Neurocomputing最新文献_第7页

GlobalLight: Exploring global influence in multi-agent deep reinforcement learning for large-scale traffic signal control

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-24 DOI: 10.1016/j.neucom.2025.130065

Yilin Liu , Jintao Liang , Yifeng Zhang , Ping Gong , Guiyang Luo , Quan Yuan , Jinglin Li

{"title":"GlobalLight: Exploring global influence in multi-agent deep reinforcement learning for large-scale traffic signal control","authors":"Yilin Liu , Jintao Liang , Yifeng Zhang , Ping Gong , Guiyang Luo , Quan Yuan , Jinglin Li","doi":"10.1016/j.neucom.2025.130065","DOIUrl":"10.1016/j.neucom.2025.130065","url":null,"abstract":"<div><div>By treating each intersection as an intelligent agent, multi-agent deep reinforcement learning (MADRL) offers a promising solution to adaptive traffic signal control (ATSC) in complex urban environments. However, existing approaches often emphasize the interactions between adjacent intersections while overlooking the global influence of distant relationships. This oversight limits their scalability to small-scale traffic networks, reducing their effectiveness in real-world urban transportation systems. In this paper, we propose <em>GlobalLight</em>, a novel MADRL-based traffic signal control method that addresses these challenges by exploring and exploiting global influence in traffic networks. We first propose a multidimensional feature extraction module via a multi-head graph attention network, which captures the mutual influence among locally adjacent intersections. Then we design a similarity mining module with two loss functions to analyze node embeddings in the representation space, uncovering latent relationships across distant intersections in the global traffic network. Finally, GlobalLight enables similar intersections to share policy parameters for decision-making within an effective MADRL framework. Our method simultaneously considers local dependencies between adjacent intersections and global traffic flow influence, enhancing scalability and decision efficiency for ATSC in city-level larger-scale traffic systems. Experimental evaluations on both synthetic and real-world traffic networks, encompassing up to 1000 of intersections, demonstrate that our method significantly outperforms SOTA approaches across multiple performance metrics, particularly in large-scale traffic scenarios.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"637 ","pages":"Article 130065"},"PeriodicalIF":5.5,"publicationDate":"2025-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HB-net: Holistic bursting cell cluster integrated network for occluded multi-objects recognition

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-23 DOI: 10.1016/j.neucom.2025.130071

Xudong Gao , Xiaoguang Gao , Jia Rong , Xiaowei Chen , Xiang Liao , Jun Chen

{"title":"HB-net: Holistic bursting cell cluster integrated network for occluded multi-objects recognition","authors":"Xudong Gao , Xiaoguang Gao , Jia Rong , Xiaowei Chen , Xiang Liao , Jun Chen","doi":"10.1016/j.neucom.2025.130071","DOIUrl":"10.1016/j.neucom.2025.130071","url":null,"abstract":"<div><div>Within the realm of image recognition, a specific category of multi-label classification (MLC) challenges arises when objects within the visual field may occlude one another, demanding simultaneous identification of both occluded and occluding objects. While traditional convolutional neural networks (CNNs) address these tasks, they are often bulky and achieve only moderate accuracy. To overcome this limitation, this paper introduces HB-net, a novel integrated network framework inspired by the Holistic Bursting (HB) cell from cutting-edge neural science research. Built upon the foundation of HB cell clusters, HB-net is designed to address the intricate task of simultaneously recognizing multiple occluded objects within images. The framework incorporates various Bursting cell cluster structures along with an evidence accumulation mechanism to enhance performance. Testing on multiple datasets, including digits and letters, shows that models incorporating the HB framework achieve a significant 2.98% improvement in recognition accuracy compared to models without the HB framework (1.0298 times, p=0.0499). Although in high-noise settings, standard CNNs exhibit slightly greater robustness when compared to HB-net models, the models that combine the HB framework and EA mechanism achieve a comparable level of accuracy and resilience to ResNet50, despite having only three convolutional layers and approximately <span><math><mrow><mn>1</mn><mo>/</mo><mn>30</mn></mrow></math></span> of the parameters. These findings of this study offer valuable insights for improving computer vision algorithms. The essential code is provided at <span><span>https://github.com/d-lab438/hb-net.git</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"637 ","pages":"Article 130071"},"PeriodicalIF":5.5,"publicationDate":"2025-03-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143715503","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Competitive Nonlinear Layered Spiking Neural P System for solving classification problems

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-23 DOI: 10.1016/j.neucom.2025.130036

Hai Nan , Hongji Chen , Ping Guo , Chunmei Liao , S.M. Ahanaf Tahmid

引用次数: 0

Neural learning rules from associative networks theory 联想网络理论的神经学习规则

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.129865

Daniele Lotito

引用次数: 0

A novel approach based on clustering and optimized ensemble deep learning for energy consumption forecasting in Ethiopia

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.130027

E. Tefera Habtemariam , M. Martínez-Ballesteros , A. Troncoso , F. Martínez-Álvarez

{"title":"A novel approach based on clustering and optimized ensemble deep learning for energy consumption forecasting in Ethiopia","authors":"E. Tefera Habtemariam , M. Martínez-Ballesteros , A. Troncoso , F. Martínez-Álvarez","doi":"10.1016/j.neucom.2025.130027","DOIUrl":"10.1016/j.neucom.2025.130027","url":null,"abstract":"<div><div>Predicting energy consumption accurately is crucial for optimizing energy management strategies and achieving sustainability goals. Traditional methods often struggle with the complexity of energy consumption patterns, particularly in developing regions such as Ethiopia, where unique challenges exist. This study proposes an ensemble deep learning approach that integrates multiple models to enhance prediction accuracy. Additionally, as a previous step, a clustering process has been applied to discover different groups of customers. Our method combines deep learning architectures, including Gated Recurrent Units, Long Short-Term Memory, and Convolutional Neural Networks, within an optimized ensemble with weights computed with the Coronavirus Optimization Algorithm. This approach aims to leverage the strengths of each model to produce robust and reliable predictions. We demonstrate that our ensemble approach yields competitive results, outperforming individual models within the ensemble. By integrating diverse models, our framework captures nuanced patterns in energy consumption data more effectively, contributing to improved prediction accuracy. Furthermore, we validate the effectiveness of our approach using three distinct datasets from Ethiopia for three different customer clusters. These datasets represent different regions and consumption profiles within the country, ensuring the robustness and generalizability of our proposed methodology.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"637 ","pages":"Article 130027"},"PeriodicalIF":5.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143739549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-level semantic-assisted prototype learning for Few-Shot Action Recognition

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.130022

Dan Liu , Qing Xia , Fanrong Meng , Mao Ye , Jianwei Zhang

{"title":"Multi-level semantic-assisted prototype learning for Few-Shot Action Recognition","authors":"Dan Liu , Qing Xia , Fanrong Meng , Mao Ye , Jianwei Zhang","doi":"10.1016/j.neucom.2025.130022","DOIUrl":"10.1016/j.neucom.2025.130022","url":null,"abstract":"<div><div>The Few-Shot Action Recognition (FSAR) task involves recognizing new categories with limited labeled data. The conventional fine-tuning-based adaptation approach is often prone to overfitting and lacks temporal modeling for video data. Moreover, the discrepancy in distribution between meta-training and meta-test sets can also lead to suboptimal performance in few-shot scenarios. This paper introduces a simple yet effective multi-level semantic-assisted prototype learning framework to tackle these challenges. Initially, we leverage CLIP to achieve multimodal adaptation learning and present a multi-level semantic-assisted learning module to enhance the prototypes of different action classes based on semantic information. Additionally, we integrate the lightweight adapters into the CLIP visual encoder to support parameter-efficient transfer learning and improve temporal modeling in videos. Especially, a bias compensation block is employed for feature rectification to mitigate the distribution bias in FSAR stemming from data scarcity. Extensive experiments conducted on five standard benchmark datasets demonstrate the effectiveness of the proposed method.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130022"},"PeriodicalIF":5.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Prescribed performance event-triggered optimal control of nonlinear multi-input systems

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.130044

Yu Tang , Yongfeng Lv , Jun Zhao , Long Jian , Linwei Li

引用次数: 0

Dynamic facial expression recognition in the wild via Multi-Snippet Spatiotemporal Learning

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.130020

Yang Lü , Fuchun Zhang , Zongnan Ma , Bo Zheng , Zhixiong Nan

{"title":"Dynamic facial expression recognition in the wild via Multi-Snippet Spatiotemporal Learning","authors":"Yang Lü , Fuchun Zhang , Zongnan Ma , Bo Zheng , Zhixiong Nan","doi":"10.1016/j.neucom.2025.130020","DOIUrl":"10.1016/j.neucom.2025.130020","url":null,"abstract":"<div><div>Dynamic Facial Expression Recognition (DFER) in-the-wild poses a significant challenge in emotion recognition research. Many studies have focused on extracting finer facial features while overlooking the effect of noisy frames on the entire sequence. In addition, the imbalance between short- and long-term temporal relationships remains inadequately addressed. To tackle these issues, we propose the Multi-Snippet Spatiotemporal Learning (MSSL) framework that uses distinct temporal and spatial modeling for snippet feature extraction, enabling more accurate simulation of subtle facial expression changes while capturing finer details. We also introduced a dual-branch hierarchical module, BiTemporal Multi-Snippet Enhancement (BTMSE), which is designed to capture spatiotemporal dependencies and model subtle visual changes across snippets effectively. The Temporal-Transformer further enhances the learning of long-term dependencies, whereas learnable temporal position embeddings ensure consistency between snippet and fused features over time. By leveraging (2+1)D multi-snippet spatiotemporal modeling, BTMSE, and the Temporal-Transformer, MSSL hierarchically explores the complex interrelationships between temporal dynamics and facial expressions. Comparative experiments and ablation studies confirmed the effectiveness of our method on three large-scale in-the-wild datasets: DFEW, FERV39K, and MAFW.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130020"},"PeriodicalIF":5.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687118","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Distributed neural predictor enhanced coordinated control of AUVs

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.129971

Minjing Wang , Di Wu , Lei Qiao , Rui Gao , Wenlong Feng

{"title":"Distributed neural predictor enhanced coordinated control of AUVs","authors":"Minjing Wang , Di Wu , Lei Qiao , Rui Gao , Wenlong Feng","doi":"10.1016/j.neucom.2025.129971","DOIUrl":"10.1016/j.neucom.2025.129971","url":null,"abstract":"<div><div>This article investigates an enhanced tunnel prescribed performance coordinated control problem of multiple autonomous underwater vehicles (AUVs) under initial constraints. To meet high performance requirements in complex underwater conditions, AUV control faces challenges. In order to address these, an enhanced tunnel prescribed performance (ETPP) method is proposed, which is composed of composite error scaling function (CESF) and tunnel prescribed performance (TPP). In particular, a CESF-based error transformation is performed to scale the tracking error within the TPP limits. In the guidance loop, an ETPP-based guidance law is devised to guarantee the transient and steady-state behavior of the tracking error. In the control loop, based on the distributed learning strategy with weighted average, a quantized input-based distributed neural predictor (QDNP) is proposed to estimate the unknown external disturbances. Using the antidisturbance technique, a QDNP-based quantized control law is designed to stabilize multi-AUV formations. The uniformly ultimately bounded (UUB) stability of the overall closed-loop system is established in the Lyapunov sense. Finally, simulation examples with four AUVs are provided to demonstrate the effectiveness of the proposed distributed tunnel performance-guaranteed coordinated control method.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 129971"},"PeriodicalIF":5.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143687100","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Attributed network community detection based on graph contrastive learning and multi-objective evolutionary algorithm

IF 5.5 2区计算机科学

Neurocomputing Pub Date : 2025-03-22 DOI: 10.1016/j.neucom.2025.130029

Yao Liang , Jian Shu , Linlan Liu

{"title":"Attributed network community detection based on graph contrastive learning and multi-objective evolutionary algorithm","authors":"Yao Liang , Jian Shu , Linlan Liu","doi":"10.1016/j.neucom.2025.130029","DOIUrl":"10.1016/j.neucom.2025.130029","url":null,"abstract":"<div><div>Attributed network community detection holds significant research value for network structure analysis and practical applications. However, existing methods still face significant challenges in addressing the conflicts between topological structure and attribute features, as well as balancing structural tightness and attribute similarity in community detection. In light of this, we propose a community detection method based on graph contrastive learning and multi-objective evolutionary algorithm (GCL-MOEA) for attributed networks. Specifically, GCL-MOEA contains two core parts: node embedding and community detection. Considering the conflict between topological structure and attribute features, the node embedding part constructs topology-augmented and attribute-augmented views, which are utilized in a cross-view graph contrastive learning model. This model comprehensively extracts node features to obtain node embedding vectors, effectively preserving the consistency and complementarity between the structure and attributes. The community detection part utilizes clustering results of node embeddings to construct high-quality initial populations. A multi-objective evolutionary algorithm is subsequently employed to obtain community structures where nodes are tightly connected and have similar attributes. The effectiveness of the proposed method is validated on five real-world networks. Experimental results demonstrate that GCL-MOEA outperforms baselines in terms of ACC, NMI, ARI, and F1, obtaining better community detection results.</div></div>","PeriodicalId":19268,"journal":{"name":"Neurocomputing","volume":"636 ","pages":"Article 130029"},"PeriodicalIF":5.5,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143706022","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0