检索结果-内蒙古大学图书馆

An Uncertainty Quantization-Based Method for Anti-UAV Detection in Infrared Images

Computers, Materials & Continua 2025年第4期83卷 1439-1458页

作者： Can Wu Wenyi Tang Yunbo Rao Yinjie Chen Hui Ding Shuzhen Zhu Yuanyuan Wang School of Information and Software Engineering University of Electronic Science and Technology of ChinaChengdu610054China State Key Laboratory of Air Traffic Management System Nanjing210000China National Airspace Management Center Beijing100094China

Infrared unmanned aerial vehicle(UAV)target detection presents significant challenges due to the inter-play between small targets and complex *** methods,while effective in controlled environments,often fail in scenarios involving long-range targets,high noise levels,or intricate backgrounds,highlighting the need for more robust *** address these challenges,we propose a novel three-stage UAV segmentation framework that leverages uncertainty quantification to enhance target *** framework incorporates a Bayesian convolutional neural network capable of generating both segmentation maps and probabilistic uncertainty *** utilizing uncer-tainty predictions,our method refines segmentation outcomes,achieving superior detection ***,this marks the first application of uncertainty modeling within the context of infrared UAV target *** evaluations on three publicly available infrared UAV datasets demonstrate the effectiveness of the proposed *** results reveal significant improvements in both detection precision and robustness when compared to state-of-the-art deep learning *** approach also extends the capabilities of encoder-decoder convolutional neural networks by introducing uncertainty modeling,enabling the network to better handle the challenges posed by small targets and complex environmental *** bridging the gap between theoretical uncertainty modeling and practical detection tasks,our work offers a new perspective on enhancing model interpretability and *** codes of this work are available openly at https://***/general-learner/UQ_Anti_UAV(acceessed on 11 November 2024).

关键词： Object segmentation uncertainty quantification bayesian convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

Optimizing Heart-Kidney Interaction for Cancer Detection through Physiological Process Simulation as a Decision Support System

引用

IEEE Access 2025年 13卷 79169-79179页

作者： Jaddi, Najmeh Sadat Abdullah, Salwanj Othnman, Zalinda Yahya, Yazrina Nazri, Mohd Zakree Ahmad Goh, Say Leng Alvankarian, Fatemeh Alvankarian, Jafar Iranian eUniversity Faculty of Computer Engineering Tehran Iran Faculty of Information Science and Technology Center for Artificial Intelligence Technology Selangor Bangi43600 Malaysia Center for Software Technology and Management Faculty of Information Science and Technology UniversitiKebangsaan Malaysia Selangor Bangi43600 Malaysia Universiti Malaysia Sabah KampusAntarabangsa Labuan Optimisation and Analytics Research Group Faculty of Computing and Informatics Labuan87000 Malaysia University of Maryland Department of Electrical & Computer Engineering College ParkMD20742 United States Tehran University Science and Technology Park RayanMiniFab Tehran Iran

Decision support system (DSS) is a computer-based tool used to improve decision-making capabilities for any organization, using analysis of the available *** heart-kidney (HK) model proposed in this paper as a DSS simulates the physiological processes of the heart and kidneys in the human body to support cancer detection. The first part of the HK algorithm is inspired by the functions of the heart, where blood molecules (solutions) are sent to the heart, simulating the processes of oxygenation and the pumping of oxygenated blood to the kidneys as a local search. The solutions generated by the heart are then fed into the kidney-inspired algorithm (KA), which performs filtration, reabsorption, secretion, and excretion. The heart component enhances the KA's local search capability, guiding the algorithm toward optimal solutions. The HK model is evaluated on eight test functions, with results compared to those of the heart algorithm and KA alone. Additionally, the HK algorithm's effectiveness as a decision support system is tested on benchmark classification and time series prediction problems, with statistical analysis against existing methods in the literature. Finally, the HK algorithm is applied to cancer detection from microRNA data, demonstrating its potential in optimizing decision-making processes in healthcare. © 2013 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Imbalanced Heartbeat Classification Based on a Convseq2seq Model with Focal Loss

SSRN

引用

SSRN 2025年

作者： Yang, Ping Jiang, Yu-Peng Wang, Meng School of Economics and Management Beijing Information Science and Technology University Beijing China Software Research and Development Center Postal Savings Bank of China Beijing China Department of Mathematics and Physics Beijing Information Science and Technology University Beijing China

The electrocardiogram (ECG) serves as a crucial tool for cardiovascular disease diagnosis and arrhythmia detection. In this paper, we propose a deep learning approach named ConvSeq2Seq, which combines convolutional neural network (CNN) and sequence-to-sequence (Seq2Seq) models, for automatic ECG classification. We employ CNN to extract spatial features from ECG data, which exhibit inter-patient variations, capturing significant spatial patterns within heartbeat sequences. Subsequently, these spatial features are input into the encoder of a Seq2Seq model to capture and encode temporal dependencies among heartbeat sequences into semantic vector representations. The decoder component of the Seq2Seq model performs semantic transformations and outputs final classification results. Our method is both simple and effective, as it does not involve any form of ECG signal filtering or processing. Despite existing literature proposing enhanced ECG heartbeat classification algorithms, they often fail to achieve high performance in detecting certain abnormal heartbeat categories, particularly in imbalanced datasets. To address this challenge, we introduce an optimization step for our ConvSeq2Seq model using a novel loss function called focal loss. This function prioritizes minority heartbeat classes by increasing their loss contribution. We evaluate our proposed methodology on the public MIT-BIH arrhythmia database using the inter-patient scheme, classifying four types of abnormal and normal beats. Experimental results demonstrate that the ConvSeq2Seq model with focal loss is effective for heartbeat classification. Furthermore, compared with state-of-the-art methods, our approach not only achieves superior overall performance but also significantly improves the performance of minority categories while maintaining the strong performance of majority categories. © 2025, The Authors. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Digital Human Techniques for Education Reform 24

Digital Human Techniques for Education Reform

引用

7th International Conference on Educational technology management, ICETM 2024

作者： Guo, Peirong Zhang, Qi Tian, Chunwei Xue, Wanli Feng, Xiaocheng School of Software Northwestern Polytechnical University Shaanxi Xi’an China School of Economics and Management Harbin Institute of Technology at Weihai Shandong Weihai China Shenzhen Research Institute of Northwestern Polytechnical University Northwestern Polytechnical University Guangdong Shenzhen China School of Computer Science and Engineering Tianjin University of Technology Tianjin China Research Center for Social Computing and Information Retrieval Harbin Institute of Technology Heilongjiang Harbin China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Guangdong Shenzhen China

ISBN: (纸本)9798400717468

The rapid evolution of artificial intelligence, big data, and generative AI models has ushered in significant transformations across various sectors, including education. Digital Human Technique, an innovative technology grounded in advanced computer science and artificial intelligence, is reshaping educational paradigms by enabling virtual humans to simulate human behavior, express emotions, and interact with users. This paper explores the application of Digital Human Technique in education reform, focusing on creating immersive, intelligent classroom experiences that foster meaningful interactions between teachers and students. We define Digital Human Technique and delve into its key technical components such as character modeling and rendering, natural language processing, computer vision, and augmented reality technologies. Our methodology involves analyzing the role of educational digital humans created through these technologies, assessing their impact on educational processes, and examining various application scenarios in educational reform. Results indicate that Digital Human Technique significantly enhances the learning experience by enabling personalized teaching, increasing engagement, and fostering emotional connections. Educational digital humans serve as virtual teachers, interactive learning aids, and facilitators of emotional interaction, effectively addressing the challenges of traditional educational methods. They also promote a deeper understanding of complex concepts through simulated environments and interactive digital content. © 2024 Copyright held by the owner/author(s).

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

BSDSGANet: Bidirectional Skip-stored Dual-Stream Gated Attention Network for multivariate time series classification

引用

Knowledge-Based Systems 2025年 318卷

作者： Yi, Yugen Zhao, Panpan Sheng, Hui Liu, Min Li, Shicheng Dai, Jiangyan Kong, Jun Qiao, Shaojie School of Software Research Center for Management Science and Engineering Jiangxi Provincial Key Laboratory of Intelligent Information Processing and Affective Computing Jiangxi Normal University Nanchang330022 China School of Artificial Intelligence and Big Data Jiangxi University of Technology Nanchang330098 China School of Computer Engineering Weifang University Weifang261061 China College of Information Science and Technology Northeast Normal University Changchun130117 China School of Software Engineering Chengdu University of Information Technology Chengdu610225 China

Echo State Networks (ESNs) are popular in Time Series Classification (TSC) due to their high-dimensional stochastic projections. However, due to the echo state at the current step is susceptible to the preceding step, the existing ESNs struggle to capture the long-term temporal dependencies. Furthermore, most of them only employ the unidirectional storage to capture the sequence information, which fails to fully consider the impact of the past and future moments simultaneously. To address these issues, we propose an advanced method called Bidirectional Skip-stored Dual-Stream Gated Attention Network (BSDSGANet) for Multivariate Time Series Classification (MTSC). Specifically, to roundly exploit the sequence information, a Bidirectional Skip-Stored Encoder (BSSE) is designed to enrich the temporal context by integrating past and future information. Then, a Dual-Stream Gated Attention Learner (DSGAL) mechanism is incroporated, which employs a Gated Recurrent Self-Attention (GRSA) module to learn the long-term dependencies and variable relationships. Meanwhile, a Multi-Scale Gated Attention (MSGA) module is developed to extract more important features from multiple scales. Extensive experiments conducted on eighteen benchmark MTSC datasets show that BSDSGANet outperforms five traditional methods and twelve deep learning models. © 2025 Elsevier B.V.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

How Do Hackathons Foster Creativity? Towards Automated Evaluation of Creativity at Scale 25

How Do Hackathons Foster Creativity? Towards Automated Evalu...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Jeanette Falk Yiyi Chen Janet Rafner Mike Zhang Johannes Bjerva Alexander Nolte Computer Science Aalborg University Copenhagen Denmark Department of Computer Science Aalborg University Copenhagen Denmark Center for Hybrid Intelligence Department of Management Aarhus University Aarhus Denmark and Aarhus Institute for Advanced Studies Aarhus University Aarhus Denmark Software Engineering and Technology Eindhoven University of Technology Eindhoven Netherlands

来源：评论

学校读者我要写书评

暂无评论

How Do Hackathons Foster Creativity? Towards AI Collaborative Evaluation of Creativity at Scale

arXiv

引用

arXiv 2025年

作者： Falk, Jeanette Chen, Yiyi Rafner, Janet Zhang, Mike Bjerva, Johannes Nolte, Alexander Aalborg University Copenhagen Department of Computer Science Copenhagen Denmark Center for Hybrid Intelligence Department of Management and Aarhus Institute for Advanced Studies Aarhus University Aarhus Denmark Aalborg University Copenhagen Department of Computer Science Pioneer Centre for Artificial Intelligence Copenhagen Denmark Software Engineering and Technology Eindhoven University of Technology Eindhoven Netherlands and Software and Societal Systems Carnegie Mellon University PittsburghPA United States

Hackathons have become popular collaborative events for accelerating the development of creative ideas and prototypes. There are several case studies showcasing creative outcomes across domains such as industry, education, and research. However, there are no large-scale studies on creativity in hackathons which can advance theory on how hackathon formats lead to creative outcomes. We conducted a computational analysis of 193,353 hackathon projects. By operationalizing creativity through usefulness and novelty, we refined our dataset to 10,363 projects, allowing us to analyze how participant characteristics, collaboration patterns, and hackathon setups influence the development of creative projects. The contribution of our paper is twofold: We identified means for organizers to foster creativity in hackathons. We also explore the use of large language models (LLMs) to augment the evaluation of creative outcomes and discuss challenges and opportunities of doing this, which has implications for creativity research at large. © 2025, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Full-Coverage Mapping of Daily High-Resolution XCO2 across China from 2015 to 2020 by Deep Learning-Based Spatio-Temporal Fusion

引用

IEEE Transactions on Geoscience and Remote Sensing 2025年

作者： Li, Yi Yan, Jining Zhong, Liheng Bao, De Sun, Leigang Li, Guangyu China University of Geosciences School of Computer Science Wuhan430074 China Ministry of Education Engineering Research Center of Natural Resource Information Management and Digital Twin Engineering Software Wuhan430074 China Ant Group World Financial Center Beijing100020 China Hebei Academy of Sciences Institute of Geographical Sciences Shijiazhuang050011 China Hebei Technology Innovation Center for Geographic Information Application Shijiazhuang050011 China Environmental Development Center of the Ministry of Ecology and Environment China

Carbon neutrality has become a global priority, and high spatio-temporal resolution data on the column-average dry-air mole fraction carbon dioxide (XCO2) is essential for tracking progress and guiding policy adjustments. However, satellite-derived XCO2 exhibits significant temporal and spatial gaps due to influences such as orbital dynamics and cloud cover. Additionally, the low spatial resolution of CarbonTracker (CT) is insufficient to meet the current demands for fine-scale monitoring. Current XCO2 assessment methods often rely solely on single-pixel data, overlooking the spatio-temporal correlations. In this article, we introduce a deep learning-based spatio-temporal model (DSTM) that extracts features from multiple data sources related to atmospheric transport, carbon emissions, and carbon sinks, enabling fine-scale XCO2 assessments. Additionally, XCO2 data from the Orbiting Carbon Observatory-2 (OCO-2) and CT were fused at a 0.1° spatial resolution to generate training labels with broader coverage and more samples, serving as fitting labels. Our approach produced daily, full-coverage 0.1° resolution XCO2 maps for China from 2015 to 2020, and analyzed changes in XCO2 growth trends over this period. Numerical results show that our model outperforms traditional deep learning methods. Model validation using data from four ground-based observation sites of the Total Carbon Column Observing Network (TCCON) achieved an average R2 of 0.86 and an RMSE of 2.67 ppm. The extraction and fusion of spatio-temporal features from multiple data sources provide a novel approach for reconstructing missing XCO2 data. © 1980-2012 IEEE.

关键词： Atmospheric movements

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Multi-Kernel Graph Learning for Autism Prediction and Biomarker Discovery

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 842-854页

作者： Jin Liu Junbin Mao Hanhe Lin Hulin Kuang Shirui Pan Xusheng Wu Shan Xie Fei Liu Yi Pan Hunan Provincial Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of software Xinjiang University Wulumuqi China Hunan Province Key Lab on Bioinformatics School of Computer Science and Engineering Central South University Changsha China School of Science and Engineering University of Dundee Dundee U.K. School of Information and Communication Technology Griffith University Gold Coast QLD Australia Shenzhen Health Development Research and Data Management Center Shenzhen China Faculty of Computer Science and Control Engineering Shenzhen University of Advanced Technology Shenzhen China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

Graph learning-based multi-modal integration and classification is one of the most challenging tasks for disease prediction. To effectively offset the negative impact among modalities in the process of multi-modal integration and heterogeneous information extractions from graphs, we propose a novel method called Multi-modal Multi-Kernel Graph Learning (MMKGL). To solve the problem of negative impact among modalities, we propose a multi-modal graph embedding module to construct a multi-modal graph. Different from conventional methods that manually construct static graphs for all modalities, each modality generates a separate graph by adaptive learning, where a function graph and a supervision graph are introduced for optimization during the multi-graph fusion embedding process. We then propose a multi-kernel graph learning module to extract heterogeneous information from the multi-modal graph. The information in the multi-modal graph at different levels is aggregated by convolutional kernels with different receptive field sizes, followed by generating a cross-kernel discovery tensor for disease prediction. Our method is evaluated on the benchmark Autism Brain Imaging Data Exchange (ABIDE) dataset and outperforms the state-of-the-art methods. In addition, discriminative brain regions associated with autism are identified by our model, providing guidance for the study of autism pathology.

关键词： Diseases Autism Random access memory Data mining Kernel Electronic mail Training Neuroimaging Graph convolutional networks Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Simulation of Membrane System on the GPU for the N-Queens Problem

引用

Chinese Journal of Electronics 2015年第4期24卷 740-743页

作者： Ravie Chandren Muniyandi Ali Maroosi Research Center for Software Technology and Management (SOFTAM) Faculty of Information Science and Technology(FTSM) National University of Malaysia (UKM)

Previous approaches using active membrane systems to solve the N-queens problem defined many membranes with just one rule inside them. This resulted in many communication rules utilised to communicate between membranes, which made communications between the cores and the threads a very time-consuming *** proposed approach reduces unnecessary membranes and communication rules by defining two membranes with many objects and rules inside each membrane. With this structure, objects and rules can evolve concurrently in parallel, which makes the model suitable for implementation on a Graphics processing unit(GPU). The speedup using a GPU with global memory for N=10 is 10.6 times, but using tiling and shared memory, it is 33 times.

关键词： Membrane computing Graphics processing unit(GPU) N-queens problem Parallel processing

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：