检索结果-内蒙古大学图书馆

YOLO-Ant: A Lightweight Detector via Depthwise Separable Convolutional and Large Kernel Design for Antenna Interference Source Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Tang, Xiaoyu Chen, Xingming Cheng, Jintao Wu, Jin Fan, Rui Zhang, Chengxi Zhou, Zebo The School of Electronic and Information Engineering Faculty of Engineering South China Normal University Guangdong Foshan528225 China The School of Physics South China Normal University Guangdong Guangzhou510000 China The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong The College of Electronics & Information Engineering Shanghai Research Institute for Intelligent Autonomous Systems The State Key Laboratory of Intelligent Autonomous Systems Frontiers Science Center for Intelligent Autonomous Systems Tongji University Shanghai201804 China The School of Internet of Things Engineering Jiangnan University Wuxi214122 China The School of Aeronautics Astronautics University of Electronic Science and Technology of China and Aircraft swarm intelligent sensing and cooperative control Key Laboratory of Sichuan Province Chengdu610097 China The National Laboratory on Adaptive Optics Chengdu610209 China

In the era of 5G communication, removing interference sources that affect communication is a resource-intensive task. The rapid development of computer vision has enabled unmanned aerial vehicles to perform various high-altitude detection tasks. Because the field of object detection for antenna interference sources has not been fully explored, this industry lacks dedicated learning samples and detection models for this specific task. In this article, an antenna dataset is created to address important antenna interference source detection issues and serves as the basis for subsequent research. We introduce YOLO-Ant, a lightweight CNN and transformer hybrid detector specifically designed for antenna interference source detection. Specifically, we initially formulated a lightweight design for the network depth and width, ensuring that subsequent investigations were conducted within a lightweight framework. Then, we propose a DSLK-Block module based on depthwise separable convolution and large convolution kernels to enhance the network’s feature extraction ability, effectively improving small object detection. To address challenges such as complex backgrounds and large interclass differences in antenna detection, we construct DSLKVit-Block, a powerful feature extraction module that combines DSLK-Block and transformer structures. Considering both its lightweight design and accuracy, our method not only achieves optimal performance on the antenna dataset but also yields competitive results on public datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Antennas

Decentralized control barrier functions for coupled multi-agent systems under signal temporal logic tasks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Lindemann, Lars Dimarogonas, Dimos V. Department of Automatic Control School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm100 44 Sweden

We study the problem of controlling multi-agent systems under a set of signal temporal logic tasks. Signal temporal logic is a formalism that is used to express time and space constraints for dynamical systems. Recent methods to solve the control synthesis problem for single-agent systems under signal temporal logic tasks are, however, subject to a high computational complexity. Methods for multi-agent systems scale at least linearly with the number of agents and induce even higher computational burdens. We propose a computationally-efficient control strategy to solve the multi-agent control synthesis problem that results in a robust satisfaction of a set of signal temporal logic tasks. In particular, a decentralized feedback control law is proposed that is based on time-varying control barrier functions. The obtained control law is discontinuous and formal guarantees are provided by nonsmooth analysis. Simulations show the efficacy of the presented method. Copyright © 2020, The Authors. All rights reserved.

关键词： Multi agent systems

Highly accelerated multi-shot intravoxel incoherent motion diffusion-weighted imaging in brain enabled by parametric POCS-based multiplexed sensitivity encoding

学校读者我要写书评

暂无评论

NMR in Biomedicine 2024年第3期37卷 e5063-e5063页

作者： Chen, Shihui Chu, Mei-Lan Liang, Liyuan Liu, Yi-Jui Chen, Nan-Kuei Wang, He Juan, Chun-Jung Chang, Hing-Chiu Department of Biomedical Engineering The Chinese University of Hong Kong Shatin Hong Kong Department of Diagnostic Radiology Li Ka Shing Faculty of Medicine The University of Hong Kong Pokfulam Hong Kong Graduate Institute of Biomedical Electronics and Bioinformatics National Taiwan University Taipei Taiwan Department of Automatic Control Engineering Feng Chia University Taichung Taiwan Department of Biomedical Engineering University of Arizona TucsonAZ United States Brain Imaging and Analysis Center Duke University Medical Center DurhamNC United States Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China Ministry of Education Shanghai China Human Phenome Institute Fudan University Shanghai China Department of Medical Imaging China Medical University Hsinchu Hospital Hsinchu Taiwan Department of Radiology School of Medicine College of Medicine China Medical University Taichung Taiwan Department of Medical Imaging China Medical University Hospital Taichung Taiwan Multi-Scale Medical Robotics Center Shatin Hong Kong

Recently, intravoxel incoherent motion (IVIM) diffusion-weighted imaging (DWI) has also been demonstrated as an imaging tool for applications in neurological and neurovascular diseases. However, the use of single-shot diffusion-weighted echo-planar imaging for IVIM DWI acquisition leads to suboptimal data quality: for instance, geometric distortion and deteriorated image quality at high spatial resolution. Although the recently commercialized multi-shot acquisition methods, such as multiplexed sensitivity encoding (MUSE), can attain high-resolution and high-quality DWI with signal-to-noise ratio (SNR) performance superior to that of the conventional parallel imaging method, the prolonged scan time associated with multi-shot acquisition is impractical for routine IVIM DWI. This study proposes an acquisition and reconstruction framework based on parametric-POCSMUSE to accelerate the four-shot IVIM DWI with 70% reduction of total scan time (13 min 8 s versus 4 min 8 s). First, the four-shot IVIM DWI scan with 17 b values was accelerated by acquiring only one segment per b value except for b values of 0 and 600 s/mm2. Second, an IVIM-estimation scheme was integrated into the parametric-POCSMUSE to enable joint reconstruction of multi-b images from under-sampled four-shot IVIM DWI data. In vivo experiments on both healthy subjects and patients show that the proposed framework successfully produced multi-b DW images with significantly higher SNRs and lower reconstruction errors than did the conventional acceleration method based on parallel imaging. In addition, the IVIM quantitative maps estimated from the data produced by the proposed framework showed quality comparable to that of fully sampled MUSE-reconstructed images, suggesting that the proposed framework can enable highly accelerated multi-shot IVIM DWI without sacrificing data quality. In summary, the proposed framework can make multi-shot IVIM DWI feasible in a routine MRI examination, with reasonable scan time a

关键词： Image reconstruction

INSTANCE SEGMENTATION AND TEETH CLASSIFICATION IN PANORAMIC X-RAYS

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Budagam, Devichand Ghosh, Sayan Imanbayev, Azamat Zhanatuly Kaplun, Dmitrii Rychenkov, Artem Sinitca, Aleksandr Kumar, Ayush Shrivastav, Anuj Akhmetov, Iskander Rafailovich Antonov, Sergey Cyganov, Gleb Department of Computer Science and Engineering Indian Institute of Technology Kharagpur Kharagpur India Department of Chemical Engineering Indian Institute of Technology Kharagpur Kharagpur India School of IT and Engineering Kazakh-British Technical University Almaty Kazakhstan Artificial Intelligence Research Institute China University of Mining and Technology Xuzhou China Department of Automation and Control Processes St. Petersburg Electrotechnical University"LETI" St. Petersburg Russia Centre for Digital Telecommunication Technologies St. Petersburg Electrotechnical University"LETI" St. Petersburg Russia Department of Humanities and Social Sciences Indian Institute of Technology Kharagpur Kharagpur India Department of Architecture and Regional Planning Indian Institute of Technology Kharagpur Kharagpur India Faculty of Digital Transformation ITMO University St. Petersburg Russia

Teeth segmentation and recognition are critical in various dental applications and dental diagnosis. automatic and accurate segmentation approaches have been made possible by integrating deep learning models. Although teeth segmentation has been studied in the past, only some techniques were able to effectively classify and segment teeth simultaneously. This article offers a pipeline of two deep learning models, U-Net and YOLOv8, which results in BB-UNet, a new architecture for the classification and segmentation of teeth on panoramic X-rays that is efficient and reliable. We have improved the quality and reliability of teeth segmentation by utilising the YOLOv8 and U-Net capabilities. The proposed networks have been evaluated using the mean average precision (mAP) and dice coefficient for YOLOv8 and BB-UNet, respectively. We have achieved a 3% increase in mAP score for teeth classification compared to existing methods, and a 10-15% increase in dice coefficient for teeth segmentation compared to U-Net across different categories of teeth. A new Dental dataset was created based on UFBA-UESC dataset with Bounding-Box and Polygon annotations of 425 dental panoramic X-rays. The findings of this research pave the way for a wider adoption of object detection models in the field of dental diagnosis. © 2024, CC BY.

关键词： Object detection

Comparing of transfer process data in PLC and mcu based on IoT 5th

学校读者我要写书评

暂无评论

Comparing of transfer process data in PLC and mcu based on I...

5th International Conference on Advanced engineering Theory and Applications, AETA 2018

作者： Gavlas, Antonin Koziorek, Jiri Rakay, Robert Department of Cybernetics and Biomedical Engineering Faculty of Electrical Engineering and Computer Science VSB-Technical University of Ostrava 17. listopadu 15 Ostrava70833 Czech Republic Department of Automation Control and Human Machine Interactions Faculty of Mechanical Engineering Technical University of Košice Park Komenského 8 Košice042 00 Slovakia

ISBN: (纸本)9783030149062

An article is based on comparing of data processing within PLC and MCU with using Cloud platforms. The last advances in computation and communication technologies are taking shape in the form of IoT (Internet of Things), M2M (Machine to Machine) technology, Industry 4.0 and Cyber Physical Systems. Internet of Things connects an enormous number of devices. Devices within IoT need small number of sensors and control data, but with numerous messages. Today Cloud services work with the volume of these data and support large scale IoT systems. In this paper we would like to represent a comparison of solutions Industrial and Commercial IoT. The proposed systems use one of the newest communication protocols MQTT. © Springer Nature Switzerland AG 2020.

关键词： Internet of things

Investigation on application of egg shell micro powder based epoxy composite for vibration isolation of MEMS sensor

学校读者我要写书评

暂无评论

AIP Conference Proceedings 2023年第1期2976卷

作者： Nitin Satpute Atharva Joshi Kaustubh Utpat Nishant Kulkarni Siddharth Jabade Ludwin Molina Arias Ramesh Narina Marek Iwaniec Faculty of Science and Technology Vishwakarma University Pune India Department of Mechanical Engineering Vishwakarma Institute of Technology Pune India Department of Process Control AGH University of Science and Technology Krakow Poland Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering Department of Biocybernetics and Biomedical Engineering AGH University of Science and Technology Krakow Poland

In the presented work, the stiffness and damping properties of eggshell-based epoxy composites are investigated. The ingredients used for the preparation of the composite include 25 - 45 µm sized eggshell powder, polydimethylsiloxane (PDMS), hardener, and silane as a coupling agent. Experimentation on prototype samples has been conducted using a vibration shaker, accelerometer, and fast Fourier transform (FFT) analyzer, to investigate the influence of the addition of micro-powder on the damping factor and stiffness of the composite. The study reveals that there is an improvement of up to 201% in damping factor with the 2.5% addition of micro powder by weight. The experimental study indicates that the stiffness properties of the composite are not influenced by the addition of eggshell micro powder. Additionally, a case study is demonstrated with finite element simulation to validate the advantages of using the proposed epoxy composite for Microelectromechanical System (MEMS) sensor packaging. In case of a harmonic force of 0.2 N acting on the sensor within the frequency range of 40-60 Hz, the maximum acceleration of the MEMS sensor increases by 48%, whereas the force transmissibility decreases by 44%.

关键词：

Novel symmetric numerical methods for solving symmetric mathematical problems

学校读者我要写书评

暂无评论

International Journal of Circuits, Systems and Signal Processing 2021年 15卷 1545-1557页

作者： Ibrahimov, V.R. Mehdiyeva, G.Y.U. Yue, Xiao-Guang Kaabar, Mohammed K.A. Noeiaghdam, Samad Juraev, Davron Aslonqulovich Institute of Control Systems named after Academician A.Huseynov BakuAZ1141 Azerbaijan Computational mathematics Baku State University BakuAZ1148 Azerbaijan Department of Computer Science and Engineering School of Sciences European University Cyprus Nicosia1516 Cyprus Institute of Mathematical Sciences Faculty of Science University of Malaya Kuala Lumpur50603 Malaysia Department of Mathematics and Statistics Washington State University PullmanWA99163 United States Industrial Mathematics Laboratory Baikal School of BRICS Irkutsk National Research Technical University Irkutsk664074 Russia Department of Applied Mathematics and Programming South Ural State University Lenin Prospect 76 Chelyabinsk454080 Russia Department of Natural Science Disciplines Higher Military Aviation School of the Republic of Uzbekistan Karshi City180100 Uzbekistan

—The mathematical model for many problems is arising in different industries of natural science, basically formulated using differential, integral and integro-differential equations. The investigation of these equations is conducted with the help of numerical integration theory. It is commonly known that a class of problems can be solved by applying numerical integration. The construction of the quadrature formula has a direct relation with the computation of definite integrals. The theory of definite integrals is used in geometry, physics, mechanics and in other related subjects of science. In this work, the existence and uniqueness of the solution of above-mentioned equations are investigated. By this way, the domain has been defined in which the solution of these problems is equivalent. All proposed four problems can be solved using one and the same methods. We define some domains in which the solution of one of these problems is also the solution of the other problems. Some stable methods with the degree p © 2021, North Atlantic University Union NAUN. All rights reserved.

关键词： Integrodifferential equations

The Energy Efficiency of a Prosumer in a Photovoltaic System

学校读者我要写书评

暂无评论

The Energy Efficiency of a Prosumer in a Photovoltaic System

International Symposium for Design and Technology of Electronics Packages (SIITME)

作者： Marius-Alexandru Dobrea Stefan Bichiu Ioana Opris Mihaela Vasluianu Faculty of Automatic Control and Computer Science UPB Bucharest Romania Faculty of Power Engineering UPB Bucharest Romania Collective of Automation and Applied Informatics Faculty of Hidrotehnics UTCB Bucharest Romania

ISBN: (数字)9781728175065

ISBN: (纸本)9781728175072

This article aims to calculate the net income achieved by a prosumer for an existing On-Grid system of photovoltaic panels consisting of a set of 12 poly crystalline panels with a nominal power of 250 Wand 60 cells and an On-Grid inverter (StecaGrid model) with a maximum power of 3000 W. The prosumer is located in southern Romania, Ilfov County. Modeling of the photovoltaic panel in Matlab / SIMULINK was performed using a mathematical model, and it was compared with a real data set. Next, an analysis was made of the energy produced by the photovoltaic system, and the energy consumed by the prosumer, the excess energy being introduced in the national energy system. We have achieved a net income saving for March, so the analyzed photovoltaic system has energy efficiency that can significantly reduce electricity costs over time. Thus, using the Matlab / Simulink model, photovoltaic systems can be designed to satisfy the needs of prosumers.

关键词： Photovoltaic systems Mathematical model Solar power generation Software packages Inverters Temperature Temperature measurement

Simultaneous tactile exploration and grasp refinement for unknown objects

学校读者我要写书评

暂无评论

arXiv 2021年

作者： de Farias, Cristiana Marturi, Naresh Stolkin, Rustam Bekiroglu, Yasemin The Extreme Robotics Laboratory School of Metallurgy and Materials University of Birmingham Birmingham United Kingdom Chalmers University of Technology Department of Electrical Engineering Automatic Control research group Sweden University College London Department of Computer Science Centre for Artificial Intelligence United Kingdom

This paper addresses the problem of simultaneously exploring an unknown object to model its shape, using tactile sensors on robotic fingers, while also improving finger placement to optimise grasp stability. In many situations, a robot will have only a partial camera view of the near side of an observed object, for which the far side remains occluded. We show how an initial grasp attempt, based on an initial guess of the overall object shape, yields tactile glances of the far side of the object which enable the shape estimate and consequently the successive grasps to be improved. We propose a grasp exploration approach using a probabilistic representation of shape, based on Gaussian Process Implicit Surfaces. This representation enables initial partial vision data to be augmented with additional data from successive tactile glances. This is combined with a probabilistic estimate of grasp quality to refine grasp configurations. When choosing the next set of finger placements, a bi-objective optimisation method is used to mutually maximise grasp quality and improve shape representation during successive grasp attempts. Experimental results show that the proposed approach yields stable grasp configurations more efficiently than a baseline method, while also yielding improved shape estimate of the grasped object. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning