检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhaohua Chen Rui Ai Mingwei Yang Yuqi Pan Chang Wang Xiaotie Deng School of Computer Science Peking University Haidian Beijing China IDSS & LIDS Massachusetts Institute of Technology Cambridge MA Dept. of Management Science and Engineering Stanford University Stanford CA School of Engineering and Applied Sciences Harvard University Cambridge MA Dept. of Computer Science Northwestern University Evanston IL School of Computer Science Institute for Artificial Intelligence Peking University Haidian Beijing China

ISBN: (纸本)9798331314385

We study the framework of a dynamic decision-making scenario with resource constraints. In this framework, an agent, whose target is to maximize the total reward under the initial inventory, selects an action in each round upon observing a random request, leading to a reward and resource consumptions that are further associated with an unknown random external factor. While previous research has already established an Õ(√T) worst-case regret for this problem, this work offers two results that go beyond the worst-case perspective: one for the worst-case gap between benchmarks and another for logarithmic regret rates. We first show that an Ω(√T) distance between the commonly used fluid benchmark and the online optimum is unavoidable when the former has a degenerate optimal solution. On the algorithmic side, we merge the re-solving heuristic with distribution estimation skills and propose an algorithm that achieves an Õ(1) regret as long as the fluid LP has a unique and non-degenerate solution. Furthermore, we prove that our algorithm maintains a near-optimal Õ(√T) regret even in the worst cases and extend these results to the setting where the request and external factor are continuous. Regarding information structure, our regret results are obtained under two feedback models, respectively, where the algorithm accesses the external factor at the end of each round and at the end of a round only when a non-null action is executed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A New Robust Hybrid Active Noise control System

A New Robust Hybrid Active Noise Control System

引用

IEEE International Conference on Signal and Image Processing (ICSIP)

作者： Z. Wang Y. Xiao Y. Ma L. Ma K. Khorasani Dept. of Management & Information Systems Prefectural University of Hiroshima Hiroshima Japan Institute of Automation Jiangnan University Wuxi China Dept. of Electrical & Computer Engineering Concordia University Montreal Canada

The conventional hybrid active noise control (ANC, HANC) may significantly degrade if the reference signal for the feedforward ANC (FFANC) subcontroller consists of not only a broadband component but also a low-frequency sinusoidal component that is uncorrelated or partially correlated with the narrowband noise component that is attenuated by the feedback ANC (FBANC) subcontroller. In this paper, a new robust HANC system is proposed to mitigate the performance degradation resulting from the low-frequency sinusoidal component. A band-pass filter bank (BPFB) is applied to the FFANC reference signal to separate the low-frequency sinusoidal component from the broadband one and each of them is fed to an FFANC subcontroller that solely focuses on a single noise component. A supporting filter takes the extracted broadband component and the residual error as its input and desired signal, respectively. The same BPFB is then applied to the supporting filter error in order to separate the remaining low-frequency sinusoidal component from the narrowband component that persists in the residual error. The use of the two BPFBs and the supporting filter allows the three HANC subcontrollers to operate practically independently, each taking care of one of the pre-processed noise components which are uncorrelated with each other irrespective of the relationship between the two original noise sources. Extensive simulations are provided to demonstrate the improved effectiveness and robust capability of the proposed HANC as compared to its counterpart, even in a case that the low-frequency sinusoidal component in the FFANC reference signal is partially corrected with the primary narrowband noise component that is targeted by the FBANC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Review on Architectures of Convolutional Neural Network

Review on Architectures of Convolutional Neural Network

引用

Disruptive Technologies (ICDT), International Conference on

作者： Sachin Chawla Deepa Gupta Sanjeev Kumar Pippal Dept. Amity School of Engineering and Technology Amity University Greater Noida UP India Dept. Amity Institute of Information Technology Amity University Noida UP India Dept. Computer Science-Artificial Intelligence G.L Bajaj Institute of Technology and Management Greater Noida UP India

ISBN: (数字)9798331519582

ISBN: (纸本)9798331519599

This review provides a broad overview of CNN architectures, focusing on the crucial building blocks and layered structures that form complete networks. It traces the evolution of CNNs, summarizing key publications and highlighting the diverse array of architectures that have emerged in recent years. While simplifying some technical details, the review maintains conceptual rigor to ensure a thorough understanding of CNN principles and development. This review serves as a valuable resource for those seeking to navigate the complexities of CNNs, offering insights into their operational principles, architectural innovations, and potential applications beyond the realm of computer Vision.

关键词： Training Technological innovation computer vision Reviews Architecture Buildings computer architecture Self-supervised learning Time measurement Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Holistic and State of the Art of Understanding the Linkages of Smart-City Healthcare Technologies 3

A Holistic and State of the Art of Understanding the Linkage...

引用

3rd International Conference on Smart Electronics and Communication, ICOSEC 2022

作者： Ogunmola, Gabriel Ayodeji Lourens, Melanie Elizabeth Chaudhary, Ayushi Tripathi, Vikas Effendy, Femmy Sharma, Dilip Kumar Sharda University Faculty of Management India Durban University of Technology Department of Human Resources Management South Africa Iimt University School of Computer Science and Applications Meerut India Graphic Era Deemed to Be University Dept. of Computer Science & Engineering Uttarakhand India Universitas Pendidikan Indonesia Jaypee University of Engineering and Technology Department of Mathematics M.P Guna India

ISBN: (数字)9781665497640

ISBN: (纸本)9781665497640

One can expect a day to come where internet would connect people from across the globe whenever required and become a mainstay for business function. But the realization of this would need a lot of time. Internet of Things is still in a primary stage and development has a long way to go. Wide range applications for IoT require infrastructure, application architecture, security measures and a standard system is yet to be established. By introducing IoT, several challenges, constraints, security concerns have to be addressed differently unlike the currently existing data systems. The current systems use make use of easy to implement standards and these are compatible for most of the devices used in communications and storage systems. But no such standard exists for devices using IoT owing to the various constraints arising between different devices that results in different classifications within IoT itself. It also discusses the requirement of security architectures for IoT and feasible mechanisms that can be implemented for various architecture layers of IoT for e-Health applications. The challenges faced in order to integrate IoT into health care applications are also discussed alongside the standards and security mechanisms. IoT can be considered as a key to providing improved medical facilities for patients whilst facilitating doctors, staff and hospitals. Most importantly, this work presents the ways to handle security for implementing IoT in healthcare sector not only in the currently existing systems but also for future applications. The current systems that use various domains and different technologies have been studied and analyzed to present a clear and precise solutions to challenges faced by IoT implementations as of *** electronic document is a 'live' template and already defines the components of you © 2022 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

I Can Read Your Mind: control Mechanism Secrecy of Networked Dynamical Systems under Inference Attacks

arXiv

引用

arXiv 2022年

作者： He, Jianping Li, Yushan Cai, Lin Guan, Xinping The Dept. of Automation Shanghai Jiao Tong University Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai Engineering Research Center of Intelligent Control and Management Shanghai China The Dept. of Electrical and Computer Engineering University of Victoria BC Canada

Recent years have witnessed the fast advance of security research for networked dynamical system (NDS). Considering the latest inference attacks that enable stealthy and precise attacks into NDSs with observation-based learning, this article focuses on a new security aspect, i.e., how to protect control mechanism secrets from inference attacks, including state information, interaction structure and control laws. We call this security property as control mechanism secrecy, which provides protection of the vulnerabilities in the control process and fills the defense gap that traditional cyber security cannot handle. Since the knowledge of control mechanism defines the capabilities to implement attacks, ensuring control mechanism secrecy needs to go beyond the conventional data privacy to cover both transmissible data and intrinsic models in NDSs. The prime goal of this article is to summarize recent results of both inference attacks on control mechanism secrets and countermeasures. We first introduce the basic inference attack methods on the state and structure of NDSs, respectively, along with their inference performance bounds. Then, the corresponding countermeasures and performance metrics are given to illustrate how to preserve the control mechanism secrecy. Necessary conditions are derived to guide the secrecy design. Finally, thorough discussions on the control laws and open issues are presented, beckoning future investigation on reliable countermeasure design and tradeoffs between the secrecy and control performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Python-Based Optical Character Recognition (OCR)

Python-Based Optical Character Recognition (OCR)

引用

Interdisciplinary Approaches in Technology and management for Social Innovation (IATMSI), IEEE Conference on

作者： Priyanka Kaushik Priyanka Rawat Devyansh Batra P. Vensheeba Delin Saurabh Pratap Singh Rathore S. Kaliappan Dept. of CSE (AIML) CSE-APEX Chandigarh University Chandigarh India Dept. of Computer Science and Engineering Chandigarh University Chandigarh India Dept. of Civil Eng. Dhanalakshmi Srinivasan College of Eng. Coimbatore India Dept. of Management & Research ICAPSR New Delhi India Division of Research and Development Lovely Professional University Punjab India

ISBN: (数字)9798331521691

ISBN: (纸本)9798331521707

Optical Character Acknowledgment (OCR) stands as a transformative innovation at the crossing point of computer vision and machine learning, encouraging the extraction of printed data from pictures or checked archives. Within the period of advanced change, OCR serves as a foundation for different applications, such as archive digitization, content mining, and cleverly data recovery. The first thing that pops into one’s mind in building vigorous and versatile OCR frameworks for different scenarios is the choice of a successful programming dialect. The Python programming dialect is discussed here, which is renowned for its simplicity, vast libraries, and dynamic community, as an impressive tool to execute OCR arrangements.

关键词： Technological innovation Image processing Optical character recognition Pipelines Programming Libraries Data mining Reliability Python Testing

来源：评论

学校读者我要写书评

暂无评论

Automated Healthcare Medical Imaging through EOA Optimized Hyperparameter in CNN

Automated Healthcare Medical Imaging through EOA Optimized H...

引用

6th International Conference on Futuristic Trends in Networks and Computing Technologies, FTNCT 2024

作者： Agrawal, Umang Kumar Panda, Nibedan Das, Debashreet Dalai, Asish Kumar Ramana, B.V. Mishra, Ayush School of Computer Engineering KIIT Deemed to Be University Odisha Bhubaneswar751024 India Dept. of Computer Science and Engineering Centre for UG and PG Studies BPUT Odisha Rourkela India School of Computer Science and Engineering VIT-AP University AP Amaravati India Department of IT Aditya Institute of Technology and Management AP Tekkali532201 India

Medical imaging (MI) is the prefatory field of healthcare that plays a vital role in the patient's clinical and medical intervention. Recent developments in MI help healthcare professionals such as doctors and radiologists diagnose patients with improved quality of MI methods such as X-ray, CT and MRI scans. The upsurge of the Convolutional Neural Network (CNN) offers the latent for timely detection and classification of the disease with deeper insights. It adapts the spatial features and learns the input data hierarchically, which makes well-suited for this task. To improve the robustness of the CNN, the parameters are optimized through a nature-inspired dynamic mass balance-based metaheuristic approach named the Equilibrium Optimizer Algorithm (EOA). As a real-life implication, the suggested EOA-CNN approach has been verified by utilizing two benchmark datasets. The competence of EOA-CNN is assessed by present-day methods in terms of parameters namely accuracy, error rate, min, avg, std, accuracy, sensitivity and specificity. By streamlining the workflow, the said approach is a valuable asset conforming to the reliability to resolve healthcare imaging complications with advanced diagnostics support. This framework is being used to optimize the constraints meanwhile bridging the gaps in healthcare convenience. © 2025 The Author(s). Published by Elsevier B.V.

关键词： Functional neuroimaging

来源：评论

学校读者我要写书评

暂无评论

Real-Time Local Map Generation and Collision-Free Trajectory Planning for Autonomous Vehicles in Dynamic Environments

Real-Time Local Map Generation and Collision-Free Trajectory...

引用

International Conference on control, Artificial Intelligence, Robotics & Optimization (ICCAIRO)

作者： Aristeidis Geladaris Lampis Papakostas Athanasios Mastrogeorgiou Michael Sfakiotakis Panagiotis Polygerinos TWI-Hellas Athens Greece Mechanical Engineering Dept. Control Systems and Robotics Lab (CSRL) School of Engineering Hellenic Mediterranean University Heraklion Crete Greece Control Systems Lab (CSL) School of Mechanical Engineering National Technical University of Athens Greece Electrical and Computer Engineering Dept. Control Systems and Robotics Lab (CSRL) School of Engineering Hellenic Mediterranean University Heraklion Crete Greece

In this paper we propose a method for autonomous navigation in GPS-denied environments that can be deployed in all types of robotic vehicles requiring only a single RGB-D camera. Our algorithm is an integration of localization, mapping and trajectory planning software modules that can handle dynamic environments. dept. measurements and visual odometry are used to (a) create a robocentric Euclidean Signed Distance Fields (ESDF) map in real-time, (b) estimate the position of obstacles surrounding the robot, and (c) calculate the distance and gradient from them. Subsequently, we use an optimization algorithm to plan a collision-free trajectory. We show that a local map can be created faster than with the fixed-size array method used in current optimization methods. Our approach also allows for effective detection of dynamic obstacles by constantly updating the map. As a result, the robot deviates from its initial path only when necessary. We validate our results in simulation by deploying our algorithm in a skid steering rover and a hexacopter in an environment with static and dynamic obstacles.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Wireless Network Distribution (5G/LTE)

Deep Learning for Wireless Network Distribution (5G/LTE)

引用

Communications, Information, Electronic and Energy Systems (CIEES), International Conference on

作者： Mohammed Khodayer Hassan Al-Dulaimi Omer Mohammed Khodayer Al-Dulaimi Aymen Mohammed Khodayer Al-Dulaimi Maiduc Osiceanu Alexandra Nidal Jihad Dept. Computer Engineering Al-Rafidain University of college Baghdad Iraq Dept. of Telecommunication Engineering University Politehnica of Bucharest Bucharest Romania Dept. of Technical Communication Engineering Al- Farahidi University College Baghdad Iraq Dept. of Director for management of scientific research University Politehnica of Bucharest Bucharest Romania Dept. of Iraqi prime ministers’ council Baghdad Iraq

As a result of using machine learning and deep learning in the network, we were able to more efficiently manage the allocation of network resources and the availability of the network overall. Key performance indicators are used to analyze incoming traffic and make predictions to allocate network resources to unknown devices. High load balancing and efficient use of available resources on current network portions are made possible with intelligent resource allocation. The underlying model is smart enough to determine which piece of the network is most suited for the challenge at present. 5G mobile networks, mobile communications, and the latency of modern and future wireless networks are affected by strict regulations about how long it takes for data transmission to reach its destination, dependability, how much data can be transmitted without a problem, capacity, how much data can be transmitted securely, and speed of user connection. Mobile providers are always looking for new ways to make it possible for multiple, autonomous users to share a single network. Slicing is a method that uses network fragmentation to share the same physical infrastructure among multiple networks that have competing needs. Future communication networks will need to make decisions based on data in order to keep up with the exponential rise in traffic.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperation and mental states neurophysiological assessment for pilots’ training and expertise evaluation

Cooperation and mental states neurophysiological assessment ...

引用

Technologies for Defense and Security (TechDefense), IEEE International Workshop on

作者： Gianluca Borghini Andrea Giorgi Vincenzo Ronca Lorenzo Mezzadri Rossella Capotorto Pietro Aricò Gianluca Di Flumeri Fabio Babiloni Dept. of Molecular Medicine Sapienza University of Rome Rome Italy Dept. of Anatomical Histological Forensic and Orthopaedic Sciences Sapienza University of Rome Rome Italy Dept. of Computer Control and Management Engineering Antonio Ruberti Sapienza University of Rome Rome Italy Flight Training School Urbe Aero ATO Rome Italy

The aim of the study was to validate a methodology for professional pilots’ neurophysiological assessment to improve training program tailoring and management. In particular, the assessment focused on quantifying (i) mental workload, (ii) stress level (iii) and the cooperation degree between the two members of the crews. Two groups of pilots were involved in the experiments: Experienced and Unexperienced. Additionally, the Instructor was responsible to provide subjective evaluation about the pilots’ mental states and cooperation. During the entire flight simulations, the pilots’ brain activity was acquired through the Electroencephalography (EEG). The results demonstrated that it is possible to quantify operators’ mental states and degree of cooperation while dealing with flight simulations under realistic settings. Pilots’ mental workload and stress behavioral levels resulted to be positively and significantly correlated with the corresponding neurophysiological measurements (all R > 0.6, all p < 0.05), while cooperation was observed to be higher (p < 0.05) for the Experienced than the Unexperienced. Although the results are preliminary, they show how the capability of quantifying pilots’ mental states and cooperation while dealing with tasks will provide the instructors with additional and objective information. In particular, this information would allow for tailoring the training sessions based on crew’s behavior.

关键词：

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：