检索结果-内蒙古大学图书馆

Training Latency Minimization for Model-Splitting Allowed Federated Edge Learning

IEEE Transactions on Network Science and Engineering 2025年第3期12卷 2081-2092页

作者： Wen, Yao Zhang, Guopeng Wang, Kezhi Yang, Kun China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Brunel University London Department of Computer Science MiddlesexUB8 3PH United Kingdom Nanjing University State Key Laboratory of Novel Software Technology Nanjing210008 China School of Intelligent Software and Engineering Nanjing University Suzhou Campus Suzhou215163 China

To alleviate the shortage of computing power faced by clients in training deep neural networks (DNNs) using federated learning (FL), we leverage the edge computing and split learning to propose a model-splitting allowed FL (SFL) framework, with the aim to minimize the training latency without loss of test accuracy. Under the synchronized global update setting, the latency to complete a round of global training is determined by the maximum latency for the clients to complete a local training session. Therefore, the training latency minimization problem (TLMP) is modelled as a minimizing-maximum problem. To solve this mixed integer nonlinear programming problem, we first propose a regression method to fit the quantitative-relationship between the cut-layer and other parameters of an AI-model, and thus, transform the TLMP into a continuous problem. Considering that the two subproblems involved in the TLMP, namely, the cut-layer selection problem for the clients and the computing resource allocation problem for the parameter-server are relative independence, an alternate-optimization-based algorithm with polynomial time complexity is developed to obtain a high-quality solution to the TLMP. Extensive experiments are performed on a popular DNN-model EfficientNetV2 using dataset MNIST, and the results verify the validity and improved performance of the proposed SFL framework. © 2013 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Dual-encoder model for typhoon path prediction with multiscale spatiotemporal data fusion

引用

Earth Science Informatics 2025年第2期18卷 1-17页

作者： Ren, Shuxia Zhong, Ruikun Guo, Zewei Zhang, Zining School of Software Engineering Tiangong University Tianjin 300387 China School of Computer Science and Technology Tiangong University Tianjin 300387 China

Extreme weather caused by typhoons poses a severe threat to human life safety and socio-economic development, making accurate prediction of typhoon paths crucial. However, existing prediction models struggle to effectively handle and integrate heterogeneous data, overlooking deep correlations between the data, which in turn affects the accuracy of the models. This paper proposes a Dual-Encoder Spatiotemporal Fusion Model for Typhoon Path Prediction (DESF-Typhoon), designed to effectively integrate data from different time scales and extract the underlying relationships between the data, thereby improving prediction accuracy. Specifically, we designed a dual-encoder module that effectively captures complex nonlinear data structures, accounting for the intricate influences of factors such as geography and environment on path, while integrating spatial features of typhoon at different time scales. Subsequently, we introduced a feature interaction module to explore the relationships between different features, which can adaptively learn the interaction weights between them, resulting in a richer feature representation. We evaluated the model using the dataset from the China Meteorological Administration (CMA) and compared its performance with traditional prediction methods and deep learning-based approaches. The results demonstrate that the model significantly improves accuracy and robustness, making innovative contributions in data fusion and spatiotemporal feature modeling. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Dual encoder Feature interaction Spatiotemporal data Tropical cyclone prediction

来源：评论

学校读者我要写书评

暂无评论

CogLign: Interpretable Text Sentiment Determination by Aligning Cognition Between EEG-Derived Brain Graph and Text-Derived Knowledge Graph

引用

IEEE Transactions on Knowledge and Data Engineering 2025年第6期37卷 3220-3239页

作者： Rong, Huan Ji, Wenxuan Ma, Tinghuai Ding, Weiyi Sheng, Victor S. Jiangsu210044 China Nanjing University of Information Science and Technology School of Computer and Software Jiangsu210044 China Texas Tech University Department of Computer Science LubbockTX79409 United States

Nowadays, detecting sentiment or emotion from user generated texts has been intensively studied in natural language understanding, especially via neural-based models based on text representation. However, the interpretability on how could the final text sentiment be determined by neural-based text representation has not been thoroughly unfolded yet. Consequently, in this paper, we propose CogLign which injects the neural-cognition derived from Electroencephalogram (EEG)-signal into the neural-based text sentiment analysis model, aimed at learning the activation of brain regions stimulated by different sentiments, so as to guide our proposed CogLign to make proper determination on text sentiment in brain-like way. Specifically, on the one hand, the given videos in different sentiments have been watched by subjects, during which the EEG-signals are monitored to construct brain connectivity pattern as brain graph (BG), attaining more obvious sentiment response on brain region activation for neural-cognition. On the other hand, we interpret the video-plots (or video-semantics) along timeline into text, where the entire video-interpreted-text will be strictly bound with the whole EEG-signal-sequence by segment via the fixed size of time-window. Then, entities and relations are extracted from the video-interpreted-text to construct knowledge graph (KG), depicting text semantics. Next, mapping from entities (or nodes) in KG to EEG-Electrodes (or nodes) in BG, further dated back to different brain regions, has been learned via cognition alignment between the EEG-derived BG and text-derived KG. In this way, by aligning neural cognition from brain graph with the semantic cognition from knowledge graph, our proposed framework CogLign can not only achieve the overall best sentiment analysis performance on the video-interpreted-text, but can also detect brain connectivity patterns in different sentiments more consistent with the prior conclusion of brain region sentiment prefere

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Characterizing the app recommendation relationships in the iOS app store: a complex network's perspective

引用

Science China(Information Sciences) 2025年第4期68卷 284-299页

作者： Gang HUANG Fuqi LIN Yun MA Haoyu WANG Qingxiang WANG Gareth TYSON Xuanzhe LIU Key Lab of High Confidence Software Technologies (Peking University) Ministry of Education School of Computer Science Peking University Institute for Artificial Intelligence Peking University School of Cyber Science and Engineering Huazhong University of Science and Technology Alibaba Group Hong Kong University of Science and Technology (Guangzhou)

Mobile apps have become widely adopted in our daily lives. To facilitate app discovery, most app markets provide recommendations for users, which may significantly impact how apps are accessed. However, little has been known about the underlying relationships and how they reflect(or affect) user behaviors. To fill this gap, we characterize the app recommendation relationships in the i OS app store from the perspective of the complex network. We collect a dataset containing over 1.3 million apps and 50 million app recommendations. This dataset enables us to construct a complex network that captures app recommendation relationships. Through this, we explore the recommendation relationships between mobile apps and how these relationships reflect or affect user behavior patterns. The insights gained from our research can be valuable for understanding typical user behaviors and identifying potential policy-violating apps.

关键词： mobile app recommendation complex network user behavior policy-violating app

来源：评论

学校读者我要写书评

暂无评论

DIEONet:Domain-Invariant Information Extraction and Optimization Network for Visual Place Recognition

引用

computers, Materials & Continua 2025年第3期82卷 5019-5033页

作者： Shaoqi Hou Zebang Qin Chenyu Wu Guangqiang Yin Xinzhong Wang Zhiguo Wang School of Computer Science and Technology Xinjiang UniversityUrumqi830046China School of Information and Software Engineering University of Electronic Science and Technology ofChinaChengdu611731China Institute of Public Security Kash Institute of Electronics and Information IndustryKashi844000China

Visual Place Recognition(VPR)technology aims to use visual information to judge the location of agents,which plays an irreplaceable role in tasks such as loop closure detection and *** is well known that previous VPR algorithms emphasize the extraction and integration of general image features,while ignoring the mining of salient features that play a key role in the discrimination of VPR *** this end,this paper proposes a Domain-invariant Information Extraction and Optimization Network(DIEONet)for *** core of the algorithm is a newly designed Domain-invariant Information Mining Module(DIMM)and a Multi-sample Joint Triplet Loss(MJT Loss).Specifically,DIMM incorporates the interdependence between different spatial regions of the feature map in the cascaded convolutional unit group,which enhances the model’s attention to the domain-invariant static object *** Loss introduces the“joint processing of multiple samples”mechanism into the original triplet loss,and adds a new distance constraint term for“positive and negative”samples,so that the model can avoid falling into local optimum during *** demonstrate the effectiveness of our algorithm by conducting extensive experiments on several authoritative *** particular,the proposed method achieves the best performance on the TokyoTM dataset with a Recall@1 metric of 92.89%.

关键词： Visual place recognition domain-invariant information mining module multi-sample joint triplet loss

来源：评论

学校读者我要写书评

暂无评论

Automatic Positioning of Intelligent Mobile Robot Based on Improved Front-End Scanning Matching

Journal of Network Intelligence

引用

Journal of Network Intelligence 2025年第1期10卷 559-572页

作者： Wang, Hong Wang, Yi-Gui Zhang, Jie Department of Computer and Software Engineering Shandong College of Electronic Technology Jinan250200 China School of Computer Science and Technology Shandong Jianzhu University Jinan250101 China College of Agricultural Science and Technology Yana Royal Polytechnic University Chiang Mai50000 Thailand

Traditional autonomous navigation methods for mobile robots mainly rely on geometric feature-based LiDAR scan-matching algorithms, but in complex environments, this method is often affected due to the presence of moving objects, occlusions, and other interfering factors, resulting in a decrease in positioning accuracy. With the growing demand for robotics applications in logistics, security, exploration and other fields, the need for robust autonomous navigation and high-precision mapping in highly dynamic and complex environments is becoming more and more urgent. To solve this problem, an improved front-end scan matching algorithm based on Frequency Modulated Continuous Wave (FMCW) LiDAR is proposed in this paper. Firstly, by using the target Doppler velocity information provided by the FMCW LiDAR, we design a novel point cloud segmentation algorithm based on velocity clustering, which is able to effectively distinguish between stationary and moving objects, and avoid the dynamic interference affecting the position estimation. Secondly, we introduce the Gaussian Mixture Model Sampling Consistency (GMMSC) algorithm, which is more robust to reject the mis-matched pairs in the scanning matching process and improve the alignment accuracy. Finally, based on the residual high-quality matched pairs, we combine the classical ICP algorithm with the robust kernel function to further enhance the stability of the position estimation in the case of occlusion and local mismatch. The experimental results show that the proposed improved algorithm significantly improves the mapping capability of mobile robots in complex environments compared with the existing techniques. The average relative error of the improved front-end scanning matching algorithm is reduced by 40.6 % compared with the pre-improved one. © 2025, Taiwan Ubiquitous Information CO LTD. All rights reserved.

关键词： Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Auto-3D-house Design from Structured User Requirements

引用

Machine Intelligence Research 2025年第2期22卷 368-385页

作者： Minkui Tan Qi Chen Zixiong Huang Qi Wu Yuanqing Li Jiaqiu Zhou School of Software Engineering South China University of TechnologyGuangzhou 510006China Faculty of Engineering Computer and Mathematical ScienceUniversity of AdelaideAdelaide SA 5005Australia School of Automation Science and Engineering South China University of TechnologyGuangzhou 510006China

We study the task of automated house design,which aims to automatically generate 3D houses from user ***,in the automatic system,it is non-trivial due to the intrinsic complexity of house designing:1)the understanding of user requirements,where the users can hardly provide high-quality requirements without any professional knowledge;2)the design of house plan,which mainly focuses on how to capture the effective information from user *** address the above issues,we propose an automatic house design framework,called auto-3D-house design(A3HD).Unlike the previous works that consider the user requirements in an unstructured way(e.g.,natural language),we carefully design a structured list that divides the requirements into three parts(i.e.,layout,outline,and style),which focus on the attributes of rooms,the outline of the building,and the style of decoration,*** the processing of architects,we construct a bubble diagram(i.e.,graph)that covers the rooms′attributes and relations under the constraint of *** addition,we take each outline as a combination of points and orders,ensuring that it can represent the outlines with arbitrary ***,we propose a graph feature generation module(GFGM)to capture layout features from the bubble diagrams and an outline feature generation module(OFGM)for outline ***,we render 3D houses according to the given style requirements in a rule-based *** on two benchmark datasets(i.e.,RPLAN and T3HM)demonstrate the effectiveness of our A3HD in terms of both quantitative and qualitative evaluation metrics.

关键词： Automated house design user requirements understanding outline processing layout generation graph feature generation.

来源：评论

学校读者我要写书评

暂无评论

Reflective clothing detection based on YOLOv5s fused with SE attention mechanism

引用

International Journal of Reasoning-based Intelligent Systems 2025年第1期17卷 9-16页

作者： Wang, Yuanyuan Gu, Dingyun Zhu, Yemeng Zhang, Zhihan Cao, Jiahui Zhang, Haiyan School of Computer and Software Engineering Huaiyin Institute of Technology Huaian223001 China Engineering Laboratory of Mobile Interconnection Technology for Internet of Things Jiangsu Province Huai’an Huaian City223001 China

This paper proposes a YOLOv5s deep learning algorithm incorporating the SE attention mechanism to address the issue of workers failing to wear reflective clothing on duty, which has resulted in casualties from time to time. The YOLOv5s model is used to train the reflective clothing dataset obtained by collecting images of construction sites, and the SE attention mechanism module is added to the network structure of YOLOv5 for improved performance. The reflective clothing detection algorithm is then deployed to the web for real-time detection. The experimental results show that the algorithm achieves mAP value of 96.70% with the SE attention module, resulting in an accuracy improvement of 1.09% compared to the model without the SE module. This enables practical applications to reduce the incidence of construction accidents at construction sites. Coрyright © 2025 Inderscience Enterрrises Ltd.

关键词： attention mechanism flask reflective clothing detection vue YOLOv5

来源：评论

学校读者我要写书评

暂无评论

Heterologous Image Matching Based on Salience Region

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer Science 2025年第4期52卷 894-900页

作者： Zhai, Jinlong Xu, Yang Yan, Xiaohu Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China School of Computer Science and Software Engineering University of Science and Technology LiaoNing Anshan114051 China Institute of Applied Artificial Intelligence of the Guangdong-Hong Kong-Macao Greater Bay Area Shenzhen Polytechnic University Shenzhen518055 China

To address the matching problem caused by the significant differences in spatial features, spectrum and contrast between heterologous images, a heterologous image matching method based on salience region is proposed in this paper. Firstly, texture features and corner features are detected. Secondly, the epanechnikov kernel function is used to calculate the point with the maximum kernel function value among all feature points, which is then defined as E-point. Thirdly, the salience region is defined and extracted according to the position of the E-point. Finally, six groups of heterologous images are used as data sources, and compared with HAPCG, HOWP, SIFT, and PSO_SIFT algorithms respectively. The results show that the comprehensive matching performance of the proposed method is better than the original algorithm without salience region processing. The root mean square error and the matching time are less than the original method while ensuring a similar number of matching points, which greatly improves the accuracy and speed of heterologous image matching. © (2025.0), (International Association of Engineers). All Rights Reserved.

关键词： Image matching

来源：评论

学校读者我要写书评

暂无评论

DROWN: Towards Tighter LiRPA-based Robustness Certification 31

DROWN: Towards Tighter LiRPA-based Robustness Certification

引用

31st International Conference on Computational Linguistics, COLING 2025

作者： Zhang, Yunruo Du, Tianyu Ji, Shouling Guo, Shanqing School of Cyber Science and Technology Shandong University China School of Software Technology Zhejiang University China College of Computer Science and Technology Zhejiang University China

ISBN: (纸本)9798891761964

The susceptibility of deep neural networks to adversarial attacks is a well-established concern. To address this problem, robustness certification is proposed, which, unfortunately, suffers from precision or scalability issues. In this paper, we present DROWN (Dual CROWN), a novel method for certifying DNNs' robustness. The advantage of DROWN is that it tightens classic LiRPA-based methods yet maintains similar scalability, which comes from refining pre-activation bounds of ReLU (and other activations) relaxations using two pairs of linear bounds derived from different relaxations of ReLU units in previous layers. The extensive evaluations show that DROWN achieves up to 83.39% higher certified robust accuracy than the baseline on CNNs and up to 4.68 times larger certified radii than the baseline on Transformers. Meanwhile, the running time of DROWN is about twice that of the baseline. © 2025 Association for Computational Linguistics.

关键词： Deep neural networks

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：