检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Poe, Kyle Mallada, Enrique Vidal, René Applied Mathematics and Computational Science Group University of Pennsylvania PA19104 United States Department of Electrical and Computer Engineering Johns Hopkins University MD21218 United States Departments of Electrical and Systems Engineering Radiology Computer and Information Science Statistics and Data Science University of Pennsylvania PA19104 United States

One of the fundamental problems of interest for discrete-time linear systems is whether its input sequence may be recovered given its output sequence, a.k.a. the left inversion problem. Many conditions on the state space geometry, dynamics, and spectral structure of a system have been used to characterize the well-posedness of this problem, without assumptions on the inputs. However, certain structural assumptions, such as input sparsity, have been shown to translate to practical gains in the performance of inversion algorithms, surpassing classical guarantees. Establishing necessary and sufficient conditions for left invertibility of systems with sparse inputs is therefore a crucial step toward understanding the performance limits of system inversion under structured input assumptions. In this work, we provide the first necessary and sufficient characterizations of left invertibility for linear systems with sparse inputs, echoing classic characterizations for standard linear systems. The key insight in deriving these results is in establishing the existence of two novel geometric invariants unique to the sparse-input setting, the weakly unobservable and strongly reachable subspace arrangements. By means of a concrete example, we demonstrate the utility of these characterizations. We conclude by discussing extensions and applications of this framework to several related problems in sparse control. © 2024, CC BY.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

Geospatial Analysis of Extreme Temperature Impacts in Agricultural systems Using Machine Learning

Geospatial Analysis of Extreme Temperature Impacts in Agricu...

引用

IEEE International Symposium on systems engineering (ISSE)

作者： Rayshaun L. Wheeler John S. Miller Gia N. Smith James H. Lambert Cody A. Pennetti Garrick E. Louis Deandre A. Johnson Department of Civil & Environmental Engineering University of Virginia Charlottesville VA USA School of Data Science University of Virginia Charlottesville VA USA Department of Systems & Information Engineering University of Virginia Charlottesville VA USA Department of Engineering & Society University of Virginia Charlottesville VA USA

ISBN: (数字)9798350353723

ISBN: (纸本)9798350353730

Recent higher temperatures, observed compared to previous years, have led to more frequent and intense heat waves, adversely affecting agriculture and human health. This paper explores using Inverse Distance Weighting (IDW) and Kriging to develop GIS layers for a heat-based risk index. Recent increases in global mean temperatures have led to more frequent and intense heat waves, impacting food supply, vegetation, and human health. Optimal plant growth temperatures in temperate climates range from 20°C to 30°C, with nighttime temperatures also being critical. Exceeding these temperature ranges can reduce plant immunity, cause disease, and result in poor crop yields. For example, mango cultivars need a "safe" temperature range of 10°C to 12°C to avoid damage. The intensification of higher temperatures established July 2023 record the hottest days on Earth, highlighting the need for effective monitoring and management tools. IDW, a deterministic method, offers a straightforward and efficient approach by assuming closer points have more influence. Kriging, a probabilistic geostatistical technique, accounts for spatial autocorrelation and prediction uncertainty, making it suitable for complex datasets. The study compares these methods' performance in creating continuous surfaces representing heat-based risk. IDW is simple and efficient but less accurate in sparsely populated areas, while Kriging is more accurate and detailed but requires more computational resources and expertise. An automated workflow for data preprocessing, model training, and cross-validation ensures consistent results. The study recommends adopting IDW for initial assessments and transitioning to Kriging as expertise grows. Enhanced data collection on temperature and population density is also advised to improve GIS layer accuracy, aiding better decision-making and resource allocation to mitigate extreme heat effects on agriculture and public health.

关键词： Heating systems Support vector machines Training Temperature distribution Accuracy Computational modeling Decision making Linear regression Resource management Random forests Climate change

来源：评论

学校读者我要写书评

暂无评论

Interactive Blood Bank Repository: Django AWS Approach

Interactive Blood Bank Repository: Django AWS Approach

引用

Intelligent Communication Technologies and Virtual Mobile Networks (ICICV), International Conference on

作者： E. Sujatha V. Manickavasagan. S. Lakshminarayanan R. Ani Minisha K.S. Rekha V. Loganathan Department of Computer Science and Engineering Saveetha Engineering College Tamil Nadu Department of Computer Science and Business Systems Sri Sairam Engineering College Tamil Nadu Department of Computer Science and Engineering Sri Sairam Engineering College Tamil Nadu Department of Information Technology Saveetha Engineering College Tamil Nadu Department of Artificial Intelligence and Data Science Vel Tech Multi Tech Dr RR and Dr SR Engineering College Tamil Nadu

Everyday, there are a growing number of people who require blood transfusions and there is no substitute for human blood. The secure blood donors are voluntary non-remunerated blood donors from risk populations. Donors in India and across the globe are three types namely, Voluntary donors, Professional donors and replacement donors. The deadline-driven web framework that supports Django's clean, practical design and speedy development. The existing system has a manual work restriction. This has restrictions on securely controlling the task for timely results declaration, and has a significant resource consumption. Web-based blood donation is the coordination of the supply and demand of blood through an online portal. The main goal of this research study is to give blood donors and blood searchers an online platform and to develop an engaging method of connecting the two groups. The suggested system provides a great deal of information regarding blood types, blood supply, and blood donation specifics to raise awareness among the public. Additionally, other system features like password-based security protection, report generation, chat functionality, and stock shortages can even improve the management tasks by streamlining them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Backtracing Social Events of Interest via Logical Correlation Using GDELT

Backtracing Social Events of Interest via Logical Correlatio...

引用

International Conference on Big data and information Analytics (BigDIA)

作者： Dongxu Zhao Xin Zhang Yan Pan Honglin Shi Liwei Qian Guang Yang Science and Technology on Information Systems Engineering Laboratory National University of Defense Technology Changsha China Laboratory for Big Data and Decision National University of Defense Technology Changsha China College of Systems Engineering National University of Defense Technology Changsha China

In response to the inability of mainstream methods in existing social event backtracing studies to address the logical correlation problem, the insufficient and inaccurate utilization of event characteristics for implementing logical association backtracing events, we propose a backtracing method for social events of interest. The basic idea is to obtain a set of related events given a small amount of labeled data on interested events, and to construct the causal chain of event occurrence through their merging and fusion. Specifically, we design a node feature construction strategy to select topic and title information from various elements of events to construct node features, thereby addressing the problem of insufficient and inaccurate node feature composition. We also design an adjacency relationship construction strategy, which uses the co-occurrence of participants in event records as the basis for constructing adjacency relationships, and completes the final construction of adjacency relationships by considering time elements comprehensively, thereby resolving the problem of inaccurate construction of inter-event correlation relationships. We construct a multi-layer graph convolutional network to learn the associated features and achieve node classification through a normalization function, thereby solving the problem of logical association inference between events. Experimental results demonstrate that LC-BTE is effective in backtracing analysis of events related to social events of interest. Additionally, this paper explores the performance changes of the method under semi-supervised mode and conducts experimental analysis. Finally, this paper provides the causal chain of events based on the backtracing results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empowering Consumer Healthcare Through Sensor-Rich Devices using Federated Learning for Secure Resource Recommendation

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Fathima, Afifa Salsabil Basha, Syed Muzamil Ahmed, Syed Thouheed Khan, Surbhi Bhatia Asiri, Fatima Basheer, Shakila Shukla, Madhu School of Computer Science and Engineering REVA University Karnataka Bengaluru India School of Computing and Information Technology REVA University Karnataka Bengaluru India Department of Data Science School of Science Engineering and Environment University of Salford Manchester United Kingdom Centre for Research Impact and Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India College of computer science Informatics and computer systems department King Khalid University Saudi Arabia Department of Information Systems College of computer and Information science Princess Nourah bint Abdulrahman University P.O. BOX 84428 Riyadh11671 Saudi Arabia the Department of CSE - AI ML & DS Marwadi University Gujarat Rajkot360003 India

When implementing zero-trust edge computing, offloading computational tasks and data access through traditional model training and usage approaches can lead to increased latency. Since the traditional methods often involve extensive communication with a central server, creating additional network hopping stations/nodes resulting in increased latency. The challenge is bound to allocate a befitting resource at a given consumer demand. In this proposed system, a federated learning model based data offloading and consumer medical resource recommendation of IoT is discussed and validated. The user/consumer group and local training models are aligned with edge servers for data preprocessing and customization with a series of resources demand creation and coordination. The consumer resource allocating priorities are fine-grained with the proposed blockchain based priority analyzer for recommendation and allocation. The computational parameter such as resource pool, average waiting time, energy consumption and transmission trust delays are observed and validated. The proposed framework fetches consumer resources logs and synchronizes the centralized training model for effective scheduling and allocation of resources with an accuracy of 94.92% under the 5G operating spectrum. The technique has demonstrated minimal latency in offloading the data request demand and resource allocation at the cloud servers. © 2025 Institute of Electrical and Electronics Engineers Inc.. All rights reserved.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

SwimVG: Step-wise Multimodal Fusion and Adaption for Visual Grounding

arXiv

引用

arXiv 2025年

作者： Shi, Liangtao Liu, Ting Hu, Xiantao Hu, Yue Yin, Quanjun Hong, Richang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Hefei230009 China Ministry of Education and School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China School of systems engineering National University of Defense Technology Hunan Province Changsha410073 China Department of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210014 China

Visual grounding aims to ground an image region through natural language, which heavily relies on cross-modal alignment. Most existing methods transfer visual/linguistic knowledge separately by fully fine-tuning uni-modal pre-trained models, followed by a simple stack of visual-language transformers for multimodal fusion. However, these approaches not only limit adequate interaction between visual and linguistic contexts, but also incur significant computational costs. Therefore, to address these issues, we explore a step-wise multimodal fusion and adaption framework, namely SwimVG. Specifically, SwimVG proposes step-wise multimodal prompts (Swip) and cross-modal interactive adapters (CIA) for visual grounding, replacing the cumbersome transformer stacks for multimodal fusion. Swip can improve the alignment between the vision and language representations step by step, in a token-level fusion manner. In addition, weight-level CIA further promotes multimodal fusion by cross-modal interaction. Swip and CIA are both parameter-efficient paradigms, and they fuse the cross-modal features from shallow to deep layers gradually. Experimental results on four widely-used benchmarks demonstrate that SwimVG achieves remarkable abilities and considerable benefits in terms of efficiency. Our code is available at https://***/liuting20/SwimVG. Copyright © 2025, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Performance improvement by enhancing spatial parallelism on FPGA for HPC applications

Performance improvement by enhancing spatial parallelism on ...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Yuka Sano Taisuke Boku Mitsuhisa Sato Miwako Tsuji Norihisa Fujita Ryohei Kobayashi Degree Programs in Systems and Information Engineering University of Tsukuba Japan Center for Computational Sciences University of Tsukuba Japan Faculty of Health Data Science Juntendo University Japan Center for Computational Science RIKEN Japan

In today’s HPC systems, GPUs with high computational performance and memory bandwidth under relatively low power consumption are the leading players. However, GPU-based acceleration is designed to excel when utilizing many computation cores and performing SIMD/STMD manner of synchronized computation over a large number of uniform data array elements. Therefore, it may not fully exploit its computational performance in calculations with low parallelism, complex operations involving conditional branching, or parallel applications with frequent inter-node communication to interrupt continuous computing on GPU devices. One of the alternative solutions for accelerated computing is FPGA (Field Programmable Gate Array), especially with recent advancements in devices containing a large number of logic elements, high memory bandwidth, and even multiple channels of high-speed optical interconnection interfaces, reaching up to 100 Gbps for each. The performance of an FPGA is based on pipeline parallelism, enabling the computation stream to continue even with conditional branches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

OverlapMamba: Novel Shift State Space Model for LiDAR-based Place Recognition

arXiv

引用

arXiv 2024年

作者： Xiang, Qiuchi Cheng, Jintao Luo, Jiehao Wu, Jin Fan, Rui Chen, Xieyuanli Tang, Xiaoyu School of Data Science and Engineering Xingzhi College South China Normal University Shanwei516600 China School of Electronic and Information Engineering South China Normal University Guangdong Foshan528225 China Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong College of Intelligence Science and Technology National University of Defense Technology Changsha China College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China

Place recognition is the foundation for enabling autonomous systems to achieve independent decision-making and safe operations. It is also crucial in tasks such as loop closure detection and global localization within SLAM. Previous methods utilize mundane point cloud representations as input and deep learning-based LiDAR-based Place Recognition (LPR) approaches employing different point cloud image inputs with convolutional neural networks (CNNs) or transformer architectures. However, the recently proposed Mamba deep learning model, combined with state space models (SSMs), holds great potential for long sequence modeling. Therefore, we developed OverlapMamba, a novel network for place recognition, which represents input range views (RVs) as sequences. In a novel way, we employ a stochastic reconstruction approach to build shift state space models, compressing the visual representation. Evaluated on three different public datasets, our method effectively detects loop closures, showing robustness even when traversing previously visited locations from different directions. Relying on raw range view inputs, it outperforms typical LiDAR and multi-view combination methods in time complexity and speed, indicating strong place recognition capabilities and realtime efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Auto capture on drug text detection in social media through NLP from the heterogeneous data

引用

Measurement: Sensors 2022年 24卷

作者： Lavanya, P.M. Sasikala, E. Department of Computer Science and Engineering SRM Institute of Science & Technology Kattankulathur India Department of Information Technology Easwari Engineering College Ramapuram India Department of Data Science & Business Systems SRM Institute of Science & Technology Kattankulathur India

Auto Capture Drug Text detects (ACDTD) that textual content has currently gained important activities in Pharmaceutical drugs research. The recent studies focused on the different resources of textual content-related messages including social networks. Where a huge quantity of consumers posted information about the usage of pharmaceutical drugs and it's combined and cleared neatly. Our textual content classification strategies depend on regenerating the features of a large set of designs;it represents the semantic rules from the short textual nuggets. Significantly use the detailed structured files and it is combined by instruction data from the various collections to regulate the classification approach. Social Media Online Natural Language Processing (SMONLP) with ACDTD class achieves the F-scores of 0.90, 0.738, and 0.878 for the three information files. Integrating the instruction messages from various compatible files enhances the ACDTD F-scores for the in-house information files to 0.797 and 0.854 respectively. The heterogeneous textual content training using the cases where information sets are maintained may reduce the cost and time in the future. © 2022 The Authors

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

NcoVis: A Visual Analysis Framework for Exploring Academic Collaboration Networks under New Collaborative Relationships 25

NcoVis: A Visual Analysis Framework for Exploring Academic C...

引用

25th IEEE International Conference on Computer Supported Cooperative Work in Design, CSCWD 2022

作者： Yu, Ye Wu, Yao Liang, Xi Ma, Cheng Lu, Qiang Key Laboratory of Knowledge Engineering with Big Data Hefei University of Technology Ministry of Education Hefei China School of Computer Science and Information Hefei University of Technology Hefei China Intelligent Interconnected Systems Laboratory of Anhui Province Hefei University of Technology Hefei China

ISBN: (纸本)9781665405270

Academic collaboration has become one of the topics of large-scale social network analysis. The information extracted from academic collaboration also shows the contextual value in combination with other data. For academic collaborative social networks with intricate collaborative relationships, previous research methods mainly focused on network structure and community discovery, lacking in mining the characteristics of relationships in collaborative networks. There were some limitations in the research perspective. In this work, we propose a collaborative relationship representation method that is more suitable for academic collaborative social networks. It marks the attribute characteristics of nodes in collaborative relationships and highlights collaborative relationships in visualization. By adopting this new representation of collaborative relationships, we designed a visual analysis framework NcoVis, to visualize academic collaborative social networks. We further visually analyze the link relationship groups guided by nodes, and explore the potential representation of the structure and attribute characteristics of link relationships, so that analysts can explore the theme and structural change characteristics of link relationships, communities and the whole network in collaborative social networks. To prove the proposed framework, we conducted a case study on the academic collaboration literature data set, and analyzed the questionnaire with Likert scale through the user evaluation experiment, which verified the effectiveness of our method and the practicability of NcoVis. © 2022 IEEE.

关键词： Visualization

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：