检索结果-内蒙古大学图书馆

13th International Conference on Intelligent Control and Information processing, ICICIP 2025

作者： Huang, Haoen Zeng, Zhigang Wang, Jun School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Computer Science Department of Data Science City University of HongKong Kowloon Hong Kong

ISBN: (纸本)9798331516147

In this paper, a discrete-time projection neural network with an adaptive step size (DPNN) is proposed for distributed global optimization. The DPNN is proven to be convergent to a Karush-Kuhn-Tucker point. Several DPNNs are utilized in a collaborative neurodynamic framework for solving distributed global optimization problem. The efficacy of the collaborative neurodynamic approach with DPNNs is demonstrated through simulation results. © 2025 IEEE.

关键词： neural network models

来源：评论

学校读者我要写书评

暂无评论

The Mindful Brain: A Systematic Review of the neural Correlates of Trait Mindfulness

引用

JOURNAL OF COGNITIVE NEUROSCIENCE 2024年第11期36卷 2518-2555页

作者： Treves, Isaac N. Pichappan, Kannammai Hammoud, Jude Bauer, Clemens C. C. Ehmann, Sebastian Sacchet, Matthew D. Gabrieli, John D. E. MIT 46-4037 Vassar St Cambridge MA 02139 USA Massachusetts Gen Hosp Ctr Precis Psychiat Dept Psychiat Boston MA USA Northeastern Univ Boston MA USA West Chester Univ Penn W Chester PA USA Harvard Med Sch Massachusetts Gen Hosp Boston MA USA

Trait self-report mindfulness scales measure one's disposition to pay nonjudgmental attention to the present moment. Concerns have been raised about the validity of trait mindfulness scales. Despite this, there is extensive literature correlating mindfulness scales with objective brain measures, with the goal of providing insight into mechanisms of mindfulness, and insight into associated positive mental health outcomes. Here, we systematically examined the neural correlates of trait mindfulness. We assessed 68 correlational studies across structural magnetic resonance imaging, task-based fMRI, resting-state fMRI, and EEG. Several consistent findings were identified, associating greater trait mindfulness with decreased amygdala reactivity to emotional stimuli, increased cortical thickness in frontal regions and insular cortex regions, and decreased connectivity within the default-mode network. These findings converged with results from intervention studies and those that included mindfulness experts. On the other hand, the connections between trait mindfulness and EEG metrics remain inconclusive, as do the associations between trait mindfulness and between-network resting-state fMRI metrics. ERP measures from EEG used to measure attentional or emotional processing may not show reliable individual variation. Research on body awareness and self-relevant processing is scarce. For a more robust correlational neuroscience of trait mindfulness, we recommend larger sample sizes, data-driven, multivariate approaches to self-report and brain measures, and careful consideration of test-retest reliability. In addition, we should leave behind simplistic explanations of mindfulness, as there are many ways to be mindful, and leave behind simplistic explanations of the brain, as distributed networks of brain areas support mindfulness.

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

neural Compress-and-Forward for the Relay Channel 25

Neural Compress-and-Forward for the Relay Channel

引用

25th IEEE International Workshop on Signal processing Advances in Wireless Communications (SPAWC)

作者： Ozyilkan, Ezgi Carpi, Fabrizio Garg, Siddharth Erkip, Elza NYU Dept Elect & Comp Engn Brooklyn NY 10012 USA

ISBN: (纸本)9798350393194;9798350393187

The relay channel, consisting of a source-destination pair and a relay, is a fundamental component of cooperative communications. While the capacity of a general relay channel remains unknown, various relaying strategies, including compress-and-forward (CF), have been proposed. For CF, given the correlated signals at the relay and destination, distributed compression techniques, such as Wyner-Ziv coding, can be harnessed to utilize the relay-to-destination link more efficiently. In light of the recent advancements in neural network-based distributed compression, we revisit the relay channel problem, where we integrate a learned one-shot Wyner-Ziv compressor into a primitive relay channel with a finite-capacity and orthogonal (or out-of-band) relay-to-destination link. The resulting neural CF scheme demonstrates that our task-oriented compressor recovers binning of the quantized indices at the relay, mimicking the optimal asymptotic CF strategy, although no structure exploiting the knowledge of source statistics was imposed into the design. We show that the proposed neural CF scheme, employing finite order modulation, operates closely to the capacity of a primitive relay channel that assumes a Gaussian codebook. Our learned compressor provides the first proof-of-concept work toward a practical neural CF relaying scheme.

关键词： relay channel Wyner-Ziv source coding decoder-only side information task-aware compression binning

来源：评论

学校读者我要写书评

暂无评论

High-resolution image generation using Artificial Intelligence and diffusion modelling 32

High-resolution image generation using Artificial Intelligen...

引用

32nd Euromicro International Conference on Parallel, distributed and network-Based processing (PDP)

作者： Scoles, Amanda Sionis, Giulia Otero, Beatriz Utrera, Gladys Univ Politecnica Catalunya BarcelonaTECH Escola Tecn Super Engn Telecomunicacio Barcelona Barcelona 08034 Spain Univ Politecnica Catalunya BarcelonaTECH Comp Architecture Dept Barcelona 08034 Spain

ISBN: (纸本)9798350363074;9798350363081

Super-Resolution via Repeated Refinement (SR3) is a state-of-the-art super-resolution algorithm based on diffusion model that can enhance the resolution of images. This method is used to pre-trained models on large datasets and can be used for various tasks without requiring training from scratch. Training SR3 from scratch using the ImageNet dataset involves a complex process that requires substantial computational resources and expertise. The idea is applied the trained SR3 model to new images by feeding the low-resolution inputs and obtaining the high-resolution outputs. It's important to note that training SR3 from scratch is a resource-intensive process that requires powerful GPUs and significant computation time. If you do not have access to such resources, an alternative is to use pre-trained models that are already available and fine-tune them on specific datasets or tasks. The paper shows the result of comparing the resolution of the preprocessed images using a significantly smaller number of images to perform the training with those obtained using the pre-trained model. The results obtained show acceptable results without having to perform on large datasets minimizing the computation time to obtain the resolution of images.

关键词： SR3 Diffusion model Deep neural network Artificial intelligence Super-resolution

来源：评论

学校读者我要写书评

暂无评论

A Novel Evaluation Strategy to Artificial neural network Model Based on Bionics

引用

Journal of Bionic Engineering 2022年第1期19卷 224-239页

作者： Sen Tian Jin Zhang Xuanyu Shu Lingyu Chen Xin Niu You Wang School of Mathematics and Statistics Hunan Normal UniversityChangsha410081China College of Information Science and Engineering Hunan Normal UniversityChangsha410081China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China Key Laboratory of Industrial Control Technology Zhejiang UniversityHangzhou310058China Science and Technology on Parallel and Distributed Laboratory College of ComputerNational University of Defense TechnologyChangsha410199China Key Laboratory of Industrial Control Technology Institute of Cyber Systems and ControlZhejiang UniversityHangzhou310027China

With the continuous deepening of Artificial neural network(ANN)research,ANN model structure and function are improving towards diversification and ***,the model is more evaluated from the pros and cons of the problem-solving results and the lack of evaluation from the biomimetic aspect of imitating neural networks is not inclusive ***,a new ANN models evaluation strategy is proposed from the perspective of bionics in response to this problem in the ***,four classical neural network models are illustrated:Back Propagation(BP)network,Deep Belief network(DBN),LeNet5 network,and olfactory bionic model(KIII model),and the neuron transmission mode and equation,network structure,and weight updating principle of the models are analyzed *** analysis results show that the KIII model comes closer to the actual biological nervous system compared with other models,and the LeNet5 network simulates the nervous system in ***,evaluation indexes of ANN are constructed from the perspective of bionics in this paper:small-world,synchronous,and chaotic ***,the network model is quantitatively analyzed by evaluation indexes from the perspective of *** experimental results show that the DBN network,LeNet5 network,and BP network have synchronous *** the DBN network and LeNet5 network have certain chaotic characteristics,but there is still a certain distance between the three classical neural networks and actual biological neural *** KIII model has certain small-world characteristics in structure,and its network also exhibits synchronization characteristics and chaotic *** with the DBN network,LeNet5 network,and the BP network,the KIII model is closer to the real biological neural network.

关键词： Artificial neural network(ANN) Back Propagation(BP)network Deep Belief network(DBN) LeNet5 network Olfactory bionic model(KIII model) Small world Chaos Synchronous

来源：评论

学校读者我要写书评

暂无评论

distributed Radar Interval Distance Estimation Based on Deep neural network

Distributed Radar Interval Distance Estimation Based on Deep...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Xiayu Li Peng Chen State Key Laboratory of Millimeter Waves Southeast University Nanjing China

ISBN: (纸本)9781665450867

In recent years, millimeter wave (mmWave) radar has played an indispensable role in several applications. mm Wave radars can measure the distance, speed, and angle of objects, but the transmit power of a single mm Wave radar is limited. By deploying multiple mm Wave radars in a distributed manner and fusing signals from them, detection results will be improved. Before data fusion, it is necessary to accurately measure the external parameters between different radars to complete the coordinates calibration of the radar network. Current methods focus on the calibration method by jointly observing moving objects in overlapping view fields of the radar network. The calibration process requires one target to move within a defined area. Because the radar cross section (RCS) characteristics of the target in all directions are usually inconsistent, if the reflected signal of this target is weak during the calibration process, the error of this method will be relatively large. This paper proposes a new neural network-based method to estimate the interval distance between different radars without passing through a moving target. The distance estimation error of the proposed network can reach within 0.1 m, which is smaller than the calibration method based on moving objects. Through the verification of actual measured data, the proposed network can more accurately estimate the interval distance between radars.

关键词： Wireless communication Radar cross-sections neural networks Millimeter wave measurements Training data Radar detection Millimeter wave radar

来源：评论

学校读者我要写书评

暂无评论

SplitPlace: AI Augmented Splitting and Placement of Large-Scale neural networks in Mobile Edge Environments

引用

IEEE TRANSACTIONS ON MOBILE COMPUTING 2023年第9期22卷 5539-5554页

作者： Tuli, Shreshth Casale, Giuliano Jennings, Nicholas R. Imperial Coll London Dept Comp London SW7 2BX England Loughborough Univ Loughborough LE11 3TU England

In recent years, deep learning models have become ubiquitous in industry and academia alike. Deep neural networks can solve some of the most complex pattern-recognition problems today, but come with the price of massive compute and memory requirements. This makes the problem of deploying such large-scale neural networks challenging in resource-constrained mobile edge computing platforms, specifically in mission-critical domains like surveillance and healthcare. To solve this, a promising solution is to split resource-hungry neural networks into lightweight disjoint smaller components for pipelined distributed processing. At present, there are two main approaches to do this: semantic and layer-wise splitting. The former partitions a neural network into parallel disjoint models that produce a part of the result, whereas the latter partitions into sequential models that produce intermediate results. However, there is no intelligent algorithm that decides which splitting strategy to use and places such modular splits to edge nodes for optimal performance. To combat this, this work proposes a novel AI-driven online policy, SplitPlace, that uses Multi-Armed-Bandits to intelligently decide between layer and semantic splitting strategies based on the input task's service deadline demands. SplitPlace places such neural network split fragments on mobile edge devices using decision-aware reinforcement learning for efficient and scalable computing. Moreover, SplitPlace fine-tunes its placement engine to adapt to volatile environments. Our experiments on physical mobile-edge environments with real-world workloads show that SplitPlace can significantly improve the state-of-the-art in terms of average response time, deadline violation rate, inference accuracy, and total reward by up to 46, 69, 3 and 12 percent respectively.

关键词： Mobile edge computing neural network splitting container orchestration artificial intelligence QoS optimization

来源：评论

学校读者我要写书评

暂无评论

Physics-Guided neural networks for distributed Sparse Gas Source Localization Using Poisson's Equation and Green's Function Method 32

Physics-Guided Neural Networks for Distributed Sparse Gas So...

引用

32nd European Signal processing Conference (EUSIPCO)

作者： Ruiz, Victor Scott Prieto Shutin, Dmitriy Wiedemann, Thomas Hinsen, Patrick German Aerosp Ctr DLR Muenchner Str 20 D-82234 Wessling Germany Tech Univ Munich Munich Inst Robot & Machine Intelligence Percept Intelligent Syst Munich Germany

ISBN: (纸本)9789464593617;9798331519773

Finding sources or leaks of airborne material in Chemical, Biological, Radiological, or Nuclear (CBRN) accidents is crucial for effective disaster response. This paper makes use of sparse Bayesian learning (SBL) to cooperatively estimate source locations based on measurements by multiple robots or a sensor network. The SBL approach facilitates the identification of sparse source support, indirectly providing information about the number of sources and their locations. To achieve this, we introduce a novel method that includes a trained surrogated model for the gas dispersion process described by a Partial Differential Equation (PDE). Namely, a Physics-Guided neural network (PGNN) is employed to approximate a parameterized Green's function of the PDE. The obtained approximation is integrated into a gradient-based optimization process. The proposed method allows estimating super-resolution arbitrary source locations, eliminating constraints to a specific grid. Further, the newly proposed PGNN surrogate model comes with the advantage that the approach can be extended to cases where no analytic Green's function is available. Simulation results demonstrate the effectiveness of the proposed approach, showcasing its potential for enhanced airborne material detection in CBRN scenarios.

关键词： Poisson equation

来源：评论

学校读者我要写书评

暂无评论

3D Point Cloud Object Detection on Edge Devices for Split Computing 3

3D Point Cloud Object Detection on Edge Devices for Split Co...

引用

IEEE 3rd Real-Time and Intelligent Edge Computing Workshop (RAGE)

作者： Noguchi, Taisuke Azumi, Takuya Saitama Univ Grad Sch Sci & Engn Saitama Japan

ISBN: (纸本)9798350363357;9798350363340

The field of autonomous driving technology is rapidly advancing, with deep learning being a key component. Particularly in the field of sensing, 3D point cloud data collected by LiDAR is utilized to run deep neural network models for 3D object detection. However, these state-of-the-art models are complex, leading to longer processing times and increased power consumption on edge devices. The objective of this study is to address these issues by leveraging Split Computing, a distributed machine learning inference method. Split Computing aims to lessen the computational burden on edge devices, thereby reducing processing time and power consumption. Furthermore, it minimizes the risk of data breaches by only transmitting intermediate data from the deep neural network model. Experimental results show that splitting after voxelization reduces the inference time by 70.8% and the edge device execution time by 90.0%. When splitting within the network, the inference time is reduced by up to 57.1%, and the edge device execution time is reduced by up to 69.5%.

关键词： Split Computing point cloud 3D object detection deep neural network

来源：评论

学校读者我要写书评

暂无评论

PANCODE: Multilevel Partitioning of neural networks for Constrained Internet-of-Things Devices

引用

IEEE ACCESS 2023年 11卷 2058-2077页

作者： de Oliveira, Fabiola Martins Campos Bittencourt, Luiz Fernando Kamienski, Carlos Alberto Borin, Edson Fed Univ ABC Ctr Math Comp & Cognit BR-09210580 Santo Andre SP Brazil Univ Estadual Campinas Inst Comp BR-13083852 Campinas SP Brazil

The increasing number of Internet-of-Things (IoT) devices will generate unprecedented data in the upcoming years. Fog computing may prevent the saturation of the network infrastructure by processing data at the edge or within these devices. Consequently, the machine intelligence built almost exclusively on the cloud can be scattered to the edge devices. While deep learning techniques can adequately process IoT-massive data volumes, their high resource-demanding nature poses a trade-off for execution on resource-constrained devices. This paper proposes and evaluates the performance of the PArtitioning networks for COnstrained DEvices (PANCODE), a novel algorithm that employs a multilevel approach to partition large convolutional neural networks for distributed execution on constrained IoT devices. Experimental results with the LeNet and AlexNet models show that our algorithm can produce partitionings that achieve up to 2173.53 times more inferences per second than the Best Fit algorithm and up to 1.37 times less communication than the second-best approach. We also show that the METIS state-of-the-art framework only produces invalid partitionings in more constrained setups. The results indicate that our algorithm achieves higher inference rates and low communication costs in convolutional neural networks distributed among constrained and exceptionally very constrained devices.

关键词： Convolutional neural networks distributed systems fog computing graph partitioning algorithms Internet of Things performance evaluation

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：