检索结果-内蒙古大学图书馆

Towards end-to-end deep learning for autonomous racing: On data collection and a unified architecture for steering and throttle prediction

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Wadekar, Shakti N. Schwartz, Benjamin J. Kannan, Shyam S. Mar, Manuel Manna, Rohan Kumar Chellapandi, Vishnu Gonzalez, Daniel J. Gamal, Aly El School of Electrical and Computer Engineering Purdue University West LafayetteIN47907 United States Computer Information Technology Polytechnic Institute Purdue University West LafayetteIN47907 United States Robotics Research Center Department of Electrical Engineering and Computer Science United States Military Academy West PointNY10996 United States

Deep Neural networks (DNNs) which are trained end-to-end have been successfully applied to solve complex problems that we have not been able to solve in past decades. Autonomous driving is one of the most complex problems which is yet to be completely solved and autonomous racing adds more complexity and exciting challenges to this problem. Towards the challenge of applying end-to-end learning to autonomous racing, this paper shows results on two aspects: (1) Analyzing the relationship between the driving data used for training and the maximum speed at which the DNN can be successfully applied for predicting steering angle, (2) Neural network architecture and training methodology for learning steering and throttle without any feedback or recurrent connections. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Incompatibility as a Resource for Programmable Quantum Instruments

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Ji, Kaiyuan Chitambar, Eric Center for Quantum Information Institute for Interdisciplinary Information Sciences Tsinghua University Beijing100084 China School of Electrical and Computer Engineering Cornell University IthacaNY14850 United States Department of Electrical and Computer Engineering Coordinated Science Laboratory University of Illinois at Urbana-Champaign UrbanaIL61801 United States

Quantum instruments represent the most general type of quantum measurement, as they incorporate processes with both classical and quantum outputs. In many scenarios, it may be desirable to have some "on-demand" device that is capable of implementing one of many possible instruments whenever the experimenter desires. We refer to such objects as programmable instrument devices (PIDs), and this paper studies PIDs from a resourcetheoretic perspective. A physically important class of PIDs are those that do not require quantum memories to implement, and these are naturally "free" in this resource theory. Additionally, these free objects correspond precisely to the class of unsteerable channel assemblages in the study of channel steering. The traditional notion of measurement incompatibility emerges as a resource in this theory since any PID controlling an incompatible family of instruments requires a quantum memory to build. We identify an incompatibility preorder between PIDs based on whether one can be transformed into another using processes that do not require additional quantum memories. Necessary and sufficient conditions are derived for when such transformations are possible based on how well certain guessing games can be played using a given PID. Ultimately our results provide an operational characterization of incompatibility, and they offer semi-device-independent tests for incompatibility in the most general types of quantum instruments. Copyright © 2021, The Authors. All rights reserved.

关键词： Three term control systems

A high-frequency mobility big-data reveals how COVID-19 spread across professions, locations and age groups

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhao, Chen Zhang, Jialu Hou, Xiaoyue Yeung, Chi Ho Zeng, An College of Computer and Cyber Security Hebei Normal University Shijiazhuang050024 China Hebei Key Laboratory of Network and Information Security Shijiazhuang050024 China Hebei Provincial Engineering Research Center for Supply Chain Big Data Analytics and Data Security Shijiazhuang050024 China Department of Science and Environmental Studies The Education University of Hong Kong Hong Kong School of Systems Science Beijing Normal University Beijing100875 China

As infected and vaccinated population increases, some countries decided not to impose non-pharmaceutical intervention measures anymore and to coexist with COVID-19. However, we do not have a comprehensive understanding of its consequence, especially for China where most population has not been infected and most Omicron transmissions are silent. This paper serves as the first study to reveal the complete silent transmission dynamics of COVID-19 overlaying a big data of more than 0.7 million real individual mobility tracks without any intervention measures throughout a week in a Chinese city, with an extent of completeness and realism not attained in existing studies. Together with the empirically inferred transmission rate of COVID-19, we find surprisingly that with only 70 citizens to be infected initially, 0.33 million becomes infected silently at last. We also reveal a characteristic daily periodic pattern of the transmission dynamics, with peaks in mornings and afternoons. In addition, retailing, catering and hotel staff are more likely to get infected than other professions. Unlike all other age groups and professions, elderly and retirees are more likely to get infected at home than outside home. Copyright © 2022, The Authors. All rights reserved.

关键词： COVID-19

Problems in NP can Admit Double-Exponential Lower Bounds when Parameterized by Treewidth or Vertex Cover

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Foucaud, Florent Galby, Esther Khazaliya, Liana Li, Shaohua Inerney, Fionn Mc Sharma, Roohani Tale, Prafullkumar Université Clermont Auvergne CNRS Mines Saint-Étienne Clermont Auvergne INP LIMOS Clermont-Ferrand63000 France Department of Computer Science and Engineering Chalmers University of Technology University of Gothenburg Gothenburg Sweden Technische Universität Wien Vienna Austria CISPA Helmholtz Center for Information Security Saarbrücken Germany University of Bergen Bergen Norway Indian Institute of Science Education and Research Pune Pune India

Treewidth serves as an important parameter that, when bounded, yields tractability for a wide class of problems. For example, graph problems expressible in Monadic Second Order (MSO) logic and Quantified SAT or, more generally, Quantified CSP, are fixed-parameter tractable parameterized by the treewidth of the input's (primal) graph plus the length of the MSO-formula [Courcelle, information & Computation 1990] and the quantifier rank [Chen, ECAI 2004], respectively. The algorithms generated by these (meta-)results have running times whose dependence on treewidth is a tower of exponents. A conditional lower bound by Fichte, Hecher, and Pfandler [LICS 2020] shows that, for Quantified SAT, the height of this tower is equal to the number of quantifier alternations. These types of lower bounds, which show that at least double-exponential factors in the running time are necessary, exhibit the extraordinary level of computational hardness for such problems, and are rare in the current literature: there are only a handful of such lower bounds (for treewidth and vertex cover parameterizations) and all of them are for problems that are #NP-complete, (Equation presented)-complete, (Equation presented)-complete, or complete for even higher levels of the polynomial hierarchy. Our results demonstrate, for the first time, that it is not necessary to go higher up in the polynomial hierarchy to achieve double-exponential lower bounds: we derive double-exponential lower bounds in the treewidth (tw) and the vertex cover number (vc), for natural, important, and well-studied NP-complete graph problems. Specifically, we design a technique to obtain such lower bounds and show its versatility by applying it to three different problems: Metric Dimension, Strong Metric Dimension, and Geodetic Set. We prove that these problems do not admit 22o(tw) ·nO(1)-time algorithms, even on bounded diameter graphs, unless the ETH fails (here, n is the number of vertices in the graph). In fact, for Strong

关键词： Parameterization

Explainable AI over the Internet of Things (IoT): Overview, State-of-the-Art and Future Directions

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Jagatheesaperumal, Senthil Kumar Pham, Quoc-Viet Ruby, Rukhsana Yang, Zhaohui Xu, Chunmei Zhang, Zhaoyang Department of Electronics and Communication Engineering Mepco Schlenk Engineering College Tamil Nadu Sivakasi India The Korean Southeast Center for the 4th Industrial Revolution Leader Education Pusan National University Busan46241 Korea Republic of College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen China The College of Information Science and Electronic Engineering Zhejiang University Hangzhou310027 China Hangzhou310007 China Zhejiang Lab Hangzhou31121 China The School of Information Science and Engineering Southeast University China

Explainable Artificial Intelligence (XAI) is transforming the field of Artificial Intelligence (AI) by enhancing the trust of end-users in machines. As the number of connected devices keeps on growing, the Internet of Things (IoT) market needs to be trustworthy for the end-users. However, existing literature still lacks a systematic and comprehensive survey work on the use of XAI for IoT. To bridge this lacking, in this paper, we address the XAI frameworks with a focus on their characteristics and support for IoT. We illustrate the widely-used XAI services for IoT applications, such as security enhancement, Internet of Medical Things (IoMT), Industrial IoT (IIoT), and Internet of City Things (IoCT). We also suggest the implementation choice of XAI models over IoT systems in these applications with appropriate examples and summarize the key inferences for future works. Moreover, we present the cutting-edge development in edge XAI structures and the support of sixth-generation (6G) communication services for IoT applications, along with key inferences. In a nutshell, this paper constitutes the first holistic compilation on the development of XAI-based frameworks tailored for the demands of future IoT use cases. © 2022, CC BY.

关键词： Internet of things

A Microscopic Human-Inspired Adaptive Cruise Control for Eco-Driving

学校读者我要写书评

暂无评论

A Microscopic Human-Inspired Adaptive Cruise Control for Eco...

European Control Conference (ECC)

作者： Marco Mirabilio Alessio Iovine Elena De Santis Maria Domenica Di Benedetto Giordano Pola Department of Information Engineering Computer Science and Mathematics Center of Excellence DEWS University of LAquila

The following topics are dealt with: control system synthesis; nonlinear control systems; predictive control; linear systems; feedback; stability; robust control; optimisation; closed loop systems; and optimal control.

ISBN: (数字)9783907144022

ISBN: (纸本)9781728188133

关键词： Biological system modeling Automata Safety Acceleration Microscopy Fuels Cruise control

Hyperspectral Image Classification via Neighborhood Adaptive Graph Isomorphism network

学校读者我要写书评

暂无评论

IEEE Transactions on Geoscience and Remote Sensing 2025年 63卷

作者： Zhang, Jian Tu, Bing Liu, Bo Li, Jun Plaza, Antonio Nanjing University of Information Science and Technology Institute of Optics and Electronics State Key Laboratory Cultivation Base of Atmospheric Optoelectronic Detection and Information Fusion Jiangsu International Joint Laboratory on Meteorological Photonics and Optoelectronic Detection Jiangsu Engineering Research Center for Intelligent Optoelectronic Sensing Technology of Atmosphere Nanjing 210044 China China University of Geosciences (Wuhan) Faculty of Computer Science Wuhan 430074 China University of Extremadura Hyperspectral Computing Laboratory Department of Technology of Computers and Communications Escuela Politécnica Cáceres 10003 Spain

Graph convolutional network (GCN) has garnered significant attention in hyperspectral image (HSI) classification due to their ability to model non-Euclidean structured data. Compared with convolutional neural network (CNN), GCN can perform convolutions over irregular image regions and learn global dependencies among pixels in the whole image. Most existing GCN-based methods in the HSI community rely on average aggregation or weighted average aggregation strategies to aggregate neighboring node features. This process tends to obscure the differences between the nodes. However, for HSI classification tasks with obvious intra-class variability, average aggregation is a suboptimal choice. Moreover, the quality of the initial graph structure plays a crucial role in the model’s capacity to represent spectral relationships effectively. To mitigate these issues, we propose a neighborhood adaptive graph isomorphism network (NAGIN) for HSI classification to ensure that the diversified spectra representation of land-cover can be effectively captured. The neighborhood adaptive block (NAB) enhances spectral discriminability between land-cover classes via spectral reconstruction, enabling more precise removal of anomalous pixels in neighboring nodes. The graph isomorphism network (GIN) aggregates the features of neighboring nodes in an isomorphic manner to obtain multiple spectral expressions of the same type of land-cover, ensuring that the spectral features of different land-cover classes can be accurately distinguished. The Kolmogorov-Arnold network (KAN) leverages its ability to learn adaptive activation functions to better extract and refine the spectral features aggregated by GIN. Experimental results demonstrate that NAB can effectively improve the quality of the graph structure, the GIN aggregation method is competitive in HSI classification, and the proposed NAGIN outperforms the state-of-the-art methods on several public HSI datasets. © 1980-2012 IEEE.

关键词： graph convolutional network (GCN) Graph isomorphism network (GIN) hyperspectral image (HSI) classification Kolmogorov-Arnold network (KAN)

In-situ data scheduling optimization based on rainbow DQN for IIoT

学校读者我要写书评

暂无评论

Future Generation computer Systems 2026年 174卷

作者： Peiying Zhang Siyi Li Lizhuang Tan Neeraj Kumar Jian Wang Kai Liu Qingdao Institute of Software College of Computer Science and Technology China University of Petroleum (East China) Qingdao 266580 China Shandong Key Laboratory of Intelligent Oil & Gas Industrial Software Qingdao 266580 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan 250014 China Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Patiala 147004 India Department of Computer Science University of Economics and Human Sciences Warszawa 01-043 Poland Department of Networks and Communications College of Computer Science and Information Technology Imam Abdulrahman Bin Faisal University Dammam 31441 Saudi Arabia College of Science China University of Petroleum (East China) Qingdao 266580 China Beijing National Research Center for Information Science and Technology Tsinghua University Beijing 100084 China State Key Laboratory of Space Network and Communications Tsinghua University Beijing 100084 China

In industrial systems, in-situ computing refers to a mode of local or proximate data processing within the cloud–edge-terminal architecture. In the Industrial Internet of Things (IIoT) environment, servers are typically deployed near terminal devices to coordinate and manage the scheduling of in-situ data, forming a comprehensive in-situ server system. With the rapid growth of IIoT terminal devices, challenges such as high processing delays and severe demand congestion arise in the in-situ data scheduling process. To address this challenge, this paper proposes a scheduling optimization scheme based on Rainbow DQN. The scheme designs a scheduling buffer and classification strategy to distinguish in-situ data based on storage demand characteristics, thereby optimizing the scheduling process. At the same time, a multi-level storage structure is introduced to store in-situ data classified according to the scheduling strategy. Additionally, the Rainbow DQN algorithm is utilized to assist in the scheduling decision-making of in-situ data retrieval, effectively alleviating system congestion while ensuring certain throughput performance. Extensive simulation experiments show that the Rainbow DQN algorithm achieves a reduction of 60.82% in average waiting delay, 62.94% in average unprocessed demand, and a 58.27% reduction in average completion delay.

关键词：

A Comprehensive Survey of Few-shot Learning: Evolution, Applications, Challenges, and Opportunities

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Song, Yisheng Wang, Ting Mondal, Subrota K. Sahoo, Jyoti Prakash The Engineering Research Center of Software/Hardware Co-design Technology and Application Ministry of Education The Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai200062 China The Faculty of Information Technology Macau University of Science and Technology Macao China The Department of Computer Science & Information Technology Institute of Technical Education and Research Siksha 'o' Anusandhan University India

Few-shot learning (FSL) has emerged as an effective learning method and shows great potential. Despite the recent creative works in tackling FSL tasks, learning valid information rapidly from just a few or even zero samples still remains a serious challenge. In this context, we extensively investigated 200+ latest papers on FSL published in the past three years, aiming to present a timely and comprehensive overview of the most recent advances in FSL along with impartial comparisons of strengths and weaknesses of the existing works. For the sake of avoiding conceptual confusion, we first elaborate and compare a set of similar concepts including few-shot learning, transfer learning, and meta-learning. Furthermore, we propose a novel taxonomy to classify the existing work according to the level of abstraction of knowledge in accordance with the challenges of FSL. To enrich this survey, in each subsection we provide in-depth analysis and insightful discussion about recent advances on these topics. Moreover, taking computer vision as an example, we highlight the important application of FSL, covering various research hotspots. Finally, we conclude the survey with unique insights into the technology evolution trends together with potential future research opportunities in the hope of providing guidance to follow-up research. © 2022, CC BY.

关键词： Surveys