检索结果-内蒙古大学图书馆

IEEE Transactions on Intelligent Vehicles 2024年 1-15页

作者： Wang, Li Zhang, Xinyu Zhao, Fachuan Wu, Chuze Wang, Yichen Song, Ziying Yang, Lei Xu, Bin Li, Jun Ge, Shuzhi Sam School of Machanical Engineering Beijing Institute of Technology Beijing China School of Vehicle and Mobility Tsinghua University Beijing China School of Computer and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China Department of Electrical and Computer Engineering Interactive Digital Media Institute Social Robotics Laboratory National University of Singapore Singapore

Non-maximum suppression (NMS) is an essential post-processing module in many 3D object detection frameworks to remove overlapping candidate bounding boxes. However, an overreliance on classification scores and difficulties in determining appropriate thresholds can affect the resulting accuracy directly. To address these issues, we introduce fuzzy learning into NMS and propose a novel generalized Fuzzy-NMS module to achieve finer candidate bounding box filtering. The proposed Fuzzy-NMS module combines the volume and clustering density of candidate bounding boxes, refining them with a fuzzy classification method and optimizing the appropriate suppression thresholds to reduce uncertainty in the NMS process. Adequate validation experiments use the mainstream KITTI and large-scale Waymo 3D object detection benchmarks. The results of these tests demonstrate the proposed Fuzzy-NMS module can improve the accuracy of numerous recently NMS-based detectors significantly, including PointPillars, PV-RCNN, and IA-SSD, etc. This effect is particularly evident for small objects such as pedestrians and bicycles. As a plug-and-play module, Fuzzy-NMS does not need to be retrained and produces no obvious increases in inference time. IEEE

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Investigating the Use of Multi-Sourced Input Data for Time Series Algorithms Applied to Hyper Spectral Imagery 5th

Investigating the Use of Multi-Sourced Input Data for Time S...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Raj, Shanthi Pichandi Ananda Mishra, Awakash D, Preethi Sivaraman, Himani School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Manduwala Dehradun Navgaon India

ISBN: (纸本)9789819780426

This paper examines the efficacy of merging multi-sourced enter records into time series algorithms for analyzing hyperspectral imagery. Combining entered information from different resources (e.g., from Radar, Landsat, and LiDAR) with usually used time collection algorithms (e.g., SVM, Random Forests, and Gradient Boosting) is investigated in this study. First, Landsat, LiDAR, and Radar data are purified, and the derived pixels are stacked and rasterized to generate input datasets as collections of vectors. Secondly, the entered datasets are transformed into temporal capabilities with the same old Deviation technique (SDM) and minimum Spanning Tree (MST) to visualize the records from a temporal angle. The temporal features enter the various time series algorithms for hyper hyperspectral type. The paper concludes by showing the capacity improvements because of merging more than one asset within the analyzed algorithms and further discussing feasible explorative programs. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： analyzed explorative hyperspectral

来源：评论

学校读者我要写书评

暂无评论

Combining CNN and SVM for High-Precision Wheat Disease Classification using Leaf Image Analysis 2

Combining CNN and SVM for High-Precision Wheat Disease Class...

引用

2nd IEEE Global Conference on Communications and information Technologies, GCCIT 2024

作者： Jain, Anuj Kumar Jain, Sonam Kaur, Urvinder Dahiya, Atisha Bhandari, Rahul Goel, Sandeep Chandigarh University Department of Cse Punjab Mohali India Panipat Institute of Engineering and Technology Department of Computer Applications Haryana Samalkha India Panipat Institute of Engineering and Technology Department of Information Technology Haryana Samalkha India

ISBN: (纸本)9798350388916

This study presents a novel classification algorithm designed to accurately identify plant diseases using leaf image analysis. The model employs a hybrid architecture containing a CNN (Convolutional Neural Network) and an SVM (Support Vector Machine) classifier, featuring 2 convolutional layers and 2 max-pooling layers. A variety of datasets encompassing five distinct plant diseases have been utilized for assessment: Stripe Rust, Powdery Mildew, Leaf Rust, Septoria Leaf Blotch, and Fusarium Head Blight. For each disease category, the model can correctly classify a positive case with precision values ranging from 92.45% to 93.75%. Similarly, the recall values are consistent with a range from 91.84% to 94.12%, which were very good too and would be shown that no matter what was taken into account either ring or original brain scans researchers could obtain positive instances well enough using this model resources The model showcases a significant performance, with F1-Score (a balanced metric concerning precision and recall) having high values constant between 92.78% and 93.75%. Support Proportions indicate how much of the overall dataset can be attributed to a given disease class and Support Values show where there are occurrences in each proportion. Its great Weighted Average Accuracy of 93.25% shows that the model is trained on a wide range of plant diseases so it does not only work for one or two datasets but across all datasets. This endto-end macro-average and micro-average evaluation, again only shows all around effectiveness of the model. Results & conclusions: This study provides a highly accurate automated plant disease diagnostic model, which is of great significance for crop management and precision agriculture. If validated through follow-up studies, the findings could improve crop yields and sustainability as well as help develop remote sensing technology that rapidly identifies plant disease. © 2024 IEEE.

关键词： Precision agriculture

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Marine Predator Algorithm for Thermal-aware Routing Scheme in Wireless Body Area Networks

引用

Journal of Bionic engineering 2023年第1期20卷 81-104页

作者： Tao Hai Jincheng Zhou Mohammad Masdari Haydar Abdulameer Marhoon School of Computer and Information Qiannan Normal University for NationalitiesDuyun558000GuizhouChina Key Laboratory of Complex Systems and Intelligent Optimization of Guizhou Duyun558000GuizhouChina Institute for Big Data Analytics and Artificial Intelligence(IBDAAI) Universiti Teknologi MARA40450Shah AlamSelangorMalaysia Department of Computer Engineering Islamic Azad UniversityUrmia BranchUrmiaIran Information and Communication Technology Research Group Scientific Research CenterAl-Ayen UniversityThi-QarIraq College of Computer Sciences and Information Technology University of KerbalaKarbalaIraq

Thermal-aware routing protocols in WBANs consider temperature factors in the routing process for preventing overheating of the tissues surrounding the sensor ***,providing an energy-efficient and thermal-aware routing in WBANs is a challenging *** deal with this problem,this article presents a novel temperature-aware routing protocol that applies Mamdani-based Fuzzy Logic Controllers(FLCs)for selecting the next forwarding node in routing data *** FLCs apply five important input factors such as the priority of the packet,and sensor node's remaining energy,temperature,distance,and link path ***,a new hybrid version of the Marine Predator Algorithm(MPA),named MPAOA is presented by combining the exploration and exploitation phases of the MPA and Arithmetic Optimization Algorithm(AOA).This algorithm is effectively applied for selecting the best possible set of fuzzy rules for FLCs and tuning their fuzzy *** experiments conducted in the Castalia simulator exhibit that the proposed temperature and priority-aware routing scheme can outperform other well-known routing schemes such as LATOR,TTRP,TAEO,ATAR,and EOCC-TARA in terms of metrics such as sensor nodes lifetime,the average temperature of the sensor nodes,and the percentage of the packets routed through non-overheated ***,it is shown that the MPAOA outperforms other algorithms such as Bat Algorithm(BA),Genetic Algorithm(GA),AOA,and MPA regarding the specified metrics.

关键词： WBANs Multi-hop routing Temperature Priority Fuzzy logic Bio-inspiration

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based knowledge-aware semantic communications for remote driving image transmission

引用

Digital Communications and Networks 2025年第2期11卷 317-325页

作者： Yangfei Lin Tutomu Murase Yusheng Ji Wugedele Bao Lei Zhong Jie Li Department of Computer and Network Engineering University of Electro-CommunicationsChofuTokyo 182-8585Japan Information Technology Center Nagoya UniversityNagoya 464-8601Japan National Institute of Informatics(NII) Tokyo 101-8430Japan Hohhot Minzu College Hohhot 010051China Toyota Motor Corporation Tokyo 112-8701Japan Department of Computer Science and Engineering Shanghai Jiaotong UniversityShanghai 200240China

Remote driving,an emergent technology enabling remote operations of vehicles,presents a significant challenge in transmitting large volumes of image data to a central *** requirement outpaces the capacity of traditional communication *** tackle this,we propose a novel framework using semantic communications,through a region of interest semantic segmentation method,to reduce the communication costs by transmitting meaningful semantic information rather than bit-wise *** solve the knowledge base inconsistencies inherent in semantic communications,we introduce a blockchain-based edge-assisted system for managing diverse and geographically varied semantic segmentation knowledge *** system not only ensures the security of data through the tamper-resistant nature of blockchain but also leverages edge computing for efficient ***,the implementation of blockchain sharding handles differentiated knowledge bases for various tasks,thus boosting overall blockchain *** results show a great reduction in latency by sharding and an increase in model accuracy,confirming our framework's effectiveness.

关键词： Semantic communication Remote driving Semantic segmentation Blockchain Knowledge base management

来源：评论

学校读者我要写书评

暂无评论

Does Sri Lanka Have a Good Maritime Strategy to Stop Cyber-Terrorist Attacks 14

Does Sri Lanka Have a Good Maritime Strategy to Stop Cyber-T...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Samaraweera, S.A.R.P. Siriwardana, S.M.D.N. Fernando, W.D.V. Rajakarunaratne, D.N. Sri Lanka Institute of Information Technology Dept. of Computer Systems Engineering Malabe Sri Lanka

ISBN: (纸本)9798350335095

Maritime cyber-terrorist attacks have become a major concern to the entire world in recent decades. Everyone should be more aware of marine strategies to prevent cyberterrorist attacks, both locally and globally. This study investigates how Sri Lanka and the Sri Lanka Navy (SLN) may successfully address maritime security concerns by utilizing current resources and developing a marine strategy to counter such maritime cyber-terrorism assaults. The literature review in this thesis primarily evaluates the level of understanding in Sri Lanka concerning when marine cyber terrorism strikes may occur. Furthermore, this thesis investigates if Sri Lanka has any maritime rules and regulations. The use of such laws and regulations will concentrate on how they can increase their expertise. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Facial Emotion Recognition Method Based on Canny Edge Detection Using Convolutional Neural Network 4

Facial Emotion Recognition Method Based on Canny Edge Detect...

引用

4th IEEE International Conference on Computing, Communication, and Intelligent Systems, ICCCIS 2023

作者： Harshith, V. Shilpa, T. Siddappa, M. Banglore Institute of Technology Information Science and Engineering Department Bangalore India Sri Siddhartha Institute of Technology Computer Science and Engineering Department Tumkur India

ISBN: (纸本)9798350306118

Facial Emotion Recognition(FER) has made a pivotal contribution to Human Society by accomplishing complex tasks which humans struggle to achieve. The traditional Machine Learning (ML) models that follow explicit feature extraction from images require domain expertise, manual effort and also lack spatial invariance. The primary cause for the hindrance of the recognition accuracy is the imbalance of classes that exist in the datasets along with the limited availability of training data. To address these limitations, a facial emotion recognition method based on Canny edge detection utilizing a convolutional neural network is proposed in this paper. Important structural information from facial images is extracted to intensify the recognition rate, and techniques such as data augmentation, and oversampling are utilized. The proposed Convolutional Neural Network (CNN) model is trained using the dataset FER2013. The accuracy achieved with only 40 iterations of training was 76.92 percent with the devised method that surpasses other CNN architectural methods such as traditional CNN, Xception and AlexNet. © 2023 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Dynamic-Feature-Based Object Tracking Using Real-Time Image Processing 5th

Dynamic-Feature-Based Object Tracking Using Real-Time Image ...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Mishra, Awakash Rengarajan Bhatt, Rahul Prince, P. Blessed Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India

ISBN: (纸本)9789819780426

This research explores the utility of today's real-time picture processing for dynamic-characteristic-primarily based object monitoring. Notably, this painting proposes a novel tracking method that combines an actual-time, place-primarily based convolutional neural community (R-CNN) with monitoring with the detection (TbD) technique. The proposed approach is for contemporary R-CNNs to constantly come across transferring objects in video frames and then modern-day the TbD technique to generate accurate item tracking information. The proposed system is evaluated on two benchmark datasets and compared to numerous tracking methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Investigating the Use of Hierarchical Recurrent Neural Networks for Medical Image Segmentation 5th

Investigating the Use of Hierarchical Recurrent Neural Netwo...

引用

5th International Conference on Data Science, Machine Learning and Applications, ICDSMLA 2023

作者： Suneetha, K. Dobriyal, Rohit Elangovan, Vetrimani Savita Karnataka Bangalore India Department of Computer Science and Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering and Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

This paper investigates the usage of hierarchical recurrent neural networks (HRNNs) for clinical photo segmentation. HRNNs are a neural network structure combining more than one layer of recurrent cells and layers of convolution cells. The intention of this paper changed to evaluate the effectiveness of HRNNs for medical picture segmentation and how well it can be applied for this reason. The paper evaluates a present HRNN implementation for medical picture segmentation and shows its accuracy primarily based on the dice coefficient (DC). The authors additionally proposed a changed HRNN architecture to improve the segmentation performance: the architecture integrated residual connections, multi-scale inputs, multi-resolution outputs, and an utterly convolution structure. The proposed DT-SL loss was potent in improving the segmentation accuracy. Typically, the outcomes reveal that HRNNs are promising devices for clinical photograph segmentation tasks and can effectively facilitate faster and extra correct segmentation. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Exploring Data as Quantum Bits: Analysis of Quantum Image Encoding Patterns for NISQ era

Exploring Data as Quantum Bits: Analysis of Quantum Image En...

引用

2023 IEEE International Conference on Quantum Technologies, Communications, Computing, Hardware and Embedded Systems Security, iQ-CCHESS 2023

作者： Gopakumar, Parvathy Rubell Marion Lincy, G. Indian Institute of Information Technology Kottayam Department of Computer Science and Engineering Kerala Pala Kottayam India

ISBN: (纸本)9798350314946

The generall efficiency of a computational system, be it simple or complex, presentation of the data plays a crucial role in getting the most out of it. Classical information theory, quantum mechanics, and computer science collectively influence Quantum information in comprehending how information can be encoded, transmitted, and modified using quantum systems. Quantum mechanics allows quantum information to incorporate a variety of properties, such as quantum encoding of classical information, storing coherent details in quantum superpositions, quantum computations and entanglement, which occurs when two or more qubits become highly correlated and share an unbreakable quantum state. There are numerous barriers and constraints in the broad field of quantum computation, ranging from dealing with Decoherence to ensuring error correction. Moreover, the qubit, a fundamental computational unit, is challenging to create, manipulate, and store. To ensure the quality of the Quantum Algorithms, the area of quantum data encoding has been thoroughly researched and explored as relevant results can be obtained by adequate encoding. In this paper, we reviewed the terminology and physical modeling of qubits, as well as the encoding approaches used to transform data from classical to quantum models. Furthermore, different encoding schemes for Quantum Image Processing were explored to determine the efficiency of quantum pixel representation(QPIXL) framework for effective application in NISQ era. © 2023 IEEE.

关键词： Qubits

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：