检索结果-内蒙古大学图书馆

A parallel approach to accelerate neural network hyperparameter selection for energy forecasting

EXPERT SYSTEMS WITH APPLICATIONS 2025年 279卷

作者： Criado-Ramon, D. Ruiz, L. G. B. Pegalajar, M. C. Univ Granada Dept Comp Sci & Artificial Intelligence Granada Spain Univ Granada Dept Software Engn Granada Spain

Finding the optimal hyperparameters of a neural network is a challenging task, usually done through a trial-and-error approach. Given the complexity of just training one neural network, particularly those with complex architectures and large input sizes, many implementations accelerated with GPU (Graphics processing Unit) and distributed and parallel technologies have come to light over the past decade. However, whenever the complexity of the neural network used is simple and the number of features per sample is small, these implementations become lackluster and provide almost no benefit from just using the CPU (Central processing Unit). As such, in this paper, we propose a novel parallelized approach that leverages GPU resources to simultaneously train multiple neural networks with different hyperparameters, maximizing resource utilization for smaller networks. The proposed method is evaluated on energy demand datasets from Spain and Uruguay, demonstrating consistent speedups of up to 1164x over TensorFlow and 410x over PyTorch.

关键词： neural networks Energy Time series forecasting Parallel computing Hyperparameter selection

来源：评论

学校读者我要写书评

暂无评论

Internet of Things Enabled Smart Energy Management of distributed Energy Resources using Self-Adaptive Physics-Informed neural network Optimized with Green Anaconda Optimization

Internet of Things Enabled Smart Energy Management of Distri...

引用

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Rahul D. Ghongade J. Sri Arunaa P. S. Latha Mageshwari K. Vinoth M. Shanmugathai J. Femila Mercy Rani Department of Electronics and Telecommunication Engineering P. R. Pote Patil College of Engineering and Management Amravati Maharashtra India Department of Electronics and Communication Engineering Dr. M. G. R Educational and Research Institute Chennai Tamil Nadu India Department of S&H (Physics) R. M. K. Engineering College Kavaraipettai Tamil Nadu India Department of Electrical and Electronics Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of English Sri Sairam Engineering College Chennai Tamil Nadu India Department of Mathematics PSNA College of Engineering and Technology (Autonomous) Dindigul Tamil Nadu India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Internet of Things (IoT)-enabled Smart Energy Management (SEM) in distributed Energy Resources (DERs), while crucial for optimizing energy distribution and resource management faces challenges such as data inconsistencies and the variability of renewable energy generation. These issues result in inaccurate demand forecasts, leading to suboptimal allocation of resources and inefficient Energy Management (EM). Additionally, as energy demand and generation patterns are influenced by factors like weather conditions, time of day, and energy consumption behaviors, prediction models may struggle to capture these dynamic changes, affecting the reliability of forecasts. To address these limitations, this manuscript proposes a novel approach for energy demand prediction. Data is collected from IoT-enabled sensors monitoring DERs. The data undergoes pre-processing, where the Fast Resampled Iterative Filtering (FRIF) method is used to eliminate missing values and normalize the inputs. The Self-Adaptive Physics-Informed neural network (SAPINN) model then utilizes the processed data to forecast energy demand, renewable energy generation, and storage levels. Green Anaconda Optimization (GAO) is applied to optimize the weight parameters of the SAPINN model. The proposed SAPINN-GAO method is implemented using the MATLAB platform and compared with existing models, such Stacked Convoluted Bi-Directional Gated Attention network-Hybrid Darts Seagull Optimizer (SConBGAN-HDSO), Recurrent neural network (RNN), and Support Vector Machine-Particle Swarm Optimization (SVM-PSO). The SAPINN-GAO method achieves an accuracy of 99.2%, precision of 99.2%, and a Root Mean Square Error (RMSE) of 2.2%, demonstrating its superior performance in energy demand prediction. The SAPINN-GAO method's higher accuracy and precision, coupled with its robust performance, make it a reliable and efficient solution for energy demand, renewable energy generation, and storage levels forecasting in IoT-enabled SEM syst

关键词： Energy consumption Renewable energy sources Accuracy Recurrent neural networks Green products Predictive models Internet of Things Reliability Energy management Optimization

来源：评论

学校读者我要写书评

暂无评论

Space-Time Adaptive processing Based on Interpretable Multimodule Convolutional neural network

引用

IEEE SENSORS JOURNAL 2025年第7期25卷 12347-12360页

作者： Liao, Zhipeng Duan, Keqing Qiu, Zizhou Yang, Xingjia Li, Yu Sun Yat Sen Univ Sch Elect & Commun Engn Shenzhen 518107 Peoples R China Natl Key Lab Sci & Technol Space Microwave Xian 710100 Peoples R China

Space-time adaptive processing (STAP) performance in complex clutter environments often degrades due to the difficulty in obtaining sufficient independent and identically distributed (IID) training samples. Sparse recovery (SR) STAP reduces IID sample requirements but faces challenges in parameter tuning and computational complexity. Deep-learning (DL) STAP methods also lower IID sample needs and reduce online computation, but their poor interpretability limits reliability. In addition, both SR and DL STAP methods are prone to off-grid issues. To address these challenges, this article proposes a multimodule deep convolutional neural network that combines data-driven and model-driven approaches to achieve fast and accurate clutter covariance matrix estimation under small-sample conditions. The network comprises four parts: a channel self-attention module, data modules, prior modules, and a hyperparameter module. Each module has a clear mathematical foundation and physical significance, enhancing the interpretability of the network. Meanwhile, the network leverages prior knowledge of clutter ridges to nonuniformly partition the spatial-Doppler profile, effectively mitigating the impact of off-grid issues. Both simulated and measured data demonstrate that the proposed method outperforms existing small-sample STAP methods in clutter suppression within nonhomogeneous clutter environments, significantly reducing computational time.

关键词： Clutter suppression deep learning (DL) nonhomogeneous clutter off-grid effect space-time adaptive processing (STAP) Clutter suppression deep learning (DL) nonhomogeneous clutter off-grid effect space-time adaptive processing (STAP)

来源：评论

学校读者我要写书评

暂无评论

Precision Traffic Monitoring: Leveraging distributed Acoustic Sensing and Deep neural networks

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第6期26卷 7678-7689页

作者： Khacef, Yacine van den Ende, Martijn Richard, Cedric Ferrari, Andre Sladen, Anthony Univ Cote dAzur Lagrange Lab CNRS F-06000 Nice France Univ Cote dAzur Geoazur Lab IRD CNRS F-06560 Valbonne France

distributed Acoustic Sensing (DAS) has recently emerged as a promising technology for traffic monitoring. It transforms standard fiber-optic telecommunication cables into an array of vibration sensors capable of capturing vehicle-induced subsurface deformation with high spatio-temporal resolution. In this study, we propose a deep learning framework for the detection and velocity estimation of traffic flow. Our neural network based model yields accurate and well-resolved vehicle localization and speed tracking, outperforming off-the-shelf Dynamic Time Warping based solutions while achieving an order of magnitude faster processing time. A multi-day comparison with dedicated sensors installed along an urban highway shows a strong correlation, even under dense traffic conditions.

关键词： Monitoring Sensors Roads Optical fiber sensors Optical fibers Optical fiber cables Time series analysis Optical fiber networks Detectors Real-time systems Traffic monitoring intelligent transportation distributed acoustic sensing deep neural network

来源：评论

学校读者我要写书评

暂无评论

D²CN: distributed Deep Convolutional network

引用

IEEE TRANSACTIONS ON SIGNAL processing 2025年 73卷 1309-1322页

作者： Ding, Yi Shi, Junpeng Yang, Zai Zhang, Zhiyuan Liu, Yongxiang Li, Xiang Natl Univ Def Technol Coll Elect Engn Hefei 230037 Peoples R China Jiaotong Univ Sch Math & Stat Xian 710049 Peoples R China Natl Univ Def Technol Coll Elect Sci & Technol Changsha 410037 Peoples R China

With the rapid growth of distributed systems, deep learning-based multi-source data processing has drawn extensive attention, especially for the multi-channel networks. However, the conventional ones lack a strong theoretical foundation and the data in each channel lack necessary interactions, giving rise to insufficient robustness. Here we derive a network termed as distributed deep convolutional network ((DCN)-C-2) to overcome this issue, which is explained by integrating generalized singular value decomposition (GSVD) with the principles of Hankel convolution framelet. Specifically, we employ the feature extraction capability of GSVD to perform data interactions by forward/backward propagation, where numerous inputs are designed using the common bases and reliable performance is achieved by training a shared set of right bases. We go over the network's scalability to show its benefits in performance and robustness. Moreover, we show that the encoder-decoder scheme allows the network suitable for a wide range of inverse situations. Finally, we demonstrate the superiority of the (DCN)-C-2 over other fundamental networks through numerical experiments conducted on classical image denoising.

关键词： Convolution Matrix decomposition distributed databases Vectors Feature extraction Image denoising Training Data mining Decoding Numerical models Convolutional neural network GSVD image denoising deep learning

来源：评论

学校读者我要写书评

暂无评论

Intelligent Pattern Recognition Using distributed Fiber Optic Sensors for Smart Environment

引用

SENSORS 2025年第1期25卷 47-47页

作者： Pamukti, Brian Afifah, Shofuro Liaw, Shien-Kuei Sung, Jiun-Yu Chu, Daping Natl Taiwan Univ Sci & Technol Grad Inst Electroopt Engn Taipei 10607 Taiwan Natl Taiwan Univ Sci & Technol Dept Elect & Comp Engn Taipei 10607 Taiwan Univ Cambridge Ctr Photon Devices & Sensors Dept Engn Cambridge CB3 0FA England

distributed fiber optic sensors (DFOSs) have become increasingly popular for intrusion detection, particularly in outdoor and restricted zones. Enhancing DFOS performance through advanced signal processing and deep learning techniques is crucial. While effective, conventional neural networks often involve high complexity and significant computational demands. Additionally, the backscattering method requires the signal to travel twice the normal distance, which can be inefficient. We propose an innovative interferometric sensing approach utilizing a Mach-Zehnder interferometer (MZI) combined with a time forest neural network (TFNN) for intrusion detection based on signal patterns. This method leverages advanced sensor characterization techniques and deep learning to improve accuracy and efficiency. Compared to the conventional one-dimensional convolutional neural network (1D-CNN), our proposed approach achieves an 8.43% higher accuracy, demonstrating the significant potential for real-time signal processing applications in smart environments.

关键词： pattern recognition deep learning smart environment

来源：评论

学校读者我要写书评

暂无评论

A Memristor-Based neural network Circuit With Retrospective Revaluation Effect and Application in Intelligent Household Robots

引用

IEEE TRANSACTIONS ON neural networkS AND LEARNING SYSTEMS 2025年 PP卷 PP页

作者： Sun, Junwei Shen, Yijin Wang, Yingcong Wang, Yanfeng Zhengzhou Univ Light Ind Sch Elect & Informat Engn Zhengzhou 450002 Peoples R China

The traditional association theory maintains that associations between cues can change only in trials where the cue is actually presented. However, the retrospective revaluation (RR) studies the phenomenon that responses to a cue can change even when the cue is not actually presented. A hardware memristor-based neural network circuit with an RR effect is proposed in this article. The neural network circuit successfully demonstrates various phenomena of RR, including the impact of deflation and inflation of companion cue associations on target cue, higher order RR, and context dependence. The correctness of the circuit design is verified by Pspice simulation. The key feature of this design lies in its ability to learn cue associations even in training trials, where the target cues are absent. This distinctive attribute offers a fresh perspective for the creation of more intricate, brain-inspired information processing systems with enhanced integration capabilities.

关键词： Memristors Electric shock Training Biological neural networks Immune system Threshold voltage Hardware Learning systems Integrated circuit modeling Brain modeling Associative memory companion cue memristor retrospective revaluation (RR)

来源：评论

学校读者我要写书评

暂无评论

Quantum Fuzzy Federated Learning for Privacy Protection in Intelligent Information processing

引用

IEEE TRANSACTIONS ON FUZZY SYSTEMS 2025年第1期33卷 278-289页

作者： Qu, Zhiguo Zhang, Lailei Tiwari, Prayag Nanjing Univ Informat Sci & Technol Jiangsu Collaborat Innovat Ctr Atmospher Environm Equipment Technol Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Engn Res Ctr Digital Forens Minist Educ Nanjing 210044 Peoples R China Nanjing Univ Informat Sci & Technol Sch Comp Sci Nanjing 210044 Peoples R China Halmstad Univ Sch Informat Technol S-30118 Halmstad Sweden

With the advent of the intelligent information processing era, more and more private sensitive data are being collected and analyzed for intelligent decision making tasks. Such information processing also brings many challenges with existing privacy protection algorithms. On the one hand, the algorithms based on data encryption compromise the integrity of the original data or incur high computational and communication costs to some extent. On the other hand, algorithms based on distributed learning require frequent sharing of parameters between different computing nodes, which poses risks of leaking local model information and reducing global learning efficiency. To mitigate the impact of these issues, a quantum fuzzy federated learning (QFFL) algorithm is proposed. In the QFFL algorithm, a quantum fuzzy neural network is designed at the local computing nodes, which enhances data generalization while preserving data integrity. In global model, QFFL makes predictions through the quantum federated inference (QFI). QFI leads to a general framework for quantum federated learning on non-independent and identically distributed (IID) data with one-shot communication complexity, achieving privacy protection of local data and accelerating the global learning efficiency of the algorithm. The experiments are conducted on the COVID-19 and MNIST datasets, and the results indicate that QFFL demonstrates superior performance compared to the baselines, manifesting in faster training efficiency, higher accuracy, and enhanced security. In addition, based on the fidelity experiments and related analysis under four common quantum noise channels, the results demonstrated that it has good robustness against quantum noises, proving its applicability and practicality.

关键词： Data privacy Computational modeling Protection Privacy Fuzzy neural networks Quantum computing Distance learning Intelligent information processing privacy protection quantum federated inference (QFI) quantum fuzzy federated learning (QFFL) quantum fuzzy neural network (QFNN)

来源：评论

学校读者我要写书评

暂无评论

Load-Aware Orchestrator for Edge-Computing-Aided Wireless Augmented Reality

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第6期12卷 6595-6606页

作者： Qian, Weiyang Coutinho, Rodolfo W. L. Concordia Univ Dept Elect & Comp Engn Montreal PQ H3G 1M8 Canada

Mobile augmented reality (MAR) has gained increased attention thanks to its potential to transform applications in different domains. One of the challenges to realizing MAR systems is the processing of video frames efficiently. MAR user devices are often resource-constrained and unsuitable for real-time object detection and recognition from video streams. Edge computing has tremendous potential to enable MAR systems, where processing instances (e.g., serverless functions, containers, or virtual machines) can implement and manage the execution of convolutional neural networks (CNNs) for processing MAR offloaded video frames. One of the challenges is how to balance the video frames across the edge servers and processing instances. In this article, we proposed the LAOS orchestrator for resource management and load balancing of distributed edge servers for MAR systems. The LAOS orchestrator balances incoming video frames among processing instances at the edge servers that process video frames. It also determines when to spawn new instances of the CNN functions aimed at ensuring a predefined latency threshold for the processing of video frames. Besides, we devised a novel queuing-based framework for modeling the resource management problem of distributed edge servers for MAR systems. The obtained numerical results show that the proposed LAOS orchestrator reduces the latency and efficiently manages the edge computing resources when dynamic workload peaks are considered.

关键词： Augmented reality (AR) edge computing mobile computing mobile computing network performance modeling network performance modeling network performance modeling

来源：评论

学校读者我要写书评

暂无评论

Robust Airborne Radar Clutter Suppression Algorithm via Deep neural networks Under Small-Sample Conditions

引用

IEEE SENSORS JOURNAL 2025年第7期25卷 11587-11600页

作者： Huang, Weijun Wang, Tong Cui, Weichen Xidian Univ Natl Lab Radar Signal Proc Xian 710071 Peoples R China Beijing Aerosp Automat Control Inst Beijing 100854 Peoples R China Natl Key Lab Sci & Technol Aerosp Intelligence Con Beijing 100854 Peoples R China

Space-time adaptive processing (STAP) is a powerful technique for clutter suppression in airborne radar systems. However, in practical applications, STAP performance is often compromised by the limited availability of independent and identically distributed (i.i.d.) samples, which restricts its clutter suppression capabilities. Inspired by compressed sensing, researchers have extensively investigated sparse recovery-based STAP (SR-STAP) algorithms, which can achieve near-optimal performance under ideal conditions. Yet, these algorithms experience notable performance degradation in the presence of spatial and temporal errors. To address this issue, we propose a deep neural network framework for clutter suppression, cascading a gridless sparse recovery network (GLSRNet) with a generative adversarial network (GAN), ensuring accurate clutter covariance matrix estimation under small-sample conditions with errors. During GAN training, we observed that the traditional binary cross-entropy (BCE) loss function led to significant oscillations in the training loss, impeding effective convergence. To resolve this, we design a new loss function that achieves stable convergence. Extensive experiments validate the effectiveness of the proposed algorithm in clutter suppression.

关键词： Clutter Training Vectors Generative adversarial networks Signal processing algorithms Generators Airborne radar Minimization Accuracy Radar clutter Clutter suppression deep unfolding generative adversarial network (GAN) space-time adaptive processing (STAP)

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：