检索结果-内蒙古大学图书馆

Aicaregaitrehabilitationbyfusion: Multi-Model and Multi-Modalities Sensor Data Fusion for Ai-Iot Enabled Realtime Electrical Stimulation Device for Pre-Fog and Post-Fog to Person with Parkinson's

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Ghayvat, Hemant Geddam, Rebakah Awais, Muhammad Tiwari, Prayag Milrad, Marcelo Kumar, Neeraj Computer Science and Media Technology Department Faculty of Technology Linnaeus University P G Vejdes väg 351 95 Växjö35234 Sweden Department of Computer Science and Engineering Institute of Technology Nirma University Gujarat Ahmedabad382481 India Department of Imaging Physics The University of Texas MD Anderson Cancer Center Houston77030 United States School of Information Technology Halmstad University Halmstad11042 Sweden Department of Computer Science and Engineering Thapar University Punjab Patiala India School of Computer Science University of Petroleum and Energy Studies Dehradun Uttarakhand Patiala147001 India

People with Parkinson's disease (PD) frequently experience the Freezing of Gait (FoG), a locomotive issue that reduces their quality of life and increases their risk of falling. These people are given timely bio-feedback cues to assist them in controlling their gait utilizing wearable FoG sensing technology. However, the currently used FoG detection methods are cumbersome and intrusive. As a result, the current study intends to incorporate the FoG detection method into a single sensor node using characteristics with low computational load and specialized hardware, which restricts the area and memory use. For the classification, a real-time learning neural network is used, allowing the method to adjust to the needs of a patient as needed. Machine learning techniques based on Support Vector Machines (SVM) and a tri-axial accelerometer are used in the research to design a new gadget for FoG detection that will be worn by the patient around their waist. The proposed device's categorization performance is highly competitive, comfortable to wear, and real-time adaptable. The findings indicate that an electrical stimulation-based cueing strategy has a beneficial, universal effect on gait and FoG in PD. Federated Learning (FL), a machine learning strategy, provides encouraging options for customization while protecting delicate health data. This study examines how federated learning can be used to wearable electrical stimulation devices for more effective, individualized Parkinson's treatment. © 2024, The Authors. All rights reserved.

关键词： Deep learning

The Effect of Data Augmentation on the Accuracy of Fish Species Classification Using Deep Learning

学校读者我要写书评

暂无评论

The Effect of Data Augmentation on the Accuracy of Fish Spec...

International Conference on Informatics and Computing (ICIC)

作者： Ellya Helmud Catur Edi Widodo Oky Dwi Nurhayati Doctor Information System Postgraduate Diponegoro University Semarang Indonesia Faculty of Information Technology Information Systems Study Program Atma Luhur Institute of Science and Business Pangkalpinang Indonesia Physics Department Faculty of Science and Mathematics Diponegoro University Semarang Indonesia Department of Computer Engineering Faculty of Engineering Diponegoro University Semarang Indonesia

ISBN: (数字)9798331517601

ISBN: (纸本)9798331517618

Fish image classification presents an intriguing challenge in the field of computer vision. This research aims to develop an accurate classification model to differentiate between four different fish species using a convolutional neural network. The dataset used consists of $\mathbf{3 0 1 0}$ fish images, divided into training, validation, and testing sets. The convolutional neural network model was trained both with and without data augmentation. Evaluation results show that the model trained with data augmentation achieved an accuracy of $95 \%$ with a loss value of 0.0983, slightly better than the model without augmentation which achieved an accuracy of $94.56 \%$ with a loss value of $\mathbf{0. 1 7 9 4}$. This indicates that data augmentation techniques are effective in improving model performance, likely because augmentation helps the model generalize better to variations in fish image data. The results of this research demonstrate the significant potential of convolutional neural network for fish image classification tasks. The developed model can serve as a foundation for the development of computer vision-based applications such as automatic fish species identification in fisheries or educational applications. Further research can be conducted by exploring different convolutional neural network architectures, more advanced data augmentation techniques, and larger datasets to improve model performance.

关键词： Deep learning Training Accuracy Computational modeling computer architecture Fish Data augmentation Data models Convolutional neural networks Image classification

Probing collectivity in heavy-ion collisions with fluctuations of the pT spectrum

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Parida, Tribhuban Samanta, Rupam Ollitrault, Jean-Yves Department of Physical Sciences Indian Institute of Science Education and Research Berhampur Govt ITI Transit Campus Odisha Berhampur760010 India AGH University of Krakow Faculty of Physics and Applied Computer Science aleja Mickiewicza 30 Cracow30-059 Poland Université Paris Saclay CNRS CEA Institut de physique théorique Gif-sur-Yvette91191 France

Event-by-event fluctuations in the initial stages of ultrarelativistic nucleus-nucleus collisions depend little on rapidity. The hydrodynamic expansion which occurs in later stages then gives rise to correlations among outgoing particles which depend weakly on their relative rapidity. Azimuthal correlations, through which anisotropic flow (vn(pT)) is defined, have been the most studied. Here we study a new observable introduced in 2020 by Schenke, Shen and Teaney and dubbed v0(pT), which quantifies the relative change in the pT spectrum induced by a fluctuation. We describe how it can be measured. Using hydrodynamic simulations, we make quantitative predictions for v0(pT) of charged and identified hadrons. We then discuss how v0(pT) relates to two phenomena which have been measured: The increase of the mean transverse momentum in ultracentral collisions, and the event-by-event fluctuations of the transverse momentum per particle [pT]. We show that v0(pT) determines the dependence of these quantities on the pT cuts implemented in the analysis. We quantitatively explain the rise of σpT observed by ATLAS as the upper pT-cut is increased from 2 to 5 GeV/c. Copyright © 2024, The Authors. All rights reserved.

关键词： Heavy ions

Non-homogeneous Dirichlet problems with concave-convex reaction

学校读者我要写书评

暂无评论

Atti della Accademia Nazionale dei Lincei, Classe di Scienze Fisiche, Matematiche e Naturali, Rendiconti Lincei Matematica e Applicazioni 2021年第4期32卷 799-818页

作者： Bonanno, Gabriele Livrea, Roberto Rădulescu, Vicenţiu D. Messina98166 Italy Department of Mathematics and Computer Science University of Palermo Via Archirafi 34 Palermo90123 Italy Faculty of Applied Mathematics AGH University of Science and Technology Kraków30-059 Poland Department of Mathematics University of Craiova Street A.I. Cuza No. 13 Craiova200585 Romania ''Simion Stoilow'' Institute of Mathematics The Romanian Academy P.O. Box 1-764 Bucharest014700 Romania

The variational methods are adopted for establishing the existence of at least two nontrivial solutions for a Dirichlet problem driven by a non-homogeneous differential operator of p-Laplacian type. A large class of nonlinear terms is considered, covering the concave-convex case. In particular, two positive solutions to the problem are obtained under a (p - 1)-superlinear growth at infinity, provided that a behaviour less than (p - 1)-linear of the nonlinear term in a suitable set is requested. © 2021 European Mathematical Society Publishing House. All rights reserved.

关键词： Mathematical operators

Digital Twins Approaches and Methods Review

学校读者我要写书评

暂无评论

Digital Twins Approaches and Methods Review

Telecommunications Conference (ITC-Egypt), International

作者： Mohammed E. Helal Hamed Shawky Zied Ahmed Khairy Mahmoud Manal Helal Ali E. Takieldeen Samia M. Abd-Alhalem Faculty of Engineering AASTMT Cairo Egypt Air Defense College Alexandria University Alexandria Egypt School of Physics Engineering & Computer Science Hertfordshire University HATFIELD UK Faculty of Artificial Intelligence Delta University for Science and Technology Gamasa Egypt

This paper investigates the recent advances in Digital Twin technologies. The aim is to compare the approaches, available open source and proprietary technologies and methods, their features, and their integration capabilities. The motivation is to enable better design decisions based on the available literature and case studies. Various tools for 3D reconstruction and visualisation, IoT and sensor integration, Physical simulations and other complete platforms provide complete solutions. A conclusion of current challenges and future work identified that the lack of standardisation and interoperability makes the life-time of a digital twin short, with a high cost and time to build and rebuild if required.

关键词：

Completely entangled subspaces of entanglement depth k

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Demianowicz, Maciej Vogtt, Kajetan Augusiak, Remigiusz Institute of Physics and Applied Computer Science Faculty of Applied Physics and Mathematics Gdańsk University of Technology Narutowicza 11/12 Gdańsk80-233 Poland Center for Theoretical Physics Polish Academy of Sciences Aleja Lotników 32/46 Warsaw02-668 Poland Faculty of Physics University of Warsaw Pasteura 5 Warsaw02-093 Poland

We introduce a class of entangled subspaces: completely entangled subspaces of entanglement depth k (k-CESs). These are subspaces of multipartite Hilbert spaces containing only pure states with an entanglement depth of at least k. We present an efficient construction of k-CESs of any achievable dimensionality in any multipartite scenario. Further, we discuss the relation between these subspaces and unextendible product bases (UPBs). In particular, we establish that there is a non-trivial bound on the cardinality of a UPB whose orthocomplement is a k-CES. Further, we discuss the existence of such UPBs for qubit systems. © 2023, CC BY.

关键词： Quantum entanglement

Convolutional Neural Network-based Architecture for Detecting Face Mask in Crowded Areas

学校读者我要写书评

暂无评论

Convolutional Neural Network-based Architecture for Detectin...

IEEE/SP Workshop on Statistical Signal Processing (SSP)

作者： Jad Abou Chaaya Batoul Zaraket Hassan Harb Ali Mansour Lab-STICC UMR 6285 CNRS ENSTA Bretagne Brest France Applied Physics Lab Faculty of Science Lebanese University Jdeideh Lebanon Department of Computer Science American University of Culture and Education Tyre Lebanon College of Engineering and Technology American University of the Middle East Kuwait

After the invasion of the Covid-19 virus, governments started containing the spread of the virus by forcing people to wear face masks in public places. Therefore, automatic face mask detection has become very important to limit the virus spread. Unfortunately, existing methods present limited performance in accurately detecting masks in crowded areas due to the significant number of faces per scene. In order to tackle this challenge, we propose a two-stage neural network-based architecture that can accurately detect face masks in crowded environments. Several simulations have been conducted to investigate the efficiency of the proposed architecture and the results show a high accuracy of detection that can reach up to 96.5%.

关键词：

Uncertainty relations from state polynomial optimization

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Morán, Moisés Bermejo Huber, Felix Faculty of Physics Astronomy and Applied Computer Science Institute of Theoretical Physics Jagiellonian University Kraków30-348 Poland University of Bordeaux 351 cours de la Liberation Talence33405 France

Uncertainty relations are a fundamental feature of quantum mechanics. How can these relations be found systematically? Here we develop a semidefinite programming hierarchy for additive uncertainty relations in the variances of non-commuting observables. Our hierarchy is built on the state polynomial optimization framework, also known as scalar extension. The hierarchy is complete, in the sense that it converges to tight uncertainty relations. We improve upon upper bounds for all 1292 additive uncertainty relations on up to nine operators for which a tight bound is not known. The bounds are dimension-free and depend entirely on the algebraic relations among the operators. The techniques apply to a range of scenarios, including Pauli, Heisenberg-Weyl, and fermionic operators, and generalize to higher order moments and multiplicative uncertainty relations. Copyright © 2023, The Authors. All rights reserved.

关键词： Polynomials

Quantum pushforward designs

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Czartowski, Jakub Życzkowski, Karol Faculty of Physics Astronomy and Applied Computer Science Jagiellonian University Kraków30-348 Poland Polish Academy of Sciences Al. Lotników 32/46 Warszawa02-668 Poland

Designs, structures connected to averaging with respect to a given measure using finite sets of points, have proven themselves as invaluable tools across the field of quantum information, finding their uses in state and process tomography, key distribution and others. In this work, we introduce a new concept of pushforward designs, which allows us to obtain new structures from already existing ones by mapping them between the spaces, with specific examples including simplex designs and mixed state designs from complex projective designs. Based on the general concept, we put forward a structure called channel [t, k]-design, allowing for averaging over space of quantum channels for systems in contact with an environment of dimension k. Based on this notion, we introduce the concept of effective environment dimensionality k∗, which we estimate for the IBM Kyoto quantum computer to be below 2.2 for times up to 350µs. © 2024, CC BY.

关键词： Quantum channel