Organic electrochemical transistor(OECT)devices demonstrate great promising potential for reservoir computing(RC)systems,but their lack of tunable dynamic characteristics limits their application in multi-temporal sca...Organic electrochemical transistor(OECT)devices demonstrate great promising potential for reservoir computing(RC)systems,but their lack of tunable dynamic characteristics limits their application in multi-temporal scale tasks.In this study,we report an OECT-based neuromorphic device with tunable relaxation time(τ)by introducing an additional vertical back-gate electrode into a planar structure.The dual-gate design enablesτreconfiguration from 93 to 541 ms.The tunable relaxation behaviors can be attributed to the combined effects of planar-gate induced electrochemical doping and back-gateinduced electrostatic coupling,as verified by electrochemical impedance spectroscopy analysis.Furthermore,we used theτ-tunable OECT devices as physical reservoirs in the RC system for intelligent driving trajectory prediction,achieving a significant improvement in prediction accuracy from below 69%to 99%.The results demonstrate that theτ-tunable OECT shows a promising candidate for multi-temporal scale neuromorphic computing applications.展开更多
Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrain...Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively.展开更多
In the field of edge computing,achieving low-latency computational task offloading with limited resources is a critical research challenge,particularly in resource-constrained and latency-sensitive vehicular network e...In the field of edge computing,achieving low-latency computational task offloading with limited resources is a critical research challenge,particularly in resource-constrained and latency-sensitive vehicular network environments where rapid response is mandatory for safety-critical applications.In scenarios where edge servers are sparsely deployed,the lack of coordination and information sharing often leads to load imbalance,thereby increasing system latency.Furthermore,in regions without edge server coverage,tasks must be processed locally,which further exacerbates latency issues.To address these challenges,we propose a novel and efficient Deep Reinforcement Learning(DRL)-based approach aimed at minimizing average task latency.The proposed method incorporates three offloading strategies:local computation,direct offloading to the edge server in local region,and device-to-device(D2D)-assisted offloading to edge servers in other regions.We formulate the task offloading process as a complex latency minimization optimization problem.To solve it,we propose an advanced algorithm based on the Dueling Double Deep Q-Network(D3QN)architecture and incorporating the Prioritized Experience Replay(PER)mechanism.Experimental results demonstrate that,compared with existing offloading algorithms,the proposed method significantly reduces average task latency,enhances user experience,and offers an effective strategy for latency optimization in future edge computing systems under dynamic workloads.展开更多
This work presents a high-stability self-rectifying memristor(SRM)array based on the Pt/TaO_(x)/Ti structure,with an indepth investigation of the performance and potential applications of the device.The device demonst...This work presents a high-stability self-rectifying memristor(SRM)array based on the Pt/TaO_(x)/Ti structure,with an indepth investigation of the performance and potential applications of the device.The device demonstrates excellent rectification and on/off ratios,along with low-power readout,multi-state storage,and multi-level switching capabilities,highlighting its practicality and adaptability.Notably,the device exhibits outstanding fluctuation suppression and exceptional uniformity.The coefficient of variation(CV)of the rectification ratio,calculated as 0.11497 at 3 V,indicates its high stability under multiple cycles and low-voltage operation,making it well-suited for large-scale integration and operational applications.Moreover,the stability of the rectification ratio further reinforces its potential as a hardware foundation for large-scale inmemory computing systems.By combining the neuromorphic characteristics of the device with a simulated annealing algorithm and optimizing the annealing temperature function,the system emulates biological neuron behavior,enabling fast and efficient image restoration tasks.Experimental results demonstrate that this approach significantly outperforms traditional algorithms in both optimization speed and repair accuracy.The present study offers a novel perspective for the design of in-memory computing hardware and showcases promising applications in neuromorphic computing and image processing.展开更多
As emerging two-dimensional(2D)materials,carbides and nitrides(MXenes)could be solid solutions or organized structures made up of multi-atomic layers.With remarkable and adjustable electrical,optical,mechanical,and el...As emerging two-dimensional(2D)materials,carbides and nitrides(MXenes)could be solid solutions or organized structures made up of multi-atomic layers.With remarkable and adjustable electrical,optical,mechanical,and electrochemical characteristics,MXenes have shown great potential in brain-inspired neuromorphic computing electronics,including neuromorphic gas sensors,pressure sensors and photodetectors.This paper provides a forward-looking review of the research progress regarding MXenes in the neuromorphic sensing domain and discussed the critical challenges that need to be resolved.Key bottlenecks such as insufficient long-term stability under environmental exposure,high costs,scalability limitations in large-scale production,and mechanical mismatch in wearable integration hinder their practical deployment.Furthermore,unresolved issues like interfacial compatibility in heterostructures and energy inefficiency in neu-romorphic signal conversion demand urgent attention.The review offers insights into future research directions enhance the fundamental understanding of MXene properties and promote further integration into neuromorphic computing applications through the convergence with various emerging technologies.展开更多
High-entropy oxides(HEOs)have emerged as a promising class of memristive materials,characterized by entropy-stabilized crystal structures,multivalent cation coordination,and tunable defect landscapes.These intrinsic f...High-entropy oxides(HEOs)have emerged as a promising class of memristive materials,characterized by entropy-stabilized crystal structures,multivalent cation coordination,and tunable defect landscapes.These intrinsic features enable forming-free resistive switching,multilevel conductance modulation,and synaptic plasticity,making HEOs attractive for neuromorphic computing.This review outlines recent progress in HEO-based memristors across materials engineering,switching mechanisms,and synaptic emulation.Particular attention is given to vacancy migration,phase transitions,and valence-state dynamics—mechanisms that underlie the switching behaviors observed in both amorphous and crystalline systems.Their relevance to neuromorphic functions such as short-term plasticity and spike-timing-dependent learning is also examined.While encouraging results have been achieved at the device level,challenges remain in conductance precision,variability control,and scalable integration.Addressing these demands a concerted effort across materials design,interface optimization,and task-aware modeling.With such integration,HEO memristors offer a compelling pathway toward energy-efficient and adaptable brain-inspired electronics.展开更多
The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,fle...The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,flexible memristors exhibit great application potential in emulating artificial synapses for highefficiency and low power consumption neuromorphic computing.This paper provides comprehensive overview of flexible memristors from perspectives of development history,material system,device structure,mechanical deformation method,device performance analysis,stress simulation during deformation,and neuromorphic computing applications.The recent advances in flexible electronics are summarized,including single device,device array and integration.The challenges and future perspectives of flexible memristor for neuromorphic computing are discussed deeply,paving the way for constructing wearable smart electronics and applications in large-scale neuromorphic computing and high-order intelligent robotics.展开更多
Beam-tracking simulations have been extensively utilized in the study of collective beam instabilities in circular accelerators.Traditionally,many simulation codes have relied on central processing unit(CPU)-based met...Beam-tracking simulations have been extensively utilized in the study of collective beam instabilities in circular accelerators.Traditionally,many simulation codes have relied on central processing unit(CPU)-based methods,tracking on a single CPU core,or parallelizing the computation across multiple cores via the message passing interface(MPI).Although these approaches work well for single-bunch tracking,scaling them to multiple bunches significantly increases the computational load,which often necessitates the use of a dedicated multi-CPU cluster.To address this challenge,alternative methods leveraging General-Purpose computing on Graphics Processing Units(GPGPU)have been proposed,enabling tracking studies on a standalone desktop personal computer(PC).However,frequent CPU-GPU interactions,including data transfers and synchronization operations during tracking,can introduce communication overheads,potentially reducing the overall effectiveness of GPU-based computations.In this study,we propose a novel approach that eliminates this overhead by performing the entire tracking simulation process exclusively on the GPU,thereby enabling the simultaneous processing of all bunches and their macro-particles.Specifically,we introduce MBTRACK2-CUDA,a Compute Unified Device Architecture(CUDA)ported version of MBTRACK2,which facilitates efficient tracking of single-and multi-bunch collective effects by leveraging the full GPU-resident computation.展开更多
BACKGROUND Early screening,preoperative staging,and diagnosis of lymph node metastasis are crucial for improving the prognosis of gastric cancer(GC).AIM To evaluate the diagnostic value of combined multidetector compu...BACKGROUND Early screening,preoperative staging,and diagnosis of lymph node metastasis are crucial for improving the prognosis of gastric cancer(GC).AIM To evaluate the diagnostic value of combined multidetector computed tomography(MDCT)and gastrointestinal endoscopy for GC screening,preoperative staging,and lymph node metastasis detection,thereby providing a reference for clinical diagnosis and treatment.METHODS In this retrospective study clinical and imaging data of 134 patients with suspected GC who were admitted between January 2023 and October 2024 were initially reviewed.According to the inclusion and exclusion criteria,102 patients were finally enrolled in the analysis.All enrolled patients had undergone both MDCT and gastrointestinal endoscopy examinations prior to surgical intervention.Preoperative clinical staging and lymph node metastasis findings were compared with pathological results.RESULTS The combined use of MDCT and gastrointestinal endoscopy demonstrated a sensitivity of 98.53%,specificity of 97.06%,accuracy of 98.04%,positive predictive value of 98.53%,and negative predictive value of 97.06%for diagnosing GC.These factors were all significantly higher than those of MDCT or endoscopy alone(P<0.05).The accuracy rates of the combined approach for detecting clinical T and N stages were 97.06%and 92.65%,respectively,outperforming MDCT alone(86.76% and 79.41%)and endoscopy alone(85.29% and 70.59%)(P<0.05).Among 68 patients with confirmed GC,50(73.53%)were pathologically diagnosed with lymph node metastasis.The accuracy for detecting lymph node metastasis was 66.00%with endoscopy,76.00%with MDCT,and 92.00% with the combined approach,all with statistically significant differences(P<0.05).CONCLUSION The combined application of MDCT and gastrointestinal endoscopy enhanced diagnostic accuracy for GC,provided greater consistency in preoperative staging,and improved the detection of lymph node metastasis,thereby demonstrating significant clinical utility.展开更多
Neuromorphic devices have garnered significant attention as potential building blocks for energy-efficient hardware systems owing to their capacity to emulate the computational efficiency of the brain.In this regard,r...Neuromorphic devices have garnered significant attention as potential building blocks for energy-efficient hardware systems owing to their capacity to emulate the computational efficiency of the brain.In this regard,reservoir computing(RC)framework,which leverages straightforward training methods and efficient temporal signal processing,has emerged as a promising scheme.While various physical reservoir devices,including ferroelectric,optoelectronic,and memristor-based systems,have been demonstrated,many still face challenges related to compatibility with mainstream complementary metal oxide semiconductor(CMOS)integration processes.This study introduced a silicon-based schottky barrier metal-oxide-semiconductor field effect transistor(SB-MOSFET),which was fabricated under low thermal budget and compatible with back-end-of-line(BEOL).The device demonstrated short-term memory characteristics,facilitated by the modulation of schottky barriers and charge trapping.Utilizing these characteristics,a RC system for temporal data processing was constructed,and its performance was validated in a 5×4 digital classification task,achieving an accuracy exceeding 98%after 50 training epochs.Furthermore,the system successfully processed temporal signal in waveform classification and prediction tasks using time-division multiplexing.Overall,the SB-MOSFET's high compatibility with CMOS technology provides substantial advantages for large-scale integration,enabling the development of energy-efficient reservoir computing hardware.展开更多
As Internet of Things(IoT)applications expand,Mobile Edge Computing(MEC)has emerged as a promising architecture to overcome the real-time processing limitations of mobile devices.Edge-side computation offloading plays...As Internet of Things(IoT)applications expand,Mobile Edge Computing(MEC)has emerged as a promising architecture to overcome the real-time processing limitations of mobile devices.Edge-side computation offloading plays a pivotal role in MEC performance but remains challenging due to complex task topologies,conflicting objectives,and limited resources.This paper addresses high-dimensional multi-objective offloading for serial heterogeneous tasks in MEC.We jointly consider task heterogeneity,high-dimensional objectives,and flexible resource scheduling,modeling the problem as a Many-objective optimization.To solve it,we propose a flexible framework integrating an improved cooperative co-evolutionary algorithm based on decomposition(MOCC/D)and a flexible scheduling strategy.Experimental results on benchmark functions and simulation scenarios show that the proposed method outperforms existing approaches in both convergence and solution quality.展开更多
This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagno...This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.展开更多
Classical computation of electronic properties in large-scale materials remains challenging.Quantum computation has the potential to offer advantages in memory footprint and computational scaling.However,general and v...Classical computation of electronic properties in large-scale materials remains challenging.Quantum computation has the potential to offer advantages in memory footprint and computational scaling.However,general and viable quantum algorithms for simulating large-scale materials are still limited.We propose and implement random-state quantum algorithms to calculate electronic-structure properties of real materials.Using a random state circuit on a small number of qubits,we employ real-time evolution with first-order Trotter decomposition and Hadamard test to obtain electronic density of states,and we develop a modified quantum phase estimation algorithm to calculate real-space local density of states via direct quantum measurements.Furthermore,we validate these algorithms by numerically computing the density of states and spatial distributions of electronic states in graphene,twisted bilayer graphene quasicrystals,and fractal lattices,covering system sizes from hundreds to thousands of atoms.Our results manifest that the random-state quantum algorithms provide a general and qubit-efficient route to scalable simulations of electronic properties in large-scale periodic and aperiodic materials.展开更多
Satellite edge computing has garnered significant attention from researchers;however,processing a large volume of tasks within multi-node satellite networks still poses considerable challenges.The sharp increase in us...Satellite edge computing has garnered significant attention from researchers;however,processing a large volume of tasks within multi-node satellite networks still poses considerable challenges.The sharp increase in user demand for latency-sensitive tasks has inevitably led to offloading bottlenecks and insufficient computational capacity on individual satellite edge servers,making it necessary to implement effective task offloading scheduling to enhance user experience.In this paper,we propose a priority-based task scheduling strategy based on a Software-Defined Network(SDN)framework for satellite-terrestrial integrated networks,which clarifies the execution order of tasks based on their priority.Subsequently,we apply a Dueling-Double Deep Q-Network(DDQN)algorithm enhanced with prioritized experience replay to derive a computation offloading strategy,improving the experience replay mechanism within the Dueling-DDQN framework.Next,we utilize the Deep Deterministic Policy Gradient(DDPG)algorithm to determine the optimal resource allocation strategy to reduce the processing latency of sub-tasks.Simulation results demonstrate that the proposed d3-DDPG algorithm outperforms other approaches,effectively reducing task processing latency and thus improving user experience and system efficiency.展开更多
The purpose of this review is to explore the intersection of computational engineering and biomedical science,highlighting the transformative potential this convergence holds for innovation in healthcare and medical r...The purpose of this review is to explore the intersection of computational engineering and biomedical science,highlighting the transformative potential this convergence holds for innovation in healthcare and medical research.The review covers key topics such as computational modelling,bioinformatics,machine learning in medical diagnostics,and the integration of wearable technology for real-time health monitoring.Major findings indicate that computational models have significantly enhanced the understanding of complex biological systems,while machine learning algorithms have improved the accuracy of disease prediction and diagnosis.The synergy between bioinformatics and computational techniques has led to breakthroughs in personalized medicine,enabling more precise treatment strategies.Additionally,the integration of wearable devices with advanced computational methods has opened new avenues for continuous health monitoring and early disease detection.The review emphasizes the need for interdisciplinary collaboration to further advance this field.Future research should focus on developing more robust and scalable computational models,enhancing data integration techniques,and addressing ethical considerations related to data privacy and security.By fostering innovation at the intersection of these disciplines,the potential to revolutionize healthcare delivery and outcomes becomes increasingly attainable.展开更多
Photon-counting computed tomography(PCCT)represents a significant advancement in pediatric cardiovascular imaging.Traditional CT systems employ energy-integrating detectors that convert X-ray photons into visible ligh...Photon-counting computed tomography(PCCT)represents a significant advancement in pediatric cardiovascular imaging.Traditional CT systems employ energy-integrating detectors that convert X-ray photons into visible light,whereas PCCT utilizes photon-counting detectors that directly transform X-ray photons into electric signals.This direct conversion allows photon-counting detectors to sort photons into discrete energy levels,thereby enhancing image quality through superior noise reduction,improved spatial and contrast resolution,and reduced artifacts.In pediatric applications,PCCT offers substantial benefits,including lower radiation doses,which may help reduce the risk of malignancy in pediatric patients,with perhaps greater potential to benefit those with repeated exposure from a young age.Enhanced spatial resolution facilitates better visualization of small structures,vital for diagnosing congenital heart defects.Additionally,PCCT’s spectral capabilities improve tissue characterization and enable the creation of virtual monoenergetic images,which enhance soft-tissue contrast and potentially reduce contrast media doses.Initial clinical results indicate that PCCT provides superior image quality and diagnostic accuracy compared to conven-tional CT,particularly in challenging pediatric cardiovascular cases.As PCCT technology matures,further research and standardized protocols will be essential to fully integrate it into pediatric imaging practices,ensuring optimized diagnostic outcomes and patient safety.展开更多
Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While suc...Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While such a computing paradigm can only employ a single photonic device as the nonlinear node for data processing,the performance highly relies on the fading memory provided by the delay feedback loop(FL),which sets a restriction on the extensibility of physical implementation,especially for highly integrated chips.Here,we present a simplified photonic scheme for more flexible parameter configurations leveraging the designed quasi-convolution coding(QC),which completely gets rid of the dependence on FL.Unlike delay-based TDRC,encoded data in QC-based RC(QRC)enables temporal feature extraction,facilitating augmented memory capabilities.Thus,our proposed QRC is enabled to deal with time-related tasks or sequential data without the implementation of FL.Furthermore,we can implement this hardware with a low-power,easily integrable vertical-cavity surface-emitting laser for high-performance parallel processing.We illustrate the concept validation through simulation and experimental comparison of QRC and TDRC,wherein the simpler-structured QRC outperforms across various benchmark tasks.Our results may underscore an auspicious solution for the hardware implementation of deep neural networks.展开更多
Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic ...Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic functions,i.e.,excita-tory post-synaptic current and pair-pulse facilitation are successfully mimicked with the memristor under electrical and optical stimulations.More importantly,the device exhibited distinguishable response currents by adjusting 4-bit input electrical/opti-cal signals.A multi-mode reservoir computing(RC)system is constructed with the optoelectronic memristors to emulate human tactile-visual fusion recognition and an accuracy of 98.7%is achieved.The optoelectronic memristor provides potential for developing multi-mode RC system.展开更多
As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the...As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the task offloading strategies by interacting with the entities. In actual application scenarios, users of edge computing are always changing dynamically. However, the existing task offloading strategies cannot be applied to such dynamic scenarios. To solve this problem, we propose a novel dynamic task offloading framework for distributed edge computing, leveraging the potential of meta-reinforcement learning (MRL). Our approach formulates a multi-objective optimization problem aimed at minimizing both delay and energy consumption. We model the task offloading strategy using a directed acyclic graph (DAG). Furthermore, we propose a distributed edge computing adaptive task offloading algorithm rooted in MRL. This algorithm integrates multiple Markov decision processes (MDP) with a sequence-to-sequence (seq2seq) network, enabling it to learn and adapt task offloading strategies responsively across diverse network environments. To achieve joint optimization of delay and energy consumption, we incorporate the non-dominated sorting genetic algorithm II (NSGA-II) into our framework. Simulation results demonstrate the superiority of our proposed solution, achieving a 21% reduction in time delay and a 19% decrease in energy consumption compared to alternative task offloading schemes. Moreover, our scheme exhibits remarkable adaptability, responding swiftly to changes in various network environments.展开更多
As the demand for advanced computational systems capable of handling large data volumes rises,nano-electronic devices,such as memristors,are being developed for efficient data processing,especially in reservoir comput...As the demand for advanced computational systems capable of handling large data volumes rises,nano-electronic devices,such as memristors,are being developed for efficient data processing,especially in reservoir computing(RC).RC enables the processing of temporal information with minimal training costs,making it a promising approach for neuromorphic computing.However,current memristor devices of-ten suffer from limitations in dynamic conductance and temporal behavior,which affects their perfor-mance in these applications.In this study,we present a multilayered indium-tin-oxide(ITO)/ZnO/indium-gallium-zinc oxide(IGZO)/ZnO/ITO memristor fabricated via radiofrequency sputtering to explore its fil-amentary and nonfilamentary resistive switching(RS)characteristics.High-resolution transmission elec-tron microscopy confirmed the polycrystalline structure of the ZnO/IGZO/ZnO active layer.Dual-switching modes were demonstrated by controlling the current compliance(I_(CC)).In the filamentary mode,the memristor exhibited a large memory window(10^(3)),low-operating voltages(±2 V),excellent cycle-to-cycle stability,and multilevel switching with controlled reset-stop voltages,making it suitable for high-density memory applications.Nonfilamentary switching demonstrated stable on/off ratios above 10,en-durance up to 102 cycles,and retention suited for short-term memory.Key synaptic behaviors,such as paired-pulse facilitation(PPF),post-tetanic potentiation(PTP),and spike-rate dependent plasticity(SRDP)were successfully emulated by modulating pulse amplitude,width,and interval.Experience-dependent plasticity(EDP)was also demonstrated,further replicating biological synaptic functions.These tempo-ral properties were utilized to develop a 4-bit reservoir computing system with 16 distinct conductance states,enabling efficient information encoding.For image recognition tasks,convolutional neural net-work(CNN)simulations achieved a high accuracy of 98.45%after 25 training epochs,outperforming the accuracy achieved following artificial neural network(ANN)simulations(87.79%).These findings demon-strate that the multilayered memristor exhibits high performance in neuromorphic systems,particularly for complex pattern recognition tasks,such as digit and letter classification.展开更多
基金supported by the National Key Research and Development Program of China under Grant 2022YFB3608300in part by the National Nature Science Foundation of China(NSFC)under Grants 62404050,U2341218,62574056,62204052。
文摘Organic electrochemical transistor(OECT)devices demonstrate great promising potential for reservoir computing(RC)systems,but their lack of tunable dynamic characteristics limits their application in multi-temporal scale tasks.In this study,we report an OECT-based neuromorphic device with tunable relaxation time(τ)by introducing an additional vertical back-gate electrode into a planar structure.The dual-gate design enablesτreconfiguration from 93 to 541 ms.The tunable relaxation behaviors can be attributed to the combined effects of planar-gate induced electrochemical doping and back-gateinduced electrostatic coupling,as verified by electrochemical impedance spectroscopy analysis.Furthermore,we used theτ-tunable OECT devices as physical reservoirs in the RC system for intelligent driving trajectory prediction,achieving a significant improvement in prediction accuracy from below 69%to 99%.The results demonstrate that theτ-tunable OECT shows a promising candidate for multi-temporal scale neuromorphic computing applications.
基金supported by Key Science and Technology Program of Henan Province,China(Grant Nos.242102210147,242102210027)Fujian Province Young and Middle aged Teacher Education Research Project(Science and Technology Category)(No.JZ240101)(Corresponding author:Dong Yuan).
文摘Vehicle Edge Computing(VEC)and Cloud Computing(CC)significantly enhance the processing efficiency of delay-sensitive and computation-intensive applications by offloading compute-intensive tasks from resource-constrained onboard devices to nearby Roadside Unit(RSU),thereby achieving lower delay and energy consumption.However,due to the limited storage capacity and energy budget of RSUs,it is challenging to meet the demands of the highly dynamic Internet of Vehicles(IoV)environment.Therefore,determining reasonable service caching and computation offloading strategies is crucial.To address this,this paper proposes a joint service caching scheme for cloud-edge collaborative IoV computation offloading.By modeling the dynamic optimization problem using Markov Decision Processes(MDP),the scheme jointly optimizes task delay,energy consumption,load balancing,and privacy entropy to achieve better quality of service.Additionally,a dynamic adaptive multi-objective deep reinforcement learning algorithm is proposed.Each Double Deep Q-Network(DDQN)agent obtains rewards for different objectives based on distinct reward functions and dynamically updates the objective weights by learning the value changes between objectives using Radial Basis Function Networks(RBFN),thereby efficiently approximating the Pareto-optimal decisions for multiple objectives.Extensive experiments demonstrate that the proposed algorithm can better coordinate the three-tier computing resources of cloud,edge,and vehicles.Compared to existing algorithms,the proposed method reduces task delay and energy consumption by 10.64%and 5.1%,respectively.
基金supported by the National Natural Science Foundation of China(62202215)Liaoning Province Applied Basic Research Program(Youth Special Project,2023JH2/101600038)+4 种基金Shenyang Youth Science and Technology Innovation Talent Support Program(RC220458)Guangxuan Program of Shenyang Ligong University(SYLUGXRC202216)the Basic Research Special Funds for Undergraduate Universities in Liaoning Province(LJ212410144067)the Natural Science Foundation of Liaoning Province(2024-MS-113)the science and technology funds from Liaoning Education Department(LJKZ0242).
文摘In the field of edge computing,achieving low-latency computational task offloading with limited resources is a critical research challenge,particularly in resource-constrained and latency-sensitive vehicular network environments where rapid response is mandatory for safety-critical applications.In scenarios where edge servers are sparsely deployed,the lack of coordination and information sharing often leads to load imbalance,thereby increasing system latency.Furthermore,in regions without edge server coverage,tasks must be processed locally,which further exacerbates latency issues.To address these challenges,we propose a novel and efficient Deep Reinforcement Learning(DRL)-based approach aimed at minimizing average task latency.The proposed method incorporates three offloading strategies:local computation,direct offloading to the edge server in local region,and device-to-device(D2D)-assisted offloading to edge servers in other regions.We formulate the task offloading process as a complex latency minimization optimization problem.To solve it,we propose an advanced algorithm based on the Dueling Double Deep Q-Network(D3QN)architecture and incorporating the Prioritized Experience Replay(PER)mechanism.Experimental results demonstrate that,compared with existing offloading algorithms,the proposed method significantly reduces average task latency,enhances user experience,and offers an effective strategy for latency optimization in future edge computing systems under dynamic workloads.
基金the National Natural Science Foundation of China(No.U23A20322)the National Key Research and Development Program of China(Nos.2023YFF0719600,2021YFA1202600,and 2021YFB4000800)+4 种基金the CAS Project for Young Scientists in Basic Research(No.YSBR-113)the Ningbo Technology Project(No.2022A-007-C)the Hunan Provincial Natural Science Foundation(Nos.2023JJ50009,2025JJ60351,and 2023JJ30599)the Foundation of Innovation Center of Radiation Application(No.KFZC2023020701)the Major Scientific and Technological Innovation Platform Project of Hunan Province(No.2024JC1003).
文摘This work presents a high-stability self-rectifying memristor(SRM)array based on the Pt/TaO_(x)/Ti structure,with an indepth investigation of the performance and potential applications of the device.The device demonstrates excellent rectification and on/off ratios,along with low-power readout,multi-state storage,and multi-level switching capabilities,highlighting its practicality and adaptability.Notably,the device exhibits outstanding fluctuation suppression and exceptional uniformity.The coefficient of variation(CV)of the rectification ratio,calculated as 0.11497 at 3 V,indicates its high stability under multiple cycles and low-voltage operation,making it well-suited for large-scale integration and operational applications.Moreover,the stability of the rectification ratio further reinforces its potential as a hardware foundation for large-scale inmemory computing systems.By combining the neuromorphic characteristics of the device with a simulated annealing algorithm and optimizing the annealing temperature function,the system emulates biological neuron behavior,enabling fast and efficient image restoration tasks.Experimental results demonstrate that this approach significantly outperforms traditional algorithms in both optimization speed and repair accuracy.The present study offers a novel perspective for the design of in-memory computing hardware and showcases promising applications in neuromorphic computing and image processing.
基金supported by the NSFC(12474071)Natural Science Foundation of Shandong Province(ZR2024YQ051,ZR2025QB50)+6 种基金Guangdong Basic and Applied Basic Research Foundation(2025A1515011191)the Shanghai Sailing Program(23YF1402200,23YF1402400)funded by Basic Research Program of Jiangsu(BK20240424)Open Research Fund of State Key Laboratory of Crystal Materials(KF2406)Taishan Scholar Foundation of Shandong Province(tsqn202408006,tsqn202507058)Young Talent of Lifting engineering for Science and Technology in Shandong,China(SDAST2024QTB002)the Qilu Young Scholar Program of Shandong University。
文摘As emerging two-dimensional(2D)materials,carbides and nitrides(MXenes)could be solid solutions or organized structures made up of multi-atomic layers.With remarkable and adjustable electrical,optical,mechanical,and electrochemical characteristics,MXenes have shown great potential in brain-inspired neuromorphic computing electronics,including neuromorphic gas sensors,pressure sensors and photodetectors.This paper provides a forward-looking review of the research progress regarding MXenes in the neuromorphic sensing domain and discussed the critical challenges that need to be resolved.Key bottlenecks such as insufficient long-term stability under environmental exposure,high costs,scalability limitations in large-scale production,and mechanical mismatch in wearable integration hinder their practical deployment.Furthermore,unresolved issues like interfacial compatibility in heterostructures and energy inefficiency in neu-romorphic signal conversion demand urgent attention.The review offers insights into future research directions enhance the fundamental understanding of MXene properties and promote further integration into neuromorphic computing applications through the convergence with various emerging technologies.
基金financially supported by the National Natural Science Foundation of China(Grant No.12172093)the Guangdong Basic and Applied Basic Research Foundation(Grant No.2021A1515012607)。
文摘High-entropy oxides(HEOs)have emerged as a promising class of memristive materials,characterized by entropy-stabilized crystal structures,multivalent cation coordination,and tunable defect landscapes.These intrinsic features enable forming-free resistive switching,multilevel conductance modulation,and synaptic plasticity,making HEOs attractive for neuromorphic computing.This review outlines recent progress in HEO-based memristors across materials engineering,switching mechanisms,and synaptic emulation.Particular attention is given to vacancy migration,phase transitions,and valence-state dynamics—mechanisms that underlie the switching behaviors observed in both amorphous and crystalline systems.Their relevance to neuromorphic functions such as short-term plasticity and spike-timing-dependent learning is also examined.While encouraging results have been achieved at the device level,challenges remain in conductance precision,variability control,and scalable integration.Addressing these demands a concerted effort across materials design,interface optimization,and task-aware modeling.With such integration,HEO memristors offer a compelling pathway toward energy-efficient and adaptable brain-inspired electronics.
基金supported by the NSFC(12474071)Natural Science Foundation of Shandong Province(ZR2024YQ051)+5 种基金Open Research Fund of State Key Laboratory of Materials for Integrated Circuits(SKLJC-K2024-12)the Shanghai Sailing Program(23YF1402200,23YF1402400)Natural Science Foundation of Jiangsu Province(BK20240424)Taishan Scholar Foundation of Shandong Province(tsqn202408006)Young Talent of Lifting engineering for Science and Technology in Shandong,China(SDAST2024QTB002)the Qilu Young Scholar Program of Shandong University.
文摘The advancement of flexible memristors has significantly promoted the development of wearable electronic for emerging neuromorphic computing applications.Inspired by in-memory computing architecture of human brain,flexible memristors exhibit great application potential in emulating artificial synapses for highefficiency and low power consumption neuromorphic computing.This paper provides comprehensive overview of flexible memristors from perspectives of development history,material system,device structure,mechanical deformation method,device performance analysis,stress simulation during deformation,and neuromorphic computing applications.The recent advances in flexible electronics are summarized,including single device,device array and integration.The challenges and future perspectives of flexible memristor for neuromorphic computing are discussed deeply,paving the way for constructing wearable smart electronics and applications in large-scale neuromorphic computing and high-order intelligent robotics.
基金supported by the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(MSIT)(No.RS-2022-00143178)the Ministry of Education(MOE)(Nos.2022R1A6A3A13053896 and 2022R1F1A1074616),Republic of Korea.
文摘Beam-tracking simulations have been extensively utilized in the study of collective beam instabilities in circular accelerators.Traditionally,many simulation codes have relied on central processing unit(CPU)-based methods,tracking on a single CPU core,or parallelizing the computation across multiple cores via the message passing interface(MPI).Although these approaches work well for single-bunch tracking,scaling them to multiple bunches significantly increases the computational load,which often necessitates the use of a dedicated multi-CPU cluster.To address this challenge,alternative methods leveraging General-Purpose computing on Graphics Processing Units(GPGPU)have been proposed,enabling tracking studies on a standalone desktop personal computer(PC).However,frequent CPU-GPU interactions,including data transfers and synchronization operations during tracking,can introduce communication overheads,potentially reducing the overall effectiveness of GPU-based computations.In this study,we propose a novel approach that eliminates this overhead by performing the entire tracking simulation process exclusively on the GPU,thereby enabling the simultaneous processing of all bunches and their macro-particles.Specifically,we introduce MBTRACK2-CUDA,a Compute Unified Device Architecture(CUDA)ported version of MBTRACK2,which facilitates efficient tracking of single-and multi-bunch collective effects by leveraging the full GPU-resident computation.
文摘BACKGROUND Early screening,preoperative staging,and diagnosis of lymph node metastasis are crucial for improving the prognosis of gastric cancer(GC).AIM To evaluate the diagnostic value of combined multidetector computed tomography(MDCT)and gastrointestinal endoscopy for GC screening,preoperative staging,and lymph node metastasis detection,thereby providing a reference for clinical diagnosis and treatment.METHODS In this retrospective study clinical and imaging data of 134 patients with suspected GC who were admitted between January 2023 and October 2024 were initially reviewed.According to the inclusion and exclusion criteria,102 patients were finally enrolled in the analysis.All enrolled patients had undergone both MDCT and gastrointestinal endoscopy examinations prior to surgical intervention.Preoperative clinical staging and lymph node metastasis findings were compared with pathological results.RESULTS The combined use of MDCT and gastrointestinal endoscopy demonstrated a sensitivity of 98.53%,specificity of 97.06%,accuracy of 98.04%,positive predictive value of 98.53%,and negative predictive value of 97.06%for diagnosing GC.These factors were all significantly higher than those of MDCT or endoscopy alone(P<0.05).The accuracy rates of the combined approach for detecting clinical T and N stages were 97.06%and 92.65%,respectively,outperforming MDCT alone(86.76% and 79.41%)and endoscopy alone(85.29% and 70.59%)(P<0.05).Among 68 patients with confirmed GC,50(73.53%)were pathologically diagnosed with lymph node metastasis.The accuracy for detecting lymph node metastasis was 66.00%with endoscopy,76.00%with MDCT,and 92.00% with the combined approach,all with statistically significant differences(P<0.05).CONCLUSION The combined application of MDCT and gastrointestinal endoscopy enhanced diagnostic accuracy for GC,provided greater consistency in preoperative staging,and improved the detection of lymph node metastasis,thereby demonstrating significant clinical utility.
基金supported in part by the Chinese Academy of Sciences(No.XDA0330302)NSFC program(No.22127901)。
文摘Neuromorphic devices have garnered significant attention as potential building blocks for energy-efficient hardware systems owing to their capacity to emulate the computational efficiency of the brain.In this regard,reservoir computing(RC)framework,which leverages straightforward training methods and efficient temporal signal processing,has emerged as a promising scheme.While various physical reservoir devices,including ferroelectric,optoelectronic,and memristor-based systems,have been demonstrated,many still face challenges related to compatibility with mainstream complementary metal oxide semiconductor(CMOS)integration processes.This study introduced a silicon-based schottky barrier metal-oxide-semiconductor field effect transistor(SB-MOSFET),which was fabricated under low thermal budget and compatible with back-end-of-line(BEOL).The device demonstrated short-term memory characteristics,facilitated by the modulation of schottky barriers and charge trapping.Utilizing these characteristics,a RC system for temporal data processing was constructed,and its performance was validated in a 5×4 digital classification task,achieving an accuracy exceeding 98%after 50 training epochs.Furthermore,the system successfully processed temporal signal in waveform classification and prediction tasks using time-division multiplexing.Overall,the SB-MOSFET's high compatibility with CMOS technology provides substantial advantages for large-scale integration,enabling the development of energy-efficient reservoir computing hardware.
基金supported by Youth Talent Project of Scientific Research Program of Hubei Provincial Department of Education under Grant Q20241809Doctoral Scientific Research Foundation of Hubei University of Automotive Technology under Grant 202404.
文摘As Internet of Things(IoT)applications expand,Mobile Edge Computing(MEC)has emerged as a promising architecture to overcome the real-time processing limitations of mobile devices.Edge-side computation offloading plays a pivotal role in MEC performance but remains challenging due to complex task topologies,conflicting objectives,and limited resources.This paper addresses high-dimensional multi-objective offloading for serial heterogeneous tasks in MEC.We jointly consider task heterogeneity,high-dimensional objectives,and flexible resource scheduling,modeling the problem as a Many-objective optimization.To solve it,we propose a flexible framework integrating an improved cooperative co-evolutionary algorithm based on decomposition(MOCC/D)and a flexible scheduling strategy.Experimental results on benchmark functions and simulation scenarios show that the proposed method outperforms existing approaches in both convergence and solution quality.
文摘This study proposes a lightweight rice disease detection model optimized for edge computing environments.The goal is to enhance the You Only Look Once(YOLO)v5 architecture to achieve a balance between real-time diagnostic performance and computational efficiency.To this end,a total of 3234 high-resolution images(2400×1080)were collected from three major rice diseases Rice Blast,Bacterial Blight,and Brown Spot—frequently found in actual rice cultivation fields.These images served as the training dataset.The proposed YOLOv5-V2 model removes the Focus layer from the original YOLOv5s and integrates ShuffleNet V2 into the backbone,thereby resulting in both model compression and improved inference speed.Additionally,YOLOv5-P,based on PP-PicoDet,was configured as a comparative model to quantitatively evaluate performance.Experimental results demonstrated that YOLOv5-V2 achieved excellent detection performance,with an mAP 0.5 of 89.6%,mAP 0.5–0.95 of 66.7%,precision of 91.3%,and recall of 85.6%,while maintaining a lightweight model size of 6.45 MB.In contrast,YOLOv5-P exhibited a smaller model size of 4.03 MB,but showed lower performance with an mAP 0.5 of 70.3%,mAP 0.5–0.95 of 35.2%,precision of 62.3%,and recall of 74.1%.This study lays a technical foundation for the implementation of smart agriculture and real-time disease diagnosis systems by proposing a model that satisfies both accuracy and lightweight requirements.
基金supported by the Major Project for the Integration of ScienceEducation and Industry (Grant No.2025ZDZX02)。
文摘Classical computation of electronic properties in large-scale materials remains challenging.Quantum computation has the potential to offer advantages in memory footprint and computational scaling.However,general and viable quantum algorithms for simulating large-scale materials are still limited.We propose and implement random-state quantum algorithms to calculate electronic-structure properties of real materials.Using a random state circuit on a small number of qubits,we employ real-time evolution with first-order Trotter decomposition and Hadamard test to obtain electronic density of states,and we develop a modified quantum phase estimation algorithm to calculate real-space local density of states via direct quantum measurements.Furthermore,we validate these algorithms by numerically computing the density of states and spatial distributions of electronic states in graphene,twisted bilayer graphene quasicrystals,and fractal lattices,covering system sizes from hundreds to thousands of atoms.Our results manifest that the random-state quantum algorithms provide a general and qubit-efficient route to scalable simulations of electronic properties in large-scale periodic and aperiodic materials.
文摘Satellite edge computing has garnered significant attention from researchers;however,processing a large volume of tasks within multi-node satellite networks still poses considerable challenges.The sharp increase in user demand for latency-sensitive tasks has inevitably led to offloading bottlenecks and insufficient computational capacity on individual satellite edge servers,making it necessary to implement effective task offloading scheduling to enhance user experience.In this paper,we propose a priority-based task scheduling strategy based on a Software-Defined Network(SDN)framework for satellite-terrestrial integrated networks,which clarifies the execution order of tasks based on their priority.Subsequently,we apply a Dueling-Double Deep Q-Network(DDQN)algorithm enhanced with prioritized experience replay to derive a computation offloading strategy,improving the experience replay mechanism within the Dueling-DDQN framework.Next,we utilize the Deep Deterministic Policy Gradient(DDPG)algorithm to determine the optimal resource allocation strategy to reduce the processing latency of sub-tasks.Simulation results demonstrate that the proposed d3-DDPG algorithm outperforms other approaches,effectively reducing task processing latency and thus improving user experience and system efficiency.
文摘The purpose of this review is to explore the intersection of computational engineering and biomedical science,highlighting the transformative potential this convergence holds for innovation in healthcare and medical research.The review covers key topics such as computational modelling,bioinformatics,machine learning in medical diagnostics,and the integration of wearable technology for real-time health monitoring.Major findings indicate that computational models have significantly enhanced the understanding of complex biological systems,while machine learning algorithms have improved the accuracy of disease prediction and diagnosis.The synergy between bioinformatics and computational techniques has led to breakthroughs in personalized medicine,enabling more precise treatment strategies.Additionally,the integration of wearable devices with advanced computational methods has opened new avenues for continuous health monitoring and early disease detection.The review emphasizes the need for interdisciplinary collaboration to further advance this field.Future research should focus on developing more robust and scalable computational models,enhancing data integration techniques,and addressing ethical considerations related to data privacy and security.By fostering innovation at the intersection of these disciplines,the potential to revolutionize healthcare delivery and outcomes becomes increasingly attainable.
文摘Photon-counting computed tomography(PCCT)represents a significant advancement in pediatric cardiovascular imaging.Traditional CT systems employ energy-integrating detectors that convert X-ray photons into visible light,whereas PCCT utilizes photon-counting detectors that directly transform X-ray photons into electric signals.This direct conversion allows photon-counting detectors to sort photons into discrete energy levels,thereby enhancing image quality through superior noise reduction,improved spatial and contrast resolution,and reduced artifacts.In pediatric applications,PCCT offers substantial benefits,including lower radiation doses,which may help reduce the risk of malignancy in pediatric patients,with perhaps greater potential to benefit those with repeated exposure from a young age.Enhanced spatial resolution facilitates better visualization of small structures,vital for diagnosing congenital heart defects.Additionally,PCCT’s spectral capabilities improve tissue characterization and enable the creation of virtual monoenergetic images,which enhance soft-tissue contrast and potentially reduce contrast media doses.Initial clinical results indicate that PCCT provides superior image quality and diagnostic accuracy compared to conven-tional CT,particularly in challenging pediatric cardiovascular cases.As PCCT technology matures,further research and standardized protocols will be essential to fully integrate it into pediatric imaging practices,ensuring optimized diagnostic outcomes and patient safety.
基金National Natural Science Foundation of China(62171305,62405206,62004135,62001317,62111530301)Natural Science Foundation of Jiangsu Province(BK20240778,BK20241917)+3 种基金State Key Laboratory of Advanced Optical Communication Systems and Networks,China(2023GZKF08)China Postdoctoral Science Foundation(2024M752314)Postdoctoral Fellowship Program of CPSF(GZC20231883)Innovative and Entrepreneurial Talent Program of Jiangsu Province(JSSCRC2021527).
文摘Photonic platforms are gradually emerging as a promising option to encounter the ever-growing demand for artificial intelligence,among which photonic time-delay reservoir computing(TDRC)is widely anticipated.While such a computing paradigm can only employ a single photonic device as the nonlinear node for data processing,the performance highly relies on the fading memory provided by the delay feedback loop(FL),which sets a restriction on the extensibility of physical implementation,especially for highly integrated chips.Here,we present a simplified photonic scheme for more flexible parameter configurations leveraging the designed quasi-convolution coding(QC),which completely gets rid of the dependence on FL.Unlike delay-based TDRC,encoded data in QC-based RC(QRC)enables temporal feature extraction,facilitating augmented memory capabilities.Thus,our proposed QRC is enabled to deal with time-related tasks or sequential data without the implementation of FL.Furthermore,we can implement this hardware with a low-power,easily integrable vertical-cavity surface-emitting laser for high-performance parallel processing.We illustrate the concept validation through simulation and experimental comparison of QRC and TDRC,wherein the simpler-structured QRC outperforms across various benchmark tasks.Our results may underscore an auspicious solution for the hardware implementation of deep neural networks.
基金supported by the"Science and Technology Development Plan Project of Jilin Province,China"(Grant No.20240101018JJ)the Fundamental Research Funds for the Central Universities(Grant No.2412023YQ004)the National Natural Science Foundation of China(Grant Nos.52072065,52272140,52372137,and U23A20568).
文摘Optoelectronic memristor is generating growing research interest for high efficient computing and sensing-memory applications.In this work,an optoelectronic memristor with Au/a-C:Te/Pt structure is developed.Synaptic functions,i.e.,excita-tory post-synaptic current and pair-pulse facilitation are successfully mimicked with the memristor under electrical and optical stimulations.More importantly,the device exhibited distinguishable response currents by adjusting 4-bit input electrical/opti-cal signals.A multi-mode reservoir computing(RC)system is constructed with the optoelectronic memristors to emulate human tactile-visual fusion recognition and an accuracy of 98.7%is achieved.The optoelectronic memristor provides potential for developing multi-mode RC system.
基金funded by the Fundamental Research Funds for the Central Universities(J2023-024,J2023-027).
文摘As an important complement to cloud computing, edge computing can effectively reduce the workload of the backbone network. To reduce latency and energy consumption of edge computing, deep learning is used to learn the task offloading strategies by interacting with the entities. In actual application scenarios, users of edge computing are always changing dynamically. However, the existing task offloading strategies cannot be applied to such dynamic scenarios. To solve this problem, we propose a novel dynamic task offloading framework for distributed edge computing, leveraging the potential of meta-reinforcement learning (MRL). Our approach formulates a multi-objective optimization problem aimed at minimizing both delay and energy consumption. We model the task offloading strategy using a directed acyclic graph (DAG). Furthermore, we propose a distributed edge computing adaptive task offloading algorithm rooted in MRL. This algorithm integrates multiple Markov decision processes (MDP) with a sequence-to-sequence (seq2seq) network, enabling it to learn and adapt task offloading strategies responsively across diverse network environments. To achieve joint optimization of delay and energy consumption, we incorporate the non-dominated sorting genetic algorithm II (NSGA-II) into our framework. Simulation results demonstrate the superiority of our proposed solution, achieving a 21% reduction in time delay and a 19% decrease in energy consumption compared to alternative task offloading schemes. Moreover, our scheme exhibits remarkable adaptability, responding swiftly to changes in various network environments.
基金supported by the National R&D Pro-gram through the National Research Foundation of Korea(NRF)funded by the Ministry of Science and ICT(Nos.RS-2024-00356939 and RS-2024-00405691).
文摘As the demand for advanced computational systems capable of handling large data volumes rises,nano-electronic devices,such as memristors,are being developed for efficient data processing,especially in reservoir computing(RC).RC enables the processing of temporal information with minimal training costs,making it a promising approach for neuromorphic computing.However,current memristor devices of-ten suffer from limitations in dynamic conductance and temporal behavior,which affects their perfor-mance in these applications.In this study,we present a multilayered indium-tin-oxide(ITO)/ZnO/indium-gallium-zinc oxide(IGZO)/ZnO/ITO memristor fabricated via radiofrequency sputtering to explore its fil-amentary and nonfilamentary resistive switching(RS)characteristics.High-resolution transmission elec-tron microscopy confirmed the polycrystalline structure of the ZnO/IGZO/ZnO active layer.Dual-switching modes were demonstrated by controlling the current compliance(I_(CC)).In the filamentary mode,the memristor exhibited a large memory window(10^(3)),low-operating voltages(±2 V),excellent cycle-to-cycle stability,and multilevel switching with controlled reset-stop voltages,making it suitable for high-density memory applications.Nonfilamentary switching demonstrated stable on/off ratios above 10,en-durance up to 102 cycles,and retention suited for short-term memory.Key synaptic behaviors,such as paired-pulse facilitation(PPF),post-tetanic potentiation(PTP),and spike-rate dependent plasticity(SRDP)were successfully emulated by modulating pulse amplitude,width,and interval.Experience-dependent plasticity(EDP)was also demonstrated,further replicating biological synaptic functions.These tempo-ral properties were utilized to develop a 4-bit reservoir computing system with 16 distinct conductance states,enabling efficient information encoding.For image recognition tasks,convolutional neural net-work(CNN)simulations achieved a high accuracy of 98.45%after 25 training epochs,outperforming the accuracy achieved following artificial neural network(ANN)simulations(87.79%).These findings demon-strate that the multilayered memristor exhibits high performance in neuromorphic systems,particularly for complex pattern recognition tasks,such as digit and letter classification.
