检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Shoaib, Mohamed R. Emara, Heba M. Zhao, Jun School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt

Food security, a global concern, necessitates precise and diverse data-driven solutions to address its multifaceted challenges. This paper explores the integration of AI foundation models across various food security applications, leveraging distinct data types, to overcome the limitations of current deep and machine learning methods. Specifically, we investigate their utilization in crop type mapping, cropland mapping, field delineation and crop yield prediction. By capitalizing on multispectral imagery, meteorological data, soil properties, historical records, and high-resolution satellite imagery, AI foundation models offer a versatile approach. The study demonstrates that AI foundation models enhance food security initiatives by providing accurate predictions, improving resource allocation, and supporting informed decision-making. These models serve as a transformative force in addressing global food security limitations, marking a significant leap toward a sustainable and secure food future. © 2023, CC BY.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

A Dynamic Object Removal and Reconstruction Algorithm for Point Clouds 17

A Dynamic Object Removal and Reconstruction Algorithm for Po...

引用

17th IEEE International Conference on Service Operations and Logistics, and Informatics, SOLI 2023

作者： Nagavarapu, Sarat Chandra Abraham, Anuj Selvaraj, Nithish Muthuchamy Dauwels, Justin Agency for Science Singapore138632 Singapore Technology Innovation Institute Masdar City Abu Dhabi9639 United Arab Emirates School of Electrical and Electronic Engineering Nanyang Technological University Singapore639798 Singapore Tu Delft Faculty of Eemcs Department of Microelectronics Delft2628 CD Netherlands

ISBN: (纸本)9798350396003

Autonomous vehicles (AV) are one of the greatest technological advancements of this decade and a giant leap in the transportation industry and mobile robotics. Autonomous vehicles face several major challenges in achieving higher levels of autonomy. One of these is to find a fast and reliable algorithm to process the sensor data so that the simultaneous localization and mapping (SLAM) algorithms run in real-time to achieve autonomous navigation. The major limitation of the SLAM algorithm, especially while building a map is to have static environmental features, i.e. without any dynamic or moving objects. To achieve this, our paper introduces a novel algorithm to remove dynamic objects from point cloud data. The algorithm focuses on identifying and removing dynamic objects from sensor data, thereby creating a static scene suitable for traditional SLAM algorithms. Simulations conducted on the benchmark dataset demonstrate the algorithm's efficacy in successfully eliminating dynamic objects and reconstructing a stable static scene. © 2023 IEEE.

关键词： Autonomous vehicles

来源：评论

学校读者我要写书评

暂无评论

A Survey on Small Sample Imbalance Problem: Metrics, Feature Analysis, and Solutions

arXiv

引用

arXiv 2025年

作者： Zhao, Shuxian Gui, Jie Dong, Minjing Yu, Baosheng Gui, Zhipeng Dong, Lu Tang, Yuan Yan Kwok, James Tin-Yau School of Cyber Science d Engineering Southeast University Nanjing210000 China School of Cyber Science and Engineering Southeast University Nanjing211189 China Engineering Research Center of Blockchain Application Supervision and Management Southeast University Nanjing211189 China Purple Mountain Laboratories Nanjing210000 China Department of Computer Science City University of Hong Kong Hong Kong Lee Kong Chian School of Medicine Nanyang Technological University Singapore School of Remote Sensing and Information Engineering Wuhan University Wuhan430079 China Collaborative Innovation Center of Geospatial Technology Wuhan University Wuhan430079 China Department of Computer and Information Science University of Macau China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong

—The small sample imbalance (S&I) problem is a major challenge in machine learning and data analysis. It is characterized by a small number of samples and an imbalanced class distribution, which leads to poor model performance. In addition, indistinct inter-class feature distributions further complicate classification tasks. Existing methods often rely on algorithmic heuristics without sufficiently analyzing the underlying data characteristics. We argue that a detailed analysis from the data perspective is essential before developing an appropriate solution. Therefore, this paper proposes a systematic analytical framework for the S&I problem. We first summarize imbalance metrics and complexity analysis methods, highlighting the need for interpretable benchmarks to characterize S&I problems. Second, we review recent solutions for conventional, complexity-based, and extreme S&I problems, revealing methodological differences in handling various data distributions. Our summary finds that resampling remains a widely adopted solution. However, we conduct experiments on binary and multiclass datasets, revealing that classifier performance differences significantly exceed the improvements achieved through resampling. Finally, this paper highlights open questions and discusses future trends. Copyright © 2025, The Authors. All rights reserved.

关键词： Taxonomies

来源：评论

学校读者我要写书评

暂无评论

A Short Survey on Multimodal Data Fusion in Image Classification

A Short Survey on Multimodal Data Fusion in Image Classifica...

引用

Global Aeronautical engineering and Satellite Technology (GAST), International Conference on

作者： Toufik Datsi Khalid Aznag Brahim Ait BenAli Karim Karbout Ahmed El Oirrak El Kharrachi Khayya Faculty of Sciences Semlalia Computer Systems Engineering Laboratory Cadi Ayyad University Marrakesh Morocco LTI Laboratory ENSA School-University Chouaib Doukkali EL Jadida Morocco Faculty of Sciences Semlalia Computer Science Engineering Laboratory Cadi Ayyad University Marrakesh Morocco

ISBN: (数字)9798350371598

ISBN: (纸本)9798350371604

Advancements in multimodal learning have experienced rapid growth over the past decade, particularly within various domains, with a significant emphasis on developments in computer vision. Multimodal data fusion has become increasingly prominent in the realm of image classification, where the integration of diverse data sources enhances the overall understanding and performance of classification models. This survey delves into the recent strides made in multimodal learning over the past decade, particularly within the field of image classification. Additionally, the paper undertakes a comparative study, critically evaluating the effectiveness and performance of different multimodal fusion approaches. The aim is to provide a comprehensive overview of the current state-of-the-art in multimodal data fusion for image classification and to identify key trends, challenges, and opportunities in this evolving field.

关键词： Surveys Adaptation models Satellites Navigation Soft sensors Data integration Data models

来源：评论

学校读者我要写书评

暂无评论

Is Partial Model Aggregation Energy-Efficient for Federated Learning Enabled Wireless Networks?

Is Partial Model Aggregation Energy-Efficient for Federated ...

引用

IEEE International Conference on Communications (ICC)

作者： Zhixiong Chen Wenqiang Yi Arumugam Nallanathan Geoffrey Ye Li School of Electronic Engineering and Computer Science Queen Mary University of London London U.K. Department of Electrical and Electronic Engineering Faculty of Engineering Imperial College London England

This work aims to address two of the main challenges for federated learning (FL), i.e., the limited communication resources and the data heterogeneity across devices. To this end, we first devise a novel FL framework with partial model aggregation (PMA), which only aggregates the lower layers of neural networks responsible for feature extraction while the upper layers corresponding to complex pattern recognition remain at devices for personalization. This design is able to address the data heterogeneity and reduce the transmitted information in wireless channels. Then, we maximize the scheduled data sample volume by joint optimizing the device scheduling, bandwidth allocation, computation and communication time division. Specifically, our analysis reveals that the optimal time division is achieved when the communication and computation parts of PMA-FL have the same power. We also develop a bisection method to solve the optimal bandwidth allocation policy and use the set expansion algorithm to address the optimal device scheduling. Experimental results on the CIFAR-10 dataset show that the proposed PMA-FL improves 11.6% accuracy compared with the state-of-art benchmarks, and the proposed joint dynamic device scheduling and resource optimization approach achieves slightly higher accuracy than the considered benchmarks but reduced 25% energy or 12.5% time budgets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Uncovering Brain Network Modules in Major Depression During Naturalistic Music Perception with Block Term Decomposition

引用

IEEE Transactions on Cognitive and Developmental Systems 2024年

作者： Zhu, Yongjie Hao, Yuxing Liu, Jia Cong, Fengyu Dalian Univ. of Tech. School of Biomedical Engineering China Univ. of Helsinki Dept. of Computer Science Finland Aalto University Dept. of Neuroscience and Biomedical Engineering Finland Dalian University of Technology School of Biomedical Engineering Faculty of Medicine Key Laboratory of Social Computing and Cognitive Intelligence Ministry of Education China University of Jyväskylä Faculty of Information Technology Jyväskylä Finland Dalian Univ. of Tech. School of Biomedical Engineering Faculty of Medicine China

Major depressive disorder (MDD) has been linked to altered brain networks and might be relieved by music therapy. Yet, the neurophysiological basis, especially the functional network mechanism, of music therapy on depression remains poorly understood. Here, we apply a novel dynamic module detection method based on block term decomposition (BTD) to examine the reorganization of time-varying topological network structures during music listening in MDD using electroencephalography (EEG). Specifically, temporal adjacency matrices generated using a sliding-window technique form a three-way tensor. The multilinear rank-(L, L, 1) BTD is applied to directly derive hidden network modules with specific time evolution from the temporally concatenated tensors for each frequency band. After temporal correlation analysis with musical features extracted from music stimuli, we identify several frequency-dependent network modules with specific temporal patterns modulated by musical features. These modular networks encompass subnetworks of default mode, frontoparietal, language, and sensorimotor networks involved in the delta, alpha, and beta bands, exhibiting significantly different modulations by music between healthy control and MDD groups. These results implicate that the altered oscillatory modular networks might affect the dynamic processing of musical features for MDD patients, which could offer valuable perspectives on revealing the neural mechanisms of music therapy for MDD. © 2016 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A Sequential Game Framework for Target Tracking

arXiv

引用

arXiv 2024年

作者： Leal, Daniel Nguyen, Ngoc Hung Skvortsov, Alex Arulampalam, Sanjeev Piraveenan, Mahendra School of Computer Science Faculty of Engineering University of Sydney Sydney Australia Group AdelaideSA5111 Australia Group MelbourneVIC3207 Australia

This paper investigates the application of game-theoretic principles combined with advanced Kalman filtering techniques to enhance maritime target tracking systems. Specifically, the paper presents a two-player, imperfect information, non-cooperative, sequential game framework for optimal decision making for a tracker and an evader. The paper also investigates the effectiveness of this game-theoretic decision making framework by comparing it with single-objective optimisation methods based on minimising tracking uncertainty. The paper assumes that both the tracker and the evader are intelligent operators capable of complex decision making, and use passive sensors to get noisy bearing information about each other. Rather than modelling a zero-sum game between the tracker and the evader, which presupposes the availability of perfect information, and therefore unrealistic, in this paper we model both the tracker and the evader as playing separate zero-sum games at each time step with an internal (and imperfect) model of the other player, which each player constructs based on the imperfect state information they have about the other player. The study defines complex multi-faceted winning criteria for both tracker and evader, and computes winning percentages for both by simulating their interaction for a range of speed ratios. The results indicate that game theoretic decision making improves the win percentage of the tracker compared to traditional covariance minimization procedures in all cases, regardless of the speed ratios and the actions of the evader. In the case of the evader, we find that a simpler linear escape action is most effective for the evader in most scenarios, though the effectiveness of game-theoretic decision making improves when the evader has a more significant speed disadvantage. Overall, the results indicate that the presented sequential-game based decision making framework significantly improves win percentages for a player in scenarios where tha

关键词： Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Powered Edge Analytics for IoT-based Sensor Networks

Deep Learning-Powered Edge Analytics for IoT-based Sensor Ne...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： M. Saravana Karthikeyan Ponnusamy Subramani M. Panneer Selvam M. L. Sworna Kokila R. Vijayalakshmi P. Sundaravadivel Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Avadi Chennai India Department of Physics Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Department of Electrical and Electronics Engineering Sona College of Technology Salem India Department of Computing Technologies Faculty of Engineering and Technology School of Computing SRM Institute of Science and Technology Kattankulathur Chennai India Department of Computer Science and Engineering Velammal College of Engineering and Technology Madurai India Department of Artificial Intelligence and Machine Learning Saveetha Engineering College Chennai India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

The rapid expansion of loT-based sensor networks has necessitated the development of efficient edge analytics frameworks to process vast amounts of data in real time while minimizing computational overhead. Deep learning-powered edge computing has emerged as a transformative approach, enhancing data processing capabilities at the network edge while addressing constraints related to latency, bandwidth, and energy consumption. This study introduces a novel algorithm, Lightweight AI Model Compression for Energy-Efficient IoT Edge Devices (LiteEdgeAI), designed to optimize deep learning models for resource-constrained edge environments. The proposed method employs quantization, pruning, and knowledge distillation techniques to achieve significant reductions in model size and computational complexity while maintaining high inference accuracy. To validate the efficiency of LiteEdgeAI, a comparative simulation analysis was conducted against existing state-of-the-art algorithms using key performance metrics such prediction accuracy, energy efficiency and computational complexity. Experimental results demonstrated that LiteEdgeAI outperformed baseline models. The findings highlight the potential of LiteEdgeAI in enabling scalable, low-power, and real-time edge intelligence for IoT-based sensor networks.

关键词： Deep learning Adaptation models Accuracy Computational modeling Predictive models Prediction algorithms Energy efficiency Real-time systems Internet of Things Computational complexity

来源：评论

学校读者我要写书评

暂无评论

Synchronous Surface Reconstruction and Grain Boundary Healing Toward Efficient and Stable Inverted Cspbi3 Perovskite Solar Cells

SSRN

引用

SSRN 2023年

作者： Liu, Ning Liu, Zhongyu Wang, Jianwei Ye, Qinli Wang, Yuheng Han, Wenhua Xu, Wenwu Zhang, Jing Huang, Like Hu, Ziyang Zhu, Yuejin Liu, Xiaohui Department of Microelectronic Science and Engineering School of Physical Science and Technology Ningbo University Ningbo315211 China Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo315211 China School of Information Engineering College of Science and Technology Ningbo University Ningbo315300 China

Cesium lead iodide (CsPbI3) perovskite has gained considerable attentions due to its unique photoelectric properties. However, numerous defects are inevitably existed on the surface and grain boundaries (GBs) of CsPbI3 resulting from the rapid crystallization and growth progress. Herein, different from the traditional ammonium salt treatment mechanism, we propose a facile strategy to synchronously achieve surface reconstruction and grain boundary healing by using 1,3-propylene diamine (PDA) post-treatment on CsPbI3 film. It is discovered that the PDA with suitable concentration can preferentially invade the defect sites of surface and GBs of CsPbI3 film, thereby break the soft perovskite structure in the shallow surface. With further low temperature annealing treatment, the broken CsPbI3 surface would undergo rapid secondary crystal growth to acquire smoother and blurred morphology with reduced GBs and pinholes, primarily derived from the strong interaction between the highly active amino groups of liquid PDA and Pb of perovskite. Meanwhile, the residual PDA molecules mainly anchor at the surface and GBs, and thus connect neighboring perovskite grains, coordinate uncoordinated sites to effectively passivate defects, and also resist the external invasions. Consequently, the inverted PDA-based CsPbI3 device yields a champion PCE of 20.02% with significantly improved long-term storage stability and operational stability. © 2023, The Authors. All rights reserved.

关键词： Perovskite solar cells

来源：评论

学校读者我要写书评

暂无评论

Methodology,progress and challenges of geoscience knowledge graph in International Big science Program of Deep-Time Digital Earth

引用

Journal of Geographical sciences 2025年第5期35卷 1132-1156页

作者： ZHU Yunqiang WANG Qiang WANG Shu SUN Kai WANG Xinbing LV Hairong HU Xiumian ZHANG Jie WANG Bin QIU Qinjun YANG Jie ZHOU Chenghu State Key Laboratory of Resources and Environmental Information System Institute of Geographic Sciences and Natural Resources ResearchCASBeijing 100101China Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing 210023China University of Chinese Academy of Sciences Beijing 100049China School of Electronic Information and Electrical EngineeringShanghai Jiao Tong UniversityShanghai 200240China Department of Automation Tsinghua UniversityBeijing 100084China State Key Laboratory for Mineral Deposits Research School of Earth Sciences and EngineeringNanjing UniversityNanjing 210023China State Key Laboratory of Information Photonics and Optical Communications Beijing University of Posts and TelecommunicationsBeijing 100876China Command Center of Natural Resources Comprehensive Survey China Geological SurveyBeijing 100055China School of Computer Science China University of GeosciencesWuhan 430074China

Deep-time Earth research plays a pivotal role in deciphering the rates,patterns,and mechanisms of Earth's evolutionary processes throughout geological history,providing essential scientific foundations for climate prediction,natural resource exploration,and sustainable planetary *** advance Deep-time Earth research in the era of big data and artificial intelligence,the International Union of Geological sciences initiated the“Deeptime Digital Earth International Big science Program”(DDE)in *** the core of this ambitious program lies the development of geoscience knowledge graphs,serving as a transformative knowledge infrastructure that enables the integration,sharing,mining,and analysis of heterogeneous geoscience big *** DDE knowledge graph initiative has made significant strides in three critical dimensions:(1)establishing a unified knowledge structure across geoscience disciplines that ensures consistent representation of geological entities and their interrelationships through standardized ontologies and semantic frameworks;(2)developing a robust and scalable software infrastructure capable of supporting both expert-driven and machine-assisted knowledge engineering for large-scale graph construction and management;(3)implementing a comprehensive three-tiered architecture encompassing basic,discipline-specific,and application-oriented knowledge graphs,spanning approximately 20 geoscience *** its open knowledge framework and international collaborative network,this initiative has fostered multinational research collaborations,establishing a robust foundation for next-generation geoscience research while propelling the discipline toward FAIR(Findable,Accessible,Interoperable,Reusable)data practices in deep-time Earth systems research.

关键词： deep-time Earth geoscience knowledge graph Deep-time Digital Earth International Big science Program

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：