Distillation Block(AGDB),which retains the strengths of the information distillation framework while introducing a sparse binary attention module to enhance both inference efficiency and feature representation.Extensive×4 superresolution experiments on four standard benchmarks—Set5,Set14,BSD100,and Urban100—demonstrate that BAID achieves Peak Signal-to-Noise Ratio(PSNR)values of 32.13,28.51,27.47,and 26.15,respectively,with only 1.22 million parameters and 26.1 G Floating-Point Operations(FLOPs),outperforming other state-of-the-art lightweight methods such as Information Multi-Distillation Network(IMDN)and Residual Feature Distillation Network(RFDN).These results highlight the proposed model’s ability to deliver high-quality image reconstruction while offering strong deployment efficiency,making it well-suited for image restoration tasks in resource-limited environments.展开更多
The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditio...The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.展开更多
Deep learning has been recognized as an effective method for indoor positioning.However,most existing real-valued neural networks(RVNNs)treat the two constituent components of complex-valued channel state information(...Deep learning has been recognized as an effective method for indoor positioning.However,most existing real-valued neural networks(RVNNs)treat the two constituent components of complex-valued channel state information(CSI)as real-valued inputs,potentially discarding useful information embedded in the original CSI.In addition,existing positioning models generally face the contradiction between computational complexity and positioning accuracy.To address these issues,we combine graph neural network(GNN)with complex-valued neural network(CVNN)to construct a lightweight indoor positioning model named CGNet.CGNet employs complexvalued convolution operation to directly process the original CSI data,fully exploiting the correlation between real and imaginary parts of CSI while extracting local features.Subsequently,the feature values are treated as nodes,and conditional position encoding(CPE)module is applied to add positional information.To reduce the number of connections in the graph structure and lower themodel complexity,feature information is mapped to an efficient graph structure through a dynamic axial graph construction(DAGC)method,with global features extracted usingmaximum relative graph convolution(MRConv).Experimental results show that,on the CTW dataset,CGNet achieves a 10%improvement in positioning accuracy compared to existing methods,while the number of model parameters is only 0.8 M.CGNet achieves excellent positioning accuracy with very few parameters.展开更多
Detecting small forest fire targets in unmanned aerial vehicle(UAV)images is difficult,as flames typically cover only a very limited portion of the visual scene.This study proposes Context-guided Compact Lightweight N...Detecting small forest fire targets in unmanned aerial vehicle(UAV)images is difficult,as flames typically cover only a very limited portion of the visual scene.This study proposes Context-guided Compact Lightweight Network(CCLNet),an end-to-end lightweight model designed to detect small forest fire targets while ensuring efficient inference on devices with constrained computational resources.CCLNet employs a three-stage network architecture.Its key components include three modules.C3F-Convolutional Gated Linear Unit(C3F-CGLU)performs selective local feature extraction while preserving fine-grained high-frequency flame details.Context-Guided Feature Fusion Module(CGFM)replaces plain concatenation with triplet-attention interactions to emphasize subtle flame patterns.Lightweight Shared Convolution with Separated Batch Normalization Detection(LSCSBD)reduces parameters through separated batch normalization while maintaining scale-specific statistics.We build TF-11K,an 11,139-image dataset combining 9139 self-collected UAV images from subtropical forests and 2000 re-annotated frames from the FLAME dataset.On TF-11K,CCLNet attains 85.8%mAP@0.5,45.5%mean Average Precision(mAP)@[0.5:0.95],87.4%precision,and 79.1%recall with 2.21 M parameters and 5.7 Giga Floating-point Operations Per Second(GFLOPs).The ablation study confirms that each module contributes to both accuracy and efficiency.Cross-dataset evaluation on DFS yields 77.5%mAP@0.5 and 42.3%mAP@[0.5:0.95],indicating good generalization to unseen scenes.These results suggest that CCLNet offers a practical balance between accuracy and speed for small-target forest fire monitoring with UAVs.展开更多
In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiologi...In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.展开更多
Space-division multiplexing(SDM)utilizing uncoupled multi-core fibers(MCF)is considered a promising candidate for nextgeneration high-speed optical transmission systems due to its huge capacity and low inter-core cros...Space-division multiplexing(SDM)utilizing uncoupled multi-core fibers(MCF)is considered a promising candidate for nextgeneration high-speed optical transmission systems due to its huge capacity and low inter-core crosstalk.In this paper,we demonstrate a realtime high-speed SDM transmission system over a field-deployed 7-core MCF cable using commercial 400 Gbit/s backbone optical transport network(OTN)transceivers and a network management system.The transceivers employ a high noise-tolerant quadrature phase shift keying(QPSK)modulation format with a 130 Gbaud rate,enabled by optoelectronic multi-chip module(OE-MCM)packaging.The network management system can effectively manage and monitor the performance of the 7-core SDM OTN system and promptly report failure events through alarms.Our field trial demonstrates the compatibility of uncoupled MCF with high-speed OTN transmission equipment and network management systems,supporting its future deployment in next-generation high-speed terrestrial cable transmission networks.展开更多
With the flourishing development of Unmanned Aerial Vehicles(UAVs), the mission tasks of UAVs have become more and more complex. Consequently, a Real-Time Operating System(RTOS) that provides operating environments fo...With the flourishing development of Unmanned Aerial Vehicles(UAVs), the mission tasks of UAVs have become more and more complex. Consequently, a Real-Time Operating System(RTOS) that provides operating environments for various mission services on these UAVs has become crucial, which leads to the necessity of having a deep understanding of an RTOS. In this paper, an empirical study is conducted on FreeRTOS, a commonly used RTOS for UAVs, from a complex network perspective. A total of 85 releases of FreeRTOS, from V2.4.2 to V10.0.0, are modeled as directed networks, in which the nodes represent functions and the edges denote function calls. It is found that the size of the FreeRTOS network has grown almost linearly with the evolution of the versions, while its main core has evolved steadily. In addition, a k-core analysis-based metric is proposed to identify major functionality changes of FreeRTOS during its evolution.The result shows that the identified versions are consistent with the version change logs. Finally,it is found that the clustering coefficient of the Linux OS scheduler is larger than that of the FreeRTOS scheduler. In conclusion, the empirical results provide useful guidance for developers and users of UAV RTOSs.展开更多
The application and development of a wide-area measurement system(WAMS)has enabled many applications and led to several requirements based on dynamic measurement data.Such data are transmitted as big data information ...The application and development of a wide-area measurement system(WAMS)has enabled many applications and led to several requirements based on dynamic measurement data.Such data are transmitted as big data information flow.To ensure effective transmission of wide-frequency electrical information by the communication protocol of a WAMS,this study performs real-time traffic monitoring and analysis of the data network of a power information system,and establishes corresponding network optimization strategies to solve existing transmission problems.This study utilizes the traffic analysis results obtained using the current real-time dynamic monitoring system to design an optimization strategy,covering the optimization in three progressive levels:the underlying communication protocol,source data,and transmission process.Optimization of the system structure and scheduling optimization of data information are validated to be feasible and practical via tests.展开更多
To achieve smart and personalized medicine, the development of hydrogel dressings with sensing properties and biotherapeutic properties that can act as a sensor to monitor of human health in real-time while speeding u...To achieve smart and personalized medicine, the development of hydrogel dressings with sensing properties and biotherapeutic properties that can act as a sensor to monitor of human health in real-time while speeding up wound healing face great challenge. In the present study, a biocompatible dual-network composite hydrogel(DNCGel) sensor was obtained via a simple process. The dual network hydrogel is constructed by the interpenetration of a flexible network formed of poly(vinyl alcohol)(PVA) physical cross-linked by repeated freeze-thawing and a rigid network of iron-chelated xanthan gum(XG) impregnated with Fe^(3+) interpenetration. The pure PVA/XG hydrogels were chelated with ferric ions by immersion to improve the gel strength(compressive modulus and tensile modulus can reach up to 0.62 MPa and0.079 MPa, respectively), conductivity(conductivity values ranging from 9 × 10^(-4) S/cm to 1 × 10^(-3)S/cm)and bacterial inhibition properties(up to 98.56%). Subsequently, the effects of the ratio of PVA and XG and the immersion time of Fe^(3+) on the hydrogels were investigated, and DNGel3 was given the most priority on a comprehensive consideration. It was demonstrated that the DNCGel exhibit good biocompatibility in vitro, effectively facilitate wound healing in vivo(up to 97.8% healing rate) under electrical stimulation, and monitors human movement in real time. This work provides a novel avenue to explore multifunctional intelligent hydrogels that hold great promise in biomedical fields such as smart wound dressings and flexible wearable sensors.展开更多
Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is cr...Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.展开更多
The effects of real-time traffic information system(RTTIS)on traffic performance under parallel,grid and ring networks were investigated.The simulation results show that the effects of the proportion of RTTIS usage de...The effects of real-time traffic information system(RTTIS)on traffic performance under parallel,grid and ring networks were investigated.The simulation results show that the effects of the proportion of RTTIS usage depend on the road network structures.For traffic on a parallel network,the performance of groups with and without RTTIS level is improved when the proportion of vehicles using RTTIS is greater than 0 and less than 30%,and a proportion of RTTIS usage higher than 90%would actually deteriorate the performance.For both grid and ring networks,a higher proportion of RTTIS usage always improves the performance of groups with and without RTTIS.For all three network structures,vehicles without RTTIS benefit from some proportion of RTTIS usage in a system.展开更多
With the continual growth of the variety and complexity of network crime means, the traditional packet feature matching cannot detect all kinds of intrusion behaviors completely. It is urgent to reassemble network str...With the continual growth of the variety and complexity of network crime means, the traditional packet feature matching cannot detect all kinds of intrusion behaviors completely. It is urgent to reassemble network stream to perform packet processing at a semantic level above the network layer. This paper presents an efficient TCP stream reassembly mechanism for real-time processing of high-speed network traffic. By analyzing the characteristics of network stream in high-speed network and TCP connection establishment process, several polices for designing the reassembly mechanism are built. Then, the reassembly implementation is elaborated in accordance with the policies. Finally, the reassembly mechanism is compared with the traditional reassembly mechanism by the network traffic captured in a typical gigabit gateway. Experiment results illustrate that the reassembly mechanism is efficient and can satisfy the real-time property requirement of traffic analysis system in high-speed network.展开更多
The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving sy...The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.展开更多
With the popularity of smart handheld devices, mobile streaming video has multiplied the global network traffic in recent years. A huge concern of users' quality of experience(Qo E) has made rate adaptation method...With the popularity of smart handheld devices, mobile streaming video has multiplied the global network traffic in recent years. A huge concern of users' quality of experience(Qo E) has made rate adaptation methods very attractive. In this paper, we propose a two-phase rate adaptation strategy to improve users' real-time video Qo E. First, to measure and assess video Qo E, we provide a continuous Qo E prediction engine modeled by RNN recurrent neural network. Different from traditional Qo E models which consider the Qo E-aware factors separately or incompletely, our RNN-Qo E model accounts for three descriptive factors(video quality, rebuffering, and rate change) and reflects the impact of cognitive memory and recency. Besides, the video playing is separated into the initial startup phase and the steady playback phase, and we takes different optimization goals for each phase: the former aims at shortening the startup delay while the latter ameliorates the video quality and the rebufferings. Simulation results have shown that RNN-Qo E can follow the subjective Qo E quite well, and the proposed strategy can effectively reduce the occurrence of rebufferings caused by the mismatch between the requested video rates and the fluctuated throughput and attains standout performance on real-time Qo E compared with classical rate adaption methods.展开更多
In this paper, the model of the online real-time information transmission network, such as wechat, micro-blog, and QQ network, is proposed and built, based on the connection properties between users of the online real...In this paper, the model of the online real-time information transmission network, such as wechat, micro-blog, and QQ network, is proposed and built, based on the connection properties between users of the online real-time information transmission network, and combined with the local world evolving characteristics in complex network, then the statistical topological properties of the network is obtained by numerical simulation. Furthermore, we simulated the process of information transmission on the network, according to the actual characteristics of the online real-time information transmission. Statistics show that the degree distribution presents the characteristics of scale free network, presenting power law distribution, while the average path length, the average clustering coefficient and the average size of the network also has a power-law relationship, moreover, the model parameters has no effect on power-law exponent. The spread of information on the network represents obvious fluctuation scaling, reflecting the characteristics that information transmission fluctuates over time.展开更多
The exponential expansion of the Internet of Things(IoT),Industrial Internet of Things(IIoT),and Transportation Management of Things(TMoT)produces vast amounts of real-time streaming data.Ensuring system dependability...The exponential expansion of the Internet of Things(IoT),Industrial Internet of Things(IIoT),and Transportation Management of Things(TMoT)produces vast amounts of real-time streaming data.Ensuring system dependability,operational efficiency,and security depends on the identification of anomalies in these dynamic and resource-constrained systems.Due to their high computational requirements and inability to efficiently process continuous data streams,traditional anomaly detection techniques often fail in IoT systems.This work presents a resource-efficient adaptive anomaly detection model for real-time streaming data in IoT systems.Extensive experiments were carried out on multiple real-world datasets,achieving an average accuracy score of 96.06%with an execution time close to 7.5 milliseconds for each individual streaming data point,demonstrating its potential for real-time,resourceconstrained applications.The model uses Principal Component Analysis(PCA)for dimensionality reduction and a Z-score technique for anomaly detection.It maintains a low computational footprint with a sliding window mechanism,enabling incremental data processing and identification of both transient and sustained anomalies without storing historical data.The system uses a Multivariate Linear Regression(MLR)based imputation technique that estimates missing or corrupted sensor values,preserving data integrity prior to anomaly detection.The suggested solution is appropriate for many uses in smart cities,industrial automation,environmental monitoring,IoT security,and intelligent transportation systems,and is particularly well-suited for resource-constrained edge devices.展开更多
Along with process control,perception represents the main function performed by the Edge Layer of an Internet of Things(IoT)network.Many of these networks implement various applications where the response time does no...Along with process control,perception represents the main function performed by the Edge Layer of an Internet of Things(IoT)network.Many of these networks implement various applications where the response time does not represent an important parameter.However,in critical applications,this parameter represents a crucial aspect.One important sensing device used in IoT designs is the accelerometer.In most applications,the response time of the embedded driver software handling this device is generally not analysed and not taken into account.In this paper,we present the design and implementation of a predictable real-time driver stack for a popular accelerometer and gyroscope device family.We provide clear justifications for why this response time is extremely important for critical applications in the acquisition process of such data.We present extensive measurements and experimental results that demonstrate the predictability of our solution,making it suitable for critical real-time systems.展开更多
As the field of autonomous driving evolves, real-time semantic segmentation has become a crucial part of computer vision tasks. However, most existing methods use lightweight convolution to reduce the computational ef...As the field of autonomous driving evolves, real-time semantic segmentation has become a crucial part of computer vision tasks. However, most existing methods use lightweight convolution to reduce the computational effort, resulting in lower accuracy. To address this problem, we construct TBANet, a network with an encoder-decoder structure for efficient feature extraction. In the encoder part, the TBA module is designed to extract details and the ETBA module is used to learn semantic representations in a high-dimensional space. In the decoder part, we design a combination of multiple upsampling methods to aggregate features with less computational overhead. We validate the efficiency of TBANet on the Cityscapes dataset. It achieves 75.1% mean Intersection over Union(mIoU) with only 2.07 million parameters and can reach 90.3 Frames Per Second(FPS).展开更多
基金supported by the National Natural Science Foundation of China(Grant No.62403486)。
文摘The highly dynamic nature,strong uncertainty,and coupled multiple safety constraints inherent in carrier aircraft recovery operations pose severe challenges for real-time decision-making.Addressing bolter scenarios,this study proposes an intelligent decision-making framework based on a deep long short-term memory Q-network.This framework transforms the real-time sequencing for bolter recovery problem into a partially observable Markov decision process.It employs a stacked long shortterm memory network to accurately capture the long-range temporal dependencies of bolter event chains and fuel consumption.Furthermore,it integrates a prioritized experience replay training mechanism to construct a safe and adaptive scheduling system capable of millisecond-level real-time decision-making.Experimental demonstrates that,within large-scale mass recovery scenarios,the framework achieves zero safety violations in static environments and maintains a fuel safety violation rate below 10%in dynamic scenarios,with single-step decision times at the millisecond level.The model exhibits strong generalization capability,effectively responding to unforeseen emergent situations—such as multiple bolters and fuel emergencies—without requiring retraining.This provides robust support for efficient carrier-based aircraft recovery operations.
基金supported by the National Natural Science Foundation of China 62402171.
文摘As a fundamental component in computer vision,edges can be categorized into four types based on discontinuities in reflectance,illumination,surface normal,or depth.While deep CNNs have significantly advanced generic edge detection,real-time multi-class semantic edge detection under resource constraints remains challenging.To address this,we propose a lightweight framework based on PiDiNet that enables fine-grained semantic edge detection.Our model simultaneously predicts background and four edge categories from full-resolution inputs,balancing accuracy and efficiency.Key contributions include:a multi-channel output structure expanding binary edge prediction to five classes,supported by a deep supervision mechanism;a dynamic class-balancing strategy combining adaptive weighting with physical priors to handle extreme class imbalance;and maintained architectural efficiency enabling real-time inference.Extensive evaluations on BSDS-RIND show our approach achieves accuracy competitive with state-of-the-art methods while operating in real time.
基金funded by Project of Sichuan Provincial Department of Science and Technology under 2025JDKP0150the Fundamental Research Funds for the Central Universities under 25CAFUC03093.
文摘Single Image Super-Resolution(SISR)seeks to reconstruct high-resolution(HR)images from lowresolution(LR)inputs,thereby enhancing visual fidelity and the perception of fine details.While Transformer-based models—such as SwinIR,Restormer,and HAT—have recently achieved impressive results in super-resolution tasks by capturing global contextual information,these methods often suffer from substantial computational and memory overhead,which limits their deployment on resource-constrained edge devices.To address these challenges,we propose a novel lightweight super-resolution network,termed Binary Attention-Guided Information Distillation(BAID),which integrates frequency-aware modeling with a binary attention mechanism to significantly reduce computational complexity and parameter count whilemaintaining strong reconstruction performance.The network combines a high–low frequency decoupling strategy with a local–global attention sharing mechanism,enabling efficient compression of redundant computations through binary attention guidance.At the core of the architecture lies the Attention-Guided Distillation Block(AGDB),which retains the strengths of the information distillation framework while introducing a sparse binary attention module to enhance both inference efficiency and feature representation.Extensive×4 superresolution experiments on four standard benchmarks—Set5,Set14,BSD100,and Urban100—demonstrate that BAID achieves Peak Signal-to-Noise Ratio(PSNR)values of 32.13,28.51,27.47,and 26.15,respectively,with only 1.22 million parameters and 26.1 G Floating-Point Operations(FLOPs),outperforming other state-of-the-art lightweight methods such as Information Multi-Distillation Network(IMDN)and Residual Feature Distillation Network(RFDN).These results highlight the proposed model’s ability to deliver high-quality image reconstruction while offering strong deployment efficiency,making it well-suited for image restoration tasks in resource-limited environments.
基金funded by the National Natural Science Foundation of China under Grant No.62371187the Open Program of Hunan Intelligent Rehabilitation Robot and Auxiliary Equipment Engineering Technology Research Center under Grant No.2024JS101.
文摘The ubiquity of mobile devices has driven advancements in mobile object detection.However,challenges in multi-scale object detection in open,complex environments persist due to limited computational resources.Traditional approaches like network compression,quantization,and lightweight design often sacrifice accuracy or feature representation robustness.This article introduces the Fast Multi-scale Channel Shuffling Network(FMCSNet),a novel lightweight detection model optimized for mobile devices.FMCSNet integrates a fully convolutional Multilayer Perceptron(MLP)module,offering global perception without significantly increasing parameters,effectively bridging the gap between CNNs and Vision Transformers.FMCSNet achieves a delicate balance between computation and accuracy mainly by two key modules:the ShiftMLP module,including a shift operation and an MLP module,and a Partial group Convolutional(PGConv)module,reducing computation while enhancing information exchange between channels.With a computational complexity of 1.4G FLOPs and 1.3M parameters,FMCSNet outperforms CNN-based and DWConv-based ShuffleNetv2 by 1%and 4.5%mAP on the Pascal VOC 2007 dataset,respectively.Additionally,FMCSNet achieves a mAP of 30.0(0.5:0.95 IoU threshold)with only 2.5G FLOPs and 2.0M parameters.It achieves 32 FPS on low-performance i5-series CPUs,meeting real-time detection requirements.The versatility of the PGConv module’s adaptability across scenarios further highlights FMCSNet as a promising solution for real-time mobile object detection.
文摘Deep learning has been recognized as an effective method for indoor positioning.However,most existing real-valued neural networks(RVNNs)treat the two constituent components of complex-valued channel state information(CSI)as real-valued inputs,potentially discarding useful information embedded in the original CSI.In addition,existing positioning models generally face the contradiction between computational complexity and positioning accuracy.To address these issues,we combine graph neural network(GNN)with complex-valued neural network(CVNN)to construct a lightweight indoor positioning model named CGNet.CGNet employs complexvalued convolution operation to directly process the original CSI data,fully exploiting the correlation between real and imaginary parts of CSI while extracting local features.Subsequently,the feature values are treated as nodes,and conditional position encoding(CPE)module is applied to add positional information.To reduce the number of connections in the graph structure and lower themodel complexity,feature information is mapped to an efficient graph structure through a dynamic axial graph construction(DAGC)method,with global features extracted usingmaximum relative graph convolution(MRConv).Experimental results show that,on the CTW dataset,CGNet achieves a 10%improvement in positioning accuracy compared to existing methods,while the number of model parameters is only 0.8 M.CGNet achieves excellent positioning accuracy with very few parameters.
基金funded by the Natural Science Foundation of Hunan Province(Grant No.2025JJ80352)the National Natural Science Foundation Project of China(Grant No.32271879).
文摘Detecting small forest fire targets in unmanned aerial vehicle(UAV)images is difficult,as flames typically cover only a very limited portion of the visual scene.This study proposes Context-guided Compact Lightweight Network(CCLNet),an end-to-end lightweight model designed to detect small forest fire targets while ensuring efficient inference on devices with constrained computational resources.CCLNet employs a three-stage network architecture.Its key components include three modules.C3F-Convolutional Gated Linear Unit(C3F-CGLU)performs selective local feature extraction while preserving fine-grained high-frequency flame details.Context-Guided Feature Fusion Module(CGFM)replaces plain concatenation with triplet-attention interactions to emphasize subtle flame patterns.Lightweight Shared Convolution with Separated Batch Normalization Detection(LSCSBD)reduces parameters through separated batch normalization while maintaining scale-specific statistics.We build TF-11K,an 11,139-image dataset combining 9139 self-collected UAV images from subtropical forests and 2000 re-annotated frames from the FLAME dataset.On TF-11K,CCLNet attains 85.8%mAP@0.5,45.5%mean Average Precision(mAP)@[0.5:0.95],87.4%precision,and 79.1%recall with 2.21 M parameters and 5.7 Giga Floating-point Operations Per Second(GFLOPs).The ablation study confirms that each module contributes to both accuracy and efficiency.Cross-dataset evaluation on DFS yields 77.5%mAP@0.5 and 42.3%mAP@[0.5:0.95],indicating good generalization to unseen scenes.These results suggest that CCLNet offers a practical balance between accuracy and speed for small-target forest fire monitoring with UAVs.
基金supported by the Science and Technology Bureau of Xi’an project(24KGDW0049)the Key Research and Development Programof Shaanxi(2023-YBGY-264)the Key Research and Development Program of Guangxi(GK-AB20159032).
文摘In recent years,the country has spent significant workforce and material resources to prevent traffic accidents,particularly those caused by fatigued driving.The current studies mainly concentrate on driver physiological signals,driving behavior,and vehicle information.However,most of the approaches are computationally intensive and inconvenient for real-time detection.Therefore,this paper designs a network that combines precision,speed and lightweight and proposes an algorithm for facial fatigue detection based on multi-feature fusion.Specifically,the face detection model takes YOLOv8(You Only Look Once version 8)as the basic framework,and replaces its backbone network with MobileNetv3.To focus on the significant regions in the image,CPCA(Channel Prior Convolution Attention)is adopted to enhance the network’s capacity for feature extraction.Meanwhile,the network training phase employs the Focal-EIOU(Focal and Efficient Intersection Over Union)loss function,which makes the network lightweight and increases the accuracy of target detection.Ultimately,the Dlib toolkit was employed to annotate 68 facial feature points.This study established an evaluation metric for facial fatigue and developed a novel fatigue detection algorithm to assess the driver’s condition.A series of comparative experiments were carried out on the self-built dataset.The suggested method’s mAP(mean Average Precision)values for object detection and fatigue detection are 96.71%and 95.75%,respectively,as well as the detection speed is 47 FPS(Frames Per Second).This method can balance the contradiction between computational complexity and model accuracy.Furthermore,it can be transplanted to NVIDIA Jetson Orin NX and quickly detect the driver’s state while maintaining a high degree of accuracy.It contributes to the development of automobile safety systems and reduces the occurrence of traffic accidents.
文摘Space-division multiplexing(SDM)utilizing uncoupled multi-core fibers(MCF)is considered a promising candidate for nextgeneration high-speed optical transmission systems due to its huge capacity and low inter-core crosstalk.In this paper,we demonstrate a realtime high-speed SDM transmission system over a field-deployed 7-core MCF cable using commercial 400 Gbit/s backbone optical transport network(OTN)transceivers and a network management system.The transceivers employ a high noise-tolerant quadrature phase shift keying(QPSK)modulation format with a 130 Gbaud rate,enabled by optoelectronic multi-chip module(OE-MCM)packaging.The network management system can effectively manage and monitor the performance of the 7-core SDM OTN system and promptly report failure events through alarms.Our field trial demonstrates the compatibility of uncoupled MCF with high-speed OTN transmission equipment and network management systems,supporting its future deployment in next-generation high-speed terrestrial cable transmission networks.
基金supported by the National Natural Science Foundation of China (No. 61772055)Equipment Preliminary R&D Project of China (No. 41402020102)
文摘With the flourishing development of Unmanned Aerial Vehicles(UAVs), the mission tasks of UAVs have become more and more complex. Consequently, a Real-Time Operating System(RTOS) that provides operating environments for various mission services on these UAVs has become crucial, which leads to the necessity of having a deep understanding of an RTOS. In this paper, an empirical study is conducted on FreeRTOS, a commonly used RTOS for UAVs, from a complex network perspective. A total of 85 releases of FreeRTOS, from V2.4.2 to V10.0.0, are modeled as directed networks, in which the nodes represent functions and the edges denote function calls. It is found that the size of the FreeRTOS network has grown almost linearly with the evolution of the versions, while its main core has evolved steadily. In addition, a k-core analysis-based metric is proposed to identify major functionality changes of FreeRTOS during its evolution.The result shows that the identified versions are consistent with the version change logs. Finally,it is found that the clustering coefficient of the Linux OS scheduler is larger than that of the FreeRTOS scheduler. In conclusion, the empirical results provide useful guidance for developers and users of UAV RTOSs.
文摘The application and development of a wide-area measurement system(WAMS)has enabled many applications and led to several requirements based on dynamic measurement data.Such data are transmitted as big data information flow.To ensure effective transmission of wide-frequency electrical information by the communication protocol of a WAMS,this study performs real-time traffic monitoring and analysis of the data network of a power information system,and establishes corresponding network optimization strategies to solve existing transmission problems.This study utilizes the traffic analysis results obtained using the current real-time dynamic monitoring system to design an optimization strategy,covering the optimization in three progressive levels:the underlying communication protocol,source data,and transmission process.Optimization of the system structure and scheduling optimization of data information are validated to be feasible and practical via tests.
基金supported by Physical Chemical Materials Analytical&Testing Center of Shandong University at Weihai,Natural Science Foundation of Shandong Province(No.ZR2022QD057)Open Project Fund for Hubei Key Laboratory of Oral and Maxillofacial Development and Regeneration(No.2021kqhm003)+1 种基金State Key Laboratory of Advanced Technology for Materials Synthesis and Processing(Wuhan University of Technology)the Science Fund of Shandong Laboratory of Advanced Materials and Green Manufacturing(Yantai,No.AMGM2021F02)。
文摘To achieve smart and personalized medicine, the development of hydrogel dressings with sensing properties and biotherapeutic properties that can act as a sensor to monitor of human health in real-time while speeding up wound healing face great challenge. In the present study, a biocompatible dual-network composite hydrogel(DNCGel) sensor was obtained via a simple process. The dual network hydrogel is constructed by the interpenetration of a flexible network formed of poly(vinyl alcohol)(PVA) physical cross-linked by repeated freeze-thawing and a rigid network of iron-chelated xanthan gum(XG) impregnated with Fe^(3+) interpenetration. The pure PVA/XG hydrogels were chelated with ferric ions by immersion to improve the gel strength(compressive modulus and tensile modulus can reach up to 0.62 MPa and0.079 MPa, respectively), conductivity(conductivity values ranging from 9 × 10^(-4) S/cm to 1 × 10^(-3)S/cm)and bacterial inhibition properties(up to 98.56%). Subsequently, the effects of the ratio of PVA and XG and the immersion time of Fe^(3+) on the hydrogels were investigated, and DNGel3 was given the most priority on a comprehensive consideration. It was demonstrated that the DNCGel exhibit good biocompatibility in vitro, effectively facilitate wound healing in vivo(up to 97.8% healing rate) under electrical stimulation, and monitors human movement in real time. This work provides a novel avenue to explore multifunctional intelligent hydrogels that hold great promise in biomedical fields such as smart wound dressings and flexible wearable sensors.
基金supported by the HFIPS Director’s Foundation(YZJJ202207-TS),the National Natural Science Foundation of China(82371931)the Natural Science Foundation of Anhui Province(2008085MC69)+3 种基金the Natural Science Foundation of Hefei City(2021033)the General Scientific Research Project of Anhui Provincial Health Commission(AHWJ2021b150)the Collaborative Innovation Program of Hefei Science Center,CAS(2021HSC-CIP013)the Anhui Province Key Research and Development Project(202204295107020004).
文摘Semantic segmentation of eye images is a complex task with important applications in human–computer interaction,cognitive science,and neuroscience.Achieving real-time,accurate,and robust segmentation algorithms is crucial for computationally limited portable devices such as augmented reality and virtual reality.With the rapid advancements in deep learning,many network models have been developed specifically for eye image segmentation.Some methods divide the segmentation process into multiple stages to achieve model parameter miniaturization while enhancing output through post processing techniques to improve segmentation accuracy.These approaches significantly increase the inference time.Other networks adopt more complex encoding and decoding modules to achieve end-to-end output,which requires substantial computation.Therefore,balancing the model’s size,accuracy,and computational complexity is essential.To address these challenges,we propose a lightweight asymmetric UNet architecture and a projection loss function.We utilize ResNet-3 layer blocks to enhance feature extraction efficiency in the encoding stage.In the decoding stage,we employ regular convolutions and skip connections to upscale the feature maps from the latent space to the original image size,balancing the model size and segmentation accuracy.In addition,we leverage the geometric features of the eye region and design a projection loss function to further improve the segmentation accuracy without adding any additional inference computational cost.We validate our approach on the OpenEDS2019 dataset for virtual reality and achieve state-of-the-art performance with 95.33%mean intersection over union(mIoU).Our model has only 0.63M parameters and 350 FPS,which are 68%and 200%of the state-of-the-art model RITNet,respectively.
文摘The effects of real-time traffic information system(RTTIS)on traffic performance under parallel,grid and ring networks were investigated.The simulation results show that the effects of the proportion of RTTIS usage depend on the road network structures.For traffic on a parallel network,the performance of groups with and without RTTIS level is improved when the proportion of vehicles using RTTIS is greater than 0 and less than 30%,and a proportion of RTTIS usage higher than 90%would actually deteriorate the performance.For both grid and ring networks,a higher proportion of RTTIS usage always improves the performance of groups with and without RTTIS.For all three network structures,vehicles without RTTIS benefit from some proportion of RTTIS usage in a system.
基金National High-Tech Research and Development Program of China (863 Program) (No.2007AA01Z309)
文摘With the continual growth of the variety and complexity of network crime means, the traditional packet feature matching cannot detect all kinds of intrusion behaviors completely. It is urgent to reassemble network stream to perform packet processing at a semantic level above the network layer. This paper presents an efficient TCP stream reassembly mechanism for real-time processing of high-speed network traffic. By analyzing the characteristics of network stream in high-speed network and TCP connection establishment process, several polices for designing the reassembly mechanism are built. Then, the reassembly implementation is elaborated in accordance with the policies. Finally, the reassembly mechanism is compared with the traditional reassembly mechanism by the network traffic captured in a typical gigabit gateway. Experiment results illustrate that the reassembly mechanism is efficient and can satisfy the real-time property requirement of traffic analysis system in high-speed network.
基金supported in part by the National Key RD Program of China (2021YFF0602104-2,2020YFB1804604)in part by the 2020 Industrial Internet Innovation and Development Project from Ministry of Industry and Information Technology of Chinain part by the Fundamental Research Fund for the Central Universities (30918012204,30920041112).
文摘The application of unmanned driving in the Internet of Things is one of the concrete manifestations of the application of artificial intelligence technology.Image semantic segmentation can help the unmanned driving system by achieving road accessibility analysis.Semantic segmentation is also a challenging technology for image understanding and scene parsing.We focused on the challenging task of real-time semantic segmentation in this paper.In this paper,we proposed a novel fast architecture for real-time semantic segmentation named DuFNet.Starting from the existing work of Bilateral Segmentation Network(BiSeNet),DuFNet proposes a novel Semantic Information Flow(SIF)structure for context information and a novel Fringe Information Flow(FIF)structure for spatial information.We also proposed two kinds of SIF with cascaded and paralleled structures,respectively.The SIF encodes the input stage by stage in the ResNet18 backbone and provides context information for the feature fusionmodule.Features from previous stages usually contain rich low-level details but high-level semantics for later stages.Themultiple convolutions embed in Parallel SIF aggregate the corresponding features among different stages and generate a powerful global context representation with less computational cost.The FIF consists of a pooling layer and an upsampling operator followed by projection convolution layer.The concise component provides more spatial details for the network.Compared with BiSeNet,our work achieved faster speed and comparable performance with 72.34%mIoU accuracy and 78 FPS on Cityscapes Dataset based on the ResNet18 backbone.
基金supported by the National Nature Science Foundation of China(NSFC 60622110,61471220,91538107,91638205)National Basic Research Project of China(973,2013CB329006),GY22016058
文摘With the popularity of smart handheld devices, mobile streaming video has multiplied the global network traffic in recent years. A huge concern of users' quality of experience(Qo E) has made rate adaptation methods very attractive. In this paper, we propose a two-phase rate adaptation strategy to improve users' real-time video Qo E. First, to measure and assess video Qo E, we provide a continuous Qo E prediction engine modeled by RNN recurrent neural network. Different from traditional Qo E models which consider the Qo E-aware factors separately or incompletely, our RNN-Qo E model accounts for three descriptive factors(video quality, rebuffering, and rate change) and reflects the impact of cognitive memory and recency. Besides, the video playing is separated into the initial startup phase and the steady playback phase, and we takes different optimization goals for each phase: the former aims at shortening the startup delay while the latter ameliorates the video quality and the rebufferings. Simulation results have shown that RNN-Qo E can follow the subjective Qo E quite well, and the proposed strategy can effectively reduce the occurrence of rebufferings caused by the mismatch between the requested video rates and the fluctuated throughput and attains standout performance on real-time Qo E compared with classical rate adaption methods.
文摘In this paper, the model of the online real-time information transmission network, such as wechat, micro-blog, and QQ network, is proposed and built, based on the connection properties between users of the online real-time information transmission network, and combined with the local world evolving characteristics in complex network, then the statistical topological properties of the network is obtained by numerical simulation. Furthermore, we simulated the process of information transmission on the network, according to the actual characteristics of the online real-time information transmission. Statistics show that the degree distribution presents the characteristics of scale free network, presenting power law distribution, while the average path length, the average clustering coefficient and the average size of the network also has a power-law relationship, moreover, the model parameters has no effect on power-law exponent. The spread of information on the network represents obvious fluctuation scaling, reflecting the characteristics that information transmission fluctuates over time.
基金funded by the Ongoing Research Funding Program(ORF-2025-890)King Saud University,Riyadh,Saudi Arabia and was supported by the Competitive Research Fund of theUniversity of Aizu,Japan.
文摘The exponential expansion of the Internet of Things(IoT),Industrial Internet of Things(IIoT),and Transportation Management of Things(TMoT)produces vast amounts of real-time streaming data.Ensuring system dependability,operational efficiency,and security depends on the identification of anomalies in these dynamic and resource-constrained systems.Due to their high computational requirements and inability to efficiently process continuous data streams,traditional anomaly detection techniques often fail in IoT systems.This work presents a resource-efficient adaptive anomaly detection model for real-time streaming data in IoT systems.Extensive experiments were carried out on multiple real-world datasets,achieving an average accuracy score of 96.06%with an execution time close to 7.5 milliseconds for each individual streaming data point,demonstrating its potential for real-time,resourceconstrained applications.The model uses Principal Component Analysis(PCA)for dimensionality reduction and a Z-score technique for anomaly detection.It maintains a low computational footprint with a sliding window mechanism,enabling incremental data processing and identification of both transient and sustained anomalies without storing historical data.The system uses a Multivariate Linear Regression(MLR)based imputation technique that estimates missing or corrupted sensor values,preserving data integrity prior to anomaly detection.The suggested solution is appropriate for many uses in smart cities,industrial automation,environmental monitoring,IoT security,and intelligent transportation systems,and is particularly well-suited for resource-constrained edge devices.
文摘Along with process control,perception represents the main function performed by the Edge Layer of an Internet of Things(IoT)network.Many of these networks implement various applications where the response time does not represent an important parameter.However,in critical applications,this parameter represents a crucial aspect.One important sensing device used in IoT designs is the accelerometer.In most applications,the response time of the embedded driver software handling this device is generally not analysed and not taken into account.In this paper,we present the design and implementation of a predictable real-time driver stack for a popular accelerometer and gyroscope device family.We provide clear justifications for why this response time is extremely important for critical applications in the acquisition process of such data.We present extensive measurements and experimental results that demonstrate the predictability of our solution,making it suitable for critical real-time systems.
文摘As the field of autonomous driving evolves, real-time semantic segmentation has become a crucial part of computer vision tasks. However, most existing methods use lightweight convolution to reduce the computational effort, resulting in lower accuracy. To address this problem, we construct TBANet, a network with an encoder-decoder structure for efficient feature extraction. In the encoder part, the TBA module is designed to extract details and the ETBA module is used to learn semantic representations in a high-dimensional space. In the decoder part, we design a combination of multiple upsampling methods to aggregate features with less computational overhead. We validate the efficiency of TBANet on the Cityscapes dataset. It achieves 75.1% mean Intersection over Union(mIoU) with only 2.07 million parameters and can reach 90.3 Frames Per Second(FPS).
