A5027563148- Advanced Optical Network Technologies
- Optical Network Technologies
- Advanced Photonic Communication Systems
- Software-Defined Networks and 5G
- Advanced Memory and Neural Computing
- Satellite Communication Systems
- Neural dynamics and brain function
- Ferroelectric and Negative Capacitance Devices
- Neural Networks and Applications
- Traffic Prediction and Management Techniques
- Traffic control and management
- Optical Wireless Communication Technologies
- Neural Networks and Reservoir Computing
- Groundwater flow and contamination studies
- Interconnection Networks and Systems
- 3D Shape Modeling and Analysis
- IoT and Edge/Fog Computing
- Age of Information Optimization
- Photonic and Optical Devices
- Time Series Analysis and Forecasting
- Transportation Planning and Optimization
- CCD and CMOS Imaging Sensors
- Mobile Agent-Based Network Management
- Geothermal Energy Systems and Applications
- Gaussian Processes and Bayesian Inference
University of Science and Technology of China
2025
Guangdong Medical College
2025
Zhengzhou University
2018-2024
Jilin University
2022-2024
University of California, Santa Cruz
2024
University of Electronic Science and Technology of China
2023-2024
Montefiore Medical Center
2024
University of Southampton
2023
China State Shipbuilding (China)
2023
Shandong Electric Power Engineering Consulting Institute Corp
2021
Spiking neural networks (SNNs) are attracting widespread interest due to their biological plausibility, energy efficiency, and powerful spatiotemporal information representation ability. Given the critical role of attention mechanisms in enhancing network performance, integration SNNs exhibits tremendous potential deliver energy-efficient high-performance computing paradigms. In this article, we present a novel temporal-channel joint mechanism for SNNs, referred as TCJA-SNN. The proposed...
The application of hardware-based neural networks can be enhanced by integrating sensory neurons and synapses that enable direct input from external stimuli. This work reports optical control an oscillatory neuron based on volatile threshold switching in V
As the size of large language models continue to scale, so does computational resources required run it. Spiking Neural Networks (SNNs) have emerged as an energy-efficient approach deep learning that leverage sparse and event-driven activations reduce overhead associated with model inference. While they become competitive non-spiking on many computer vision tasks, SNNs also proven be more challenging train. a result, their performance lags behind modern learning, we are yet see effectiveness...
Regional satellite networks are capable of supporting denser coverage and more reliable communications in the target area hence have been viewed as an essential part sixth generation (6G) communication system. Since time-varying limited resources, efficient resource management schemes needed to accommodate massive ubiquitous service requests. As a remedy, virtual network embedding (VNE) can enable diverse requests (VNRs) share same substrate resources improve utilization. However, existing...
Spiking neural networks (SNNs) are emerging as an energy-efficient alternative to traditional artificial (ANNs) due their unique spike-based event-driven nature. Coding is crucial in SNNs it converts external input stimuli into spatio-temporal feature sequences. However, most existing deep rely on direct coding that generates powerless spike representation and lacks the temporal dynamics inherent human vision. Hence, we introduce Gated Attention (GAC), a plug-and-play module leverages...
Achievable capacity of optical fiber is approaching its physical limitation in frequency domain. Space division multiplexing (SDM) technology can scale the network using multi-core and multi-mode fiber. In order to provide high-speed transmission services with fine granularities, SDM enabled elastic networks (SDM-EONs) become a promising candidate future transport networks. However, since spectrum status SDM-EONs becomes more complex introduction spatial dimension, issue fragmentation will...
Recently, network traffic has been growing exponentially and almost reached the physical capacity limit of single mode fibers. Space division multiplexing (SDM) is a promising technology to overcome looming fiber crunch. Especially, few-mode multi-core fibers (FM-MCFs) can aggregate multiple cores into one two or more modes be transmitted in core, which greatly increase yet introduce crosstalk constraints including inter- intra-core crosstalk. To our best knowledge, there no accurate...
Cloud-fog computing emerges to satisfy the low latency and high computation requirements of Internet Things (IoT) services. Elastic optical networks (EONs) are excellent substrate communication between fog datacenters cloud datacenters. However, uneven traffic massive cloud-fog services incurs many spectrum fragments, leading extra energy consumption. To solve this problem, we propose an energy-efficient deep reinforced grooming (EDTG) algorithm based on reinforcement learning. Unlike...
The ongoing roll-out of cloud–edge computing and Internet Things (IoT) has been simulating the boom new advance reservation (AR) services, such as bulk-data migration virtual machine backup, driving development substrate elastic optical networks (EONs). These AR requests are initial-delay-insensitive if they guaranteed to be completed before a predefined deadline. Therefore, routing, modulation, spectrum assignment (RMSA) problem is extended time-spectrum domain rather than single domain....
Efficient traffic light control is a critical part of realizing smart transportation. In particular, deep reinforcement learning (DRL) algorithms that use neural networks (DNNs) have superior autonomous decision-making ability. Most existing work has applied DRL to lights intelligently. this article, we propose novel context-aware multiagent broad (CAMABRL) approach based on (BRL) for mixed pedestrian-vehicle adaptive (ATLC). CAMABRL exploits the system (BLS) established in flat network...
With an effective service provisioning strategy that relies on Network Function Virtualization (NFV), cloud-edge computing can enhance the Quality of Service (QoS) in Elastic Optical Networks (EONs). NFV emerges as a promising technology to provide flexible services by orchestrating different virtual Chains (vNFCs). However, vNFC deployment process is complex and involves two stages, i.e., allocating diverse Virtual Functions (VNFs) onto physical nodes routing suitable paths for Links (VLs)....
Elastic optical network (EON) is a promising technology for the next generation of transport network. Routing, modulation and spectrum assignment one key issues in EON. In problem, constraints continuity contiguity must be satisfied. this paper, we propose policy named minimizing sum weighted resource reductions (min ΣwΔR) algorithm. The algorithm includes three contributions:1) concept reduction (ΔR) defined to measure variation idle resources path when block assigned connection request,...
Space division multiplexing enabled elastic optical networks (SDM-EONs) with multi-core fiber (MCF) have become a promising candidate for future transport networks, due to their high capacity and flexibility. Meanwhile, driven by the development of cloud computing data centers, more types requests are allowed in i.e., usual immediate reservation (IR) requests, which need be served immediately, advance (AR) support initial-delay tolerance services. However, introduction AR spectrum fragments...
Spiking Neural Networks (SNNs) are attracting widespread interest due to their biological plausibility, energy efficiency, and powerful spatio-temporal information representation ability. Given the critical role of attention mechanisms in enhancing neural network performance, integration SNNs exhibits potential deliver energy-efficient high-performance computing paradigms. We present a novel Temporal-Channel Joint Attention mechanism for SNNs, referred as TCJA-SNN. The proposed TCJA-SNN...
Energy consumption efficiency during resource allocation is crucial for large scale networks. The evolution of space division multiplexing elastic optical networks (SDM-EONs) has presented tremendous spatial dimensions over single-mode to manage transmission largetraffic volumes, peak load the fluctuating traffic. However, due capacitytransmission rates, challenges have led incremental energy consumption. This impact crosstalk (XT), which occurs between active adjacent cores, core switching,...
With the rapid development of information and communication technology (ICT), demand for flexible cost-effective network services (NSs) is growing exponentially. Network function virtualization (NFV) based on elastic optical data center interconnections (EO-DCI) can provide timely NSs. One major concerns that draws attention researchers exponential growth energy consumption EO-DCI networks. Therefore, it a practical issue to reduce service deployment in networks while ensuring success. In...
Abstract This study explores the potential of machine learning algorithms for earthquake prediction, utilizing fluid chemical anomaly data from hot springs. Six springs, located within an active fault zone along southeastern coast China, were carefully chosen as hydrochemical monitoring sites extended period two and a half years. Using this data, prediction model integrating six was developed to forecast M ≥ 5 earthquakes in Taiwan. The model's performance validated against recorded events,...