检索结果-内蒙古大学图书馆

31st European Signal Processing Conference, EUSIPCO 2023

作者： Koldovský, Zbyněk Čmejla, Jaroslav Adali, Tülay O'Regan, Stephen Acoustic Signal Analysis and Processing Group Faculty of Mechatronics Informatics and Interdisciplinary Studies Technical University of Liberec Czech Republic Department of Electrical and Computer Engineering University of Maryland Baltimore County BaltimoreMD21250 United States Naval Surface Warfare Center Carderock Division West BethesdaMD United States

ISBN: (纸本)9789464593600

Independent Vector Analysis (IVA) is a popular extension of Independent Component Analysis (ICA) for joint separation of a set of instantaneous linear mixtures, with a direct application in frequency-domain speaker separation or extraction. The mixtures are parameterized by mixing matrices, one matrix per mixture. This means that the IVA mixing model does not account for any relationships between parameters across the mixtures/frequencies. The separation proceeds jointly only through the source model, where statistical dependencies of sources across the mixtures are taken into account. In this paper, we propose a mixing model for joint blind source extraction where the mixing model parameters are linked across the frequencies. This is achieved by constraining the set of feasible parameters to the manifold of half-length separating filters, which has a clear interpretation and application in frequency-domain speaker extraction. © 2023 European Signal Processing Conference, EUSIPCO. All rights reserved.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Agro-vision IoT-enabled Crop Pest Recognition System based on VGG-16 2

Agro-vision IoT-enabled Crop Pest Recognition System based o...

引用

2nd International Conference on Multidisciplinary engineering and Applied Science, ICMEAS 2023

作者： Udeogu, Chigozie Uzochukwu Nwakanma, Cosmas Ifeanyi Ayoade, Idowu Adetona Amadi, Chimeremma Sandra Eze, Udoka Felista University of Maryland Electrical Computer Engineering College ParkMD United States Kumoh National Institute of Technology ICT Convergence Research Center Gumi Korea Republic of First Technical University Mechatronics Engineering Ibadan Nigeria Federal University of Technology Information Technology Owerri Nigeria

ISBN: (纸本)9798350358834

It is more difficult to implement recognition of crop pests in the field than the generic object recognition task because of the high variation among crop pest species which usually leads to the misclassification of crop pests from the same class. Furthermore, in deploying these recognition systems to the field, intensive hardware setups are mostly used. To improve the recognition accuracy, this paper proposes an IoT-enabled crop pest recognition system (CPRS) that utilizes Visual Geometry Group (VGG-16) which uses the multi-level learning features obtained from pest images for the automatic classification of crop pests. The Accuracy result of 88.72% obtained validates the reliability and robustness of the proposed method as capable of detecting the presence of pests in different leaf image samples. © 2023 IEEE.

关键词： Crops

来源：评论

学校读者我要写书评

暂无评论

Efficient COVID-19 detection using data mining algorithms: a comparison of basic and hybrid approaches

引用

Soft Computing 2025年第3期29卷 1437-1451页

作者： Saidi, Mohammad Gheibi, Mohammad Ghazikhani, Adel Lotfata, Aynaz Chahkandi, Benyamin Familsamavati, Sajad Behzadian, Kourosh Department of Computer Science Imam Reza International University Mashhad Iran MS of Software Engineering Information and Communication Technology Unit Mashhad Municipality Fire and Safety Services Organization Mashhad Iran Big Data Lab Imam Reza International University Mashhad Iran Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Liberec46117 Czech Republic Tallinn10615 Estonia Department of Pathology Microbiology and Immunology School of Veterinary Medicine University of California Davis95616 United States Department of Urban and Regional Planning San Jose State University San Jose95192 United States Faculty of Civil and Environmental Engineering Gdansk University of Technology Narutowicza Street 11/12 80-233 Gdansk Poland Tecnologico de Monterrey Escuela de Ingeniería y Ciencias Monterrey Mexico School of Computing and Engineering University of West London London United Kingdom

Accurate and efficient diagnosis of COVID-19 remains a significant challenge due to the limitations of current detection methods, such as blood tests and chest scans, which can be time-consuming and error-prone. This study aims to compare the performance of basic and hybrid data mining algorithms in diagnosing COVID-19, using blood test results and clinical information to identify the most effective approach. A dataset of 200 records from suspected and infected COVID-19 patients, with 23 characteristics and one diagnostic class, was analysed. Nine data mining algorithms were tested: four basic algorithms (Naive Bayes, Support Vector Machine, Decision Tree, K-Nearest Neighbor) and five hybrid algorithms (Random Forest, AdaBoost, Majority Voting, XGBoost, Bagging). The study also integrated Response Surface Methodology (RSM) and Adaptive-Network-based Fuzzy Inference System (ANFIS) to enhance model performance. The Bagging algorithm demonstrated superior performance with an accuracy of 88%, sensitivity of 74%, and F-criterion of 78%. The integration of RSM and ANFIS further showed that a smart model could be developed for efficient pandemic crisis management, achieving up to 100% accuracy when considering key factors like AST, Albumin, and CRP. The findings suggest that Bagging and hybrid data mining algorithms can significantly improve COVID-19 detection, reducing time and errors in identifying exposed individuals. The study highlights the potential of combining machine learning techniques with RSM-ANFIS models for effective pandemic management and decision-making in medical settings. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Survey on LED lamps for residential applications: characterization of performance

Survey on LED lamps for residential applications: characteri...

引用

International Scientific Conference on Electric Power engineering (EPE)

作者： Tomáš Hudač Jiri Drapela Leoš Kukačka Jan Meyer Robert Stiegler Dept. of Electrical Power Engineering Faculty of Elect. Eng. and Communication Brno University of Technology Brno Czech Republic Institute of Mechatronics and Computer Engineering Technical University of Liberec Liberec Czech Republic Institute of Electrical Power Systems and High Voltage Engineering Technische Universität Dresden Dresden Germany

Aim of the paper is to conduct a survey of the present market, focusing on the best-selling retrofit LED lamps and to analyze experimentally their fundamental EMC performance for subsequent classification of the LED drivers. Two stage experimental characterization testing approach is adopted. First, input current and output luminous flux in steady-state under nominal supply conditions is acquired. Next, transfer of input supply voltage interharmonics to output visible flicker components in terms of gain factor curves is obtained. Based on the achieved and discussed testing results, classification of the LED lamps is developed.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ultra-high speed holographic shape and displacement measurements in the hearing sciences

引用

Light(Advanced Manufacturing) 2022年第2期3卷 1-14页

作者： Haimi Tang Pavel Psota John J.Rosowski Cosme Furlong Jeffrey Tao Cheng Center for Holographic Studies and Laser micro-mechaTronics Worcester Polytechnic InstituteWorcesterMA USA01609 Mechanical Engineering Department Worcester Polytechnic InstituteWorcesterMA USA01609 Faculty of Mechatronics Informatics and Interdisciplinary StudiesTechnical University of LiberecLiberecCzech Republic46117 Eaton-Peabody Laboratory Massachusetts Eye and EarBostonMA USA02114 Department of Otolaryngology-Head and Neck Surgery Harvard Medical SchoolBostonMAUSA02115

The auditory system of mammals enables the perception of sound from our surrounding *** some of the smallest bones in the body,the ear transduces complex acoustic signals with high-temporal sensitivity to complex mechanical vibrations with magnitudes as small as tens of *** of the shape and acoustically induced motions of different components of the ear are essential if we are to expand our understanding of hearing mechanisms,and also provide quantitative information for the development of numerical ear models that can be used to improve hearing protection,clinical diagnosis,and repair of damaged or diseased *** are developing digital holographic methods and instrumentation using an ultra-high speed camera to measure shape and acoustically-induced motions in the middle *** we study the eardrum,the first structure of the middle ear which initializes the acoustic-mechanical transduction of sound for *** measurement system is capable of performing holographic measurement at rates up to 2.1 M frames per *** shape measurement modalities had previously been implemented into our holographic systems:(1)a multi-wavelength method with a wavelength tunable laser;and(2)a multi-angle illumination method with a single wavelength *** this paper,we present a third method using a miniaturized fringe projection system with a microelectromechanical system(MEMS)***,we optimize the processing of large data sets of holographic displacement measurements using a vectorized Pearson's correlation *** validate and compare the shape and displacement measurements of our methodologies using a National institute of Standards and Technology(NIST)traceable gauge and sound-activated latex membranes and human eardrums.

关键词： Ultra-high speed digital holography Microelectromechanical systems(MEMS) Miniaturized Fringe Projection Middle-ear mechanics Shape and displacement measurements.

来源：评论

学校读者我要写书评

暂无评论

Curvature-Controlled Polarization in Adaptive Ferroelectric Membranes

arXiv

引用

arXiv 2025年

作者： Segantini, Greta Tovaglieri, Ludovica Roh, Chang Jae Hsu, Chih-Ying Cho, Seongwoo Bulanadi, Ralph Ondrejkovic, Petr Marton, Pavel Hlinka, Jirka Gariglio, Stefano Alexander, Duncan T.L. Paruch, Patrycja Triscone, Jean-Marc Lichtensteiger, Céline Caviglia, Andrea D. Department of Quantum Matter Physics University of Geneva 24 Quai Ernest-Ansermet Geneva 4CH-1211 Switzerland LausanneCH-1015 Switzerland Institute of Physics Czech Academy of Sciences Na Slovance 2 Praha 8182 00 Czech Republic Institute of Mechatronics and Computer Engineering Technical University of Liberec Studentska 2 Liberec46117 Czech Republic

In this study, we explore the ferroelectric domain structure and mechanical properties of PbTiO3-based membranes, which develops a well-ordered and crystallographic-oriented ripple pattern upon release from their growth substrate. The ferrolectric domain structure of the PbTiO3 layer was examined at various length scales using optical second harmonic generation, piezoresponse force microscopy, and scanning transmission electron microscopy. These methods reveal the presence of purely in-plane domains organized into superdomains at the crest of the ripples, while an in-plane/out-of-plane domain structure was observed in the flat regions separating the ripples, in agreement with phase-field simulations. The mechanical properties of the membrane were assessed using contact resonance force microscopy, which identified distinct mechanical behaviors at the ripples compared to the flat regions. This study shows that the physical properties of the ferroelectric layer in membranes can be locally controlled within an ordered array of ripples, with well-defined geometric characteristics. © 2025, CC BY.

关键词： Ferroelectricity

来源：评论

学校读者我要写书评

暂无评论

Optimizing droplet coalescence dynamics in microchannels: A comprehensive study using response surface methodology and machine learning algorithms

引用

Heliyon 2025年第1期11卷 e41510页

作者： Javadpour, Seyed Morteza Kadivar, Erfan Zarneh, Zienab Heidary Kadivar, Ebrahim Gheibi, Mohammad Department of Mechanical Engineering University of Gonabad Gonabad Iran Department of Physics Shiraz University of Technology Shiraz 71555-313 Iran Institute of Ship Technology Ocean Engineering and Transport Systems University of Duisburg-Essen Duisburg 47057 Germany Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Liberec 46117 Czech Republic Faculty of Mechatronics Informatics and Interdisciplinary Studies Technical University of Liberec Liberec Czech Republic Faculty of Mechanical Engineering Tarbiat Modares University Tehran 141171-3116 Iran

Droplet coalescence in microchannels is a complex phenomenon influenced by various parameters such as droplet size, velocity, liquid surface tension, and droplet-droplet spacing. In this study, we thoroughly investigate the impact of these control parameters on droplet coalescence dynamics within a sudden expansion microchannel using two distinct numerical methods. Initially, we employ the boundary element method to solve the Brinkman integral equation, providing detailed insights into the underlying physics of droplet coalescence. Furthermore, we integrate Response Surface Methodology (RSM) to effectively optimize droplet coalescence dynamics, harnessing the power of machine learning algorithms. Our results showcase the efficacy of these computational techniques in enhancing experimental efficiency. Through rigorous evaluation utilizing Regression Coefficient and Mean Absolute Error metrics, we ascertain the accuracy of our estimations. Our findings highlight the significant influence of key parameters, specifically the non-dimensional initial distance of the droplets (D), viscosity ratio (μ), Capillary number (Ca), and width (w), as identified by the non-dimensional final droplet-droplet spacing (DD), velocity of the first droplet (V_FD), and velocity of the second droplet (V_BD), respectively. This comprehensive approach provides valuable insights into droplet coalescence phenomena and offers a robust framework for optimizing microfluidic systems. The most influential parameters on DD are the values of A_d and D, while viscosity has the lowest influence on DD. The most influential parameters on droplet velocity are viscosity and channel width, whereas the initial distance and Ca have the least influence on droplet velocity. The comparison of different machine learning algorithms indicates that the best ones for predicting DD, V_FD, and V_BD are function, SMOreg, Lazy-IBK, and Meta-Bagging, respectively. © 2025 The

关键词： Coalescence Droplet Machine learning Microchannel Optimization

来源：评论

学校读者我要写书评

暂无评论

Cloud-Connected Wearable Devices for Lone Worker Protection With Wireless Sensor Networks 4

Cloud-Connected Wearable Devices for Lone Worker Protection ...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Mohankumar, N. Manivannan, K.K. Babu, A. Ramesh Sampoornam, M. Maria Kovarasan, Rajesh Kambattan Srinivasan, C. Nagpur Campus Maharashtra Pune India Kcg College of Technology Department of Mechatronics Engineering Tamil Nadu Chennai India School of Computer Applications Vidya Vikas Institute of Engineering and Technology Karnataka Mysore India J.J College of Engineering and Technology Department of Information Technology Tamil Nadu Tiruchirappalli India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331540364

Various sectors continue to prioritize lone worker safety, which requires creative ways to provide quick support and monitoring. To safeguard lone workers, this paper introduces a new method that makes use of cloud-connected wearable devices that are coupled with Wireless Sensor Networks (WSNs). The system design relies on sensors embedded in wearable devices that can monitor a range of environmental elements as well as the vital signs of workers. A central cloud platform receives data in real-time via wireless communication from these devices and processes and analyzes it. The system may detect possible dangers or crises using smart techniques and immediately notify those who are supposed to react or the proper authorities. Cloud computing also makes it easy to store, analyze, and monitor large amounts of data over time, which is great for doing proactive risk assessments and improving safety standards. It demonstrates solution's capacity to improve lone worker safety, reduce reaction times, and mitigate hazards via simulations and actual deployment scenarios, efficacy and dependability. This growing body of knowledge on how to protect lone workers in various workplaces by using the power of IoT and cloud computing. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Digital Volume Correlation Analysis of Paraphysiological Deformation of Whole Human Bones Using Symmetric Normalization Registration Method

SSRN

引用

SSRN 2024年

作者： Martelli, Saulo Henyš, Petr Dall'Ara, Enrico Institute of New Technologies and Applied Informatics Faculty of Mechatronics Informatics and Interdisciplinary Studies Technical University of Liberec Liberec Czech Republic Department of Oncology and Metabolism INSIGNEO Institute for In Silico Medicine University of Sheffield Sheffield United Kingdom School of Mechanical Medical and Process Engineering Queensland University of Technology BrisbaneQLD Australia

This study examines how well the Symmetric Normalization (SyN) algorithm analyses human bone deformation. We compare SyN to BoneDVC, a standard bone deformation analysis method. We assess their ability to control image noise and predict synthetic bone deformation across different strain levels. Additionally, we compare SyN and BoneDVC in measuring displacement and strain in actual images of a femur bone under subcritical deformation levels. Our findings show that accuracy increases with higher smoothing (SyN) or nodal spacing (BoneDVC) but decreases at higher deformation gradients. SyN and BoneDVC perform similarly in terms of overall accuracy, but SyN might be better for low-quality images and detecting localized deformation, though with potentially higher peak errors. Image quality and expected deformation should guide the choice and calibration of image registration methods. © 2024, The Authors. All rights reserved.

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

An epidemiological model of SIR in a nanotechnological innovation environment

引用

Heliyon 2025年第3期11卷 e42309页

作者： Svoboda, David Havelka, Ondřej Holendová, Julie Kraft, Jiří Faculty of Economics Technical University of Liberec Voroněžská 13 Liberec 460 01 Czech Republic Institute for Nanomaterials Advanced Technologies and Innovation Technical University of Liberec Studentská 1402/2 Liberec 461 17 Czech Republic Faculty of Mechatronics Informatics and Interdisciplinary Studies Technical University of Liberec Studentská 1402/2 Liberec 461 17 Czech Republic Zittau Görlitz University of Applied Sciences Faculty of Business Administration and Industrial Engineering Theodor-Körner-Allee 16 Zittau 02763 Germany

Today, when nanotechnological innovation, in particular, faces stringent regulations, the question arises concerning a tool that can quantify individual interventions and thus complement current knowledge in the diffusion theory of innovation. This paper examines the complex nature of innovation diffusion in a rapidly evolving technological environment. The research presents current knowledge in the field linking diffusion of innovation theory and the basic epidemiological model of SIR (Susceptible, Infected, Recovered). Epidemiological models, originally developed to study the spread of infectious diseases, offer intriguing parallels to innovation diffusion due to shared characteristics in propagation dynamics. Integrating the SIR epidemiological model into the current theoretical framework allows the SIR model to be considered as a tool capable of filling current gaps in the literature. Nanotechnological innovations are chosen because of their significant impact on society, which faces unique market entry challenges. Within the framework of high interdisciplinarity, nanotechnologies, like viruses, tend to 'mutate' into different industries where their 'infectivity' varies. The case of nanotechnology serves to illustrate the usefulness of the proposed model and shows how factors that influence the spread of viruses can similarly affect the adoption of technological innovations. Similar characteristics in the propagation framework between innovations and viruses can serve as one of many arguments for the use of the SIR model in this field. Using an integrative review, aspects that have the potential to add to the SIR model in the current literature are identified. By combining epidemiological findings with innovation theory, the paper contributes to a richer and more integrated understanding of the phenomena of diffusion of nanotechnological innovations. The motivation is to open a debate regarding the ability of the epidemiological model of SIR to reveal the impact

关键词： Bass model Diffusion of innovation Nanotechnology SIR model

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：