检索结果-内蒙古大学图书馆

Machine Learning With Data Assimilation and Uncer.a.nty Quantification for Dynamical Systems:A review

IEEE/CAA Jour.a. of Automatica Sinica 2023年第6期10卷 1361-1387页

作者： Sibo Cheng César Quilodrán-Casas Said Ouala Alban Farchi Che Liu Pierre Tandeo ronan Fablet Didier Lucor Bertrand Iooss Julien Brajard Dunhui Xiao Tijana Janjic Weiping Ding Yike Guo Alberto Car.a.si Marc Bocquet rossella Arcucci Data Science Institute Department of ComputingImperial College LondonSW72AZ London Department of Earth Science and Engineering Imperial College LondonSW72AZ London Department of Computer Science and Engineering Hong Kong University of Science and TechnologyHong Kong 999077China the IMT Atlantique Lab-STICCUMR CNRS 6285France and OdysseyInria/IMTFrance.P.Tandeo is also with RIKEN Center for Computational ScienceKobeJapan the CEREA École des Ponts and EDF R&Dîle-de-FranceFrance the Laboratoire Interdisciplinaire des Sciences du Numérique CNRSParis-Saclay UniversityF-91403OrsayFrance the Electricitéde France(EDF) 78401 ChatouFranceInstitut de Mathématiques de Toulouse31062 ToulouseFrance and SINCLAIR AI LabSaclayFrance the Sorbonne University ParisFranceand also with Nansen Environmental and Remote Sensing Center(NERSC)BergenNorway the School of Mathematical Sciences Tongji UniversityShanghai 200092China the Mathematical Institute for Machine Learning and Data Science KU Eichstaett-IngolstadtBavariaGermany the School of Information Science and Technology Nantong UniversityNantong 226019China the Department of Physics and Astronomy“Augusto Righi” University of Bologna40124 BolognaItaly

Data assimilation(DA)and uncer.a.nty quantification(UQ)are extensively used in analysing and reducing error propagation in high-dimensional spatial-temporal *** applications span from computational fluid dynamics(CFD)to geoscience and climate ***,much effort has been given in combining DA,UQ and machine learning(ML)*** research efforts seek to address some critical challenges in high-dimensional dynamical systems,including but not limited to dynamical system identification,reduced order surrogate modelling,error covar.a.ce specification and model error correction.A large number of developed techniques and methodologies exhibit a br.a. applicability across numerous domains,resulting in the necessity for.a.comprehensive *** paper provides the first overview of state-of-the-art researches in this interdisciplinary field,covering a wide range of *** review is aimed at ML scientists who attempt to apply DA and UQ techniques to improve the accuracy and the interpretability of their models,but also at DA and UQ experts who intend to integrate cutting-edge ML appr.a.hes to their ***,this article has a special focus on how ML methods can overcome the existing limits of DA and UQ,and vice *** exciting perspectives of this rapidly developing research field are also *** Terms-Data assimilation(DA),deep learning,machine learning(ML),reduced-order-modelling,uncer.a.nty quantification(UQ).

关键词： assimilation overcome apply

来源：评论

学校读者我要写书评

暂无评论

Photonic Frequency Space Simulation of Tight-Binding Lattices Using Integrated LNOI ring resonators

Photonic Frequency Space Simulation of Tight-Binding Lattice...

引用

Pacific rim Conference on Lasers and Electro-Optics (CLEO/Pacific rim)

作者： Ar.a.das Balčytis Hiep Dinh Tomoki Ozawa Yasutomo Ota Toshihiko Baba Satoshi Iwamoto Ar.a. Mitchell Thach G. Nguyen Integrated Photonics and Applications Centre RMIT University Melbourne VIC Australia Advanced Institute for Materials Research Tohoku University Sendai Japan Department of Applied Physics and Physico-Informatics Keio University Yokohama Japan Department of Electrical and Computer Engineering Yokohama National University Hodogaya-ku Yokohama Japan Research Center for Advanced Science and Technology The University of Tokyo Meguro-ku Tokyo Japan

We use electro-optically modulated ring cavities, integrated on thin-film lithium niobate, to model frequency dimension tight-binding lattices with ver.a.ile connectivity. Inter-mode coupling range, strength, and hopp... 详细信息

ISBN: (数字)9798350372076

ISBN: (纸本)9798350372083

关键词： Frequency modulation Lithium niobate resonant frequency Lattices Electro-optic modulators ring lasers Laser modes

来源：评论

学校读者我要写书评

暂无评论

Prostate Cancer Classification using Cat Swarm Optimization with Deep Learning on MrI Images

Prostate Cancer Classification using Cat Swarm Optimization ...

引用

Inter.a.ional conference of Electronics, Communication and Aerospace technology (ICECA)

作者： Haritha V K V Archana Balasubramaniam D Uma Maheswari S P. Sasireka Suja G P Department of CSE RMK Engineering College Kavarapettai Chennai Department of Electronics and Communication Engineering School of Engineering Avinashilingam Institute for Home Science and Higher Education for Women Coimbatore India Department of Biomedical Engineering VelTech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai Tamilnadu India Department of Biosciences Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai ECE department S. A. Engineering college Chennai Research Center of Computer Science Muslim Arts College Thiruvithancode Kanyakumari

Prostate Cancer (PC) is a common malignancy amongst men globally, and accurate classification plays a significant part in its diagnoses and tr.a.ment planning. Due to its superior soft tissue contrast, Magnetic resonance Imaging (MrI) has developed as a valuable imaging modality for the assessment of PC. PC classification on MrI is a major task in medical imaging analysis, and deep learning (DL) appr.a.hes are employed to accomplish automated and accurate classification. In recent times, Convolutional Neural Network (CNN) structure was selected for the classification of PC. This manuscript introduces an automated Prostate Cancer Classification using Cat Swarm Optimization with Deep Learning (PCC-CSODL) technique on MrI Images. The main purpose of the PCC-CSODL algorithm lies in the effectual and accurate identification of PC. For.a.hieving this, the PCC-CSODL technique involves NASNet feature extractor.a. the initial stages. In addition, the CSO algorithm is used for the optimum hyper.a.ameter selection of the NASNet model. For classification purposes, attention based long short term memory (ALSTM) model can be used. The results demonstrated the effectiveness of the PCC-CSODL technique in accurately classifying PC on MrI. It has the potential to assist clinicians in making informed decisions and enhancing patient outcomes in PC management.

关键词：

来源：评论

学校读者我要写书评

暂无评论

EMErGENCE OF MICrOBIAL HOST DOr.a.CY DUrING A PErSISTENT VIrUS EPIDEMIC

arXiv

引用

arXiv 2025年

作者： Blath, Jochen Tóbiás, András Goethe-Universität Frankfurt Robert-Mayer-Straße 10 Frankfurt am Main60325 Germany Department of Computer Science and Information Theory Faculty of Electrical Engineering and Informatics Budapest University of Technology and Economics Műegyetem rkp. 3. BudapestH-1111 Hungary HUN-REN Alfréd Rényi Institute of Mathematics Reáltanoda utca 13–15 BudapestH-1053 Hungary

We study a minimal stochastic individual-based model for.a.microbial population challenged by a persistent (lytic) virus epidemic. We focus on the situation in which the resident microbial host population and the virus population are in stable coexistence upon arrival of a single new "mutant" host individual. We assume that this mutant is capable of switching to a reversible state of dor.a.cy upon contact with virions as a means of avoiding infection by the virus. At the same time, we assume that this new dor.a.cy trait comes with a cost, namely a reduced individual reproduction rate. We prove that there is a non-trivial range of parameters where the mutants can nevertheless invade the resident population with with strictly positive probability (bounded away from 0) in the large population limit. Given the reduced reproductive rate, such an invasion would be impossible in the absence of either the dor.a.cy trait or the virus epidemic. We explicitly characterize the parameter regime where this emergence of a (costly) host dor.a.cy trait is possible, determine the success probability of a single invader.a.d the typical amount of time it takes the successful mutants to r.a.h a macroscopic population size. We conclude this study by an investigation of the fate of the population after the successful emergence of a dor.a.cy trait. Heuristic arguments and simulations suggest that after successful invasion, either both host types and the virus will r.a.h coexistence, or the mutants will drive the resident hosts to extinction while the virus will stay in the *** Codes 92D25, 60J85, 34D05, 37G15 Copyright © 2025, The Authors. All rights reserved.

关键词： Stochastic models

来源：评论

学校读者我要写书评

暂无评论

Neutral point clamped inverter for enhanced grid connected PV system perfor.a.ce based on hexagonal space vector modulation

引用

Scientific reports 2025年第1期15卷 1-21页

作者： Palanisamy, r. Vijayakumar, K. Gulbar.a. Mohammad Imtiyaz Al Awadh, Mohammed Hui, Liew Tze Department of Electrical and Electronics Engineering College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu Chennai 603203 India Faculty of Engineering and Informatics Department of Computer Science & Engineering Ala-Too International University Bishkek Kyrgyzstan Department of Industrial Engineering College of Engineering King Khalid University P.O. Box 394 Abha 61421 Saudi Arabia Center for Engineering and Technology Innovations King Khalid University Abha 61421 Saudi Arabia Centre for Intelligent Cloud Computing (CICC) COE of Advanced Cloud Faculty of Information Science & Technology Multimedia University Jalan Ayer Keroh Lama Bukit Beruang Melaka 75450 Malaysia

The incr.a.ing global demand for renewable energy has accelerated the adoption of grid-connected photovoltaic (PV) systems. However, conventional PV inverters often rely on transformers, which add to the system’s cost, size, and power losses. Transformerless inverter topologies have emerged as a promising alter.a.ive, offering improved efficiency, compact design, and lower costs. Despite these advantages, challenges such as high total harmonic distortion (THD), common mode voltage (CMV) issues, and neutral current imbalance must be addressed to ensure reliable grid integration. This research investigates a transformerless five-level neutral point clamped (NPC) inverter for grid-connected PV applications, aiming to overcome these challenges. The study focuses on analysing THD, mitigating CMV to enhance system reliability, and optimizing output voltage levels to meet grid standards. The proposed transformerless five-level NPC inverter, incorporating a coupled inductor, is controlled using Hexagonal Space Vector Modulation (HSVM) to improve perfor.a.ce. Additionally, the research evaluates neutral current behavior to ensure stability and compliance with grid codes. Simulation and experimental results validate the proposed system’s effectiveness under varying operating conditions, highlighting its potential as a high-efficiency, cost-effective solution for sustainable energy integration into the grid. © The Author(s) 2025.

关键词： Capacitor voltage unbalance (CVU) Common mode voltage (CMV) Photovoltaic (PV) systems Total harmonic distortion (THD) Transformerless five-level neutral point clamped (NPCI) inverter

来源：评论

学校读者我要写书评

暂无评论

Implementation of Human robot Interaction with Motion Planning and Control Parameters with Autonomous Systems in Industry 4.0

Implementation of Human Robot Interaction with Motion Planni...

引用

Augmented Intelligence and Sustainable Systems (ICAISS), Inter.a.ional Conference on

作者： G. Chandramowleeswaran Chandan Choubey Sireesha Pendem Shaunak Pal Amit Verma Department of Commerce and Business Administration Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science And Technology Chennai Tamilnadu India Department of Electronics & Communication Engineering IMS Engineering College Ghaziabad Uttar Pradesh India Department of ECE CMR Technical Campus Kandlakoya Village Hyderabad Telangana India School of Computer Science and Engineering Vellore Institute of Technology Vellore Tamil Nadu India Department of Physics Graphic Era Hill University Dehradun India

By merging autonomous systems and human-robot interaction (HrI), Industry 4.0 has caused a paradigm shift in manufacturing and production processes. To maximize productivity and ensure smooth machine-human collaboration in this environment, motion planning, and control parameters must be effectively integrated with autonomous robots. With the help of hybrid deep learning models including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and recurrent Neural Networks (rNNs), the implementation of HrI with motion planning and control parameters in autonomous systems is proposed in this research. To incr.a.e productivity, safety, and flexibility in industr.a. settings, the suggested appr.a.h intends to enable robust and adaptive interaction between humans and robots. CNNs are used to analyze and comprehend the surroundings by the autonomous system through object identification and visual perception. LSTM and rNN models are used to combine this perception with the temporal components of motion planning and control. The suggested method allows the autonomous system to learn from sizable datasets of human-robot interactions, enabling the r.a.-time prediction of human intentions and behavior. The models' ability to respond to changing settings and modify the motion planning and control parameters as necessary makes it easier to complete tasks quickly and work together. By solving impor.a.t issues with human-robot collaboration, the adoption of this hybrid deep learning-based HrI system advances Industry 4.0. The suggested method improves the general effectiveness and safety of industr.a. operations by seamlessly integrating motion planning and control parameters with autonomous systems. Additionally, the hybrid deep learning models' adaptive nature enables ongoing learning and perfor.a.ce improvement over time.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Perfor.a.ce Analysis for Molecular Communication Under Feedback Channel Using Multipath and Single Path Technique

SSRN

引用

SSrN 2022年

作者： Ningthoujam, Sanjit Chingkheinganba, Tekcham Chakraborty, Swarnendu Kumar Elngar, Ahmed A. Chakrabarti, Prasun Chakrabarti, Tulika Praveen, S. Phani Gupta, Amit Mar.a.a, Martin School of Computer Science and Engineering VIT University Andhra Pradesh 522237 India BSNL Dimapur797112 India Dept. of Computer Science and Engineering National Institute of Technology Arunachal Pradesh 791112 India Faculty of Computers and Information Techno India NJR Institute of Technology India Department of Chemistry Sir Padampat Singhania University Rajasthan Udaipur313601 India Prasad V Potluri Siddhartha Institute of Technology Andhra Pradesh 520007 India Department of ECE Narasaraopeta Engineering College Andhra Pradesh Narasaraopeta522601 India Computer Science School of Computing and Informatics University of Louisiana United States

Nanomachines that can run tasks and molecular communication (MC) for interconnecting nanomachines have been made possible by advances in nanotechnology. Different techniques of Automatic repeat request (ArQ) protocols have been devised in MC for.a.quiring the necessary molecules, although the retransmission of duplicate copies requires special attention. This work presents a diffusion-based MC with a feedback loop to improve MC perfor.a.ce. Based on the received ACK(s) or NACK(s), the Channel state determines if the state is good (G) or bad (B), and then single path or multipath procedures are used to the ‘G' and ‘B' states. The results of the MATLAB simulation illustrate how the systems compare in terms of communication rate, the possibility of complete transmission of the desired molecules, and energy consumption. When the channel state is bad, the multipath appr.a.h performs better, but when the channel state is perfect in MC, the single path strategy performs better. © 2022, The Authors. All rights reserved.

关键词： Molecules

来源：评论

学校读者我要写书评

暂无评论

Basil Leaf Diseases Detection using Deep Learning architectures

Basil Leaf Diseases Detection using Deep Learning architectu...

引用

IEEE India Conference (INDICON)

作者： r. Kavitha M. Kavitha r. Srinivasan N. r. rajalakshmi r. Dhayanidhi Department of Computer Science and Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India Research Scholar Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9781665452724

An impor.a.t role played by plants on earth is unquestionable. In both the ecological and medicinal fields, every plant or.a. plays a crucial role. On Earth, however, we have a wide variety of plant species. Different plants have different diseases. Therefore, it is needed to identify the plants and their diseases to prevent loss. Now to identify the plants and their diseases manually is very time consuming. In this research an automatic plant and their disease detection system is proposed. Training and testing of high-quality leaf images is permitted for experimental purposes. Our study used color- based and region-based thresholding techniques to detect the diseased and healthy ar.a. of the leaf. The Gabor texture feature selection and the random Forest method were applied for feature selection. The final two classification methods used were random Forests and Support Vector Machines, which were used for binary and multi-label classification. 98.7% accuracy is obtained using random Forest and Support Vector Machines for feature selection. A graphic user inter.a.e was made so that all users could understand the automated system. Using computer vision and artificial intelligence (AI) to detect plant diseases early can reduce the adverse effects of disease and reduce labour costs. We have used edge detection algorithms that are based on Canny and Sobel models to detect the infected one not by its color, but rather by its shape. Image resizing and grayscale conversion were performed prior to passing them on to machine learning models to speed up processing time. In addition, mini-batch techniques were used to speed up the processing time of NN and Lr. 800 images of holy basil leaves are included in the dataset, including 400 images of healthy leaves and 400 images of infected leaves. As a result of the experiments, it has been shown that the proposed method is effective in detecting the curling leaves on holy basil.

关键词： Support vector machines Earth Training Shape Biological system modeling Feature extraction random forests

来源：评论

学校读者我要写书评

暂无评论

A Lightweight Appr.a.h to r.a.-Time Speaker Diarization: From Audio Toward Audio-Visual Data Str.a.s

SSRN

引用

SSrN 2023年

作者： Kynych, Frantisek Cer.a. Petr Zdansky, Jindrich Svendsen, Torbjørn Salvi, Giampiero Faculty of Mechatronics Informatics and Interdisciplinary Studies Technical University of Liberec Studentska 2 Liberec461 17 Czech Republic Department of Electronic Systems Norwegian University of Science and Technology Torgarden TrondheimNO-7491 Norway KTH Royal Institute of Technology School of Electrical Engineering and Computer Science Brinellvägen 8 StockholmSE-100 44 Sweden

This manuscript deals with the task of r.a.-time speaker diarization (SD) for str.a.-wise data processing. Therefore, in contrast to most of the existing papers, it considers not only the accuracy but also the computational demands of individual investigated methods. We first propose a new lightweight scheme allowing us to perform speaker diarization of str.a.ed audio data. Our.a.pr.a.h utilizes a modified residual network with squeeze-and-excitation blocks (SE-resNet-34) to extract speaker embeddings in an optimized way using cached buffers. These embeddings are subsequently used for voice activity detection (VAD) and block-online k-means clustering with a look-ahead *** described scheme yields results similar to the reference offline system while operating solely on a CPU with a low r.a.-time factor (rTF) below 0.1 and a constant latency of around 5.5 seconds. In the next part of the work, our research moves toward much more demanding and complex r.a.-time processing of audio-visual data *** this purpose, we extend the above-mentioned scheme for.a.dio data processing by adding an audio-video module. This module utilizes SyncNet combined with visual embeddings for identity tracking. Our resulting multi-modal SD framework then combines the outputs from audio and audio-video modules by using a new over.a.-based fusion strategy. It yields diarization error rates that are competitive with the existing state-of-the-art offline audio-visual methods while allowing us to process various audio-video str.a.s, e.g., from internet or TV br.a.casts, in r.a.-time and with the same latency as for.a.dio data processing. © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

IoT Farm: A robust Methodology Design to Support Smart Agricultural System Using Internet of Things with Intelligent Sensors Association

IoT Farm: A Robust Methodology Design to Support Smart Agric...

引用

Inter.a.ional conference of Electronics, Communication and Aerospace technology (ICECA)

作者： r. Karthiga C. L. Brindha Devi r. Janaki C. Gayathri V. Samuthira Pandi D Shobana Department of IT R.M.K Engineering College Kavaraipettai Chennai Tamilnadu India Department of Computer Science Queen Mary's College (Autonomous) Chennai Tamilnadu India Department of Science & Humanities Prince Shri Venkateshwara Padmavathy Engineering College Chennai Tamilnadu India Centre for Advanced Wireless Integrated Technology Chennai Institute of Technology Chennai Tamilnadu India Department of Electrical and Electronics Engineering Rajalakshmi Engineering College Chennai Tamilnadu India

The term “Smart Farming” has been incr.a.ingly popular in recent years due, in large part, to the proliferation of network-based, high-tech farm monitoring cycles. These cycles make extensive use of technologies for communication and infor.a.ion gathering in the form of machinery, equipment, and sensors. The Internet of Things, often known as IoT, is the wave of the future in every sector of the economy, and its impacts will be felt by everyone. It is a collection of different devices that are capable of configuring themselves into a fully operational network. Conventional farming practices are progressively being supplanted by smart farming, which takes use of advancements made possible by the internet of things. This makes conventional farming methods more efficient, which in turn saves farmers money and reduces the amount of food that is lost. This technology helps farmers conserve energy and time by evaluating data in actual time from sensors placed in crops and offering actionable infor.a.ion on how their crops are progressing. The data comes from the sensors themselves, which are planted in the crops. Data from the field is sent to the cloud and evaluated there so that procedures may be automated utilizing Internet of Things devices. The assessment of the farmer's contribution into the process of making choices is demonstrated with infor.a.ion regarding the temperature of the field, the soil moisture level, the humidity level, and the amount of water that is used. In addition, the technical knowledge presented here is valuable to producers at every stage of the production process, including planting, growing, harvesting, packaging and shipping.

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：