Edge devices in Internet of Things(IoT)applications can form peers to communicate in peer-to-peer(P2P)networks over P2P protocols.Using P2P networks ensures scalability and removes the need for centralized management....Edge devices in Internet of Things(IoT)applications can form peers to communicate in peer-to-peer(P2P)networks over P2P protocols.Using P2P networks ensures scalability and removes the need for centralized management.However,due to the open nature of P2P networks,they often suffer from the existence of malicious peers,especially malicious peers that unite in groups to raise each other’s ratings.This compromises users’safety and makes them lose their confidence about the files or services they are receiving.To address these challenges,we propose a neural networkbased algorithm,which uses the advantages of a machine learning algorithm to identify whether or not a peer is malicious.In this paper,a neural network(NN)was chosen as the machine learning algorithm due to its efficiency in classification.The experiments showed that the NNTrust algorithm is more effective and has a higher potential of reducing the number of invalid files and increasing success rates than other well-known trust management systems.展开更多
Numerous Internet of Things(IoT)systems produce massive volumes of information that must be handled and answered in a quite short period.The growing energy usage related to the migration of data into the cloud is one ...Numerous Internet of Things(IoT)systems produce massive volumes of information that must be handled and answered in a quite short period.The growing energy usage related to the migration of data into the cloud is one of the biggest problems.Edge computation helps users unload the workload again from cloud near the source of the information that must be handled to save time,increase security,and reduce the congestion of networks.Therefore,in this paper,Optimized Energy Efficient Strategy(OEES)has been proposed for extracting,distributing,evaluating the data on the edge devices.In the initial stage of OEES,before the transmission state,the data gathered from edge devices are supported by a fast error like reduction that is regarded as the largest energy user of an IoT system.The initial stage is followed by the reconstructing and the processing state.The processed data is transmitted to the nodes through controlled deep learning techniques.The entire stage of data collection,transmission and data reduction between edge devices uses less energy.The experimental results indicate that the volume of data transferred decreases and does not impact the professional data performance and predictive accuracy.Energy consumption of 7.38 KJ and energy conservation of 55.57 kJ was found in the proposed OEES scheme.Predictive accuracy is 97.5 percent,data performance rate was 97.65 percent,and execution time is 14.49 ms.展开更多
Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and processing.Any kind of malicious or abnormal fu...Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and processing.Any kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire IIoT.Moreover,they can allow malicious software installed on end nodes to penetrate the network.This paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge devices.The proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority voting.Experimental evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.展开更多
The replacement of personal computer terminal with edge device is recognized as a portable and cost-effective potential solution in solving equipment miniaturization and achieving high flexibility of robotic fruit har...The replacement of personal computer terminal with edge device is recognized as a portable and cost-effective potential solution in solving equipment miniaturization and achieving high flexibility of robotic fruit harvesting at in-field scale.This study proposes a lightweight improved You Only Look Once version 8n(YOLOv8n)model for detecting Orah fruits and deploying this model on an edge device.First of all,the model size was reduced while maintaining detection accuracy via the introduction of the ADown modules.Subsequently,a Concentrated-Comprehensive Dual Convolution(C3_DualConv)module combining dual convolutional bottlenecks was proposed to enhance the model capability to capture features of Orah fruits obscured by branches and leaves;this practice further reduced the model size.Additionally,a Bidirectional Feature Pyramid Network(BiFPN)that includes a pyramid level 2 high-resolution layer was employed for more efficient multi-scale feature fusion.Besides,three Coordinate Attention(CA)mechanism modules were also added to improve the recognition and capture capability for Orah fruit features.Finally,a more focused minimum points distance intersection over union loss was adopted to boost the detection efficiency of densely occluded Orah fruits.Experimentally demonstrating that the improved YOLOv8n model accurately detected Orah fruits in complex orchard environments,achieving a 97.7%of precision,an Average Precision at IoU threshold 0.5(AP@0.5)of 98.8%,and a 96.69%of F1 score,while maintaining a compact model size of 4.1 MB,under a Windows-based system terminal.This proposed model was optimally deployed on an Nvidia Jetson Orin Nano using TensorRT Python Application Programming Interface(API),the average interface speed exceeds 30 fps,indicating a real-time detection ability.This study can provide technical support for Orah fruit robotic harvesting on the basis of edge device.展开更多
In a smart system, the faults of edge devices directly impact the system’s overall fault. Further, complexity arises when different edge devices provide varying fault data. To study the Smart System Fault Evolution P...In a smart system, the faults of edge devices directly impact the system’s overall fault. Further, complexity arises when different edge devices provide varying fault data. To study the Smart System Fault Evolution Process (SSFEP) under different fault data conditions, an intelligent method for determining the Smart System Fault Probability (SSFP) is proposed. The data types provided by edge devices include the following: (1) only known edge device fault probability;(2) known Edge Device Fault Probability Distribution (EDFPD);(3) known edge device fault number and EDFPD;(4) known factor state of the edge device fault and EDFPD. Moreover, decision methods are proposed for each data case. Transfer Probability (TP) is divided into Continuity Transfer Probability (CTP) and Filterability Transfer Probability (FTP). CTP asserts that a Cause Event (CE) must lead to a Result Event (RE), while FTP requires CF probability to exceed a threshold before RF occurs. These probabilities are used to calculate SSFP. This paper introduces a decision method using the information diffusion principle for low-data SSFP determination, along with an improved method. The method is based on space fault network theory, abstracting SSFEP into a System Fault Evolution Process (SFEP) for research purposes.展开更多
Edge technology aims to bring cloud resources(specifically,the computation,storage,and network)to the closed proximity of the edge devices,i.e.,smart devices where the data are produced and consumed.Embedding computin...Edge technology aims to bring cloud resources(specifically,the computation,storage,and network)to the closed proximity of the edge devices,i.e.,smart devices where the data are produced and consumed.Embedding computing and application in edge devices lead to emerging of two new concepts in edge technology:edge computing and edge analytics.Edge analytics uses some techniques or algorithms to analyse the data generated by the edge devices.With the emerging of edge analytics,the edge devices have become a complete set.Currently,edge analytics is unable to provide full support to the analytic techniques.The edge devices cannot execute advanced and sophisticated analytic algorithms following various constraints such as limited power supply,small memory size,limited resources,etc.This article aims to provide a detailed discussion on edge analytics.The key contributions of the paper are as follows-a clear explanation to distinguish between the three concepts of edge technology:edge devices,edge computing,and edge analytics,along with their issues.In addition,the article discusses the implementation of edge analytics to solve many problems and applications in various areas such as retail,agriculture,industry,and healthcare.Moreover,the research papers of the state-of-the-art edge analytics are rigorously reviewed in this article to explore the existing issues,emerging challenges,research opportunities and their directions,and applications.展开更多
Pedestrian detection has been a hot spot in computer vision over the past decades due to the wide spectrum of promising applications,and the major challenge is false positives that occur during pedestrian detection.Th...Pedestrian detection has been a hot spot in computer vision over the past decades due to the wide spectrum of promising applications,and the major challenge is false positives that occur during pedestrian detection.The emergence of various Convolutional Neural Network-based detection strategies substantially enhances pedestrian detection accuracy but still does not solve this problem well.This paper deeply analyzes the detection framework of the two-stage CNN detection methods and finds out false positives in detection results are due to its training strategy misclassifying some false proposals,thus weakening the classification capability of the following subnetwork and hardly suppressing false ones.To solve this problem,this paper proposes a pedestrian-sensitive training algorithm to help two-stage CNN detection methods effectively learn to distinguish the pedestrian and non-pedestrian samples and suppress the false positives in the final detection results.The core of the proposed algorithm is to redesign the training proposal generating scheme for the two-stage CNN detection methods,which can avoid a certain number of false ones that mislead its training process.With the help of the proposed algorithm,the detection accuracy of the MetroNext,a smaller and more accurate metro passenger detector,is further improved,which further decreases false ones in its metro passenger detection results.Based on various challenging benchmark datasets,experiment results have demonstrated that the feasibility of the proposed algorithm is effective in improving pedestrian detection accuracy by removing false positives.Compared with the existing state-of-the-art detection networks,PSTNet demonstrates better overall prediction performance in accuracy,total number of parameters,and inference time;thus,it can become a practical solution for hunting pedestrians on various hardware platforms,especially for mobile and edge devices.展开更多
Trafic fow prediction is crucial for intelligent transportation and aids in route planning and navigation.However,existing studies often focus on prediction accuracy improvement,while neglecting external influences an...Trafic fow prediction is crucial for intelligent transportation and aids in route planning and navigation.However,existing studies often focus on prediction accuracy improvement,while neglecting external influences and practical issues like resource constraints and data sparsity on edge devices.We propose an online transfer learning(OTL)framework with a multi-layer perceptron(MLP)-assisted graph convolutional network(GCN),termed OTL-GM,which consists of two parts:transferring source-domain features to edge devices and using online learning to bridge domain gaps.Experiments on four data sets demonstrate OTL's effectiveness;in a comparison with models not using OTL,the reduction in the convergence time of the OTL models ranges from 24.77% to 95.32%.展开更多
Conforming to the rapidly increasing market demand of crack detection for tall buildings,the idea of integrating deep network technology into wall-climbing robot for crack detection is put forward in this paper.Taking...Conforming to the rapidly increasing market demand of crack detection for tall buildings,the idea of integrating deep network technology into wall-climbing robot for crack detection is put forward in this paper.Taking the dependence and hardware requirements when deployed on such edge devices as Raspberry Pi into consideration,the Darknet neural network is selected as the basic framework for detection.In order to improve the inference efficiency on edge devices and avoid the possible premature over-fitting of deep networks,the lite YOLOv4-tiny algorithm is then improved from the original YOLOv4-tiny algorithm and its structure is illustrated using Netron accordingly.The images downloaded from Internet and taken from the buildings in campus are processed to form crack detection data sets,which are trained on personal computer with the AlexeyAB version of Darknet to generate weight files.Meanwhile,the AlexeyAB version of Darknet accelerated by NNpack package is deployed on Raspberry Pi 4B,and the crack detection experiments are carried out.Some characteristics,e.g.,fast speed and lower false detection rate of the lite YOLOv4-tiny algorithm,are confirmed by comparison with those of original YOLOv4-tiny algorithm.The innovations of this paper focus on the simple network structure,fewer network layers,and earlier forward transmission of features to prevent over-fitting,showing the new lite neural network exceeds the original YOLOv4-tiny network significantly.展开更多
As the demand for edge platforms in artificial intelligence increases,including mobile devices and security applications,the surge in data influx into edge devices often triggers interference and suboptimal decision-m...As the demand for edge platforms in artificial intelligence increases,including mobile devices and security applications,the surge in data influx into edge devices often triggers interference and suboptimal decision-making.There is a pressing need for solutions emphasizing low power consumption and cost-effectiveness.In-sensor computing systems employing memristors face challenges in optimizing energy efficiency and streamlining manufacturing due to the necessity for multiple physical processing components.Here,we introduce low-power organic optoelectronic memristors with synergistic optical and mV-level electrical tunable operation for a dynamic“control-on-demand”architecture.Integrating signal sensing,featuring,and processing within the same memristors enables the realization of each in-sensor analogue reservoir computing module,and minimizes circuit integration complexity.The system achieves 97.15%fingerprint recognition accuracy while maintaining a minimal reservoir size and ultra-low energy consumption.Furthermore,we leverage wafer-scale solution techniques and flexible substrates for optimal memristor fabrication.By centralizing core functionalities on the same in-sensor platform,we propose a resilient and adaptable framework for energy-efficient and economical edge computing.展开更多
The fifth-generation(5G)wireless communication networks are expected to play an essential role in the transformation of vertical industries.Among many exciting applications to be enabled by 5G,logistics tasks in indus...The fifth-generation(5G)wireless communication networks are expected to play an essential role in the transformation of vertical industries.Among many exciting applications to be enabled by 5G,logistics tasks in industry parks can be performed more efficiently via vehicle-to-everything(V2X)communications.In this paper,a multi-layer collaboration framework enabled by V2X is proposed for logistics management in industrial parks.The proposed framework includes three layers:a perception and execution layer,a logistics layer,and a configuration layer.In addition to the collaboration among these three layers,this study addresses the collaboration among devices,edge servers,and cloud services.For effective logistics in industrial parks,task collaboration is achieved through four functions:environmental perception and map construction,task allocation,path planning,and vehicle movement.To dynamically coordinate these functions,device–edge–cloud collaboration,which is supported by 5G slices and V2X communication technology,is applied.Then,the analytical target cascading method is adopted to configure and evaluate the collaboration schemes of industrial parks.Finally,a logistics analytical case study in industrial parks is employed to demonstrate the feasibility of the proposed collaboration framework.展开更多
The superconducting quantum interference device（SQUID） amplifier is widely used in the field of weak signal detection for its low input impedance, low noise, and low power consumption. In this paper, the SQUIDs with...The superconducting quantum interference device（SQUID） amplifier is widely used in the field of weak signal detection for its low input impedance, low noise, and low power consumption. In this paper, the SQUIDs with identical junctions and the series SQUIDs with different junctions were successfully fabricated. The Nb/Al-AlOx/Nb trilayer and input Nb coils were prepared by asputtering equipment. The SQUID devices were prepared by a sputtering and the lift-off method.Investigations by AFM, OM and SEM revealed the morphology and roughness of the Nb films and Nb/Al-AlOx/Nb trilayer.In addition, the current–voltage characteristics of the SQUID devices with identical junction and different junction areas were measured at 2.5 K in the He^3 refrigerator. The results show that the SQUID modulation depth is obviously affected by the junction area. The modulation depth obviously increases with the increase of the junction area in a certain range. It is found that the series SQUID with identical junction area has a transimpedance gain of 58 Ω approximately.展开更多
With the rapid development of mobile technology and smart devices,crowdsensing has shown its large potential to collect massive data.Considering the limitation of calculation power,edge computing is introduced to rele...With the rapid development of mobile technology and smart devices,crowdsensing has shown its large potential to collect massive data.Considering the limitation of calculation power,edge computing is introduced to release unnecessary data transmission.In edge-computing-enabled crowdsensing,massive data is required to be preliminary processed by edge computing devices(ECDs).Compared with the traditional central platform,these ECDs are limited by their own capability so they may only obtain part of relative factors and they can’t process data synthetically.ECDs involved in one task are required to cooperate to process the task data.The privacy of participants is important in crowdsensing,so blockchain is used due to its decentralization and tamperresistance.In crowdsensing tasks,it is usually difficult to obtain the assessment criteria in advance so reinforcement learning is introduced.As mentioned before,ECDs can’t process task data comprehensively and they are required to cooperate quality assessment.Therefore,a blockchain-based framework for data quality in edge-computing-enabled crowdsensing(BFEC)is proposed in this paper.DPoR(Delegated Proof of Reputation),which is proposed in our previous work,is improved to be suitable in BFEC.Iteratively,the final result is calculated without revealing the privacy of participants.Experiments on the open datasets Adult,Blog,and Wine Quality show that our new framework outperforms existing methods in executing sensing tasks.展开更多
The rapid development of internet of things(loT)urgently needs edge miniaturized computing devices with high efficiency and low-power consumption.In-sensor computing has emerged as a promising technology to enable in-...The rapid development of internet of things(loT)urgently needs edge miniaturized computing devices with high efficiency and low-power consumption.In-sensor computing has emerged as a promising technology to enable in-situ data processing within the sensor array.Here,we report an optoelectronic array for in-sensor computing by integrating photodiodes(PDs)with resistive random-access memories(RRAMs).The PD-RRAM unit cell exhibits reconfigurable optoelectronic output and photo-responsivity by programming RRAMs into different resistance states.Furthermore,a 3×3 PD-RRAM array is fabricated to demonstrate optical image recognition,achieving a universal architecture with ultralow latency and low power consumption.This study highlights the great potential of the PD-RRAM optoelectronic array as an energy-effcient in-sensor computing primitive for future IoT applications.展开更多
To enable efficient and low-cost automated apple harvesting,this study presented a multi-class instance segmentation model,SCAL(Star-CAA-LADH),which utilizes a single RGB sensor for image acquisition.The model achieve...To enable efficient and low-cost automated apple harvesting,this study presented a multi-class instance segmentation model,SCAL(Star-CAA-LADH),which utilizes a single RGB sensor for image acquisition.The model achieves accurate segmentation of fruits,fruit-bearing branches,and main branches using only a single RGB image,providing comprehensive visual inputs for robotic harvesting.A Star-CAA module was proposed by integrating Star operation with a Context-Anchored Attention mechanism(CAA),enhancing directional sensitivity and multi-scale feature perception.The Backbone and Neck networks were equipped with hierarchically structured SCA-T/F modules to improve the fusion of highand low-level features,resulting in more continuous masks and sharper boundaries.In the Head network,a Segment_LADH module was employed to optimize classification,bounding box regression,and mask generation,thereby improving segmentation accuracy for small and adherent targets.To enhance robustness in adverse weather conditions,a Chain-of-Thought Prompted Adaptive Enhancer(CPA)module was integrated,thereby increasing model resilience in degraded environments.Experimental results demonstrate that SCAL achieves 94.9%AP_M and 95.1%mAP_M,outperforming YOLOv11s by 6.6%and 4.6%,respectively.Under multi-weather testing conditions,the CPA-SCAL variant consistently outperforms other comparison models in accuracy.After INT8 quantization,the model size was reduced to 14.5 MB,with an inference speed of 47.2 frames per second(fps)on the NVIDIA Jetson AGX Xavier.Experiments conducted in simulated orchard environments validate the effectiveness and generalization capabilities of the SCAL model,demonstrating its suitability as an efficient and comprehensive visual solution for intelligent harvesting in complex agricultural settings.展开更多
Federated Learning(FL)has emerged as a transformative paradigm in machine learning,advocating for decentralized,privacy-preserving model training.This study provides a comprehensive evaluation of contemporary FL frame...Federated Learning(FL)has emerged as a transformative paradigm in machine learning,advocating for decentralized,privacy-preserving model training.This study provides a comprehensive evaluation of contemporary FL frameworks–TensorFlow Federated(TFF),PySyft,and FedJAX–across three diverse datasets:CIFAR-10,IMDb reviews,and the UCI Heart Disease dataset.Our results demonstrate TFF's superior performance on image classification tasks,while PySyft excels in both efficiency and privacy for textual data.The study underscores the potential of FL in ensuring data privacy and model performance,yet emphasizes areas warranting improvement.As the volume of edge devices escalates and the need for data privacy intensifies,refining and expanding FL frameworks become essential for future machine learning deployments.展开更多
文摘Edge devices in Internet of Things(IoT)applications can form peers to communicate in peer-to-peer(P2P)networks over P2P protocols.Using P2P networks ensures scalability and removes the need for centralized management.However,due to the open nature of P2P networks,they often suffer from the existence of malicious peers,especially malicious peers that unite in groups to raise each other’s ratings.This compromises users’safety and makes them lose their confidence about the files or services they are receiving.To address these challenges,we propose a neural networkbased algorithm,which uses the advantages of a machine learning algorithm to identify whether or not a peer is malicious.In this paper,a neural network(NN)was chosen as the machine learning algorithm due to its efficiency in classification.The experiments showed that the NNTrust algorithm is more effective and has a higher potential of reducing the number of invalid files and increasing success rates than other well-known trust management systems.
基金The authors would like to thank for the support from Taif University Researchers Supporting Project number(TURSP-2020/98),Taif University,Taif,Saudi Arabia.
文摘Numerous Internet of Things(IoT)systems produce massive volumes of information that must be handled and answered in a quite short period.The growing energy usage related to the migration of data into the cloud is one of the biggest problems.Edge computation helps users unload the workload again from cloud near the source of the information that must be handled to save time,increase security,and reduce the congestion of networks.Therefore,in this paper,Optimized Energy Efficient Strategy(OEES)has been proposed for extracting,distributing,evaluating the data on the edge devices.In the initial stage of OEES,before the transmission state,the data gathered from edge devices are supported by a fast error like reduction that is regarded as the largest energy user of an IoT system.The initial stage is followed by the reconstructing and the processing state.The processed data is transmitted to the nodes through controlled deep learning techniques.The entire stage of data collection,transmission and data reduction between edge devices uses less energy.The experimental results indicate that the volume of data transferred decreases and does not impact the professional data performance and predictive accuracy.Energy consumption of 7.38 KJ and energy conservation of 55.57 kJ was found in the proposed OEES scheme.Predictive accuracy is 97.5 percent,data performance rate was 97.65 percent,and execution time is 14.49 ms.
文摘Industrial Internet of Things(IIoT)systems depend on a growing number of edge devices such as sensors,controllers,and robots for data collection,transmission,storage,and processing.Any kind of malicious or abnormal function by each of these devices can jeopardize the security of the entire IIoT.Moreover,they can allow malicious software installed on end nodes to penetrate the network.This paper presents a parallel ensemble model for threat hunting based on anomalies in the behavior of IIoT edge devices.The proposed model is flexible enough to use several state-of-the-art classifiers as the basic learner and efficiently classifies multi-class anomalies using the Multi-class AdaBoost and majority voting.Experimental evaluations using a dataset consisting of multi-source normal records and multi-class anomalies demonstrate that our model outperforms existing approaches in terms of accuracy,F1 score,recall,and precision.
基金supported by the National Natural Science Foundation of China[grant No.62163005,32401709]the Youth Science Foundation of Guangxi Province[grant No.2025GXNSFBA069270]+1 种基金the Natural Science Foundation of Guangxi Province[grant No.2022GXNSFAA035633]the Open Fund of the National Key Laboratory of Agricultural Equipment Technology(South China Agricultural University)[grant No.SKLAET-202407].
文摘The replacement of personal computer terminal with edge device is recognized as a portable and cost-effective potential solution in solving equipment miniaturization and achieving high flexibility of robotic fruit harvesting at in-field scale.This study proposes a lightweight improved You Only Look Once version 8n(YOLOv8n)model for detecting Orah fruits and deploying this model on an edge device.First of all,the model size was reduced while maintaining detection accuracy via the introduction of the ADown modules.Subsequently,a Concentrated-Comprehensive Dual Convolution(C3_DualConv)module combining dual convolutional bottlenecks was proposed to enhance the model capability to capture features of Orah fruits obscured by branches and leaves;this practice further reduced the model size.Additionally,a Bidirectional Feature Pyramid Network(BiFPN)that includes a pyramid level 2 high-resolution layer was employed for more efficient multi-scale feature fusion.Besides,three Coordinate Attention(CA)mechanism modules were also added to improve the recognition and capture capability for Orah fruit features.Finally,a more focused minimum points distance intersection over union loss was adopted to boost the detection efficiency of densely occluded Orah fruits.Experimentally demonstrating that the improved YOLOv8n model accurately detected Orah fruits in complex orchard environments,achieving a 97.7%of precision,an Average Precision at IoU threshold 0.5(AP@0.5)of 98.8%,and a 96.69%of F1 score,while maintaining a compact model size of 4.1 MB,under a Windows-based system terminal.This proposed model was optimally deployed on an Nvidia Jetson Orin Nano using TensorRT Python Application Programming Interface(API),the average interface speed exceeds 30 fps,indicating a real-time detection ability.This study can provide technical support for Orah fruit robotic harvesting on the basis of edge device.
基金supported by the National Natural Science Foundation of China(No.52004120).
文摘In a smart system, the faults of edge devices directly impact the system’s overall fault. Further, complexity arises when different edge devices provide varying fault data. To study the Smart System Fault Evolution Process (SSFEP) under different fault data conditions, an intelligent method for determining the Smart System Fault Probability (SSFP) is proposed. The data types provided by edge devices include the following: (1) only known edge device fault probability;(2) known Edge Device Fault Probability Distribution (EDFPD);(3) known edge device fault number and EDFPD;(4) known factor state of the edge device fault and EDFPD. Moreover, decision methods are proposed for each data case. Transfer Probability (TP) is divided into Continuity Transfer Probability (CTP) and Filterability Transfer Probability (FTP). CTP asserts that a Cause Event (CE) must lead to a Result Event (RE), while FTP requires CF probability to exceed a threshold before RF occurs. These probabilities are used to calculate SSFP. This paper introduces a decision method using the information diffusion principle for low-data SSFP determination, along with an improved method. The method is based on space fault network theory, abstracting SSFEP into a System Fault Evolution Process (SFEP) for research purposes.
文摘Edge technology aims to bring cloud resources(specifically,the computation,storage,and network)to the closed proximity of the edge devices,i.e.,smart devices where the data are produced and consumed.Embedding computing and application in edge devices lead to emerging of two new concepts in edge technology:edge computing and edge analytics.Edge analytics uses some techniques or algorithms to analyse the data generated by the edge devices.With the emerging of edge analytics,the edge devices have become a complete set.Currently,edge analytics is unable to provide full support to the analytic techniques.The edge devices cannot execute advanced and sophisticated analytic algorithms following various constraints such as limited power supply,small memory size,limited resources,etc.This article aims to provide a detailed discussion on edge analytics.The key contributions of the paper are as follows-a clear explanation to distinguish between the three concepts of edge technology:edge devices,edge computing,and edge analytics,along with their issues.In addition,the article discusses the implementation of edge analytics to solve many problems and applications in various areas such as retail,agriculture,industry,and healthcare.Moreover,the research papers of the state-of-the-art edge analytics are rigorously reviewed in this article to explore the existing issues,emerging challenges,research opportunities and their directions,and applications.
文摘Pedestrian detection has been a hot spot in computer vision over the past decades due to the wide spectrum of promising applications,and the major challenge is false positives that occur during pedestrian detection.The emergence of various Convolutional Neural Network-based detection strategies substantially enhances pedestrian detection accuracy but still does not solve this problem well.This paper deeply analyzes the detection framework of the two-stage CNN detection methods and finds out false positives in detection results are due to its training strategy misclassifying some false proposals,thus weakening the classification capability of the following subnetwork and hardly suppressing false ones.To solve this problem,this paper proposes a pedestrian-sensitive training algorithm to help two-stage CNN detection methods effectively learn to distinguish the pedestrian and non-pedestrian samples and suppress the false positives in the final detection results.The core of the proposed algorithm is to redesign the training proposal generating scheme for the two-stage CNN detection methods,which can avoid a certain number of false ones that mislead its training process.With the help of the proposed algorithm,the detection accuracy of the MetroNext,a smaller and more accurate metro passenger detector,is further improved,which further decreases false ones in its metro passenger detection results.Based on various challenging benchmark datasets,experiment results have demonstrated that the feasibility of the proposed algorithm is effective in improving pedestrian detection accuracy by removing false positives.Compared with the existing state-of-the-art detection networks,PSTNet demonstrates better overall prediction performance in accuracy,total number of parameters,and inference time;thus,it can become a practical solution for hunting pedestrians on various hardware platforms,especially for mobile and edge devices.
基金Project supported by the National Natural Science Foundation of China(No.62171182)the Natural Science Foundation of Chongqing,the Chongqing Science and Technology Commission(No.CSTB2022NSCQ-MSX0770)+1 种基金the Science and Technology Plan Project of Hunan Provincial Department of Transportation,China(No.202306)the Hunan Emergency Management Science and Technology Project(No.yjtkjxm_202407)。
文摘Trafic fow prediction is crucial for intelligent transportation and aids in route planning and navigation.However,existing studies often focus on prediction accuracy improvement,while neglecting external influences and practical issues like resource constraints and data sparsity on edge devices.We propose an online transfer learning(OTL)framework with a multi-layer perceptron(MLP)-assisted graph convolutional network(GCN),termed OTL-GM,which consists of two parts:transferring source-domain features to edge devices and using online learning to bridge domain gaps.Experiments on four data sets demonstrate OTL's effectiveness;in a comparison with models not using OTL,the reduction in the convergence time of the OTL models ranges from 24.77% to 95.32%.
基金the National Natural Science Foundation of China (No.51875335)。
文摘Conforming to the rapidly increasing market demand of crack detection for tall buildings,the idea of integrating deep network technology into wall-climbing robot for crack detection is put forward in this paper.Taking the dependence and hardware requirements when deployed on such edge devices as Raspberry Pi into consideration,the Darknet neural network is selected as the basic framework for detection.In order to improve the inference efficiency on edge devices and avoid the possible premature over-fitting of deep networks,the lite YOLOv4-tiny algorithm is then improved from the original YOLOv4-tiny algorithm and its structure is illustrated using Netron accordingly.The images downloaded from Internet and taken from the buildings in campus are processed to form crack detection data sets,which are trained on personal computer with the AlexeyAB version of Darknet to generate weight files.Meanwhile,the AlexeyAB version of Darknet accelerated by NNpack package is deployed on Raspberry Pi 4B,and the crack detection experiments are carried out.Some characteristics,e.g.,fast speed and lower false detection rate of the lite YOLOv4-tiny algorithm,are confirmed by comparison with those of original YOLOv4-tiny algorithm.The innovations of this paper focus on the simple network structure,fewer network layers,and earlier forward transmission of features to prevent over-fitting,showing the new lite neural network exceeds the original YOLOv4-tiny network significantly.
基金supported by the National Natural Science Foundation of China(62275130,62174089,62375125,and 61761136013)the Natural Science Foundation of Jiangsu Province(BK20240138)+1 种基金the Early Career Scheme(26210623)from the Hong Kong Research Grant Council and Postgraduate Research&Practice Innovation Program of Jiangsu Province(SJCX21_0249).
文摘As the demand for edge platforms in artificial intelligence increases,including mobile devices and security applications,the surge in data influx into edge devices often triggers interference and suboptimal decision-making.There is a pressing need for solutions emphasizing low power consumption and cost-effectiveness.In-sensor computing systems employing memristors face challenges in optimizing energy efficiency and streamlining manufacturing due to the necessity for multiple physical processing components.Here,we introduce low-power organic optoelectronic memristors with synergistic optical and mV-level electrical tunable operation for a dynamic“control-on-demand”architecture.Integrating signal sensing,featuring,and processing within the same memristors enables the realization of each in-sensor analogue reservoir computing module,and minimizes circuit integration complexity.The system achieves 97.15%fingerprint recognition accuracy while maintaining a minimal reservoir size and ultra-low energy consumption.Furthermore,we leverage wafer-scale solution techniques and flexible substrates for optimal memristor fabrication.By centralizing core functionalities on the same in-sensor platform,we propose a resilient and adaptable framework for energy-efficient and economical edge computing.
基金supported by the China National Key Research and Development Program(2018YFE0197700).
文摘The fifth-generation(5G)wireless communication networks are expected to play an essential role in the transformation of vertical industries.Among many exciting applications to be enabled by 5G,logistics tasks in industry parks can be performed more efficiently via vehicle-to-everything(V2X)communications.In this paper,a multi-layer collaboration framework enabled by V2X is proposed for logistics management in industrial parks.The proposed framework includes three layers:a perception and execution layer,a logistics layer,and a configuration layer.In addition to the collaboration among these three layers,this study addresses the collaboration among devices,edge servers,and cloud services.For effective logistics in industrial parks,task collaboration is achieved through four functions:environmental perception and map construction,task allocation,path planning,and vehicle movement.To dynamically coordinate these functions,device–edge–cloud collaboration,which is supported by 5G slices and V2X communication technology,is applied.Then,the analytical target cascading method is adopted to configure and evaluate the collaboration schemes of industrial parks.Finally,a logistics analytical case study in industrial parks is employed to demonstrate the feasibility of the proposed collaboration framework.
基金Project supported by the National Natural Science Foundation of China(Grant No.11653001)the National Basic Research Program of China(Grant No.2011CBA00304)Tsinghua University Initiative Scientific Research Program,China(Grant No.20131089314)
文摘The superconducting quantum interference device（SQUID） amplifier is widely used in the field of weak signal detection for its low input impedance, low noise, and low power consumption. In this paper, the SQUIDs with identical junctions and the series SQUIDs with different junctions were successfully fabricated. The Nb/Al-AlOx/Nb trilayer and input Nb coils were prepared by asputtering equipment. The SQUID devices were prepared by a sputtering and the lift-off method.Investigations by AFM, OM and SEM revealed the morphology and roughness of the Nb films and Nb/Al-AlOx/Nb trilayer.In addition, the current–voltage characteristics of the SQUID devices with identical junction and different junction areas were measured at 2.5 K in the He^3 refrigerator. The results show that the SQUID modulation depth is obviously affected by the junction area. The modulation depth obviously increases with the increase of the junction area in a certain range. It is found that the series SQUID with identical junction area has a transimpedance gain of 58 Ω approximately.
基金supported by the Key Science and Technology Project of Henan Province(201300210400)National Key Research and Development Project(2018YFB1800304)+1 种基金National Natural Science Foundation of China(61762058),Fundamental Research Funds for the Central Universities(xzy012020112)Natural Science Foundation of Gansu Province(21JR7RA282).
文摘With the rapid development of mobile technology and smart devices,crowdsensing has shown its large potential to collect massive data.Considering the limitation of calculation power,edge computing is introduced to release unnecessary data transmission.In edge-computing-enabled crowdsensing,massive data is required to be preliminary processed by edge computing devices(ECDs).Compared with the traditional central platform,these ECDs are limited by their own capability so they may only obtain part of relative factors and they can’t process data synthetically.ECDs involved in one task are required to cooperate to process the task data.The privacy of participants is important in crowdsensing,so blockchain is used due to its decentralization and tamperresistance.In crowdsensing tasks,it is usually difficult to obtain the assessment criteria in advance so reinforcement learning is introduced.As mentioned before,ECDs can’t process task data comprehensively and they are required to cooperate quality assessment.Therefore,a blockchain-based framework for data quality in edge-computing-enabled crowdsensing(BFEC)is proposed in this paper.DPoR(Delegated Proof of Reputation),which is proposed in our previous work,is improved to be suitable in BFEC.Iteratively,the final result is calculated without revealing the privacy of participants.Experiments on the open datasets Adult,Blog,and Wine Quality show that our new framework outperforms existing methods in executing sensing tasks.
基金the National Key Research and Development Program(2021YFA0716400)the National Natural Science Foundation of China(62225405,62350002,61991443,62127814,62235005,and 61927811)the Collaborative Innovation Center of Solid-State Lighting and Energy-Saving Electronics。
文摘The rapid development of internet of things(loT)urgently needs edge miniaturized computing devices with high efficiency and low-power consumption.In-sensor computing has emerged as a promising technology to enable in-situ data processing within the sensor array.Here,we report an optoelectronic array for in-sensor computing by integrating photodiodes(PDs)with resistive random-access memories(RRAMs).The PD-RRAM unit cell exhibits reconfigurable optoelectronic output and photo-responsivity by programming RRAMs into different resistance states.Furthermore,a 3×3 PD-RRAM array is fabricated to demonstrate optical image recognition,achieving a universal architecture with ultralow latency and low power consumption.This study highlights the great potential of the PD-RRAM optoelectronic array as an energy-effcient in-sensor computing primitive for future IoT applications.
基金supported by the Qinchuangyuan Project of Shaanxi Province(Grant No.2023KXJ-016).
文摘To enable efficient and low-cost automated apple harvesting,this study presented a multi-class instance segmentation model,SCAL(Star-CAA-LADH),which utilizes a single RGB sensor for image acquisition.The model achieves accurate segmentation of fruits,fruit-bearing branches,and main branches using only a single RGB image,providing comprehensive visual inputs for robotic harvesting.A Star-CAA module was proposed by integrating Star operation with a Context-Anchored Attention mechanism(CAA),enhancing directional sensitivity and multi-scale feature perception.The Backbone and Neck networks were equipped with hierarchically structured SCA-T/F modules to improve the fusion of highand low-level features,resulting in more continuous masks and sharper boundaries.In the Head network,a Segment_LADH module was employed to optimize classification,bounding box regression,and mask generation,thereby improving segmentation accuracy for small and adherent targets.To enhance robustness in adverse weather conditions,a Chain-of-Thought Prompted Adaptive Enhancer(CPA)module was integrated,thereby increasing model resilience in degraded environments.Experimental results demonstrate that SCAL achieves 94.9%AP_M and 95.1%mAP_M,outperforming YOLOv11s by 6.6%and 4.6%,respectively.Under multi-weather testing conditions,the CPA-SCAL variant consistently outperforms other comparison models in accuracy.After INT8 quantization,the model size was reduced to 14.5 MB,with an inference speed of 47.2 frames per second(fps)on the NVIDIA Jetson AGX Xavier.Experiments conducted in simulated orchard environments validate the effectiveness and generalization capabilities of the SCAL model,demonstrating its suitability as an efficient and comprehensive visual solution for intelligent harvesting in complex agricultural settings.
文摘Federated Learning(FL)has emerged as a transformative paradigm in machine learning,advocating for decentralized,privacy-preserving model training.This study provides a comprehensive evaluation of contemporary FL frameworks–TensorFlow Federated(TFF),PySyft,and FedJAX–across three diverse datasets:CIFAR-10,IMDb reviews,and the UCI Heart Disease dataset.Our results demonstrate TFF's superior performance on image classification tasks,while PySyft excels in both efficiency and privacy for textual data.The study underscores the potential of FL in ensuring data privacy and model performance,yet emphasizes areas warranting improvement.As the volume of edge devices escalates and the need for data privacy intensifies,refining and expanding FL frameworks become essential for future machine learning deployments.
