检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Big Data, BigData 2023

作者： Polap, Dawid Jaszcz, Antoni Prokop, Katarzyna Srivastava, Gautam Silesian University of Technology Faculty of Applied Mathematics Kaszubska 23 Gliwice44-100 Poland Brandon University Dept. of Math and Computer Science BrandonMBR7A 6A9 Canada

ISBN: (纸本)9798350324457

Autonomous vehicles are a key element of the automotive industry, where the impact of the human factor on the condition of the vehicle and driving is minimized. An important element is the analysis of vehicular condition, which allows maintainence of its value and correct operation. We propose a system based on the analysis of the image of vehicles, which determines whether there is any damage. For this purpose, we propose a new model of a Convolutional Neural Network (CNN) that has 0. 395M trained values. The architecture of the network is adapted to the analysis of spatial features that allow networks to be adapted to analyze primarily vehicular shape and orientation in relation to other objects. The model also implements spatial dropout and regularization techniques for preventing overtraining and maintaining model generalization. The modeled architecture contributes to obtaining high classification accuracy at 94.78% using a public database and exceeding metrics of known transfer learning models. © 2023 IEEE.

关键词： convolutional neural networks image processing spatial attention spatial features vehicle damage problems

来源：评论

学校读者我要写书评

暂无评论

AGV Quality of Service Throughput Prediction via Neural Networks

AGV Quality of Service Throughput Prediction via Neural Netw...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Prokop, Katarzyna Polap, Dawid Srivastava, Gautam Silesian University of Technology Faculty of Applied Mathematics Kaszubska 23 Gliwice44-100 Poland Brandon University Dept. of Math and Computer Science BrandonMBR7A 6A9 Canada

ISBN: (纸本)9798350324457

The recent development of Autonomous Guided Vehicles (AGV) use in industry has resulted in the need to model new solutions based on the latest technological achievements. One of the areas worth attention and development is Quality of Service (QoS) in relation to communication between vehicles. QoS makes it possible to divide the bandwidth in such a way that tasks performed by devices are completed with a certain priority. However, in order to manage these resources effectively, it is necessary to anticipate available network throughput. Therefore, this paper presents a neural-based model to ensure throughput prediction for AGV. The proposed solution assumes the use of information on both historical throughput values and data obtained from other sensors that AGV are equipped with. Therefore, the idea is to integrate two neural networks with another network, which is supposed to predict the result based on these two previously obtained predictions. Ultimately, prediction results with a Root Mean Squared Error (RMSE) of 0.1 for the downlink and 1.6 for the uplink were obtained. © 2023 IEEE.

关键词： AGV deep learning predictive models QoS throughput prediction

来源：评论

学校读者我要写书评

暂无评论

Robustness and Weakness of Masked Quantum Information in Noisy Environment

SSRN

引用

SSRN 2023年

作者： Metwally, Nasser Abdelwahab, A.G. Mahran, M. Helmi Obada, A.-S.F. Department of Basic Science Faculty of Computers and Informatics Suez Canal University Ismailia41522 Egypt Math. Dept. College of Science University of Bahrain PO Box Bahrain320038 Bahrain Department of Mathematics Aswan University Aswan Sahari 81528 Egypt Math. Dept. Faculty of Science Al-Azhar University Nasr City Cairo11884 Egypt

The effect of the noisy environment, that may be represented by a magnetic field, on the masked information in two-qubit system is investigated, where it is assumed that only one of the subsystems interacts locally with the magnetic field. The amount of information that may be exchanged between the masked information and the environment is discussed by means of the Markovianity phenomenon. It is shown that, the total masked information is more robust than that masked in its subsystems. The initial interaction parameters and the weight of the masked state can be used as control parameters to maximize the Markovianity of the environment, and consequently decreasing the losses of the masked information. © 2023, The Authors. All rights reserved.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Prediction of Remaining Useful Life and Cell Temperature for Li-ion Batteries Using TinyML

Prediction of Remaining Useful Life and Cell Temperature for...

引用

Midwest Symposium on Circuits and Systems (MWSCAS)

作者： Yuqin Weng Wenkai Guan Cristinel Ababei Dept. of Elec. and Comp. Engr. Marquette University Milwaukee WI USA Div. of Science and Math. University of Minnesota Morris Morris MN USA

ISBN: (数字)9798350387179

ISBN: (纸本)9798350387186

In this paper, we develop new tiny machine learning (tiny ML) temporal convolutional network (TCN) models for prediction of remaining useful life (RUL) and of cell temperature for lithium-ion batteries. The proposed models are developed, trained, optimized and verified in Python using TensorFlow. Ex-tensive simulation experiments, using datasets from the Battery Archive website and from Sandia National Lab (SNL), show that the proposed models provide better results compared to previous models. Furthermore, the proposed models are converted to Ten-sorFlow lite for microcontroller models, which are deployed on IoT hardware devices, specifically the popular Arduino Nano 33 BLE Sense board. We conduct hardware experiments that show that the tinyML models are very efficient and provide satisfactory prediction accuracy. Therefore, the proposed optimized tinyML models could be easily deployed in real practical scenarios, such as electric vehicles (EVs), to continuously monitor in real-time the health and temperature of batteries.

关键词： Temperature sensors Lithium-ion batteries Temperature measurement Microcontrollers Tiny machine learning Predictive models Hardware

来源：评论

学校读者我要写书评

暂无评论

Threshold Decision-Making Dynamics Adaptive to Physical Constraints and Changing Environment

Threshold Decision-Making Dynamics Adaptive to Physical Cons...

引用

European Control Conference (ECC)

作者： Giovanna Amorim María Santos Shinkyu Park Alessio Franci Naomi Ehrich Leonard Dept. of Mechanical and Aerospace Engineering Princeton Univ. Princeton NJ USA Computer Electrical and Math. Science and Eng. Div. King Abdullah Univ. of Science and Technology (KAUST) Thuwal Saudi Arabia Department of Electrical Engineering and Computer Science University of Liege Liége Belgium WEL Research Institute Wavre Belgium

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

We propose a threshold decision-making frame-work for controlling the physical dynamics of an agent switching between two spatial tasks. Our framework couples a nonlinear opinion dynamics model that represents the evolution of an agent's preference for a particular task with the physical dynamics of the agent. We prove the bifurcation that governs the behavior of the coupled dynamics. We show by means of the bifurcation behavior how the coupled dynamics are adaptive to the physical constraints of the agent. We also show how the bifurcation can be modulated to allow the agent to switch tasks based on thresholds adaptive to environmental conditions. We illustrate the benefits of the approach through a multi-robot task allocation application for trash collection.

关键词： Adaptation models Decision making Europe Switches Bifurcation Control systems Resource management

来源：评论

学校读者我要写书评

暂无评论

Robust Discontinuity Indicators for High-Order Reconstruction of Piecewise Smooth Functions

arXiv

引用

arXiv 2023年

作者： Li, Yipeng Chen, Qiao Jiao, Xiangmin Dept. of Applied Math. & Stat. Institute for Advanced Computational Science Stony Brook University Stony BrookNY11794 United States

In many applications, piecewise continuous functions are commonly interpolated over meshes. However, accurate high-order manipulations of such functions can be challenging due to potential spurious oscillations known as the Gibbs phenomena. To address this challenge, we propose a novel approach, Robust Discontinuity Indicators (RDI), which can efficiently and reliably detect both C0 and C1 discontinuities for node-based and cell-averaged values. We present a detailed analysis focusing on its derivation and the dual-thresholding strategy. A key advantage of RDI is its ability to handle potential inaccuracies associated with detecting discontinuities on non-uniform meshes, thanks to its innovative discontinuity indicators. We also extend the applicability of RDI to handle general surfaces with boundaries, features, and ridge points, thereby enhancing its versatility and usefulness in various scenarios. To demonstrate the robustness of RDI, we conduct a series of experiments on non-uniform meshes and general surfaces, and compare its performance with some alternative methods. By addressing the challenges posed by the Gibbs phenomena and providing reliable detection of discontinuities, RDI opens up possibilities for improved approximation and analysis of piecewise continuous functions, such as in data *** Codes 65D05, 65D15, 65D99 Copyright © 2023, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Forward Difference Properties of the (n, k)-Star Graph and Some Other Interconnection Networks

Forward Difference Properties of the (n, k)-Star Graph and S...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Eddie Cheng Ethan Gibbons Ke Qiu Zhizhang Shen Dept. of Math and Stats Oakland University Rochester MI USA Dept. of Computer Science Brock University St. Catharines Canada Dept. of Computer Science and Technology Plymouth State University Plymouth NH USA

An important invariant of an interconnection network is its surface area, the number of vertices at distance i from a node. Although much work has been done to obtain formulas for the surface areas for many interconnection networks, most of the formulas are not in the so-called closed form except for a very few trivial graphs. It is known that for an interconnection network, if its surface area satisfies the so-called forward difference property, then for any specific distance i, its surface area of radius i in closed form (a polynomial of degree i) can be obtained, provided that we have i + 1 initial values of the surface area of radius i. This property is known to hold for the hypercube and the star graph. We show in this paper that the property also holds for the (n, k)-star graph, 1 ≤ k ≤ n − 1, a family of interconnection networks that also include the star graph when k = n − 1. We then show that the technique we use for the result is general that can also be used to prove the property for some other networks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hands-on Active Learning Approach to Teach Artificial Intelligence/Machine Learning to Elementary and Middle School Students 32

Hands-on Active Learning Approach to Teach Artificial Intell...

引用

32nd Wireless and Optical Communications Conference, WOCC 2023

作者： Sinha, Neelu Evans, Ryan F. Carbo, MacKenzie Fairleigh Dickinson University Department of Mathematics and Computer Science MadisonNJ United States Fdu Cs Hub and Haskell Elementary School Wanaque School District Dept. of Math and Comp Sci HaskellNJ United States

ISBN: (纸本)9798350337150

The last decade has seen a surge in expanding access to computer science (CS) education, especially for K-12, with many states even stipulating student learning standards in CS and Computational Thinking (CT). Our 21st century K-12 students are no longer just computer users, but are now required to be computationally literate creators with proficient skills both in the concepts and practices of CS and CT. At the same time, technology continues to pervade our lives and expand at a relentless pace and all aspects of our lives are now embedded in technology surrounded by Artificial Intelligence (AI). AI in the form of Machine Learning (ML) is a key technology in a diversity of applications, where we use sensors to meaningfully perceive the world around us, analyze and organize the perceived data, and autonomously use that data to make predictions and decisions. In higher education, AI/ML courses proliferate, with many institutions now conferring degrees and certifications in these. To an extent, some high schools (grades 9-12) have started introducing these concepts in a technology class, or a robotics club, or as an after-school activity. As for middle (grades 6-8) and elementary school (grades K-5), there are very few examples of such instruction. In this paper, we present a complete framework for elementary and middle school teachers to help them prepare and incorporate AI/ML lessons in their classrooms using hands-on active learning strategies. We want to empower these teachers to impart improved learning to their students, which in turn will prepare their students to become effective thinkers, problem solvers, communicators, and gain necessary skills for high-skilled and high-demand jobs. We describe a detailed AI/ML lesson plan based on standards and framework, AI4K12 big ideas, art and science of curriculum design, active learning, and culturally responsive and inclusive pedagogy. Then we discuss our experiences in teaching the same to 4th grade students in an e

关键词： Curricula

来源：评论

学校读者我要写书评

暂无评论

Insight into Voting Problem Complexity Using Randomized Classes

arXiv

引用

arXiv 2022年

作者： Fitzsimmons, Zack Hemaspaandra, Edith Dept. of Math. and Computer Science College of the Holy Cross WorcesterMA01610 United States Department of Computer Science Rochester Institute of Technology RochesterNY14623 United States

The first step in classifying the complexity of an NP problem is typically showing the problem in P or NP-complete. This has been a successful first step for many problems, including voting problems. However, in this paper we show that this may not always be the best first step. We consider the problem of constructive control by replacing voters (CCRV) introduced by Loreggia et al. (2015) for the scoring rule First-Last, which is defined by (1, 0, ⋯;0, -1). We show that this problem is equivalent to Exact Perfect Bipartite Matching, and so CCRV for First-Last can be determined in random polynomial time. So on the one hand, if CCRV for First-Last is NP-complete then RP = NP, which is extremely unlikely. On the other hand, showing that CCRV for First-Last is in P would also show that Exact Perfect Bipartite Matching is in P, which would solve a well-studied 40-year-old open problem. By considering RP as an option we also gain insight into the complexity of CCRV for 2-Approval, ultimately showing it in P, which settles the complexity of the sole open problem in the comprehensive table from Erdélyi et al. (2021). Copyright © 2022, The Authors. All rights reserved.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Dermatology: Achieving Dermatologist-Grade Skin Cancer Classification

AI-Powered Dermatology: Achieving Dermatologist-Grade Skin C...

引用

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

作者： Priyanka Kaushik Yash Chopra Amar Kajla Minakshi Poonia Akram Khan Dhruv Yadav Dept. of CSE (AIML) CSE-APEX Chandigarh University Chandigarh India Dept. of Eng. Math’s & Computing Madhav Institute of Technology & Science Gwalior India Dept. of Computer Science Madhav University Abu Road India

In the realm of dermatology, the accurate diagnosis of skin cancer has long been a challenging endeavor. This paper introduces a cutting-edge solution for achieving dermatologist-grade skin cancer classification through the power of artificial intelligence (AI). Departing from traditional methods that necessitate laborious manual feature extraction and domain-specific preprocessing, our system adopts a deep neural network architecture, specifically Google Net Inception v3 CNN, fine-tuned using a vast and diverse clinical image dataset. Dataset comprises 135,550 images meticulously organized within a structured taxonomy encompassing 2,055 distinct disease categories. To unlock the full potential of fine-grained classification, An innovative algorithm is introduced to facilitate precise identification of various skin diseases. This research underscores the transformative potential of AI-powered dermatology in the realm of early skin cancer detection. By achieving dermatologist-level accuracy, this approach has the capacity to significantly impact public health outcomes, particularly in regions where skin cancer is a prevalent concern.

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：