检索结果-内蒙古大学图书馆

7th IET Smart Cities Symposium, SCS 2023

作者： Aljanabi, Mohammad Omran, Alaa Hamza Mijwil, Maad M. Abotaleb, Mostafa El-Kenawy, El-Sayed M. Mohammed, Sahar Yousif Ibrahim, Abdelhameed Department of computer College of Education Aliarqai university Baghdad Iraq University of information technology and communications Baghdad Iraq Computer Techniques Engineering Department Baghdad College of Economic Sciences University Baghdad Iraq Department of System Programming South Ural State University Chelyabinsk Russia Department of Communications and Electronics Delta Higher Institute of Engineering and Technology Egypt Computer Science Department Computer Science &Information Technology College Anbar University Anbar Iraq Computer Engineering and Control Systems Department Faculty of Engineering Mansoura University Mansoura Egypt

ISBN: (纸本)9781839539831

Data poisoning attacks, where adversaries manipulate training data to degrade model performance, are an emerging threat as machine learning becomes widely deployed in sensitive applications. This paper provides a comprehensive overview of data poisoning including attack techniques, adversary incentives, impacts on security and reliability, detection methods, defenses, and key research gaps. We examine label flipping, instance injection, backdoors, and other attack categories that enable malicious outcomes ranging from IP theft to accidents in autonomous systems. Promising detection approaches include statistical tests, robust learning, and forensics. However, significant challenges remain in translating academic defenses like adversarial training and sanitization into practical tools ready for operational use. With safety and trustworthiness at stake, more research on benchmarking evaluations, adaptive attacks, fundamental tradeoffs, and real-world deployment of defenses is urgently needed. Understanding vulnerabilities and developing resilient machine learning pipelines will only grow in importance as data integrity is fundamental to developing safe artificial intelligence. © The Institution of engineering & Technology 2023.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Self-management in a control architecture for parallel kinematic robots

Self-management in a control architecture for parallel kinem...

引用

2008 ASME International Design engineering Technical Conferences and computers and Information in engineering Conference, DETC 2008

作者： Maaß, Jochen Steiner, Jens Amado, Ana Michaela, Huhn Raatz, Annika Hesselbach, Jurgen Institute for Machine Tools and Production Technology Department of Mechanical Engineering TU Braunschweig 38106 Braunschweig Germany Institute for Programming and Reactive Systems Department of Computer Science TU Braunschweig 38106 Braunschweig Germany

ISBN: (纸本)9780791843253

Maintainability, extendibility and reusability of components in the design of robot control architectures is a major challenge. Parallel kinematic robots feature a wide variety of structures and applications. They are subject to easy reconfiguration because of the passive structure limbs. This class of robots requires more extensive calculations in their control laws than serial manipulators. During complex motion tasks, such as the ones required in assembly sequences, the algorithmic load may also vary over time. However, no generic control approach exists in order to reduce the complexity of control design for these kind of robots. In this paper the authors introduce an architecture for handling and assembly applications featuring self-management techniques as an approach to tackle these problems. The existing architecture features a modular and layered design. Concepts of self-management and self-optimization applied to this architecture are outlined. These properties are realized by the integration of self-managers within crucial system components. The mechanisms are extended for a future distributed version of the architecture. Real-time properties are guaranteed by an online formal analysis that verifies planned adaptations before realizing them. Copyright © 2008 by ASME.

关键词： Reusability

来源：评论

学校读者我要写书评

暂无评论

Wireless sensor network-based communication for cooperative simultaneous localization and mapping

Wireless sensor network-based communication for cooperative ...

引用

作者： Tuna, Gurkan Gungor, Vehbi Caʇri Potirakis, Stelios M. Zeadally, Sherali Department of Computer Programming Trakya University Edirne Turkey Department of Computer Engineering Bahçeşehir University Besiktas Istanbul34353 Turkey Department of Computer Engineering Abdullah Gül University Kayseri38039 Turkey Department of Electronics Engineering Technological Education Institute of Piraeus Aigaleo Greece Akademi Ar-GeYazilim Ve Muhendislik Erciyes Teknopark A.Ş. Kayseri38039 Turkey

This paper presents a novel approach of using a Wireless Sensor Network (WSN) as the communication means for Multi-Robot, Cooperative, Simultaneous Localization and Mapping (CSLAM) applications investigating the associated design challenges and suggesting corresponding solutions. Although the proposed approach brings several benefits including an increased coverage and communication range, self-organization capabilities, quick deployment, and flexible architecture, the realization is interrelated with performance in terms of energy efficiency and reliability. In this respect, the applicability of the WSNs for the presented approach is investigated. Centralized and distributed map merging methods in WSN-based CSLAM are evaluated in detail and the impacts of packet delays and losses on the performance of CSLAM algorithms are shown. Additionally, the involved network congestion and contention dynamics are presented, while the effects of observation range, speed, time intervals between observations, and odometry readings on the SLAM accuracy are shown based on an extensive set of simulation studies. © 2014 Elsevier Ltd. All rights reserved.

关键词： Wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

Multi-campus collaborations among undergraduate design teams: Opportunities and challenges

Multi-campus collaborations among undergraduate design teams...

引用

113th Annual ASEE Conference and Exposition, 2006

作者： Zoltowski, Carla Oakes, William Myers, Barrett Purdue University United States EPICS Program Purdue University United States ASEE Department of Engineering Education Purdue University United States EPICS Program Computer Programming Technology

There are many benefits to participating in multi-campus collaborations among project-based design teams. First, students gain experience in working in a distributed design environment, which is becoming more commonplace in engineering practice. Second, collaborations offer the ability to share complementary expertise and allow student design teams to participate in projects that they would not normally be able to undertake alone. Third, collaboration among teams of multiple campuses allows for sharing of prior work and the opportunity to build upon the work to have a more significant impact. There are, however, challenges to participating in multi-campus collaborations. It is difficult for student teams to partition projects such that they can be done somewhat independently. Communication issues can be complicated by distance and the lack of face-to-face contact on a regular basis. The EPICS - engineering Projects in Community Service - program engages undergraduate student design teams on long-term projects that solve technology-based problems for local community service organizations. There are sixteen universities with active EPICS programs in the 2005-2006 academic year. While the programs have some variation as EPICS has been integrated into each individual campus, they share basic characteristics. The existence of EPICS programs on multiple campuses has created the opportunity to collaborate across institutions. This paper will describe three models for multi-campus collaboration that have been used in EPICS. © American Society for engineering Education, 2006.

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

Deriving adaptive homing sequences for weakly initialized nondeterministic FSMs

Deriving adaptive homing sequences for weakly initialized no...

引用

2019 IEEE East-West Design and Test Symposium, EWDTS 2019

作者： Vinarskii, Evgenii Tvardovskii, Aleksandr Evtushenko, Larisa Yevtushenko, Nina Computer Science Department Lomonosov Moscow State University Moscow Russia Radiophysical Department Tomsk State University Tomsk Russia Software Engineering Deparment Ivannikov Institute for System Programming Moscow Russia

ISBN: (纸本)9781728110035

State identification sequences, such as homing and distinguishing sequences (HS and DS), are widely used in FSM (Finite State Machine) based testing in order to reduce the size of a returned complete test suite as well as minimize checking efforts in passive testing. Preset HS are known to always exist for deterministic complete reduced FSMs but it is not the case for nondeterministic FSMs. It is also known that in this case, adaptive HS exist more often and usually are shorter than the preset. Nowadays, a number of specifications are represented by nondeterministic FSMs and thus, a deeper study of such sequences is required. There exist sufficient and necessary conditions for the existence of an adaptive HS for complete nondeterministic FSMs when each state can be an initial state but those conditions become only sufficient for weakly initialized FSMs where only some states are initial. In this paper, we propose sufficient and necessary conditions for a weakly initialized FSM to have an adaptive homing sequence, possibly up to given length, which are based on deriving an appropriate so-called homing FSM. The experimental evaluation of the existence of adaptive and preset HS is performed for randomly generated FSMs. © 2019 IEEE.

关键词： Well testing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Cardiotocogram Data for Fetal Distress Determination by Decision Tree Based Adaptive Boosting Approach

引用

Journal of computer and Communications 2014年第9期2卷 32-37页

作者： Esra Mahsereci Karabulut Turgay Ibrikci Computer Programming Department Gaziantep University Gaziantep Turkey Department of Electrical and Electronics Engineering Cukurova University Adana Turkey

Cardiotocography is one of the most widely used technique for recording changes in fetal heart rate (FHR) and uterine contractions. Assessing cardiotocography is crucial in that it leads to iden- tifying fetuses which suffer from lack of oxygen, i.e. hypoxia. This situation is defined as fetal dis- tress and requires fetal intervention in order to prevent fetus death or other neurological disease caused by hypoxia. In this study a computer-based approach for analyzing cardiotocogram in- cluding diagnostic features for discriminating a pathologic fetus. In order to achieve this aim adaptive boosting ensemble of decision trees and various other machine learning algorithms are employed.

关键词： Cardiotocogram Fetal Distress Adaptive Boosting Decision Tree

来源：评论

学校读者我要写书评

暂无评论

Modeling of DC Traction Motor In Ansys RMXPRT 4

Modeling of DC Traction Motor In Ansys RMXPRT

引用

4th IEEE KhPI Week on Advanced Technology, KhPI Week 2023

作者： Herasymenko, Vitalii Zakovorotnyi, Oleksandr Pliuhin, Vladyslav Mezentsev, Mykola Noskov, Valentyn Orlova, Tetyana Department of Electric Transport O. M. Beketov National University of Urban Economy in Kharkiv Kharkiv Ukraine Department of Computer Engineering and Programming National Technical University «Kharkiv Polytechnic Institute» Kharkiv Ukraine Department of the Systems of Electricity Supply and Electricity Consumption of Cities O. M. Beketov National University of Urban Economy in Kharkiv Kharkiv Ukraine Computer Engineering and Programming Department National Technical University "Kharkiv Polytechnic Institute" Kharkiv Ukraine

ISBN: (纸本)9798350395532

DC traction motors are widely used in all branches of urban economy. They began to be used in industry about a hundred years ago with the advent of the first calculation methods. When designing a DC motor, it is important to consider it comprehensively, together with the electric drive system. The article discusses the application of a more correct approach to modeling a series-excited DC motor using the ANSYS software package, in particular, the ANSYS RMxprt/Maxwell/Simplorer bundle. The main stages of initial data input are considered and the main calculation results are shown. Using ANSYS Maxwell allows you to quickly and automatically build a typical machine geometry using RMxprt. When solving non-standard structures, it is possible to use 3D design with step-by-step elements. The analysis of the obtained graphic dependences of electric power parameters makes it possible to judge the efficiency of the electric motor and its operational properties in idling and under load. The simulation results show excellent agreement with the data obtained experimentally. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Analyzing the impact of machine learning and artificial intelligence and its effect on management of lung cancer detection in covid-19 pandemic

引用

Materials Today: Proceedings 2022年 56卷 2213-2216页

作者： Boddu, Raja Sarath Kumar Karmakar, Partha Bhaumik, Ankan Nassa, Vinay Kumar Vandana Bhattacharya, Sumanta Department of CSE Lenora College of Engineering Andhra Pradesh Rampachodavaram India Government of West Bengal Bikash Bhawan Salt Lake W.B. Kolkata India Dept. of Applied Mathematics With Oceanology and Computer Programming Vidyasagar University Midnapore India Department of Computer Science Engineering South Point Group of Institutions Sonepat Haryana India Department of Mathematics Dasmesh Khalsa College Zirakpur India Department of Science and Technology and Biotechnology MAKAUT India

Cancer victims, particularly those with lung cancer, are more susceptible and at higher danger of COVID-19 and associated consequences as a result of their compromised immune systems, which makes them particularly sensitive. Because of a variety of circumstances, cancer patients' diagnosis, treatment, and aftercare are very complicated and time-consuming during an epidemic. In such circumstances, advances in artificial intelligence (AI) and machine learning algorithms (ML) offer the capacity to boost cancer sufferer diagnosis, therapy, and care via the use of cutting technologies. For example, using clinical and imaging data combined with machine learning methods, the researchers may be able to distinguish among lung alterations induced by corona virus and those produced by immunotherapy and radiation. During this epidemic, artificial intelligence (AI) may be utilized to guarantee that the appropriate individuals are recruited in cancer clinical trials more quickly and effectively than in the past, which was done in a conventional and complicated manner. In order to better care for cancer patients and find novel and more effective therapies, It is critical that we move beyond traditional research methods and use artificial intelligence (AI) and machine learning to update our research (ML). Artificial intelligence (AI) and machine learning (ML) are being utilised to help with several aspects of the COVID-19 epidemic, such as epidemiology, molecular research and medication development, medical diagnosis and treatment, and socioeconomics. The use of artificial intelligence (AI) and machine learning (ML) in the diagnosis and treatment of COVID-19 patients is also being investigated. The combination of artificial intelligence and machine learning in COVID-19 may help to identify positive patients more quickly. In order to understand the dynamics of an epidemic that is relevant to artificial intelligence, when used in different patient groups, AI-based algorithms can quic

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Synchronous composition of quasi-complete and quasi-deterministic FSMs

Synchronous composition of quasi-complete and quasi-determin...

引用

International Conference on Actual Problems of Systems and Software engineering

作者： Igor Burdonov Alexandr Kossachev Nina Yevtushenko Tiziano Villa Software Engineering department Ivannikov Institute for System Programming of RAS Software engineering deparment Ivannikov Institute for System Programming Computer Science Department University of Verona

ISBN: (纸本)9781728160627

In this paper, we consider the synchronous composition of Finite State Machines (FSMs) that corresponds to instantaneous communication of hardware components. Such FSMs can be deterministic or nondeterministic, partial or complete. We first extend the existing synchronous composition operator from a pair of components to a collection of components with multiple input and output ports, and provide a procedure to compute the composition working directly on the collection of transition tables of the component FSMs. Then, based on the notion of input-output Moore pair (the output is not sensitive to the input), we prove the following sufficient condition: if the composition has the property that every cycle of ports has a component with a Moore pair, then the class of quasi-complete and quasi-deterministic FSMs is closed under the proposed synchronous composition.

关键词： Finite state machine (FSM) Quasi-deterministic FSM Quasi-complete FSM Moore pair Synchronous composition Pairing multi-input output ports harbors finite state machines deterministic

来源：评论

学校读者我要写书评

暂无评论

Features of the distribution of computing resources in cloud systems 3

Features of the distribution of computing resources in cloud...

引用

3rd IEEE KhPI Week on Advanced Technology, KhPI Week 2022

作者： Petrovska, Inna Kuchuk, Heorhii Mozhaiev, Mykhailo National Technical University 'Kharkiv Polytechnic Institute' Department of Computer Engineering and Programming Kharkiv Ukraine Computer Technology and Telecommunications Researches Sector National Scientific Center «hon. Prof Bokarius Forensic Science Institute» Kharkiv Ukraine

ISBN: (数字)9798350399202

ISBN: (纸本)9798350399202

The report considers the peculiarities of the distribution of computing resources in cloud systems. The most used classification of existing technologies of cloud services is considered. The advantages and disadvantages of such technologies are analyzed. The characteristic features of cloud computing that will need to be taken into account when allocating resources have been identified. IAAS technology has been shown to be most vulnerable to suboptimal resource allocation or reallocation. An expanded set of indicators for IAAS technology has been identified, including time-varying ones that need to be considered in resource allocation. Solving this problem will increase the efficiency of the use of cloud computing resources in general, increase application productivity and reduce the cost of infrastructure and its maintenance. © 2022 IEEE.

关键词： Resource allocation

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：