检索结果-内蒙古大学图书馆

2024 International Conference on IT and Industrial Technologies, ICIT 2024

作者： Alam, Wahaj Ali, Raja Hashim Ali, Nisar Imad, Muhammad ul Abideen, Zain Shah, Muhammad Huzaifa Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi23460 Pakistan Department of Business University of Europe for Applied Sciences Potsdam14476 Germany Faculty of Engineering and Applied Science University of Regina ReginaS4S0A2 Canada BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain

ISBN: (纸本)9798331504465

Maintaining the integrity of financial systems and preventing people and organizations from suffering financial losses depend heavily on the ability to spot fraudulent financial transactions. Traditional rule-based fraud detection methods have trouble identifying intricate patterns and developing fraud tactics. Machine learning approaches have become powerful fraud detection tools in recent years, utilizing the strength of data-driven models to spot fraudulent actions. The Existing rule-based fraud detection has difficulty in identifying complex patterns and evolving fraud tactics. This study thoroughly investigates the use of machine learning techniques, including decision trees and random forests, for financial transaction fraud detection, while also exploring feature engineering approaches to extract essential data from transaction records such as temporal, spatial, and relational features. In this study, real-world financial transaction datasets are used to conduct experimental evaluations, comparing the performance of various machine learning models based on accuracy, precision, recall, and F1-score. The results indicate that certain algorithms outperform others, demonstrating promising and favorable outcomes for CatBoost algorithm. This significance of our study lies in showcasing the effectiveness of machine learning techniques, compared to traditional rule-based methods, for detecting fraud in financial transactions, leading to more promising outcomes and contributing to the integrity and security of financial systems. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Beyond pixels:Learning from multimodal hyperspectral superpixels for land cover classification

引用

science China(Technological sciences) 2022年第4期65卷 802-808页

作者： HONG DanFeng WU Xin YAO Jing ZHU XiaoXiang Key Laboratory of Computational Optical Imaging Technology Aerospace Information Research InstituteChinese Academy of SciencesBeijing 100094China School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and TelecommunicationsBeijing 100876China Remote Sensing Technology Institute German Aerospace Center(DLR)Wessling 82234Germany Data Science in Earth Observation Technical University of MunichMunich 80333Germany

Despite tons of advanced classification models that have recently been developed for the land cover mapping task,the monotonicity of a single remote sensing data source,such as only using hyperspectral data or multispectral data,hinders the classification accuracy from being further improved and tends to meet the performance *** this reason,we develop a novel superpixel-based subspace learning model,called Supace,by jointly learning multimodal feature representations from HS and MS superpixels for more accurate LCC *** can learn a common subspace across multimodal RS data,where the diverse and complementary information from different modalities can be better combined,being capable of enhancing the discriminative ability of to-be-learned features in a more effective *** better capture semantic information of objects in the feature learning process,superpixels that beyond pixels are regarded as the study object in our Supace for *** experiments have been conducted on two popular hyperspectral and multispectral datasets,demonstrating the superiority of the proposed Supace in the land cover classification task compared with several well-known baselines related to multimodal remote sensing image feature learning.

关键词： classification hyperspectral image land cover multimodal multispectral image remote sensing subspace learning superpixels

来源：评论

学校读者我要写书评

暂无评论

Generalization-Enhanced Few-Shot Object Detection in Remote Sensing

引用

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5445-5460页

作者： Lin, Hui Li, Nan Yao, Pengjuan Dong, Kexin Guo, Yuhan Hong, Danfeng Zhang, Ying Wen, Congcong China Academy of Electronics and Information Technology Beijing100846 China China Meteorological Administration National Satellite Meteorological Center Innovation Center for FengYun Meteorological Satellite Beijing100081 China Tsinghua University State Key Laboratory of Hydroscience and Engineering Department of Hydraulic Engineering Beijing100084 China Chinese Academy of Sciences Aerospace Information Research Institute Beijing100094 China University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering Beijing100049 China University of Science and Technology Beijing School of Automation and Electrical Engineering Beijing100083 China New York University Abu Dhabi Department of Electrical and Computer Engineering Abu Dhabi United Arab Emirates University of Science and Technology of China Anhui China

Object detection is a fundamental task in computer vision that involves accurately locating and classifying objects within images or video frames. In remote sensing, this task is particularly challenging due to the high resolution, multi-scale features, and diverse ground object characteristics inherent in satellite and UAV imagery. These challenges necessitate more advanced approaches for effective object detection in such environments. While deep learning methods have achieved remarkable success in remote sensing object detection, they typically rely on large amounts of labeled data. Acquiring sufficient labeled data, particularly for novel or rare objects, is both challenging and time-consuming in remote sensing scenarios, limiting the generalization capabilities of existing models. To address these challenges, few-shot learning (FSL) has emerged as a promising approach, aiming to enable models to learn new classes from limited labeled examples. Building on this concept, few-shot object detection (FSOD) specifically targets object detection challenges in data-limited conditions. However, the generalization capability of FSOD models, particularly in remote sensing, is often constrained by the complex and diverse characteristics of the objects present in such environments. In this paper, we propose the Generalization-Enhanced Few-Shot Object Detection (GE-FSOD) model to improve the generalization capability in remote sensing FSOD tasks. Our model introduces three key innovations: the Cross-Level Fusion Pyramid Attention Network (CFPAN) for enhanced multi-scale feature representation, the Multi-Stage Refinement Region Proposal Network (MRRPN) for more accurate region proposals, and the Generalized Classification Loss (GCL) for improved classification performance in few-shot scenarios. GE-FSOD demonstrates superior robustness and accuracy in remote sensing FSOD tasks through these enhancements. Extensive experiments on the DIOR and NWPU VHR-10 datasets show that our

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Feedback Delay-Tolerant Proactive Caching Scheme Based on Federated Learning at the Wireless Edge

IEEE Networking Letters

引用

IEEE Networking Letters 2023年第1期5卷 26-30页

作者： Lin, Na Wang, Yamei Zhang, Enchao Yu, Keping Zhao, Liang Guizani, Mohsen Shenyang Aerospace University School of Computer Science Shenyang110136 China Hosei University Graduate School of Science and Engineering Tokyo184-8584 Japan Riken Riken Center for Advanced Intelligence Project Tokyo103-0027 Japan Mohamed Bin Zayed University of Artificial Intelligence Machine Learning Department Abu Dhabi United Arab Emirates

Edge caching has emerged as a promising approach to meet explosive mobile data on 6G networks. One critical issue in edge caching is file popularity prediction. The federated learning (FL) based distributed algorithm is used to predict file popularity, which solves user privacy issues in centralized algorithms. However, due to the heterogeneity of user devices, the feedback time (i.e., the update and upload time of model parameters) is various for each user, which causes the feedback delay in the framework of FL-based edge caching. In this letter, we devise a feedback delay-tolerant proactive caching scheme (FLASH) based on FL in which each user utilizes hybrid filtering on stacked autoencoders to train the prediction model locally. Experimental results indicate that FLASH can effectively handle feedback delay and outperform counterpart algorithms in cache efficiency. © 2019 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Five-level anti-counterfeiting based on versatile luminescence of tri-doped double perovskites

引用

Nano Research 2024年第11期17卷 9971-9979页

作者： Xingru Yang Yuhang Sheng Linglong Zhang Lun Yang Fangjian Xing Yunsong Di Cihui Liu Fengrui Hu Xifeng Yang Guofeng Yang Yushen Liu Zhixing Gan Center for Future Optoelectronic Functional Materials School of Computer and Electronic Information/School of Artificial Intelligence Nanjing Normal University Nanjing 210023 China College of Physics Nanjing University of Aeronautics and Astronautics Key Laboratory of Aerospace Information Materials and Physics (NUAA) MIIT Nanjing 211106 China Hubei Key Laboratory of Photoelectric Materials and Devices School of Materials Science and Engineering Hubei Normal University Huangshi 435002 China College of Engineering and Applied Sciences and MOE Key Laboratory of Intelligent Optical Sensing and Manipulation Nanjing University Nanjing 210093 China College of Electronic and Information Engineering Changshu Institute of Technology Suzhou 215500 China School of Science Jiangsu Provincial Research Center of Light Industrial Optoelectronic Engineering and Technology Jiangnan University Wuxi 214122 China Yancheng Polytechnic College Yancheng 224005 China

Luminescent materials with multi-emission features are difficult to be replicated, which are highly desirable for advanced anti-counterfeiting. Here, we report the pioneering synthesis of Mn^(2+)/Yb^(3+)/Er^(3+) tri-doped Cs2Ag0.8Na0.2InCl6 double perovskites (MYE-DP), which exhibit photoluminescence (PL) covering from visible to near-infrared (NIR). The PL colors under excitations of 254 and 365 nm are notably different due to the changed relative emission intensities of self-trapped excitons (STEs) and Mn^(2+) d–d transition. Moreover, under the excitation of a NIR laser, the MYE-DP exhibits upconversion (UC) emissions of Mn^(2+) and Er^(3+). After ceasing the excitation, the long-lived trapped electrons can be thermally released to Mn^(2+) and Er^(3+) ions, resulting in both visible and NIR afterglow. Based on multi-modal emissions of the MYE-DP, we demonstrate a five-level anti-counterfeiting strategy, which significantly increases the anti-counterfeiting security. In addition, this work provides valuable insights into the energy transfer between STEs, Mn^(2+), Ln^(3+), and traps, laying a solid foundation for future development of new lead-free perovskites.

关键词： anti-counterfeiting photoluminescence self-trapped excitons upconversion

来源：评论

学校读者我要写书评

暂无评论

RailPC: A large-scale railway point cloud semantic segmentation dataset

引用

CAAI Transactions on Intelligence Technology 2024年第6期9卷 1548-1560页

作者： Tengping Jiang Shiwei Li Qinyu Zhang Guangshuai Wang Zequn Zhang Fankun Zeng Peng An Xin Jin Shan Liu Yongjun Wang Jiangsu Center for Collaborative Innovation in Geographical Information Resource Development and Application Nanjing Normal UniversityNanjingChina Technology Innovation Center for Integrated Applications in Remote Sensing and Navigation Ministry of Natural ResourcesNanjingChina Eastern Institute of Technology(EIT) NingboChina Tianjin Key Laboratory of Rail Transit Navigation Positioning and Spatio-temporal Big Data Technology TianjinChina College of Computer Science and Engineering Northwest Normal UniversityLanzhouChina Mckelvey School of Engineering Washington University in St.LouisSt.LouisMissouriUSA School of Electronic and Information Engineering Ningbo University of TechnologyNingboChina

Semantic segmentation in the context of 3D point clouds for the railway environment holds a significant economic value,but its development is severely hindered by the lack of suitable and specific ***,the models trained on existing urban road point cloud datasets demonstrate poor generalisation on railway data due to a large domain gap caused by non-overlapping special/rare categories,for example,rail track,track bed *** harness the potential of supervised learning methods in the domain of 3D railway semantic segmentation,we introduce RailPC,a new point cloud *** provides a large-scale dataset with rich annotations for semantic segmentation in the railway ***,RailPC contains twice the number of annotated points compared to the largest available mobile laser scanning(MLS)point cloud dataset and is the first railway-specific 3D dataset for semantic *** covers a total of nearly 25 km railway in two different scenes(urban and mountain),with 3 billion points that are finely labelled as 16 most typical classes with respect to railway,and the data acquisition process is completed in China by MLS *** extensive experimentation,we evaluate the performance of advanced scene understanding methods on the annotated dataset and present a synthetic analysis of semantic segmentation *** on our findings,we establish some critical challenges towards railway-scale point cloud semantic *** dataset is available at https://***/NNU-GISA/GISA-RailPC,and we will continuously update it based on community feedback.

关键词： data benchmark MLS point clouds railway scene semantic segmentation

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning-Based Connectivity Restoration in an Ocean Network of Fishing Vessels

Reinforcement Learning-Based Connectivity Restoration in an ...

引用

2022 IEEE International Conference on Advanced Networks and Telecommunications Systems, ANTS 2022

作者： Surendran, Simi Montresor, Alberto Ramesh, Maneesha Vinodini Casari, Paolo Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Amritapuri India University of Trento Department of Information Engineering and Computer Science via Sommarive 9 Trento35131 Italy Amrita Center for Wireless Networks & Applications Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (纸本)9781665473408

An Offshore Communication Network (OCN) is a network of fishing vessels at sea aimed at providing wireless Internet access over the ocean. The connectivity of fishing vessels is essential to disseminate messages, monitor emergency management, and provide information services. The impact of extreme weather conditions on wireless signals, the inability to deploy additional infrastructure, the movements induced by sea waves, the expanded mobility freedom at sea, and the nonuniform density of nodes create connectivity holes in an OCN. This paper proposes a reinforcement learning-based connectivity restoration scheme for OCNs. During the planning phase, a node examines the history of its contacts with other nodes and estimates their mobility vector to determine the expected location. Mobile nodes discover the best spots to re-establish connectivity and the most appropriate path to reach these spots via a trialand-error strategy. In a reinforcement learning framework, we simulate actions to move toward the expected contact locations and learn the optimal movement directions without guessing the contact's actual position. During the control phase, these learned policies are utilized to relocate isolated OCN nodes and restore high-quality connectivity. Simulation results show that our scheme improves the nodes' connectivity probability. © 2022 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A New Rhythm in A1: Convolutional Neural Networks for Music Genre Classification 18

A New Rhythm in A1: Convolutional Neural Networks for Music ...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Javed, Huzaifa Arshad, Usama Abideen, Zain Ul Ali, Raja Hashim BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany

ISBN: (纸本)9798350328172

Despite the significance of music genre classification in audio identification, it remains under-explored within AI research. This tool is crucial for personalized music recommendations and similar music detection. We have developed an efficient AI model that leverages Convolutional Neural Networks (CNNs), offering high-precision genre identification when integrated into a graphical user interface. The model effectively extracts audio features like Mel Frequency Cepstral Coefficients (MFCCs), zero-crossing rate, and tempo. Testing results reveal strong performance in genre prediction across diverse tracks, affirming the model's ability to discern unique characteristics of various music genres. This performance not only attests to the model's capability in discerning the unique characteristics inherent to different music genres but also suggests that it can effectively generalize to novel, unseen data. Our model lays the groundwork for future enhancements and demonstrates the potential of AI in transforming the music industry - from personalized music playlists to exploratory recommendation systems. The success of this model paves the way for more intricate applications of AI within music analysis. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Multimedia Classification via Tensor Linear Discriminant Analysis

引用

IEEE Transactions on Broadcasting 2024年第4期70卷 1139-1152页

作者： Chang, Shih-Yu Wu, Hsiao-Chun Yan, Kun Chih-Hao Huang, Scott Wu, Yiyan San Jose State University Department Of Applied Data Science San JoseCA95192 United States Louisiana State University School Of Electrical Engineering And Computer Science Baton RougeLA70803 United States Yuan Ze University Innovation Center For Ai Applications Taoyuan32003 Taiwan Guilin University Of Electronic Technology Guangxi Key Laboratory Of Wireless Wideband Communication And Signal Processing Department Of Information And Telecommunication Guilin541004 China National Tsing Hua University Department Of Electrical Engineering Hsinchu300 Taiwan Western University Department Of Electrical And Computer Engineering LondonONN6A 3K7 Canada

Linear discriminant analysis (LDA) is a well-known feature-extraction technique for data analytic and pattern classification. As the dimensionality of multimedia data has increased in this big era, it is often to characterize data by tensors. Over the past two decades, researchers have thus explored to extend LDA to the general tensor space, especially in two common ways: LDA of tensors using tensor decomposition methods (by conversion of tensors to matrices) and LDA of tensors built upon the T-product. However, both of the aforementioned approaches have restrictions thereby. A critical problem about how to carry out LDA of arbitrary scatter tensors based on the Einstein product still remains unsolved by the existing methods. Therefore, we propose a novel tensor LDA (a.k.a. TLDA) approach, which can carry out the LDA of arbitrary-dimensional scatter-tensors without any need of tensor decomposition. Besides, for reducing the computation time, we also design a parallel paradigm to execute our proposed TLDA in this work. Numerical experiments conducted over real multimedia data demonstrate the efficacy of our proposed new TLDA in terms of classification accuracy. Moreover, the comparison of the classification accuracies, computational-complexities, and memory-complexities of our proposed novel TLDA scheme and other existing tensor-based LDA methods is made. By leveraging TLDA for high-dimensional feature extraction, segmentation, and user-item interaction data processing, future multimedia recommendation systems can facilitate more accurate, engaging, and satisfactory user experience over the Internet. © 1963-12012 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

The YOLOv8 Edge: Harnessing Custom Datasets for Superior Real-Time Detection 18

The YOLOv8 Edge: Harnessing Custom Datasets for Superior Rea...

引用

18th IEEE International Conference on Emerging Technologies, ICET 2023

作者： Ahmed, Tafreed Maaz, Ahmad Mahmood, Danyaal Abideen, Zain Ul Arshad, Usama Ali, Raja Hashim BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany

ISBN: (纸本)9798350328172

YOLO has become a central real-time object detection system for robotics, driverless cars, and video monitoring applications. Developing a custom object detection solution that can detect specific objects in real-time video streams has the potential to revolutionize various fields and has been the subject of extensive research. Although there have been advances in object detection, there is still a gap in the research for real-time detection of custom objects with high accuracy and speed. This research addresses this gap by training a YOLOv8 detector on a custom dataset of objects and evaluating its performance on real-time video streams which is by far the latest model and thus is faster and more accurate. Our experimental results demonstrate that our custom-trained YOLOv8 detector achieves high accuracy and real-time performance on a custom dataset of objects. The detector achieved an overall mAP50 of 0.864 and a mAP50-95 of 0.758, with individual class results ranging from 0.47 to 0.995. These findings show that custom training data and YOLOv8 are effective in real-time object detection, which has practical applications in various fields. The significance of the results and our contribution lies in demonstrating the effectiveness of custom training data for improving object detection accuracy and speed using YOLO, which has implications for a wide range of real-world applications. © 2023 IEEE.

关键词： Object detection

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：