Dit proefschrift is goedgekeurd door de promotor(en): This work was carried out in graduate school ASCI. ASCI dissertation series number 39. This thesis presents image restoration techniques for applications in (confocal) fluorescence microscopy. We have gained a better understanding of the behavior of non-linear image restoration algorithms and we have developed novel methods to improve their performance in such a way that more accurate measurements can be performed on three-dimensional fluorescence images. In this first chapter we introduce the principles of fluorescence microscopy and discuss the properties of the three-dimensional image formation in a fluorescence microscope. An image is blurred and distorted by noise during its formation and acquisition. These distortions hide fine details in the image hampering both the visual and the quantitative analysis of the image. The purpose of image restoration is to invert this and to suppress the noise restoring the fine details in the image which results in an improved analysis of the image. The principles of image restoration are discussed in the second part of this chapter. We give an overview of various restoration techniques used in fluorescence microscopy. We discuss the influence of regularization and the background on the performance of non-linear image restoration algorithms. Since the invention of the first compound light microscope by Zacharias Jansen in 1595 (Jones, 1995), the instrument has evolved enormously. The modern light microscope is a versatile instrument for microscopic analysis. The construction of the first epi-illuminated fluorescence microscope by Ploem (Ploem, 1967), made the light microscope a useful instrument for fluorescence microscopy. In epi-illumination, the illumination of the sample and the detection of its emitted fluorescence light are done using the same objective lens (Figure 1.1). This strongly reduces the penetration of illumination light in the detection light path, which makes the detection of the weak fluorescence light feasible 1. light source sample plane of focus dichroic mirror epi-illumination objective C CD camera out of focus light Figure 1.1 Schematic diagram of a conventional wide-field fluorescence microscope showing its inability of to discriminate the out-of-focus light from the in-focus light. A strong characteristic of the epi-fluorescence microscope is its wide-field illumination, which enables the simultaneous imaging of the entire focal plane. Modern scientific grade fluorescence microscopes are excellent tools for acquiring microscopic images of two-dimensional samples with a discriminating power of well below one micrometer. The performance of a wide-field microscope in acquiring three-dimensional data is not …

/pdf/image-restoration-in-fluorescence-microscopy-5gtsszmlg9.pdf

Image Restoration in Fluorescence Microscopy

In the design of a controller for mobile robot, there are only few results on the problem of integrating the nonholonomic kinematic controller and the dynamic controller for mobile robots. Also there are only few literatures on the robustness of the controller in the presence of uncertainties or external disturbances in the dynamical model of mobile robot. In this paper, a robust adaptive controller which can achieve velocity tracking while considering not only kinematic model but also dynamic model of mobile robot is proposed. The proposed controller can overcome model uncertainty or external disturbances by the robust adaptive technique. The stability of the dynamic system is shown through the Lyapunov method.

Design of a robust adaptive controller for a mobile robot

To improve the functionality and efficiency of electric vehicles (EVs), the smart battery management system (BMS) is essential. The accurate estimation of the state of health (SOH) and remaining useful life (RUL) in BMS enhance battery safety, longevity, and reliability, which enhances EV performance and efficiency. However, the accurate estimation of SOH and RUL is challenging because of capacity degradation during charging and discharging operations. The conventional research to estimate the SOH and RUL of lithium-ion battery (LIB) is based on the single model framework. However, the single model for SOH and RUL estimation may not deliver accurate outcomes due to the complex internal LIB mechanism and varying external conditions. In recent times, the application of expert hybrid techniques (combining two or more models) has drawn huge attention from the research community due to their high accuracy and robustness under varying environmental conditions. Nonetheless, the implementation of hybrid techniques for SOH and RUL estimation for BMS in EVs is currently limited. Therefore, the originality of this work is to provide a thorough review of hybrid methods for SOH and RUL estimation in LIB with an emphasis on methodologies, executions, advantages, disadvantages, accuracy, and contributions. Additionally, the co-estimation of SOH and RUL utilizing the same model is gaining global popularity among researchers. Henceforth, the presented review work also investigates various techniques utilized to co-estimate the SOH and RUL simultaneously. Furthermore, some critical operation factors associated with SOH and RUL estimation framework are analyzed related to the dataset, model execution, battery parameters and their features. The applicability of the reviewed hybrid SOH and RUL estimation techniques are discussed along with current issues and limitations. Lastly, selected future suggestions are provided to guide the automobile sector to develop a reliable and accurate framework utilizing the hybrid and co-estimation framework to estimate the SOH and RUL in LIB. 

A Review of Expert Hybrid and Co-Estimation Techniques for SOH and RUL Estimation in Battery Management System with Electric Vehicle Application

The imperative to address traditional energy crises and environmental concerns has accelerated the need for energy structure transformation. However, the variable nature of renewable energy poses challenges in meeting complex practical energy requirements. To address this issue, the construction of a multifunctional large-scale stationary energy storage system is considered an effective solution. This paper critically examines the battery and hydrogen hybrid energy storage systems. Both technologies face limitations hindering them from fully meeting future energy storage needs, such as large storage capacity in limited space, frequent storage with rapid response, and continuous storage without loss. Batteries, with their rapid response (<1 s) and high efficiency (>90 %), excel in frequent short-duration energy storage. However, limitations such as a self-discharge rate (>1 %) and capacity loss (∼20 %) restrict their use for long-duration energy storage. Hydrogen, as a potential energy carrier, is suitable for large-scale, long-duration energy storage due to its high energy density, steady state, and low loss. Nevertheless, it is less efficient for frequent energy storage due to its low storage efficiency (∼50 %). Ongoing research suggests that a battery and hydrogen hybrid energy storage system could combine the strengths of both technologies to meet the growing demand for large-scale, long-duration energy storage. To assess their applied potentials, this paper provides a detailed analysis of the research status of both energy storage technologies using proposed key performance indices. Additionally, application-oriented future directions and challenges of the battery and hydrogen hybrid energy storage system are outlined from multiple perspectives, offering guidance for the development of advanced energy storage systems. 

An overview of application-oriented multifunctional large-scale stationary battery and hydrogen hybrid energy storage system

Recent studies show that artificial intelligence (AI), such as machine learning and deep learning, models can be adopted and have advantages in fault detection and diagnosis for building energy systems. This paper aims to conduct a comprehensive and systematic literature review on fault detection and diagnosis (FDD) methods for heating, ventilation, and air conditioning (HVAC) systems. This review covers the period from 2013 to 2023 to identify and analyze the existing research in this field. Our work concentrates explicitly on synthesizing AI-based FDD techniques, particularly summarizing these methods and offering a comprehensive classification. First, we discuss the challenges while developing FDD methods for HVAC systems. Next, we classify AI-based FDD methods into three categories: those based on traditional machine learning, deep learning, and hybrid AI models. Additionally, we also examine physical model-based methods to compare them with AI-based methods. The analysis concludes that AI-based HVAC FDD, despite its higher accuracy and reduced reliance on expert knowledge, has garnered considerable research interest compared to physics-based methods. However, it still encounters difficulties in dynamic and time-varying environments and achieving FDD resolution. Addressing these challenges is essential to facilitate the widespread adoption of AI-based FDD in HVAC. 

AI in HVAC fault detection and diagnosis: A systematic review

Segmentation and other image processing operations rely on convolution calculations with heavy computational and memory access demands. The article presents an analysis of a texture segmentation application containing a 96/spl times/96 convolution. Sequential execution required several hours an single processor systems with over 99% of the time spent performing the large convolution. 70% to 75% of execution time is attributable to cache misses within the convolution. We implemented the same application on CM-5, iPSC/860 and PVM distributed memory multicomputers, tailoring the parallel algorithms to each machine's architecture. Parallelization significantly reduced execution time, taking 49 seconds on a 512 node CM-5 and 6.5 minutes on a 32 node iPSC/860. The results indicate for large kernel convolutions the size and bandwidth of the fast memory store is more important than processor power or communication overhead. >

Communication and computation patterns of large scale image convolutions on parallel architectures

State of health (SOH) is crucial to battery management system. However, SOH accuracy and reliability is difficult to be guaranteed owing to complex ageing mechanisms and driving conditions. This paper proposes a novel battery SOH prediction method based on gated recurrent unit (GRU) neural network for real-world vehicles. Firstly, real-vehicle operating data is extracted as well as cleaned and sliced to improve data reliability, then the Kalman filter and recursive least squares method are used to identify the ohmic internal resistance (OIR). The GRU neural network is established to realize the battery SOH prediction, and the average relative error of final validation set is less than 0.65 %. To further validate the reliability and applicability of the prediction method, four other vehicles data are set as input, and the SOH results indicate that all average relative errors are still within 4 %. This study demonstrates the feasibility of using OIR as a health factor for real-world vehicles, and also provides a new solution for accurately predicting battery SOH for real-world vehicles. 

A novel state of health prediction method for battery system in real-world vehicles based on gated recurrent unit neural networks

The development of new energy industry is an essential guarantee for the sustainable development of society, and big data technology can enable new energy industrialization. Firstly, this paper presents an in-depth analysis and discussion of big data technology in new energy power and energy storage systems. Furthermore, the current status of big data technology application is discussed based on power generation, grid and user side, while future development trends are proposed based on the characteristics of big data technology. Finally, a comprehensive cloud-platform-based new energy power and energy storage system is proposed, which efficiently combines new energy power generation, consumption, and transmission sides to optimize energy allocation and improve energy utilization efficiency. This paper aims to provide certain guidance significance for new energy research and application. 

Research progress, trends and prospects of big data technology for new energy power and energy storage system

Machine learning-based state of health prediction for battery systems in real-world electric vehicles

Battery state-of-charge (SOC) is an evaluation metric for the electric vehicles' remaining driving range and one of the main monitoring parameters for battery management systems. However, there are rarely data-driven studies on multi-step prediction of battery SOC, which cannot accurately provide and realize electric vehicle remaining driving range prediction and SOC safety pre-warning. Therefore, this study aims to perform SOC multi-forward-step prediction for real-world vehicle battery system by a novel hybrid long short-term memory and gate recurrent unit (LSTM-GRU) neural network. The paper firstly analyses the characteristics of correlation analysis and adopts similarity metric method to reduce the parameter dimensionality for the input neural network. Then the advantages between LSTM-GRU, LSTM, GRU, and long short-term memory and convolutional neural network (LSTM-CNN) are analyzed by comparing experimental and real-world vehicle data, and the effectiveness and accuracy of the proposed method is demonstrated. In addition, the proposed method robustness is verified by adding noise data to the input parameters. In this study, the prediction results were validated with real-world vehicle data in spring, summer, autumn and winter, and the proposed method achieved a minimum MAPE and MAE of 1.03% and 0.73 for summer conditions, while the minimum standard deviation of prediction was 0.06% for experimental conditions. The research process shows that the method has high accuracy when applied to large data and is expected to be applied to real-world vehicle battery system SOC multi-forward-step prediction in the future. 

Multi- forword-step state of charge prediction for real-world electric vehicles battery systems using a novel LSTM-GRU hybrid neural network

Handle everyday research tasks with reliable, citation-backed results

Your personal Research Agent to handle research tasks with citation-backed results

Popular Tasks used by Researchers

How can I help with your research?

Meet SciSpace

Get more enhanced response by uploading the PDFs you want me to reference.

No relevant PDFs in your library

SciSpace is the AI research assistant for academics. Run systematic literature reviews on 280M+ papers, and write papers with cited sources. Trusted by 1M+ students, PhDs & researchers.

SciSpace | AI for Research

Analyze PDFs

Code & Manuscripts

Funding & Grants

Literature & Patents

Medical & Clinical Data

Systematic Review

Visualize & Present

Web & Data

Build a Google Scholar-like website for your research.

Build a website

Create charts and images for your research

Create a Chart

Write a paper for submission to a journal

Draft a manuscript

Patent Search

Design eye-catching scientific posters in minutes.

Scientific Poster Generation

Systematic Literature Review

One task is running at the moment. Your messages will be shown right after.

Drag and drop or click here to browse

Loved by <highlight>1 million+</highlight> researchers

Extract a list of specific topics and their sources from unstructured text

Topics

Compare and analyze relevant papers that matches with your search

Papers

Get insights from PDFs and bookmarked papers from your library

My library

Recent searches

Try searching for:

Catch AI-generated content in scholarly and non-scholarly content

{ai} Detector

Ai Writer

Get PDF Summaries, highlighted text explanations 

Chat with PDF

Effortlessly create in-text citations and bibliographies in APA and 2,500 other formats

Citation generator

Get explanations, summaries, and answers on academic papers

Ease up your research workflow with {scispace}'s cohort of exciting AI tools

Elevate your academic writing skills and convey your ideas the way you want

Paraphraser

Explore our range of reading and writing tools

Your file is being prepared and should be ready in a few minutes. If it's a large file, it might take a bit longer. You can close this window, and we'll email you the file when it's done.

You have reached a maximum limit of <strong>{limit}</strong> columns in the table. Remove at least <strong>1</strong> column to add or create another one.

Haixu Yang

Author Tools

Chat about Author