检索结果-内蒙古大学图书馆

RULE-BASED SYMBOLIC PROCESSOR FOR OBJECT RECOGNITION

APPLIED OPTICS 1987年第22期26卷 4795-4802页

作者： CASASENT, D MAHALANOBIS, A []Carnegie Mellon University Department of Electrical Computer Engineering Center for Excellence in Optical Data Processing Pittsburgh Pennsylvania 15213

The application of symbolic processing and rule-based methods for target recognition using correlation filters is considered. The concept of partitioning images is introduced, and its advantages are described. Techniques for rule development, symbolic substitution, error correction via associative processing, and on-line filter adaptation are advanced. Initial simulation results are also presented and discussed.

关键词： Associative memory computer simulation Fourier transforms Infrared sensors Spatial filtering Synthetic discrimination functions

来源：评论

学校读者我要写书评

暂无评论

Multi-sensor processing: Object detection and identification

Multi-sensor processing: Object detection and identification

引用

Mobile Robots II 1987

作者： Liebowitz, Suzanne Casasent, David Center for Excellence in Optical Data Processing Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA15213 United States

Following a brief review of multi-sensor image processing techniques for obstacle detection, we consider a new method to employ range data to extract object regions of interest from an outdoor natural scene. Our emphasis and intent is scene analysis and object identification in the face of 3-D distortions using range sensor data. The range image is segmented into background/nonbackground pixels based on line-by-line processing. Non-background pixels are clustered together by a projectionbased technique to determine possible regions of interest. Following extraction of object regions of interest, we can merge the range and other sensor image data to obtain multi-sensor images of the regions in the field of view. Emphasis in this paper is given to the aforementioned tasks;however, for completeness, the remainder of the full processor is briefly described. The use of a hybrid optical/digital processor for such tasks is noted. © 1987 SPIE. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A geometry processor for image processing and pattern recognition

A geometry processor for image processing and pattern recogn...

引用

Architectures and Algorithms for Digital Image Processing III 1985

作者： Suk, Minsoo Pyo, Sam S. Department of Electrical and Computer Engineering Syracuse University SyracuseNY13244-1240 United States Center for Advanced Technology in Computer Applications and Software Engineering Syracuse University United States

A one-dimensional systolic geometry processor (SGP) which is useful in image processing and pattern recognition is described. The geometry processor can be used to enhance processing speed and throughput of the host computer by working as an attached processor. SGP algorithms for solving several primitive geometric problems such as convex hull, inclusion and intersection are shown. © 1986 SPIE. All rights reserved.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

SHIPBOARD MAIN BOILER AND FEED PUMP CONTROL-SYSTEM ONLINE ALIGNMENT VERIFICATION

引用

NAVAL ENGINEERS JOURNAL 1982年第6期94卷 39-46页

作者： BANHAM, JW ADAM, DJ James W. Banham:holds positions both as Director of the Machinery Automation Systems Department of the Naval Ship Systems Engineering Station and as Assistant Chairman of the Mechanical and Industrial Engineering Department of Drexel University's Evening College where he holds the rank of Adjunct Associate Professor. He is the author of a text on Numerical Methods Applications in Engineering. In addition to numerous technical papers he is also the author of the ISA film on Boiler Feedwater Control Systems. A registered professional engineer in the state of Pennsylvania Mr. Banham is co-author of a forthcoming handbook on preparing for the Professional Engineering Examination in mechanical engineering. Mr. Banham holds a bachelor of science degree in mechanical engineering from the Pennsylvania State University his graduate studies were taken at the University of Pennsylvania. He is currently a member of the American Society for Engineering Education and the Instrument Society of America. He served as a member of the ISA Education Committee from 1964 through 1973 and as a member of the ISA Power Plant Dynamics Committee since 1969. His service on the latter committee includes terms as Executive Secretary Vice-Chairman and Chairman. Among other honors Mr. Banham was the winner of the Naval Ship Engineering Center's first Technical Achievement Award (1963) Technical Publication Award (1974) and Equal Employment Opportunity Award (1978). He was also the recipient of Drexel University's Laura S. Campbell Award for Excellence in Teaching (1978). He has taught undergraduate courses in classical control theory numerical methods computer programming systems design and analysis and instrumentation. He also teaches systems theory and computer science in an EIT Review and heat transfer in a PE Review conducted by the Drexel University Department of Continuing Professional Education. Mr. David J. Adam:is a Project Engineer in the Naval Sea Systems Command (PMS301) Steam Propulsion Plant Improvement Program where he i

One of the most serious problems encountered in Naval steam plants following World War II was the unreliable performance of boiler and main feedpump pneumatic control systems. In addition to control component and system design deficiencies, these control systems suffered from inadequate methods to measure and adjust system alignment. This paper describes the development of a set of procedures for on-line alignment verification (OLV) of pneumatic main boiler and feedpump control systems. The procedures are designed for use by N avy control system technicians and, in addition to on-line alignment verification, provide guidance for troubleshooting and for performing system alignment. Procedure static checks measure steady state steaming performance and OLV procedure dynamic checks measure the ability of the boiler and control systems to respond to load changes. The paper describes typical control system characteristics that influence OLV procedure content and the supporting analysis that was used to establish alignment criteria ranges that satisfy both steady state and transient performance requirements. Also described is the alignment criteria tolerance analysis along with the steps involved in a typical OLV check procedure development. Descriptions of the various OLV checks, troubleshooting procedures and alignment procedures are provided. Typical shipboard implementation requirements are described and experience to date with the procedures is provided along with a status report on OLV procedure implementations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Recent Advances in Vision Transformer Robustness Against Adversarial Attacks in Traffic Sign Detection and Recognition: A Survey

引用

ACM Computing Surveys 1000年

作者： Oluwajuwon Fawole Danda Rawat DoD Center of Excellence in AI/ML and Department of Electrical Engineering & Computer Science Howard University Washington United States

The emergence of Vision Transformers (ViTs) has marked a significant advancement in machine learning, particularly in applications requiring robust visual recognition capabilities, such as traffic sign detection for autonomous driving systems. But, deploying these models in adversarial environments where robustness is critical remains a challenge. This survey provides a comprehensive review of the integration of ViTs in traffic sign detection and recognition, emphasizing their vulnerability to adversarial attacks and the methods developed to enhance their robustness. This paper also presents a compressive comparison of ViTs in a tabular form for side-by-side comparison.

关键词： Adversarial attack adversarial training vision transformers and traffic signs.

来源：评论

学校读者我要写书评

暂无评论

Cost-Efficient Deep Neural Network Placement in Edge Intelligence-Enabled Internet of Things

引用

ACM Transactions on Sensor Networks 1000年

作者： Hao Tian Xiaolong Xu Hongyue Wu Qingzhan Zhao Jianguo Dai Maqbool Khan State Key Laboratory for Novel Software Technology Nanjing University Nanjing Jiangsu China Nanjing China School of Software Nanjing University of Information Science and Technology Nanjing Jiangsu China Nanjing China College of Intelligence and Computing Tianjin University Tianjin China Tianjin China Geospatial Information Engineering Research Center College of Information Science and Technology Shihezi University Shihezi Xinjiang China Shihezi China Department of IT and Computer Science Pak-Austria Fachhochschule Institute of Applied Sciences and Technology Haripur Pakistan Haripur Pakistan

Edge intelligence (EI) integrates edge computing and artificial intelligence empowering service providers to deploy deep neural networks (DNNs) on edge servers in proximity to users to provision intelligent applications (e.g., autonomous driving) for ubiquitous Internet of Things (IoT) in smart cities, which facilitates the quality of experience (QoE) of users and improves the processing and energy efficiency. However, considering DNN is typically computational-intensive and resource-hungry, conventional placement approaches ignore the influence of multi-dimensional resource requirements (processor, memory, etc.), which may degrade the real-time performance. Moreover, with the increasing scale of geo-distributed edge servers, centralized decision-making is still challenging to find the optimal strategies effectively. To overcome these shortcomings, in this paper we propose a game theoretic DNN placement approach in EI-enabled IoT. First, a DNN placement optimization problem is formulated to maximize system benefits, which is proven to be \(\mathcal {N}\mathcal {P}\)-hard and model the original problem as an exact potential game (EPG). Moreover, an EPG-based DNN model placement algorithm, named EPOL, is designed for edge servers to make sub-optimal strategies independently and theoretical analysis is possessed to guarantee the performance of EPOL. Finally, real-world dataset based experimental results corroborate the superiority and effectiveness of EPOL.

关键词： Edge intelligence DNN placement Game theory Internet of Things

来源：评论

学校读者我要写书评

暂无评论

An Onboard UAV Multi-task System for Trajectory Prediction and State Estimation Employing Transformer- and Reservoir-based Networks

引用

ACM Journal on Autonomous Transportation Systems 1000年

作者： Nikolas Souli Panagiotis Katzanis Panayiotis Kardaras Yiannis Grigoriou Stavros Stavrinides Panayiotis Kolios Georgios Ellinas Electrical and Computer Engineering University of Cyprus Nicosia Cyprus International Hellenic University School of Science and Technology Thessaloniki Greece Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence Aglantzia Cyprus Physics Department Democritus University of Thrace Komotini Greece Computer Science University of Cyprus Nicosia Cyprus

With the increasing technological advancements and deployment of unmanned aerial vehicles (UAVs) in different applications (e.g., delivery services, surveillance, critical infrastructure monitoring, military operations, and search-and-rescue operations), a robust, lightweight, and accurate system for UAV state identification and trajectory prediction is becoming a mandate. This work introduces an onboard real-time multi-task learning framework that combines Transformer neural networks and reservoir computing (RC) architectures to enhance outdoor UAV operations. The proposed system employs the Transformer-based architecture to capture the temporal dependencies in sequential data for long-term horizons, while RC-based networks are utilized to ensure robust and real-time performance. Specifically, custom multi-task models are implemented and fine-tuned to collect multi-modal sensor measurements, aiming to enhance the two-fold objective of simultaneous UAV state identification and trajectory prediction through shared feature learning. A dataset comprised of measurements collected from real-world UAV operations (in 3D space) under various conditions is employed to train and evaluate the proposed system. Further, a prototype onboard UAV system is implemented and tested in real-world field experiments. Extensive evaluations of the experimental results demonstrate that the onboard framework achieves accuracy close to the ground truth in both state identification and trajectory prediction, consequently showcasing its potential for practical applications.

关键词： Machine learning multi-task learning trajectory prediction state identification UAV applications Transformers Reservoir Computing.

来源：评论

学校读者我要写书评

暂无评论

Genetic and Evolutionary Computing 1

引用

丛书名： Advances in Intelligent Systems and Computing

1000年

作者： Hui Sun Chin-Yu Yang Chun-Wei Lin Jeng-Shyang Pan Vaclav Snasel Ajith Abraham

来源：评论

学校读者我要写书评

暂无评论

Web 3.0-Enabled Microservice Re-Scheduling for Heterogenous Resources Co-Optimization in Metaverse-Integrated Edge Networks

引用

ACM Transactions on Autonomous and Adaptive Systems 1000年

作者： Yihong Yang Zhangbing Zhou Lei Shu Feng Zhou Walid Gaaloul Arif Ali Khan School of Information Engineering China University of Geosciences (Beijing) China School of Information Engineering Frontiers Science Center for Deep-time Digital Earth China University of Geosciences (Beijing) China Technology Innovation Center of Geoscience Knowledge and Intelligent Service China Geological Survey China and Computer Science Department TELECOM SudParis France College of Artificial Intelligence Nanjing Agricultural University China National Geological Library of China China Computer Science Department TELECOM SudParis France M3S Empirical Software Engineering Research Unit University of Oulu Finland

The Web 3.0 and metaverse can empower intelligent application of Connected Autonomous Vehicles (CAVs). The adoption of edge computing can contribute to the low latency interaction between CAVs and the metaverse. Microservices are widely deployed on edge networks and the cloud nowadays. User's requests from CAVs are typically fulfilled through the composition of microservices, which may be hosted by contiguous edge nodes. Requests may differ on their required resources at runtime. Consequently, when requests are continuously injected into edge networks, the usage of heterogenous resources, including CPU, memory, and network bandwidth, may not be the same, or differ significantly, on certain edge nodes. This happens especially when burst requests are injected into the network to be satisfied concurrently. Therefore, the usage of heterogenous resources provided by edge nodes should be co-optimized through re-scheduling microservices. To address this challenge, this paper proposes a Web 3.0-enabled Microservice Re-Scheduling approach (called MRS), which is a migration-based mechanism integrating a placement strategy. Specifically, we formulate the microservice re-scheduling task as a multi-objective and multi-constraint optimization problem, which can be solved through a penalty signal-integrated framework and an improved pointer network. Extensive experiments are conducted on two real-world datasets. Evaluation results show that our MRS performs better than the counterparts with improvements of at least 7.7%, 2.4% and 2.2% in terms of network throughput, latency and energy consumption.

关键词： Web 3.0 Microservice Re-Scheduling Heterogenous Resources Co-Optimization Metaverse Connected Autonomous Vehicles (CAVs)

来源：评论

学校读者我要写书评

暂无评论

Transactions on Pattern Languages of Programming III 1

引用

丛书名： Lecture Notes in computer Science

1000年

作者： James Noble Ralph Johnson Uwe Zdun Eugene Wallingford

ISBN: (数字)9783642386763

ISBN: (纸本)9783642386756

The Transactions on Pattern Languages of Programming subline aims to publish papers on patterns and pattern languages as applied to software design, development, and use, throughout all phases of the software life cycle, from requirements and design to implementation, maintenance and evolution. The primary focus of this LNCS Transactions subline is on patterns, pattern collections, and pattern languages themselves. The journal also includes reviews, survey articles, criticisms of patterns and pattern languages, as well as other research on patterns and pattern languages. This book, the third volume in the Transactions on Pattern Languages of Programming series, presents five papers that have been through a careful peer review process involving both pattern experts and domain experts. The papers present various pattern languages and a study of applying patterns and represent some of the best work that has been carried out in design patterns and pattern languages of programming over the last few years.

关键词： software engineering Programming Languages, Compilers, Interpreters Programming Techniques Management of Computing and Information Systems

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：