检索结果-内蒙古大学图书馆

Weightless photonic spike processing of time-of-flight signals with delay learning

OPTICS LETTERS 2025年第3期50卷 924-927页

作者： Duan, Lian Ma, Bowen Zou, Weiwen Shanghai Jiao Tong Univ Intelligent Microwave Lightwave Integrat Innovat C Dept Elect Engn State Key Lab Adv Opt Commun Syst & Networks 800 Dongchuan Rd Shanghai 200240 Peoples R China

Time-of-flight (ToF) signal processing has become increasingly crucial in depth perception applications. We propose a photonic spike processing method for ToF signals based on synaptic delay plasticity, which adjusts the spike timing of encoded signals to achieve low-latency processing without the need for weight loading and control. This method employs photonic neurons that directly encode optical pulses of ToF signals into temporal spike sequences, eliminating the necessity for a time-to-digital converter (TDC). We use tunable optical delay lines to emulate the photonic synaptic regulation of spike timing. In addition, we demonstrate the efficacy of a photonic spiking neural network that trains the synaptic delay parameters using the ModelNet dataset, achieving an accuracy of 96.36%. In experiments, the processing delay of ToF signals is 58.66 ns, representing a reduction of two orders of magnitude compared with traditional TDC-based methods. This approach facilitates applying synaptic diversity in photonic neuromorphic information processing.(c) 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved

关键词： distributed feedback lasers Information processing neural networks Optical delay lines Semiconductor optical amplifiers Signal processing

来源：评论

学校读者我要写书评

暂无评论

PAICORE: A 1.9-Million-Neuron 5.181-TSOPS/W Digital Neuromorphic Processor With Unified SNN-ANN and On-Chip Learning Paradigm

引用

IEEE JOURNAL OF SOLID-STATE CIRCUITS 2025年第2期60卷 651-671页

作者： Zhong, Yi Kuang, Yisong Liu, Kefei Wang, Zilin Feng, Shuo Chen, Guang Yang, Youming Cui, Xiuping Wang, Qiankun Cao, Jian Jia, Song Liang, Yun Sun, Guangyu Cui, Xiaoxin Huang, Ru Wang, Yuan Peking Univ MPW Ctr Sch Integrated Circuits Key Lab Microelect Devices & Circuits Beijing 100871 Peoples R China Beijing Adv Innovat Ctr Integrated Circuits Beijing 100871 Peoples R China

The neuromorphic approach of fulfilling brain-like edge intelligence is confronted with three paramount challenges: 1) ever-increasing application demands versus insufficient on-chip resources;2) diverse data sources and models versus heterogeneous computing paradigms;and 3) adaptation to real scenarios versus absence of on-chip learning. To bridge those gaps in the current research community, this article presents PAICORE, a 537.98-mm(2) digital neuromorphic processor with a unified computing and learning paradigm. PAICORE is a scalable 1024-core design, integrating over 1.919 million neurons and 4.773 billion synapses on a single chip. PAICORE is implemented in globally asynchronous locally synchronous (GALS) style with a five-level fat up-down quadtree as dedicated network-on-chip (NoC) infrastructure and tiled 2-D chip array as inter-chip architecture. The distributed processing cores fuse the hybrid spiking neural network (SNN), artificial neural network (ANN), and on-chip spike-timing-dependent plasticity (STDP) learning models into a unified description by modular-level reconfiguration. PAICORE achieves the peak performance of 20.74 TSOPS, 41.49 TOPS, and 115.25 GSOPS, with the best energy efficiency of 5.181 TSOPS/W, 10.372 TOPS/W, and 1.222 TSOPS/W for SNN, ANN, and on-chip learning paradigms, respectively. Benefiting from the PAIFLOW software framework, PAICORE hardware platform can be equivalently simulated and efficiently programmed in a large-scale deployment, in accordance with specific optimizing demands for its target multi-paradigm tasks.

关键词： Neurons Computational modeling Artificial neural networks Biological system modeling Data models Adaptation models Task analysis Artificial neural network (ANN) edge application multi-chip scalability network-on-chip (NoC) neuromorphic computing on-chip learning spike-timing-dependent plasticity (STDP) spiking neural network (SNN) unified paradigm

来源：评论

学校读者我要写书评

暂无评论

Sg-snn: a self-organizing spiking neural network based on temporal information

引用

COGNITIVE NEURODYNAMICS 2025年第1期19卷 1-20页

作者： Gao, Shouwei Zhu, Ruixin Qin, Yu Tang, Wenyu Zhou, Hao Shanghai Univ Shanghai Peoples R China

Neurodynamic observations indicate that the cerebral cortex evolved by self-organizing into functional networks, These networks, or distributed clusters of regions, display various degrees of attention maps based on input. Traditionally, the study of network self-organization relies predominantly on static data, overlooking temporal information in dynamic neuromorphic data. This paper proposes Temporal Self-Organizing (TSO) method for neuromorphic data processing using a spiking neural network. The TSO method incorporates information from multiple time steps into the selection strategy of the Best Matching Unit (BMU) neurons. It enables the coupled BMUs to radiate the weight across the same layer of neurons, ultimately forming a hierarchical self-organizing topographic map of concern. Additionally, we simulate real neuronal dynamics, introduce a glial cell-mediated Glial-LIF (Leaky Integrate-and-fire) model, and adjust multiple levels of BMUs to optimize the attention topological *** demonstrate that the proposed Self-organizing Glial Spiking neural network (SG-SNN) can generate attention topographies for dynamic event data from coarse to fine. A heuristic method based on cognitive science effectively guides the network's distribution of excitatory regions. Furthermore, the SG-SNN shows improved accuracy on three standard neuromorphic datasets: DVS128-Gesture, CIFAR10-DVS, and N-Caltech 101, with accuracy improvements of 0.3%, 2.4%, and 0.54% respectively. Notably, the recognition accuracy on the DVS128-Gesture dataset reaches 99.3%, achieving state-of-the-art (SOTA) performance.

关键词： Spiking neural network Self-organizing map Glial neuron model Neuromorphic data

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Data-Driven distributed LFC Using Controller-Dynamic-Linearization Method

引用

IEEE TRANSACTIONS ON SIGNAL AND INFORMATION processing OVER networkS 2025年 11卷 85-96页

作者： Bu, Xuhui Zhang, Yan Zeng, Yiming Hou, Zhongsheng Henan Polytech Univ Sch Elect Engn & Automat Jiaozuo 454003 Peoples R China Qingdao Univ Sch Automat Qingdao 266071 Peoples R China

This paper is concerned with an event-triggered distributed load frequency control method for multi-area interconnected power systems. Firstly, because of high dimension, nonlinearity and uncertainty of the power system, the relevant model information cannot be fully obtained. To realize the design of LFC algorithm under the condition that the model information is unknown, the equivalent functional relationship between the control signal and the area-control-error signal is established by using a dynamic linearization technique. Secondly, a novel distributed load frequency control algorithm is proposed based on controller dynamic-linearization method and the controller parameters are tuned online by constructing a radial basis function neural network. In addition, to reduce the computation and communication burden on the system, an event-triggered mechanism is also designed, in which whether the data is transmitted at the current instant is completely determined by a triggering condition. Rigorous analysis shows that the proposed method can render the frequency deviation of the power system to converge to a bounded value. Finally, simulation results in a four-area power system verify the effectiveness of the proposed algorithm.

关键词： Power systems Power system stability Power system dynamics Frequency control Mathematical models Event detection Information processing Load modeling Nonlinear dynamical systems Uncertainty Multi-area power systems load frequency control distributed controller-dynamic-linearization method event-triggered strategy data-driven

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient, Delay-Constrained Edge Computing of a network of DNNs

引用

IEEE TRANSACTIONS ON COMPUTERS 2025年第2期74卷 569-581页

作者： Ghasemi, Mehdi Heidari, Soroush Kim, Young Geun Wu, Carole-Jean Vrudhula, Sarma Arizona State Univ Tempe AZ 85281 USA Korea Univ Seoul 02841 South Korea Meta Inc Cambridge MA 02142 USA

This paper presents a novel approach for executing the inference of a network of pre-trained deep neural networks (DNNs) on commercial-off-the-shelf devices that are deployed at the edge. The problem is to partition the computation of the DNNs between an energy-constrained and performance-limited edge device EE, and an energy-unconstrained, higher performance device CC, referred to as the cloudlet, with the objective of minimizing the energy consumption of EE subject to a deadline constraint. The proposed partitioning algorithm takes into account the performance profiles of executing DNNs on the devices, the power consumption profiles, and the variability in the delay of the wireless channel. The algorithm is demonstrated on a platform that consists of an NVIDIA Jetson Nano as the edge device EE and a Dell workstation with a Titan Xp GPU as the cloudlet. Experimental results show significant improvements both in terms of energy consumption of EE and processing delay of the application. Additionally, it is shown how the energy-optimal solution is changed when the deadline constraint is altered. Moreover, the overhead of decision-making for our proposed method is significantly lower than the state-of-the-art Integer Linear Programming (ILP) solutions.

关键词： Flow graphs Performance evaluation Delays Computational modeling Servers Artificial neural networks Energy efficiency Energy consumption Data models Image edge detection Deep neural networks IoT edge energy efficiency

来源：评论

学校读者我要写书评

暂无评论

DAS Up- and Downgoing Wavefield Separation via Radon Transform Combined With Parallel U-network

引用

IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING 2025年 63卷

作者： Sun, Decheng Yao, Guijin Li, Yue Jilin Univ Coll Commun Engn Dept Informat Changchun 130012 Peoples R China

After mitigating noise pollution, the primary challenge in processing downhole distributed acoustic sensing (DAS) data is the effective separation of its wavefield. Wavefield separation networks specifically for DAS data are scarce. Existing vertical seismic profiling (VSP) wavefield separation methods include traditional techniques, establishing propagation models applied to neural networks, and using the results of traditional methods as labels. Traditional methods can lead to issues of spatial aliasing and artifacts. Using such "not-so-clean" data for network training results in suboptimal performance. In addition, constructing models under simplified conditions results in training data that are overly simplistic, leading to a loss of detailed information in modern, higher sampling frequency, and more densely sampled complex DAS data. Inspired by the Radon transform and neural networks, we propose a DAS wavefield separation framework that combines the Radon transform with parallel U-Net (RTPU-Net) to address the issue of spatial aliasing in the Radon transform. We identified two key features in wavefield separation based on Radon transform: phase-reversed spatial aliasing and high amplitude preservation. In addition to constraining the network with loss functions, we also used reconstruction loss (MSE) to associate these two features. Using the Radon transform as a preprocessing method, our approach can also synthesize a large amount of training data automatically from raw data. Applications to both synthetic and field DAS data demonstrate that RTPU-Net can be widely used for high-precision DAS wavefield separation. When comparing the MSE metric of the overlapped wavefield from separated field data, our method also consistently achieves the lowest value among all the tested methods.

关键词： Transforms Training Noise reduction Signal to noise ratio Reflection Energy loss Training data Radon Geoscience and remote sensing Data models distributed acoustic sensing (DAS) encoder-decoder multiscale radon transform wave field separation

来源：评论

学校读者我要写书评

暂无评论

Charbonnier Quasi Hyperbolic Momentum Spline Based Incremental Strategy for Nonlinear distributed Active Noise Control

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF SIGNAL processing 2025年 6卷 1-15页

作者： Kranthi, Rajapantula Vasundhara Kar, Asutosh Christensen, Mads Grasboll Natl Inst Technol Dept Elect & Commun Engn Warangal 506004 India Dr BR Ambedkar Natl Inst Technol Jalandhar Dept Elect & Commun Engn Jalandhar 144008 India Aalborg Univ Dept Elect Syst DK-9220 Aalborg Denmark

Noise mitigation proves to be a challenging task for active noise control in the existence of nonlinearities. In such environments, functional link neural network (FLN) and adaptive exponential FLN techniques improve the performance of distributed active noise control systems. Nonlinear spline approaches are well known for their low computational complexity and ability to effectively alleviate noise in nonlinear systems. This paper proposes a new cost function for distributed active noise control (DANC) system which is based on the Charbonnier quasi hyperbolic momentum spline (CQHMS) involving incremental approach. This incremental based CQHMS DANC method employs Charbonnier loss and quasi hyperbolic momentum approach which minimizes gradient variance and local crossover points in order to enhance the convergence and steady-state performance. The technique being proposed demonstrates enhanced performance and achieves accelerated convergence when compared to existing techniques in a range of nonlinear DANC scenarios in lieu of varied nonlinear primary path and nonlinear secondary path conditions.

关键词： Noise Splines (mathematics) Microphones Convergence Adaptive systems Adaptation models Prevention and mitigation Loudspeakers Adaptive filters Signal processing algorithms Charbonnier function nonlinear distributed ANC quasi hyperbolic momentum spline

来源：评论

学校读者我要写书评

暂无评论

Acoustic-to-hyper-spectral: real-time perimeter intrusion detection system monitoring through learnable filters and hyper-spectral image generation from distributed acoustic sensing systems

引用

OPTICS EXPRESS 2025年第3期33卷 4109-4126页

作者： Pierau, Ruth-emely Katsifolis, Jim Meehan, Alaster Rezatofighi, Hamid Stuckey, Peter J. Monash Univ Clayton Vic 3800 Australia Univ Melbourne ARC Training Ctr Optimisat Technol Integrated Meth Parkville Vic 3052 Australia AVA Risk Grp Co Future Fibre Technol 10 Hartnett CL Mulgrave Vic 3170 Australia

This paper presents an integrated distributed acoustic sensing (DAS) system with artificial intelligence to provide real-time system monitoring for fence perimeter and buried system applications. The DAS system is a Rayleigh backscatter based fibre optic sensing system that has been deployed in two real-world, commercial applications to detect acoustic wave propagation and scattering along perimeter lines, and classify intrusions accurately. What we believe to be three novel signal processing methods are proposed to train filters for automatically selecting frequency bands from the power spectrum and generating hyper-spectral images from the data gathered by the DAS system without expert knowledge. The hyper-spectral images are analyzed by a neural network based object detection model. The system achieves 81.8% accuracy on a fence perimeter installation and 60.4% accuracy on a buried system application in detecting and classifying various intrusion events. The evaluation interval of the integrated DAS system framework between event sensing and detection does not exceed 5 s. (c) 2025 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

关键词： Deep learning Hyperspectral imaging Machine learning neural networks Signal processing Wave propagation

来源：评论

学校读者我要写书评

暂无评论

distributed wavelet-learning-based fusion estimation for multirate multisensor systems with integer and non-integer multiple sample ratios

引用

DIGITAL SIGNAL processing 2025年 162卷

作者： Wang, Rusheng Jin, Weihang Li, Han Chen, Bo Han, Yan Yu, Li Zhejiang Univ Technol Dept Automat Hangzhou 310023 Peoples R China Zhejiang Key Lab Intelligent Percept & Control Com Hangzhou 310023 Peoples R China Key Lab Intelligent Rehabil & Translat Neuroelect Hangzhou 310023 Peoples R China Zhe Jiang Nurotron Biotechnol Co Hangzhou 310023 Peoples R China

This paper explores the asynchronous fusion estimation problem of multirate multisensor systems under sensor time-varying sampling. First, the sensors are divided into integer and non-integer multiples based on the ratio of the sensor sampling rate to the state updating rate. Under the case of integer multiple, a synchronous state space model is established by state projection through wavelet transform, and then a Kalman-based multirate estimator is designed to calculate local estimation. Under the case of no-integer multiple, a measurement compensation mechanism is designed using the measurement information closest to the state updating instant, and then a back propagation neural network is constructed to obtain the corresponding estimation. Based on the above obtained local estimation, a learning-based fusion criterion is developed by taking into account the time difference between the state updating moment and the measurement sampling moment. Finally, the simulation results demonstrate the advantages and effectiveness of the proposed method.

关键词： Multirate sampling distributed fusion estimation Wavelet transform BP neural network

来源：评论

学校读者我要写书评

暂无评论

Learning Feature Matching via Matchable Keypoint-Assisted Graph neural network

引用

IEEE TRANSACTIONS ON IMAGE processing 2025年 34卷 154-169页

作者： Li, Zizhuo Ma, Jiayi Wuhan Univ Elect Informat Sch Wuhan 430072 Peoples R China

Accurately matching local features between a pair of images corresponding to the same 3D scene is a challenging computer vision task. Previous studies typically utilize attention-based graph neural networks (GNNs) with fully-connected graphs over keypoints within/across images for visual and geometric information reasoning. However, in the background of local feature matching, a significant number of keypoints are non-repeatable due to factors like occlusion and failure of the detector, and thus irrelevant for message passing. The connectivity with non-repeatable keypoints not only introduces redundancy, resulting in limited efficiency (quadratic computational complexity w.r.t. the keypoint number), but also interferes with the representation aggregation process, leading to limited accuracy. Aiming at the best of both worlds on accuracy and efficiency, we propose MaKeGNN, a sparse attention-based GNN architecture which bypasses non-repeatable keypoints and leverages matchable ones to guide compact and meaningful message passing. More specifically, our Bilateral Context-Aware Sampling (BCAS) Module first dynamically samples two small sets of well-distributed keypoints with high matchability scores from the image pair. Then, our Matchable Keypoint-Assisted Context Aggregation (MKACA) Module regards sampled informative keypoints as message bottlenecks and thus constrains each keypoint only to retrieve favorable contextual information from intra- and inter-matchable keypoints, evading the interference of irrelevant and redundant connectivity with non-repeatable ones. Furthermore, considering the potential noise in initial keypoints and sampled matchable ones, the MKACA module adopts a matchability-guided attentional aggregation operation for purer data-dependent context propagation. By these means, MaKeGNN outperforms the state-of-the-arts on multiple highly challenging benchmarks, while significantly reducing computational and memory complexity compared to typical atte

关键词： Visualization Graph neural networks Accuracy Message passing Feature extraction Artificial neural networks Transformers Robustness Pose estimation Location awareness Feature matching graph neural network matchability message passing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：