检索结果-内蒙古大学图书馆

Proposal of Axial-gap type Magnetic Multiple Spur Gear for In-wheel Motor System of Electric Vehicle

学校读者我要写书评

暂无评论

Proposal of Axial-gap type Magnetic Multiple Spur Gear for I...

IEEE International Conference on Electric Machines and Drives (IEMDC)

Magnetic gears have the characteristics of maintenance-free, low noise, and low vibration due to non-contact power transmission. By taking advantage of the non-contact power transmission, the motor system can be made smaller and lighter by further increasing the motor speed. Magnetic Multiple Spur Gear (MMSG) has been proposed, the drive system of MMSG and multiple high-speed motors can reduce the size and weight of the drive system by converting the total power of multiple high-speed motors. Applying this drive system to in-wheel motors will increase the available interior space in electric vehicles. However, there is a risk that the high-speed rotor and low-speed rotor contact with each other due to the radial structure in the in-wheel motor system. In this research, an axial-gap MMSG is proposed to solve the problem and to obtain higher torque density, the performances such as torque density and efficiency are evaluated by finite element analysis.

关键词：

Image Captioning with Reinforcement Learning

学校读者我要写书评

暂无评论

Image Captioning with Reinforcement Learning

computer Vision and Machine Intelligence (CVMI), International Conference on

作者： Anand Verma Saurabh Agarwal K.V. Arya Ivan Petrlik Roberto Esparza Ciro Rodriguez Department of Information Technology ABV-IIITM Gwalior Madhya Pradesh India Department of Computer Science and Engineering Multimedia and Information Security Research Group ABV-Indian Institute of Information Technology and Management Gwalior India Faculty of Industrial and Systems Engineering National University Federico Villarreal Lima Peru Faculty of Systems Engineering and Informatics National University Mayor de San Marcos

Image captioning involves generating a natural language description that accurately represents the content and context of an image. To achieve this, image captioning utilises various machine learning techniques and fields, such as computer vision and natural language processing. In the field of image captioning, a lot of advances have been made with encoder-decoder models and reinforcement learning algorithms. However, there are still problems of imbalance between testing and training, as reinforcement learning only handles single comparator metrics such as CIDEr, SPICE, and BLEU and could not perform better in multiple metrics at once. Which is why a lack of diversity can be seen in generated captions. This idea proposes a general technique for collaborative updating that can bridge the gap between evaluation measures and test metrics to produce captions that are more human-like. To increase the precision of image captions, the approach involves using a compiled reward system that considers multiple evaluation metrics to compare the generated sentence with the provided sentences. We will evaluate the model's performance and the reward updating process on standard datasets like MS COCO.

关键词：

Computational and experimental design of fast and versatile magnetic soft robotic low Re swimmers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Pramanik, R. Park, M. Ren, Z. Sitti, M. Verstappen, R.W.C.P. Onck, P.R. Computational & Numerical Mathematics Group Bernoulli Institute for Mathematics Computer Science & Artificial Intelligence University of Groningen Netherlands Physical Intelligence Department Max Planck Institute for Intelligent Systems Stuttgart Germany School of Mechanical Engineering and Automation Beihang University Beijing China Institute for Biomedical Engineering ETH Zurich Zurich Switzerland School of Medicine College of Engineering Koc University Istanbul Turkey Micromechanics Group Zernike Institute for Advanced Materials University of Groningen Netherlands

Miniaturized magnetic soft robots have shown extraordinary capabilities of contactless manipulation, complex path maneuvering, precise localization, and quick actuation, which have equipped them to cater to challenging biomedical applications such as targeted drug delivery, internal wound healing, and laparoscopic surgery. However, despite their successful fabrication by several different research groups, a thorough design strategy encompassing the optimized kinematic performance of the three fundamental biomimetic swimming modes at miniaturized length scales has not been reported till now. Here, we resolve this by designing magnetic soft robotic swimmers (MSRSs) from the class of helical and undulatory low Reynolds number (Re) swimmers using a fully coupled, experimentally calibrated computational fluid dynamics model. We study (and compare) their swimming performance, and report their steady-state swimming speed for different non-dimensional numbers that capture the competition by magnetic loading, non-linear elastic deformation and viscous solid-fluid coupling. We investigate their stability for different initial spatial orientations to ensure robustness during real-life applications. Our results show that the helical’finger-shaped’ swimmer is, by far, the fastest low Re swimmer in terms of body lengths per cycle, but that the undulatory’carangiform’ swimmer proved to be the most versatile, bidirectional swimmer with maximum stability. © 2024, CC BY-NC-ND.

关键词： Reynolds number

Reproducibility and Geometric Intrinsic Dimensionality: An Investigation on Graph Neural Network Research

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Hille, Tobias Stubbemann, Maximilian Hanika, Tom Knowledge & Data Engineering Group University of Kassel Kassel Germany Interdisciplinary Research Center for Information System Design University of Kassel Kassel Germany Information Systems and Machine Learning Lab University of Hildesheim Hildesheim Germany Institute of Computer Science University of Hildesheim Hildesheim Germany

Difficulties in replication and reproducibility of empirical evidences in machine learning research have become a prominent topic in recent years. Ensuring that machine learning research results are sound and reliable requires reproducibility, which verifies the reliability of research findings using the same code and data. This promotes open and accessible research, robust experimental workflows, and the rapid integration of new findings. Evaluating the degree to which research publications support these different aspects of reproducibility is one goal of the present work. For this we introduce an ontology of reproducibility in machine learning and apply it to methods for graph neural networks. Building on these efforts we turn towards another critical challenge in machine learning, namely the curse of dimensionality, which poses challenges in data collection, representation, and analysis, making it harder to find representative data and impeding the training and inference processes. Using the closely linked concept of geometric intrinsic dimension we investigate to which extend the used machine learning models are influenced by the intrinsic dimension of the data sets they are trained *** Codes 68T01 68T07 68T09 51F99 Copyright © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

STARS-Enabled Full-Duplex Two-Way mMIMO System Under Spatially-Correlated Channels

学校读者我要写书评

暂无评论

IEEE Transactions on Vehicular Technology 2025年

作者： Papazafeiropoulos, Anastasios Kourtessis, Pandelis Chatzinotas, Symeon Kaklamani, Dimitra I. Venieris, Iakovos S. University of Hertfordshire Communications and Intelligent Systems Research Group HatfieldAL10 9AB United Kingdom University of Luxembourg SnT Luxembourg Microwave and Fiber Optics Laboratory Greece National Technical University of Athens Intelligent Communications and Broadband Networks Laboratory School of Electrical and Computer Engineering Athens Zografou15780 Greece

Low-cost reconfigurable intelligent surfaces (RISs) are being considered as promising physical-layer technology for next-generation wireless networks due to their ability to re-engineer the propagation environment by tuning their elements. Although RIS-aided systems have many advantages, one of their major bottlenecks is that they can provide coverage only in front of the surface. Fortunately, simultaneous transmitting and reflecting surface (STARS)-assisted systems have emerged to fill this gap by providing 360° wireless coverage. In parallel, full-duplex (FD) communication offers a higher achievable rate through efficient spectrum utilization compared to the half-duplex (HD) counterpart. Moreover, two-way/bi-directional communications in an FD system can further enhance the system's spectral efficiency. Hence, in this paper, we propose a STARS-enabled massive MIMO deployment in an FD two-way communication network for highly efficient spectrum utilization, while covering the dead zones around the STARS. This model enables simultaneous information exchange between multiple nodes, while potentially doubling the spectral efficiency (SE). By invoking the use-and-then-forget (UaTF) combining scheme, we derive a closed-form expression for an achievable SE at each user of the system considering both uplink and downlink communications based on statistical channel state information (CSI), while also accounting for imperfect CSI and correlated fading conditions. Moreover, we formulate an optimization problem to obtain an optimal passive beamforming matrix design at the STARS that maximizes the sum achievable SE. The considered problem is non-convex and we propose a provably-convergent low-complexity algorithm, termed as projected gradient ascent method (ProGrAM), to obtain a stationary solution. Extensive numerical results are provided to establish the performance superiority of the FD STARS-enabled system over the HD STARS-enabled and FD conventional RIS (cRIS)-enabled coun

关键词： Digital television

Nondeterministic Finite Automata for Modeling an Ecuadorian Sign Language Interpreter

学校读者我要写书评

暂无评论

Nondeterministic Finite Automata for Modeling an Ecuadorian ...

AHFE Virtual Conferences on Software and systems engineering, and Artificial Intelligence and Social Computing, 2020

作者： Guerra, Jose Vallejo-Huanga, Diego Jaramillo, Nathaly Macas, Richard Díaz, Daniel Department of Computer Science Universidad Politécnica Salesiana Quito Ecuador IDEIAGEOCA Research Group Universidad Politécnica Salesiana Quito Ecuador Systems Engineering Department Universidad Politécnica Salesiana Quito Ecuador

ISBN: (纸本)9783030513276

This paper presents a stand-alone application for text interpretation to Ecuadorian Sign Language (LSEC), modeled by a nondeterministic finite automaton (NFA), lexical analysis and regular expressions. This application will allow you to interpret a text entered by a user and present it through GIF graphic resources, thus allowing you to establish unidirectional communication between a hearing person and a person with hearing impairment. Our application is developed under MVC architecture. The state machine and lexical analyzer are in the model layer, which will be handled by the controller layer and that will allow the user to receive the inputs and send the outputs through the view layer. We evaluate the effectiveness of the tool using an LSEC dictionary with a total of 275 words and idioms, for different users with hearing impairment, and the results showed that our application is robust and fast. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Audition

Study on indoor pollutants emission in Akure, Ondo State, Nigeria

学校读者我要写书评

暂无评论

Arab Gulf Journal of Scientific Research

Arab Gulf Journal of Scientific Research 2024年第4期42卷 1643-1663页

作者： Abulude, Francis Olawale Suriano, Domenico Oluwagbayide, Samuel Dare Akinnusotu, Akinyinka Abulude, Ifeoluwa Ayodeji Awogbindin, Emmanuel Environmental and Sustainable Research Group Science and Education Development Institute Akure Nigeria Department of Sustainable Development Research Center of Brindisi ENEA-Italian National Agency for New Technologies Energy and Environment Brindisi Italy Department of Agricultural and Bio-Environmental Engineering Federal Polytechnic Idah Nigeria Department of Science Laboratory Technology Rufus Giwa Polytechnic Owo Nigeria Department of Agricultural Economics Bioeconomy and Food Systems Justus – Liebig University (JLU) Giessen Germany Department of Computer Science Bamidele Olumilua University of Education Science and Technology Ekiti Ikere Nigeria

Purpose: This study aimed to characterize the concentrations of indoor pollutants (such as carbon dioxide (CO2), ozone (O3), nitrogen dioxide (NO2) and sulfur dioxide (SO2), as well as particulate matter (PM) (PM1, PM... 详细信息

Purpose: This study aimed to characterize the concentrations of indoor pollutants (such as carbon dioxide (CO₂), ozone (O₃), nitrogen dioxide (NO₂) and sulfur dioxide (SO₂), as well as particulate matter (PM) (PM₁, PM_2.5 and PM₁₀) in Akure, Nigeria, as well as the relationship between the parameters’ concentrations. Design/methodology/approach: The evaluation, which lasted four months, used a low-cost air sensor that was positioned two meters above the ground. All sensor procedures were correctly carried out. Findings: CO₂ (430.34 ppm), NO₂ (93.31 ppb), O₃ (19.94 ppb), SO₂ (40.87 ppb), PM₁ (29.31 µg/m3), PM_2.5 (43.56 µg/m³), PM₁₀ (50.70 µg/m³), temperature (32.4°C) and relative humidity (50.53%) were the average values obtained. The Pearson correlation depicted the relationships between the pollutants and weather factors. With the exception of April, which had significant SO₂ (18%) and low PM₁₀ (49%) contributions, NO₂ and PM₁₀ were the most common pollutants in all of the months. The mean air quality index (AQI) for NO₂indicated that the AQI was “moderate” (51–100). In contrast to SO₂, whose AQI ranged from “moderate” to “very unhealthy,” O₃'s AQI ranged from “good” (50) to “unhealthy” (151–200). Since PM₁, PM_2.5 and PM₁₀ made up the majority of PC1’s contribution, both PM_2.5 and PM₁₀ were deemed “hazardous.” Practical implications: The practical implication of indoor air pollution is long-term health effects, including heart disease, lung cancer and respiratory diseases such as emphysema. Indoor air pollution can also cause long-term damage to people’s nerves, brain, kidneys, liver and other organs. Originality/value: Lack of literature in terms of indoor air qu

关键词： Air quality index Indoor air quality Nigeria Pollutants United States environmental protection agency (USEPA) World health organization (WHO)

Interval Markov Decision Processes with Continuous Action-Spaces

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Delimpaltadakis, Giannis Lahijanian, Morteza Mazo, Manuel Laurenti, Luca Control Systems Technology Group Mechanical Engineering Eindhoven University of Technology Eindhoven Netherlands Aerospace Engineering Sciences & Computer Science University of Colorado Boulder BoulderCO United States Delft Center for Systems and Control Mechanical Engineering Delft University of Technology Delft Netherlands

Interval Markov Decision Processes (IMDPs) are finite-state uncertain Markov models, where the transition probabilities belong to intervals. Recently, there has been a surge of research on employing IMDPs as abstractions of stochastic systems for control synthesis. However, due to the absence of algorithms for synthesis over IMDPs with continuous action-spaces, the action-space is assumed discrete a-priori, which is a restrictive assumption for many applications. Motivated by this, we introduce continuous-action IMDPs (caIMDPs), where the bounds on transition probabilities are functions of the action variables, and study value iteration for maximizing expected cumulative rewards. Specifically, we decompose the max-min problem associated to value iteration to |Q | max problems, where |Q | is the number of states of the caIMDP. Then, exploiting the simple form of these max problems, we identify cases where value iteration over caIMDPs can be solved efficiently (e.g., with linear or convex programming). We also gain other interesting insights: e.g., in certain cases where the action set A is a polytope, synthesis over a discrete-action IMDP, where the actions are the vertices of A, is sufficient for optimality. We demonstrate our results on a numerical example. Finally, we include a short discussion on employing caIMDPs as abstractions for control synthesis. © 2022, CC BY.

关键词： Markov processes

Semi-supervised Classification of Malware Families Under Extreme Class Imbalance via Hierarchical Non-Negative Matrix Factorization with Automatic Model Selection

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Eren, Maksim E. Bhattarai, Manish Joyce, Robert J. Raff, Edward Nicholas, Charles Alexandrov, Boian S. Advanced Research in Cyber Systems LANL United States Theoretical Division LANL United States Machine Learning Research Group Booz Allen Hamilton United States Department of Computer Science and Electrical Engineering UMBC United States

Identification of the family to which a malware specimen belongs is essential in understanding the behavior of the malware and developing mitigation strategies. Solutions proposed by prior work, however, are often not practicable due to the lack of realistic evaluation factors. These factors include learning under class imbalance, the ability to identify new malware, and the cost of production-quality labeled data. In practice, deployed models face prominent, rare, and new malware families. At the same time, obtaining a large quantity of up-to-date labeled malware for training a model can be expensive. In this paper, we address these problems and propose a novel hierarchical semi-supervised algorithm, which we call the HNMFk Classifier, that can be used in the early stages of the malware family labeling process. Our method is based on non-negative matrix factorization with automatic model selection, that is, with an estimation of the number of clusters. With HNMFk Classifier, we exploit the hierarchical structure of the malware data together with a semi-supervised setup, which enables us to classify malware families under conditions of extreme class imbalance. Our solution can perform abstaining predictions, or rejection option, which yields promising results in the identification of novel malware families and helps with maintaining the performance of the model when a low quantity of labeled data is used. We perform bulk classification of nearly 2,900 both rare and prominent malware families, through static analysis, using nearly 388,000 samples from the EMBER-2018 corpus. In our experiments, we surpass both supervised and semi-supervised baseline models with an F1 score of 0.80. Copyright © 2023, The Authors. All rights reserved.

关键词： Non-negative matrix factorization