检索结果-内蒙古大学图书馆

Numerical approach to design of low frequency magnetic field irradiation system for lab on chip experiments

学校读者我要写书评

暂无评论

Numerical approach to design of low frequency magnetic field...

ELEKTRO

作者： Roman Radil Marek Bajtoš Lucia Č arnecká Klaudia Hargaš ová Patrik Kamencay Department of Electromagnetic and Biomedical Engineering University of Zilina Zilina Slovakia Department of Systems Biology and Engineering Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Dept. of Electromagnetic and Biomedical Engineering Organization University of Zilina Zilina Slovakia

ISBN: (数字)9781665467261

ISBN: (纸本)9781665467278

The article is focused on design of specific electromagnetic coil system using numerical modelling and simulation methods. The proposed solution would be capable of delivering magnetic field of desired strength/ flux density and homogeneity within the specific area to affect the cultivation process of single cells in lab on chip experiments.

关键词： Radiation effects Numerical models Magnetic fields Electromagnetics

A novel pipeline employing deep multi-attention channels network for the autonomous detection of metastasizing cells through fluorescence microscopy

学校读者我要写书评

暂无评论

Computers in Biology and Medicine 2024年 181卷 109052-109052页

作者： Mamalakis, Michail Macfarlane, Sarah C. Notley, Scott V. Gad, Annica K.B. Panoutsos, George School of Electrical and Electronic Engineering University of Sheffield Sheffield United Kingdom Insigneo Institute for in-silico Medicine University of Sheffield Sheffield United Kingdom Department of Infection Immunity and Cardiovascular Disease Department of Computer science Sheffield United Kingdom Department of Psychiatry Cambridge University Cambridge United Kingdom Department of Oncology and Metabolism The Medical School University of Sheffield Sheffield United Kingdom Department of Automatic Control and Systems Engineering University of Sheffield Sheffield United Kingdom Madeira Chemistry Research Centre University of Madeira Funchal Portugal Department of Oncology-Pathology Karolinska Institutet Stockholm Sweden

Metastasis driven by cancer cell migration is the leading cause of cancer-related deaths. It involves significant changes in the organization of the cytoskeleton, which includes the actin microfilaments and the vimentin intermediate filaments. Understanding how these filament change cells from normal to invasive offers insights that can be used to improve cancer diagnosis and therapy. We have developed a computational, transparent, large-scale and imaging-based pipeline, that can distinguish between normal human cells and their isogenically matched, oncogenically transformed, invasive and metastasizing counterparts, based on the spatial organization of actin and vimentin filaments in the cell cytoplasm. Due to the intricacy of these subcellular structures, manual annotation is not trivial to automate. We used established deep learning methods and our new multi-attention channel architecture. To ensure a high level of interpretability of the network, which is crucial for the application area, we developed an interpretable global explainable approach correlating the weighted geometric mean of the total cell images and their local GradCam scores. The methods offer detailed, objective and measurable understanding of how different components of the cytoskeleton contribute to metastasis, insights that can be used for future development of novel diagnostic tools, such as a nanometer level, vimentin filament-based biomarker for digital pathology, and for new treatments that significantly can increase patient survival. © 2024

关键词： Fluorescence microscopy

RANDOM COORDINATE DESCENT METHODS FOR NONSEPARABLE COMPOSITE OPTIMIZATION

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chorobura, Flavia Necoara, Ion Automatic Control and Systems Engineering Department University Politehnica Bucharest Bucharest060042 Romania Gheorghe Mihoc-Caius Iacob Institute of Mathematical Statistics and Applied Mathematics The Romanian Academy Bucharest050711 Romania

In this paper we consider large-scale composite optimization problems having the objective function formed as a sum of two terms (possibly nonconvex), one has (block) coordinate-wise Lipschitz continuous gradient and the other is differentiable but nonseparable. Under these general settings we derive and analyze two new coordinate descent methods. The first algorithm, referred to as coordinate proximal gradient method, considers the composite form of the objective function, while the other algorithm disregards the composite form of the objective and uses the partial gradient of the full objective, yielding a coordinate gradient descent scheme with novel adaptive stepsize rules. We prove that these new stepsize rules make the coordinate gradient scheme a descent method, provided that additional assumptions hold for the second term in the objective function. We present a complete worst-case complexity analysis for these two new methods in both, convex and nonconvex settings, provided that the (block) coordinates are chosen random or cyclic. Preliminary numerical results also confirm the efficiency of our two algorithms on practical problems. © 2022, CC BY.

关键词： Gradient methods

Concepts of Self-maintaining robots and their design

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Shi, Chenjie Veres, Sandor M. Department of Automatic Control and Systems Engineering University of Sheffield S1 3JD United Kingdom

— This paper proposes an initial theory for robotic systems that can be fully self-maintaining. The new design principles focus on functional survival of the robots over long periods of time without human maintenance. Self-maintaining semi-autonomous mobile robots are in great demand in nuclear disposal sites from where their removal for maintenance is undesirable due to their radioactive contamination. Similar are requirements for robots in various defence tasks or space missions. For optimal design, modular solutions are balanced against capabilities to replace smaller components in a robot by itself or by help from another robot. Modules are proposed for the basic platform, which enable self-maintenance within a team of robots helping each other. The primary method of self-maintenance is replacement of malfunctioning modules or components by the robots themselves. Replacement necessitates a robot team’s ability to diagnose and replace malfunctioning modules as needed. Due to their design, these robots still remain manually re-configurable if opportunity arises for human intervention. Apart from the basic principles, an evolutionary design approach is presented and a first mathematical theory of the reliability of a team of self-maintaining robots is introduced. © 2021, CC BY-NC-ND.

关键词： Reliability theory

Recursive Time-Sensor Domain Data Decomposition: A Novel Method for Time-Varying Process Monitoring

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Gui, Yufei Lang, Zi-Qiang Liu, Zepeng Laalej, Hatim Department of Automatic Control and Systems Engineering University of Sheffield SheffieldS10 2TN United Kingdom School of Engineering Newcastle University Newcastle upon TyneNE1 7RU United Kingdom Advanced Manufacturing Research Centre University of Sheffield SheffieldS10 2TN United Kingdom

Process monitoring aims to timely detect faults or abnormal conditions, ensuring safety and achieving satisfactory product quality. Time-varying processes are common in various industries, including chemical, semiconductor, and advanced manufacturing. A key challenge in time-varying process monitoring is how to accommodate deterministic but unknown time-varying trends in process responses. Existing multivariate statistical process monitoring (MSPM) approaches designed for time-varying processes face challenges including intensive computation and worse adaption to unknown process changes. In this study, a new process monitoring approach is proposed based on a novel idea referred to as recursive time-sensor decomposition (RTSD). The multi-sensor data are compressed into dominant time and sensor domain components. In the time domain, the feature vectors are extracted to represent process states. In the sensor domain, the process information distributed across different sensors is used to accommodate the normal time-varying trend and determine the control limit. The proposed approach is validated first by analysing a simulated time-varying process and then by an application of monitoring tool wear states in a real milling experiment. The results demonstrate that the proposed approach is highly effective, has higher fault detection rates and lower false alarm rates when compared to existing methods, and is applicable in a real time-varying industrial process. © 2024, The Authors. All rights reserved.

关键词： Process monitoring

Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xiao, Jiaren Dai, Quanyu Shen, Xiao Xie, Xiaochen Dai, Jing Lam, James Kwok, Ka-Wai Department of Mechanical Engineering The University of Hong Kong Hong Kong Department of Computing The Hong Kong Polytechnic University Hong Kong School of Computer Science and Technology Hainan University Haikou China Department of Automation Harbin Institute of Technology Shenzhen China Institute for Automatic Control and Complex Systems University of Duisburg-Essen Duisburg Germany

Label scarcity in a graph is frequently encountered in real-world applications due to the high cost of data labeling. To this end, semi-supervised domain adaptation (SSDA) on graphs aims to leverage the knowledge of a labeled source graph to aid in node classification on a target graph with limited labels. SSDA tasks need to overcome the domain gap between the source and target graphs. However, to date, this challenging research problem has yet to be formally considered by the existing approaches designed for cross-graph node classification. This paper proposes a novel method called SemiGCL to tackle the graph Semi-supervised domain adaptation with Graph Contrastive Learning and minimax entropy training. SemiGCL generates informative node representations by contrasting the representations learned from a graph’s local and global views. Additionally, SemiGCL is adversarially optimized with the entropy loss of unlabeled target nodes to reduce domain divergence. Experimental results on benchmark datasets demonstrate that SemiGCL outperforms the state-of-the-art baselines on the SSDA tasks. © 2023, CC BY-NC-ND.

关键词： Entropy

Recursive Time-Sensor Domain Data Decomposition: A Novel Method for Time-Varying Process Monitoring

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

关键词： Process monitoring

Power control of Cascaded Doubly Fed Induction Generator Integrated Into Wind Power Generation System Using Sliding Mode control

学校读者我要写书评

暂无评论

Power Control of Cascaded Doubly Fed Induction Generator Int...

Renewable Solutions for Ecosystems: Towards a Sustainable Energy Transition (ICRSEtoSET), International Conference on

作者： Ali Mazari Kouider Laroussi Amar Maafa Hamou Ait Abbas Abdelah Kouzou Billel Naceri Laboratory of The Applied and Automation and Industrial Diagnostic University Of Djelfa Djelfa Algeria Department of Electrical Engineering University Of Bouira Bouira Algeria Laboratory of Electrical and Automatic Systems Engineering (LGSEA) University of Bouira Bouira Algeria Laboratory of Identification Commande Control and Communication (LI3CUB) University of Biskra Biskra Algeria

ISBN: (数字)9798350346336

ISBN: (纸本)9798350346343

This paper aims to study the performance of combining two doubly fed induction generators (DFIG) without changing their design, therefore the benefit of eliminating the brushes. The sliding mode control (SMC) is used for controlling the active and reactive powers for the cascaded doubly fed induction generator (CDFIG) integrated into wind power generation system (WPGS). Additionally, the system incorporates a maximum power point tracking strategy (MPPT) to optimize energy generation and a pitch control mechanism for the wind turbine's blades to adjust to changing wind conditions.

关键词： Maximum power point trackers Wind energy generation Brushes Uncertainty Wind speed Power control Doubly fed induction generators

Robust learning via ensemble density propagation in deep neural networks

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Carannante, Giuseppina Dera, Dimah Rasool, Ghulam Bouaynaya, Nidhal C. Mihaylova, Lyudmila Rowan University Department of Electrical and Computer Engineering GlassboroNJ United States University of Sheffield Department of Automatic Control and Systems Engineering United Kingdom

Learning in uncertain, noisy, or adversarial environments is a challenging task for deep neural networks (DNNs). We propose a new theoretically grounded and efficient approach for robust learning that builds upon Bayesian estimation and Variational Inference. We formulate the problem of density propagation through layers of a DNN and solve it using an Ensemble Density Propagation (EnDP) scheme. The EnDP approach allows us to propagate moments of the variational probability distribution across the layers of a Bayesian DNN, enabling the estimation of the mean and covariance of the predictive distribution at the output of the model. Our experiments using MNIST and CIFAR-10 datasets show a significant improvement in the robustness of the trained models to random noise and adversarial attacks. © 2021, CC BY.

关键词： Deep neural networks