检索结果-内蒙古大学图书馆

Research on Deep Learning Model of Feature Extraction Based on Convolutional Neural Network

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Liu, Houze Li, Iris Liang, Yaxin Sun, Dan Yang, Yining Yang, Haowei New York University Department Computer Science and Engineering New York United States New York University Graduate School of Art & Science New York United States University of Southern California Viterbi School of Engineering Los Angeles United States Washington University Department of Electrical and Systems Engineering St. Louis United States Carnegie Mellon University School of Computer Science Pittsburgh United States University of Houston Cullen College Of Engineering Houston United States

Neural networks with relatively shallow layers and simple structures may have limited ability in accurately identifying pneumonia. In addition, deep neural networks also have a large demand for computing resources, which may cause convolutional neural networks to be unable to be implemented on terminals. Therefore, this paper will carry out the optimal classification of convolutional neural networks. Firstly, according to the characteristics of pneumonia images, AlexNet and InceptionV3 were selected to obtain better image recognition results. Combining the features of medical images, the forward neural network with deeper and more complex structure is learned. Finally, knowledge extraction technology is used to extract the obtained data into the AlexNet model to achieve the purpose of improving computing efficiency and reducing computing costs. The results showed that the prediction accuracy, specificity, and sensitivity of the trained AlexNet model increased by 4.25 percentage points, 7.85 percentage points, and 2.32 percentage points respectively. The graphics processing usage has decreased by 51% compared to the InceptionV3 mode. Copyright © 2024, The Authors. All rights reserved.

关键词： Image classification

Distributed Controller Design for Discrete-Time systems Via the Integration of Extended LMI and Clique-Wise Decomposition

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Fushimi, Sotaro Watanabe, Yuto Sakurama, Kazunori Department of Systems Science Graduate School of Informatics Kyoto University Yoshida-Honmachi Sakyo-ku Kyoto606-8501 Japan Department of Electrical and Computer Engineering University of California San Diego San DiegoCA92093 United States Department of System Innovation Graduate School of Engineering Science Osaka University 1-3 Machikaneyama Toyonaka Osaka560-8531 Japan

This study addresses a distributed controller design problem for discrete-time systems using linear matrix inequalities (LMIs). Sparsity constraints on control gains of distributed controllers result in conservatism via the convexification of the existing methods such as the extended LMI method. In order to mitigate the conservatism, we introduce a novel LMI formulation for this problem, utilizing the clique-wise decomposition method from our previous work on continuous-time systems. By reformulating the sparsity constraint on the gain matrix within cliques, this method achieves a broader solution set. Also, the analytical superiority of our method is confirmed through numerical examples. Copyright © 2024, The Authors. All rights reserved.

关键词： Continuous time systems

Risk-Sensitive Inhibitory Control for Safe Reinforcement Learning

学校读者我要写书评

暂无评论

Risk-Sensitive Inhibitory Control for Safe Reinforcement Lea...

IEEE Conference on Decision and Control

作者： Armin Lederer Erfaun Noorani John S. Baras Sandra Hirche Chair of Information-oriented Control (ITR) School of Computation Information and Technology Technical University of Munich Munich Germany Department of Electrical and Computer Engineering Institute for Systems Research (ISR) at the University of Maryland College Park MD USA

Humans have the ability to deviate from their natural behavior when necessary, which is a cognitive process called response inhibition. Similar approaches have independently received increasing attention in recent years for ensuring the safety of control. Realized using control barrier functions or predictive safety filters, these approaches can effectively ensure the satisfaction of state constraints through an online adaptation of nominal control laws, e.g., obtained through reinforcement learning. While the focus of these realizations of inhibitory control has been on risk-neutral formulations, human studies have shown a tight link between response inhibition and risk attitude. Inspired by this insight, we propose a flexible, risk-sensitive method for inhibitory control. Our method is based on a risk-aware condition for value functions, which guarantees the satisfaction of state constraints. We propose a method for learning these value functions using common techniques from reinforcement learning and derive sufficient conditions for its success. By enforcing the derived safety conditions online using the learned value function, risk-sensitive inhibitory control is effectively achieved. The effectiveness of the developed control scheme is demonstrated in simulations.

关键词：

An optimal power supervising strategy for a smart home assessed based on BPMN Framework

学校读者我要写书评

暂无评论

An optimal power supervising strategy for a smart home asses...

International Conference on Sciences and Techniques of Automatic Control and computer engineering (STA)

作者： Leila Lanouar Mouna Rekik Olfa Bouchaala Lotfi Krichen Multimédia & Web Department University of Gabes Higher Institute of Computer Science and Multimedia of Gabes (ISIMG) Gabes Tunis Electrical Engineering Department Electrical systems and renewable energies Laboratory (LSEER) University of Sfax University of Gabes National Engineering School of Sfax (ENIS) Higher Institute of Computer Science and Multimedia of Gabes (ISIMG) Sfax Gabes Tunis Department of Computer Engineering and Applied Mathematics Research Laboratory on Development and Control and Distributed Applications (ReDCAD) University of Sfax National Engineering School of Sfax (ENIS) Sfax Tunis Electrical Engineering Department Electrical systems and renewable energies Laboratory (LSEER) University of Sfax National Engineering School of Sfax (ENIS) Sfax Tunis

ISBN: (纸本)9781665482622

For each smart home, the need of energy consumption supervision is necessary, which plays an important role to ensure the highest power quality and to enhance the stability of the whole grid. The current document implements a smart home supply strategy based on endless resources to reduce the electricity bill and confirm the energy balance. In this context, a proposed supervision algorithm operates in eight cases to reach optimal energy flow between renewable generators, home battery and grid in a smart home concept is presented. The system is evaluated using the framework “Business Process Model and Notation” (BPMN) Camunda basing on information stored in Firebase Cloud and results are presented in order to manifest the efficiency of this control strategy.

关键词： Renewable energy sources Energy consumption Power quality Process control Smart homes Power system stability Stability analysis

An Efficient and Secure Post-Quantum Multi-Authority Ciphertext-Policy Attribute-Based Encryption Method Using Lattice

学校读者我要写书评

暂无评论

An Efficient and Secure Post-Quantum Multi-Authority Ciphert...

IEEE Conference on computer Communications Workshops, INFOCOM Wksps

作者： Prithwi Bagchi Basudeb Bera Raj Maheshwari Ashok Kumar Das David K. Y. Yau Biplab Sikdar Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad India Information Systems Technology and Design Singapore University of Technology and Design Singapore Department of Electrical and Computer Engineering National University of Singapore Singapore

This article deals with designing an efficient post-quantum lattice based encryption scheme that relies on the multi-authority Ciphertext-Policy Attribute-Based Encryption (CP-ABE). The security of the proposed scheme is based on the hardness of the ring learning with errors (RLWE) problem. The construction of the proposed scheme is done using the Shamir's threshold secret sharing along with the Lagrange interpolation during the key generation and decryption processes in order to achieve the segmentation and restoration of private keys. A comparative study with the existing state of art schemes has been performed to show the feasibility and efficiency of the proposed scheme. Furthermore, experiments on the proposed scheme have been conducted to illustrate the computational time required during the key generation, encryption and decryption processes.

关键词：

Terahertz Meets Untrusted UAV-Relaying: Minimum Secrecy Energy Efficiency Maximization via Trajectory and Communication Co-design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Mamaghani, Milad Tatar Hong, Yi Department of Electrical and Computer Systems Engineering Faculty of Engineering Monash University MelbourneVIC3800 Australia

Unmanned aerial vehicles (UAVs) and Terahertz (THz) technology are envisioned to play paramount roles in next-generation wireless communications. In this paper, we present a novel secure UAV-assisted mobile relaying system operating at THz bands for data acquisition from multiple ground user equipments (UEs) towards a destination. We assume that the UAV-mounted relay may act, besides providing relaying services, as a potential eavesdropper called the untrusted UAV-relay (UUR). To safeguard end-to-end communications, we present a secure two-phase transmission strategy with cooperative jamming. Then, we devise an optimization framework in terms of a new measure - secrecy energy efficiency (SEE), defined as the ratio of achievable average secrecy rate to average system power consumption, which enables us to obtain the best possible security level while taking UUR's inherent flight power limitation into account. For the sake of quality of service fairness amongst all the UEs, we aim to maximize the minimum SEE (MSEE) performance via the joint design of key system parameters, including UUR's trajectory and velocity, communication scheduling, and network power allocation. Since the formulated problem is a mixed-integer nonconvex optimization and computationally intractable, we decouple it into four subproblems and propose alternative algorithms to solve it efficiently via greedy/sequential block successive convex approximation and non-linear fractional programming techniques. Numerical results demonstrate significant MSEE performance improvement of our designs compared to other known benchmarks. Copyright © 2021, The Authors. All rights reserved.

关键词： Energy efficiency

Electric Vehicles Security and Privacy: Challenges, Solutions, and Future Needs

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Brighente, Alessandro Conti, Mauro Donadel, Denis Poovendran, Raadha Turrin, Federico Zhou, Jianying The Department of Mathematics HIT Research Center University of Padova Padova35131 Italy The Department of Electrical and Computer Engineering University of Washington Seattle98195 United States School of Information Systems Technology and Design Singapore University of Technology and Design 487372 Singapore

Electric Vehicles (EVs) share common technologies with classical fossil-fueled cars, but they also employ novel technologies and components (e.g., Charging System and Battery Management System) that create an unexplored attack surface for malicious users. Although multiple contributions in the literature explored cybersecurity aspects of particular components of the EV ecosystem (e.g., charging infrastructure), there is still no contribution to the holistic cybersecurity of EVs and their related technologies from a cyber-physical system perspective. In this paper, we provide the first in-depth study of the security and privacy threats associated with the EVs ecosystem. We analyze the threats associated with both the EV and the different charging solutions. Focusing on the Cyber-Physical systems (CPS) paradigm, we provide a detailed analysis of all the processes that an attacker might exploit to affect the security and privacy of both drivers and the infrastructure. To address the highlighted threats, we present possible solutions that might be implemented. We also provide an overview of possible future directions to guarantee the security and privacy of the EVs ecosystem. Based on our analysis, we stress the need for EV-specific cybersecurity solutions. © 2023, CC BY-NC-ND.

关键词： Electric vehicles

Transformative Applications and Key Challenges of Generative AI

学校读者我要写书评

暂无评论

Transformative Applications and Key Challenges of Generative...

International IEEE Conference and Workshop: Óbuda on electrical and Power engineering (CANDO-EPE)

作者： Attila Kovari Jozsef Katona Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Institute of Digital Technology Faculty of Computer Science Eszterházy Károly Catholic University Eger Hungary Department of Institute of Engineering University of Dunaújváros Dunaujvaros Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemét Hungary Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Business University Budapest Hungary

ISBN: (数字)9798331531119

ISBN: (纸本)9798331531126

The paper discusses the integration and use of generative artificial intelligence technologies in education. Generative AI, such as OpenAI, in particular the GPT model, has fundamentally changed the way humans interact with machines. Advanced technologies in the field of generative AI in education are mostly used to personalize learning experiences by dynamically customizing learning materials according to the needs of learners, thus enabling the improvement of outcomes. This article explores the use of generative AI tools with the aim of assessing how useful students perceive these tools to be. The findings show mixed receptivity from users, highlighting the critical balance in using innovative AI capabilities through AI.

关键词： Power engineering Accuracy Generative AI Education Chatbots Market research Problem-solving Reliability

Student Perceptions of AI-Enhanced Adaptive Learning systems: A Pilot Survey

学校读者我要写书评

暂无评论

Student Perceptions of AI-Enhanced Adaptive Learning Systems...

International IEEE Conference and Workshop: Óbuda on electrical and Power engineering (CANDO-EPE)

作者： Klara Ida Katonane Gyonyoru Jozsef Katona Department of Organizational Development and Communication Science Institute of Social Sciences University of Dunaujvaros Dunaujvaros Hungary Institute of Electronics and Communication Systems Kandó Kálmán Faculty of Electrical Engineering Obuda University Budapest Hungary Department of Software Development and Application Institute of Computer Engineering University of Dunaujvaros Dunaujvaros Hungary GAMF Faculty of Engineering and Computer Science John Von Neumann University Kecskemet Hungary Department of Applied Quantitative Methods Faculty of Finance and Accountancy Budapest Business University Budapest Hungary

ISBN: (数字)9798331531119

ISBN: (纸本)9798331531126

Artificial Intelligence (AI) significantly enhances adaptive learning by personalizing and tailoring instruction to individual student needs. AI analyzes data in real-time to create personalized learning paths based on students' strengths, weaknesses, and preferences, which keeps students engaged and motivated. A major benefit of AI in adaptive learning is the provision of real-time feedback and assessment, allowing students to correct mistakes promptly and understand concepts more thoroughly. AI-based intelligent tutoring systems are primarily intended to simulate personalized tutoring processes that guide students in complex problem-solving and answering questions. It is convenient in teaching mathematics, sciences, and languages. AI also supports inclusive education, dealing with diversified learning requirements and styles, such as those of learners with disabilities. For the teacher, AI acts as a reflector of student performance so that one can intervene early and make adjustments in the method of instruction by creating effective learning environments. AI technology is a field in constant development and harbors the potential to change the face of adaptive learning, bringing an upswing in educational outcomes. This article will summarize the advantages and features that merit improvement of the AI-embedded adaptive learning systems with student feedback.

关键词： Surveys Adaptive learning Power engineering Data security Real-time systems Mathematics Problem-solving Artificial intelligence Faces