检索结果-内蒙古大学图书馆

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Liu, Hangcheng Wu, Zhenhu Wang, Hao Han, Xingshuo Guo, Shangwei Xiang, Tao Zhang, Tianwei College of Computing and Data Science Nanyang Technological University Singapore School of Computer Science Beijing University of Posts and Telecommunications China College of Computer Science Chongqing University China

Monocular Depth Estimation (MDE) enables the prediction of scene depths from a single RGB image, having been widely integrated into production-grade autonomous driving systems, e.g., Tesla Autopilot. Current adversarial attacks to MDE models focus on attaching an optimized adversarial patch to a designated obstacle. Although effective, this approach presents two inherent limitations: its reliance on specific obstacles and its limited malicious impact. In contrast, we propose a pioneering attack to MDE models that decouples obstacles from patches physically and deploys optimized patches on roads, thereby extending the attack scope to arbitrary traffic participants. This approach is inspired by our groundbreaking discovery: various MDE models with different architectures, trained for autonomous driving, heavily rely on road regions when predicting depths for different obstacles. Based on this discovery, we design the Adversarial Road Marking (AdvRM) attack, which camouflages patches as ordinary road markings and deploys them on roads, thereby posing a continuous threat within the environment. Experimental results from both dataset simulations and real-world scenarios demonstrate that AdvRM is effective, stealthy, and robust against various MDE models, achieving about 1.507 of Mean Relative Shift Ratio (MRSR) over 8 MDE models. The code is available at this Github Repo. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A RDF-based model for expressing spatio-temporal relations between Web sites 3

A RDF-based model for expressing spatio-temporal relations b...

引用

3rd International Conference on Web Information Systems Engineering, WISE 2002

作者： Buraga, S. Ciobanu, G. A.I. Cuza University Faculty of Computer Science Iaşi Romania National University of Singapore School of Computing Dept. of Computer Science Singapore

ISBN: (纸本)0769517668

The paper proposes a high-level model to represent spatio-temporal relations between Web sites or fragments of Web sites in order to facilitate resource discovery, cataloging or describe information. This model is based on the Resource Description Framework (RDF) recommendation of the World-Wide Web Consortium, a general purpose technology that enables the description of resources on the Web. The representation of the spatio-temporal relationships is expressed by an XML-based language. © 2002 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

A Systematic Literature Review of Machine Learning and Deep Learning Approaches for Spectral Image Classification in Agricultural Applications Using Aerial Photography

引用

computers, Materials & Continua 2024年第3期78卷 2967-3000页

作者： Usman Khan Muhammad Khalid Khan Muhammad Ayub Latif Muhammad Naveed Muhammad Mansoor Alam Salman A.Khan Mazliham Mohd Su’ud College of Computing and Information Sciences Karachi Institute of Economics and TechnologyKarachi75190Pakistan Faculty of Computing and Informatics(FCI) Multimedia UniversityCyberjaya63100Malaysia Faculty of Computing Riphah International UniversityIslamabad46000Pakistan Faculty of Engineering and Information Technology School of Computer ScienceUniversity of Technology SydneySydneyAustralia

Recently,there has been a notable surge of interest in scientific research regarding spectral *** potential of these images to revolutionize the digital photography industry,like aerial photography through Unmanned Aerial Vehicles(UAVs),has captured considerable *** encouraging aspect is their combination with machine learning and deep learning algorithms,which have demonstrated remarkable outcomes in image *** a result of this powerful amalgamation,the adoption of spectral images has experienced exponential growth across various domains,with agriculture being one of the prominent *** paper presents an extensive survey encompassing multispectral and hyperspectral images,focusing on their applications for classification challenges in diverse agricultural areas,including plants,grains,fruits,and *** meticulously examining primary studies,we delve into the specific agricultural domains where multispectral and hyperspectral images have found practical ***,our attention is directed towards utilizing machine learning techniques for effectively classifying hyperspectral images within the agricultural *** findings of our investigation reveal that deep learning and support vector machines have emerged as widely employed methods for hyperspectral image classification in ***,we also shed light on the various issues and limitations of working with spectral *** comprehensive analysis aims to provide valuable insights into the current state of spectral imaging in agriculture and its potential for future advancements.

关键词： Machine learning deep learning unmanned aerial vehicles multi-spectral images image recognition object detection hyperspectral images aerial photography

来源：评论

学校读者我要写书评

暂无评论

LCM: A lightweight communication mechanism in HPC cloud

LCM: A lightweight communication mechanism in HPC cloud

引用

2011 6th International Conference on Pervasive computing and Applications, ICPCA 2011

作者： Chen, Haibao Wu, Song Shi, Xuanhua Jin, Hai Fu, Yu Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9781457702082

Inspired by the concept of cloud computing, the construction of HPC Cloud with traditional HPC resources not only provides new opportunities to address the challenges to the traditional HPC, but also brings many exciting research problems. One of them is how to reduce the network overhead of virtual cluster in HPC cloud. In order to resolve the problem, this paper presents the design and implementation of lightweight communication mechanism for virtual cluster in HPC Cloud, called LCM, which maintains binary compatibility for applications written in standard socket interface. We implemented our design on Xen 3.2 with Linux kernel 2.6.18, and evaluated the speed of file transfer, the running time of NAS Parallel benchmark and binary compatibility using binary image of real socket applications. In our tests, we have proved that LCM realizes the high performance that is comparable to UNIX domain socket and ensures full binary compatibility. © 2011 IEEE.

关键词： Binary images

来源：评论

学校读者我要写书评

暂无评论

Gasoline and Crude Oil Price Prediction using Multi-headed Variational Neighbour Search-tuned Recurrent Neural Networks

引用

Computational Economics 2025年 1-36页

作者： Kljajic, Maja Mizdrakovic, Vule Jovanovic, Luka Bacanin, Nebojsa Simic, Vladimir Pamucar, Dragan Zivkovic, Miodrag Business Economics Singidunum University Belgrade Serbia Informatics and Computing Singidunum University Belgrade Serbia Department of Mathematics Saveetha School of Engineering SIMATS Chennai India Sinergija University Bijeljina Bosnia and Herzegovina University of Belgrade Faculty of Transport and Traffic Engineering Belgrade Serbia Yuan Ze University College of Engineering Taoyuan City Taiwan Department of Computer Science and Engineering College of Informatics Seoul Republic of Korea Department of Operations Research and Statistics Faculty of Organizational Sciences University of Belgrade Belgrade Serbia Department of Mechanics and Mathematics Western Caspian University Baku Azerbaijan İstinye University Faculty of Engineering and Natural Sciences Industrial Engineering Department İstanbul Türkiye

The rapidly growing worldwide demand for energy and finite reservoirs of fossil fuels have intensified interest in energy projection research. Artificial intelligence, particularly in time series forecasting, holds significant promise for enhancing predictions of both cost and demand, offering numerous prospective applications over various domains. Numerous variables, ranging from socio-economic conditions to distribution, supply, and international policies, exert influence on global price fluctuations. Thus, crafting precise forecasts necessitates consideration of these multifaceted factors. Through an examination of existing literature, a discernible gap emerges in the quest for advancement in this domain. Consequently, this study proposes to delve into the perspective of employing multi-headed long short-term memory (LSTM) models for gasoline and crude oil price prediction, an area largely untouched by multi-headed approaches. Moreover, recognizing the computational demands of such models, this research emphasizes the development of lightweight methodologies, characterized by a modest neuron within each layer and trained over a limited epoch count. Given the pivotal role of hyper-parameter selection in algorithm performance, an adapted version of the variable neighbour search algorithm is introduced to aid in tuning the model’s architecture and training parameters. A comprehensive side-by-side comparison is undertaken utilizing gasoline and oil data sourced from diverse public repositories, employing a variety of contemporary optimizers. The resultant outcomes are subjected to strict statistical scrutiny to ascertain the robustness and significance of the findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficacious Routing Approaches in Vehicular Ad hoc Network: An Empirical Study 1

Efficacious Routing Approaches in Vehicular Ad hoc Network: ...

引用

1st International Conference on Advances in Electrical, Electronics and Computational Intelligence, ICAEECI 2023

作者： Janet Kumari, J Jesy Thangam, S. Raja, A. Saleem Amrita Vishwa Vidhyapeetham Amrita School of Computing Bengaluru Department of Computer Science and Engineering India University of Technology and Applied Science-Shinas Department of Computer Science and Engineering Oman

ISBN: (纸本)9798350342796

VANET, or Vehicular Ad hoc Network is a transient wireless structure made up of different kinds of vehicles serving as network hubs and the links between them acting as links. VANET is an improving mechanism that has received an amount of growth in the fields of research, academia, and business. A VANET is a mobile network that uses vehicles as terminals. VANETs, similar to spontaneous systems, possess all the main features of independent connectivity, including processing and preservation constraints. To improve safety while driving and other services, a network of VANETs can be established. The effectiveness of VANETs has been demonstrated in numerous real-world applications, such as traffic management and driver-assist systems. Information exchanged over VANETs can undoubtedly help users experience a better driving experience and prevent accidents. academia, and government. VANET is an acronym used to describe the Vehicular ad hoc network that forms over-moving vehicles on the road. Vehicle networks are rapidly emerging as a platform for creating and implementing new and classic applications. VANETs are distinguished by their high mobility, frequently changing topology, and ephemeral, one-time connections. Vehicle interruptions are common due to how dynamic and moving vehicles are at present. Clustering techniques for vehicles that arrange to increase network scalability and connection dependability as VANET introduces vehicles in groups. Subsequently, other clustering strategies and techniques also exist, and it is necessary for a wide range of situations, including information transfer, routing, and detection of accidents. The methods used for vehicle clustering techniques are examined in this study in terms of networking techniques. © 2023 IEEE.

关键词： ant colony optimization hybrid protocol proactive reactive VANET

来源：评论

学校读者我要写书评

暂无评论

Simple characterization of polygons searchable by 1-searcher 18

Simple characterization of polygons searchable by 1-searcher

引用

18th Annual Canadian Conference on Computational Geometry, CCCG 2006

作者： Kameda, Tsunehiko Zhang, John Z. Yamashita, Masafumi School of Computing Science Simon Fraser University Canada Department of Mathematics and Computer Science University of Lethbridge Canada Department of Computer Science and Communication Engineering Kyushu University Japan

Suppose intruders are in a dark polygonal room and they can move arbitrarily fast, trying to avoid detection. A boundary 1-searcher can move along the polygon boundary, equipped with a flash light that she can direct in any direction. A polygon is searchable if there is a schedule for the searcher in order to detect the intruders no matter how they move. We identify three simple forbidden patterns such that a given polygon is searchable by a boundary 1-searcher if and only if it has none of them. The concept of sweeping the visibility diagram greatly facilitates the proof. © 2006 Canadian Conference on Computational Geometry. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Spray and Wait routing protocol for delay tolerant networks

Dynamic Spray and Wait routing protocol for delay tolerant n...

引用

9th IFIP International Conference on Network and Parallel computing, NPC 2012

作者： Zhang, Longbo Yu, Chen Jin, Hai Services Computing Technology and System Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan 430074 China

ISBN: (纸本)9783642356056

Delay Tolerant Networks (DTN) is one of the mobile wireless networks that cannot set up the end-to-end communication path between the source and destination nodes pair in most of time. In this paper, we propose an improved routing protocol named as Dynamic Spray & Wait (DS&W), which is based on Spray and Wait routing strategy attempting to gain the higher delivery ratio benefits of replication-based routing as well as the lower resource utilization benefits of forwarding-based routing. But different from S&W, DS&W routing strategy focus on dynamic control to reduce the scale of the messages' flooding by calculating the delivery success probabilities to destinations. DS&W routing protocol can dramatically reduce the overhead ratio in DTNs. Simulation results also evident that DS&W protocol outperforms other existing DTN routing protocols. © IFIP International Federation for Information Processing 2012.

关键词： Wireless networks

来源：评论

学校读者我要写书评

暂无评论

Detection and Recognition of Vehicles Using Indian Driving Datasets 11

Detection and Recognition of Vehicles Using Indian Driving D...

引用

11th IEEE International Conference on Cloud computing in Emerging Markets, CCEM 2023

作者： Padukote, Yathish H.S. Suresha, R. Manohar, N. Jipeng, Tian Department of Computer Science School of Computing Mysuru Amrita Vishwa Vidyapeetham India Computer Science college Zhongyuan University of Technology Henan Province Zhengzhou China

ISBN: (纸本)9798350360059

Vehicle identification and recognition are essential computer vision tasks with important applications in autonomous driving, traffic management, and surveillance systems. The Indian Driving Dataset (IDD) dataset used in this work was compiled from a variety of driving scenarios in the Indian environment, and it includes a thorough investigation on vehicle detection and recognition. The dataset is meticulously chosen to reflect the difficulties brought on by the state of Indian roads, traffic patterns, and vehicle kinds. In this study, a Faster RCNN method for precise and effective vehicle detection and recognition deep learning approaches by enhancing images using power-law transformation. The collection consists of annotated IDD dataset images taken in a range of lighting situations, urban-rural locales, and camera angles. The testing results demonstrate the effectiveness of the recommended approach, which achieves competitive performance with 79.5% detection accuracy and 76% recognition accuracy. Additionally, the performance of the model is impacted by elements like various lighting situations and various vehicle models. This research offers insightful information about the model's ability to generalise in realistic situations. ©2023 IEEE.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Evolutionary selection for regression test cases based on diversity

引用

Frontiers of computer science 2021年第2期15卷 201-203页

作者： Baoying MA Li WAN Nianmin YAO Shuping FAN Yan ZHANG School of Health Management Mudanjiang Medical UniversityMudanjiang157011China Department of intelligence and Computing Tianjin UniversityTianjin300350China School of Computer Science and Technology Dalian University of TechnologyDalian116024China School of Computer and Information Technology Mudanjiang Normal UniversityMudanjiang157011China

1 Introduction Regression testing refers to retest code after modification to ensure that changes will not introduce new faults or cause faults in other lines of code[1].Regression test selection(RTS)is one of the predominant *** identifies test cases that are relevant to test recent changes in an application and seeks to reduce the number of test suite while preserving the capability to reveal faults[2].

关键词： preserving predominant changes

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：