检索结果-内蒙古大学图书馆

Evaluating the performance of gaze interaction for map target selection

The American Cartographer 2025年第1期52卷

作者： Changbo Zhang Hua Liao Jinhua Meng a School of Geographic Sciences Hunan Normal University Changsha Chinab Hunan Key Laboratory of Geospatial Big Data Mining and Application Hunan Normal University Changsha China

ABSTRACTThe eye tracking approach has the potential to facilitate more tailored and intelligent geoapplication interactions. There is a lack of knowledge regarding how gaze interaction influences user performance (accuracy and efficiency), visual behavior, and cognitive workload in real-world map-reading settings. In this study, we adopted a low-cost eye tracker and dwell time method to implement a fundamental gaze-based map interaction: target (point, line and area) selection. We administered a comparative experiment in which 36 participants were asked to perform a series of map target selection tasks using gaze-based and mouse interactions. The results demonstrated that gaze-based map interaction is comparable to mouse in terms of overall efficiency. By evaluating the visual behavior of the participants, we found that mouse interaction exhibited heightened fixation frequency and larger saccade amplitude than gaze interaction. Although gaze-based map interaction frustrated participants more often, the overall cognitive workload was no different from that of mouse interaction. These differences between interaction modes were largely affected by task types but rarely dependent on target shapes or positions. Moreover, participants evaluated gaze interaction higher in terms of attractiveness, stimulation and novelty. These results are beneficial for map interaction researchers and developers.

关键词： Gaze-based map interaction human-computer interaction (HCI) eye tracking visual behavior cognitive workload

来源：评论

学校读者我要写书评

暂无评论

Unsupervised learning for lake underwater vegetation classification: Constructing high-precision, large-scale aquatic ecological datasets

引用

Science of the Total Environment 2025年 958卷 177895页

作者： Liu, Lei Bao, Zhengsen Liang, Ying Deng, Huanxi Zhang, Xiaolin Cao, Te Zhou, Chichun Zhang, Zhenyu School of Engineering Dali University Yunnan 671003 China National Observation and Research Station of Erhai Lake Ecosystem in Yunnan Dali671006 China Air-Space-Ground Integrated Intelligence and Big Data Application Engineering Research Center of Yunnan Provincial Department of Education Yunnan 671003 China State Key Laboratory of Freshwater Ecology and Biotechnology Institute of Hydrobiology Chinese Academy of Sciences Wuhan430072 China

Monitoring underwater vegetation is vital for evaluating lake ecosystem health. Automated data collection and analysis play key roles in achieving large-scale, high-precision, and high-frequency monitoring. While technologies such as unmanned vessels have made data collection more efficient, challenges persist in the analysis process, particularly in addressing the varied needs of different lake environments. Supervised AI methods can automatically identify underwater vegetation but are heavily reliant on labeled datasets. In practice, models trained on public datasets often struggle with generalization due to differences in vegetation types, collection environments, and equipment, resulting in discrepancies between training and testing datasets. Moreover, traditional dataset construction methods that rely on manual annotation are time-consuming and costly, limiting their scalability and application. This study aims to overcome these challenges by proposing an unsupervised method for automatically classifying underwater vegetation data, aiming to reduce manual annotation efforts and construct unbiased datasets at lower costs with greater efficiency. Compared with existing unsupervised, self-supervised, and unsupervised domain adaptation methods, this method introduces two key innovations: 1) a two-step dimensionality reduction method that combines pre-trained model and manifold learning to extract key features and 2) a multialgorithm voting mechanism to increase classification confidence. These features enable high-accuracy classification without prior data annotation. Experiments show 97.32 % accuracy on public dataset and 92.43 % and 96.15 % accuracy on private datasets from Erhai Lake and Wuhan East Lake, respectively, surpassing supervised methods and matching manual classification. Additionally, it drastically reduces the annotation effort, requiring only approximately 20 labeled images to classify thousands of points. By integrating unmanned vessel technology,

关键词： Lake ecological monitoring Species classification Unbiased datasets Underwater vegetation Unsupervised methods

来源：评论

学校读者我要写书评

暂无评论

UAV-Based Thermal Radiation Directionality Capture and Its Evaluation on Kernel-Driven Models

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Hu, Qingyang Yu, Wenping Zhu, Shenchao Huang, Yajun Zhang, Xi Liu, Meng Cao, Biao Southwest University Chongqing Engineering Research Center for Remote Sensing Big Data Application School of Geographical Sciences Chongqing400715 China Yibin Academy of Southwest University Yibin644000 China Jiaying University School of Geographic Sciences and Tourism Guangdong Meizhou514000 China Aerospace Information Research Institute Chinese Academy of Sciences State Key Laboratory of Remote Sensing Science Beijing100101 China

In order to correct the land surface temperature (LST) errors caused by angular effects to normalize the multisource data, various models have been proposed, especially the kernel-driven model shows good prospects for development. However, there are fewer studies on the validation of thermal radiation directionality (TRD) characteristics of features based on real measurements. In this article, a method based on unmanned aerial vehicle (UAV) observation of TRD characteristics of different surfaces is proposed to validate the TRD, which uses the circling flight mode to obtain the thermal radiation characteristics of features in multiple directions. Observations show that there is a significant hotspot effect in the three vegetation scenes, and the TRD and dispersion degree are different due to the differences in vegetation structure. For the realization of further applications of UAV-based methods for measuring TRD, the UAV-based angular observations are evaluated against the simulation results of the current kernel-driven model with high accuracy, and the results show that the correlation coefficients are all greater than 0.78, the coefficients of determination are greater than 0.60, and the root-mean-square error (RMSE) is less than 1. However, the ability of the model to extrapolate forward varies considerably in different vegetation scenes. The present study provides an effective and potential way to observe the TRD, which can lay a practical foundation for the theoretical study and model simulation of the TRD. © 2025 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

HodgeRankWeight: An Integration Algorithm for Feature Ranking Based on Weight Quantization

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 528-536页

作者： Chaolu Meng Yunyun Shi Quan Zou Ruijun Liu Colledge of Computer and Information Engineering Inner Mongolia Autonomous Region Key Laboratory of Big Data Research and Application of Agriculture and Animal Husbandry Inner Mongolia Agricultural University Hohhot China Colledge of Computer and Information Engineering Inner Mongolia Agricultural University Hohhot China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu China School of Software Beihang University Beijing China

The identification of protein sequences depends on the effective selection of an optimized set of features. Traditional algorithms prioritize global feature importance, often overshadowing the significance of local metrics. Addressing this imbalance, we introduce an innovative algorithm that fuses feature ranking with an advanced weight quantization technique. This algorithm unfolds in two pivotal stages: initially, it generates a weighted directed graph based on normal distribution metrics; subsequently, it employs the HodgeRank algorithm to amalgamate these rankings. Specifically, the algorithm evaluates feature score normality by employing z-scores for skewness and kurtosis, resulting in a graph that quantitatively reflects both local and global feature contributions. HodgeRank then translates this graph into a Laplacian matrix, enabling the calculation of a comprehensive scoring function for each feature. We refine the initial rankings by incorporating weights during the integration phase, capturing a holistic view of feature significance. The proposed method, termed HodgeRankWeight, showcases superior performance, achieving accuracy rates of 87.02%, 92.84%, and 74.51% across different datasets. In head-to-head comparisons, HodgeRankWeight outstripped existing models, achieving an overall accuracy of 82.6923% and setting a new benchmark for precision in protein sequence identification. We also offer a complimentary web server for related research.

关键词： Sorting Directed graphs Kurtosis Gaussian distribution Feature extraction Measurement Matrix decomposition Bioinformatics Vectors Quantization (signal)

来源：评论

学校读者我要写书评

暂无评论

Convolutional Attention Fusion for RGBT Tracking

引用

IEEE Signal Processing Letters 2025年 32卷 2149-2153页

作者： Zhang, Dawei Wang, Xuan Xiao, Xin Chen, Hao Zheng, Zhonglong Zhejiang Normal University School of Computer Science and Technology Jinhua 321004 China Zhejiang Normal University Zhejiang Key Laboratory of Intelligent Education Technology and Application Jinhua 321004 China Big Data AI Research Institute of China Telecom Corporation Limited Jinhua Branch China

RGBT target tracking accomplishes the tracking task by fusing visible and thermal infrared information. The development of Convolutional Neural Networks (CNNs) and Transformer has greatly advanced this field. Most existing transformer-based trackers focus on global modeling while neglecting the utilization of local information. In this paper, we propose a novel Convolutional Attention Fusion Module (CAFM) for RGBT target tracking. To be specific, this module continuously slides local windows on the image like convolution, and captures context features in each window like attention. Additionally, local position embedding is added to the window and works in conjunction with global position embedding to enhance the model's understanding of spatial information. Therefore, our CAFM enhances the extraction of local features by restricting the attention area and promotes multimodal fusion through cross-attention. We extend OSTrack to RGBT tracking and integrate the proposed CAFM into it. Experimental results show that our method performs well on the LasHeR, RGBT210, and RGBT234 datasets, and is superior to other advanced trackers. © 1994-2012 IEEE.

关键词： attention convolution local features multimodal fusion RGBT target tracking

来源：评论

学校读者我要写书评

暂无评论

ZuantuSet: A Collection of Historical Chinese Visualizations and Illustrations

arXiv

引用

arXiv 2025年

作者： Mei, Xiyao Zhang, Yu Yang, Chaofan Shi, Rui Yuan, Xiaoru National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University Beijing China Department of Computer Science University of Oxford Oxford United Kingdom Center for Research on Ancient Chinese History Peking University Beijing China National Engineering Laboratory for Big Data Analysis and Application Peking University Beijing China PKU-WUHAN Institute for Artificial Intelligence Wuhan China

Historical visualizations are a valuable resource for studying the history of visualization and inspecting the cultural context where they were created. When investigating historical visualizations, it is essential to consider contributions from different cultural frameworks to gain a comprehensive understanding. While there is extensive research on historical visualizations within the European cultural framework, this work shifts the focus to ancient China, a cultural context that remains underexplored by visualization researchers. To this aim, we propose a semi-automatic pipeline to collect, extract, and label historical Chinese visualizations. Through the pipeline, we curate ZuantuSet, a dataset with over 71K visualizations and 108K illustrations. We analyze distinctive design patterns of historical Chinese visualizations and their potential causes within the context of Chinese history and culture. We illustrate potential usage scenarios for this dataset, summarize the unique challenges and solutions associated with collecting historical Chinese visualizations, and outline future research directions. Copyright © 2025, The Authors. All rights reserved.

关键词： data collection

来源：评论

学校读者我要写书评

暂无评论

Hyper-IIoT: A Smart Contract-inspired Access Control Scheme for Resource-constrained Industrial Internet of Things

IEEE Transactions on Sustainable Computing

引用

IEEE Transactions on Sustainable Computing 2025年

作者： Li, Dun Li, Hongzhi Crespi, Noel Minerva, Roberto Li, Ming Liang, Wei Li, Kuan-Ching Tsinghua University Department of Industrial Engineering China Institut Polytechnique de Paris Samovar Telecom SudParis Palaiseau91120 France Chizhou University College of Big Data and Artificial Intelligence Chizhou247100 China The Hong Kong Polytechnic University Research Institute for Advanced Manufacturing Hung Hom Hong Kong Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Sanya Research Institute Hunan Key Laboratory for Service Computing and Novel Software Technology China Providence University Dept. of Computer Science and Information Engineering Taiwan

In recent years, the refinements in industrial processes and the increasing complexity of managing privacy-sensitive data in Industrial Internet of Things (IIoT) devices have highlighted the need for secure, robust, and adaptive data management solutions. In this work, we propose a smart contract-assisted access control scheme for IIoT, which employs the Attribute-Based Access Control (ABAC) model to set access permissions for different industrial components. Besides, we defined a storage model and data format for private data by designing and deploying smart contracts to manage system operations and access policies. In addition, the bloom filter component is deployed to optimize the efficiency of contract management and system performance. Experimental results show that in real-world simulations, Hyper-IIoT demonstrates excellent contract execution time control, stable system throughput, and rapid consensus processes that are capable of handling high throughput and efficient consensus in distributed systems, even in large-scale request scenarios. © 2016 IEEE.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Visual abstraction of dynamic network via improved multi-class blue noise sampling

引用

Frontiers of Computer Science 2023年第1期17卷 171-185页

作者： Yanni PENG Xiaoping FAN Rong CHEN Ziyao YU Shi LIU Yunpeng CHEN Ying ZHAO Fangfang ZHOU School of Computer Science and Engineering Central South UniversityChangsha 410083China Institute of Big Data Hunan University of Finance and EconomicsChangsha 410205China Rail Data Research and Application Key Laboratory of Hunan Province Changsha 410083China

Massive sequence view (MSV) is a classic timeline-based dynamic network visualization approach. However, it is vulnerable to visual clutter caused by overlapping edges, thereby leading to unexpected misunderstanding of time-varying trends of network communications. This study presents a new edge sampling algorithm called edge-based multi-class blue noise (E-MCBN) to reduce visual clutter in MSV. Our main idea is inspired by the multi-class blue noise (MCBN) sampling algorithm, commonly used in multi-class scatterplot decluttering. First, we take a node pair as an edge class, which can be regarded as an analogy to classes in multi-class scatterplots. Second, we propose two indicators, namely, class overlap and inter-class conflict degrees, to measure the overlapping degree and mutual exclusion, respectively, between edge classes. These indicators help construct the foundation of migrating the MCBN sampling from multi-class scatterplots to dynamic network samplings. Finally, we propose three strategies to accelerate MCBN sampling and a partitioning strategy to preserve local high-density edges in the MSV. The result shows that our approach can effectively reduce visual clutters and improve the readability of MSV. Moreover, our approach can also overcome the disadvantages of the MCBN sampling (i.e., long-running and failure to preserve local high-density communication areas in MSV). This study is the first that introduces MCBN sampling into a dynamic network sampling.

关键词： dynamic network visualization massive sequence view multi-class blue noise sampling visual abstraction

来源：评论

学校读者我要写书评

暂无评论

Recognizing autonomous driving disengagement scenarios using the transferable knowledge from human driver's EEG cognitive data

引用

Accident Analysis and Prevention 2025年 219卷 108102页

作者： Qi, Geqi Zhao, Shuo Yu, Jixiang Li, Peihao Guan, Wei Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing 100044 China Key Laboratory of Brain Machine Intelligence for Information Behavior-Ministry of Education Shanghai International Studies University Shanghai 200083 China Research Institute of Highway Ministry of Transport Beijing 100088 China School of Systems Science Beijing Jiaotong University Beijing 100044 China

Without human participation in driving operations, the adoption of autonomous driving (AD) technology greatly enhances driving safety by reducing human errors. Even though AD can handle common scenarios properly, some exceptions still call for the human takeover with AD failing to engage due to the incomprehensible or intensely conflict situations that rarely occur. To help AD understand and recognize the disengagement scenarios effectively, this paper incorporates the human electroencephalogram (EEG) cognitive data into modeling and proposes a transfer learning framework to let AD absorb the integrative knowledge from the manual driving (MD). Several disengagement scenarios are designed using a driving simulator and EEG data are collected from both “drivers” in MD and “supervisors” in AD. A conditional maximum mean discrepancy (CMMD) function is introduced to identify the common brain activity characteristics, allowing the recognition model to be transferred from the cognitively demanding domain of MD to the less demanding domain of AD. The results indicate that the proposed model can achieve an 80 % recognition rate for typical disengagement scenarios, such as static obstacles, intersection conflict and vehicle cut-in, using only 30 % of AD training labels. The transferable common feature space from EEG data improves the recognition accuracy by 21.2 % compared with the model only using AD domain data. By accurately recognizing the type of disengagement scenarios, the AD system can activate appropriate safety mechanisms or provide more explicit takeover prompts, which could effectively reduce the risk of accidents due to delayed or incorrect takeovers. © 2025 Elsevier Ltd

关键词： Autonomous driving Disengagement scenarios EEG Human cognition Transfer learning

来源：评论

学校读者我要写书评

暂无评论

Attention-based unsupervised prompt learning for SAM in leaf disease segmentation

引用

Knowledge-Based Systems 2025年 320卷

作者： Tian, Luda Yuan, Yingchun En, Qing Ma, Wei Zhang, Guanghui Liang, Fangfang School of Information Science and Technology Hebei Agricultural University Baoding071001 China Hebei Key Laboratory of Agricultural Big Data Baoding071001 China Hebei Engineering Research Center for Agricultural Remote Sensing Application Baoding071001 China Lab School of Computer Science Carleton University OttawaK1S 5B6 Canada Faculty of Information Technology Beijing University of Technology Beijing100124 China

In modern agriculture, leaf disease segmentation is crucial for crop disease management and yield improvement. Since most deep learning-based segmentation models require extensive annotations, pursuing unsupervised methods becomes a practical solution. Although advanced models like the Segment Anything Model (SAM) can produce precise class-agnostic masks without annotations, their reliance on human-interactive prompts limits their utility to unsupervised disease segmentation tasks. To address this limitation, we present UPLS, a novel three-stage framework that leverages unsupervised prompt learning to enable SAM for leaf disease segmentation. This method employs unsupervised contrastive learning to progressively segment leaf and disease areas and automatically generate disease prompts for SAM. Concretely, for fine and intricate lesions, we utilize an improved high-frequency attention mechanism to extract high-frequency features from the leaf area, and construct contrastive losses between global priors and foreground/background features. Furthermore, we devise a strategy to automatically generate disease-related prompts from the segmented leaf and initial lesion regions, enabling SAM to refine disease boundaries without human intervention. Experiments on three public plant disease segmentation datasets show that UPLS outperforms existing non-fully supervised segmentation methods in accuracy and robustness. Source code is available at https://***/Tianluda/UPLS. © 2025 Elsevier B.V.

关键词： Unsupervised learning

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：