Islanded microgrids (IMGs) provide a promising solution for reliable and environmentally friendly energy supply to remote areas and off-grid systems. However, the operation management of IMGs is a ...complex task including the coordination of a variety of distributed energy resources and loads with an intermittent nature in an efficient, stable, reliable, robust, resilient, and self-sufficient manner. In this regard, the energy management system (EMS) of IMGs has been attracting considerable attention during the last years, especially from the economic and emissions point of view. This paper provides an in-depth overview of the EMS optimization problem of IMGs by systematically analyzing the most representative studies. According to the state-of-the-art, the optimization of energy management of IMGs has six main aspects, including framework, time-frame, uncertainty handling approach, optimizer, objective function, and constraints. Each of these aspects is discussed in detail and an up-to-date overview of the existing EMSs for IMGs and future trends is provided. The future trends include the need for improved models, advanced data analytic and forecasting techniques, performance assessment of real-time EMSs in the whole MG’s control hierarchy, fully effective decentralized EMSs, improved communication and cyber security systems, and validations under real conditions. Besides, a comprehensive overview of the widely-used heuristic optimization methods and their application in EMSs of IMGs as well as their advantages and disadvantages are given. It is hoped that this study presents a solid starting point for future researches to improve the EMS of IMGs.
•The six aspects of the energy management system optimization of islanded microgrids.•Overview of heuristic algorithms for EMS optimization problem.•EMS optimization frameworks and uncertainty schemes: Deterministic, stochastic, robust.•Reviewing constraints, cost functions, and time-frames for EMS optimization problem.•Introducing the future trends in energy management system of islanded microgrids.
•A closed formula for the fractional derivation based on Gaussian function.•Analysed expression is based on Caputo–Fabrizio definition.•Gaussian based derivatives are applied on practical signal ...processing problems.•Convolution properties increase applicability of Gaussian based derivatives.•Gaussian parameters give additional customising to fractional filter design.
The Gaussian function has been employed in a vast number of practical and theoretical applications since it was proposed. Likewise, Gaussian function and its ordinary derivatives are considered as powerful tools for signal processing and control applications, e.g., smoothing, sampling, change detection, blob detection, and transforms based on the Hermite polynomials. Nonetheless, it has impressive characteristics hidden amongst its fractional derivatives eager to be explored and studied in-depth. This work proposes a closed formula for the (n+ν)–order fractional derivative of the Gaussian function, based on the Caputo–Fabrizio definition, as an approach for analysing those attributes. The obtained expression was numerically tested with several fractional orders, and their resulting behaviours were eventually analysed. Finally, three practical applications on signal processing via this closed formula were discussed, i.e., customisable wavelets, image processing filters, and Rayleigh distributions.
Brain tumor segmentation is a routine process in a clinical setting and provides useful information for diagnosis and treatment planning. Manual segmentation, performed by physicians or radiologists, ...is a time-consuming task due to the large quantity of medical data generated presently. Hence, automatic segmentation methods are needed, and several approaches have been introduced in recent years including the Localized Region-based Active Contour Model (LRACM). There are many popular LRACM, but each of them presents strong and weak points. In this paper, the automatic selection of LRACM based on image content and its application on brain tumor segmentation is presented. Thereby, a framework to select one of three LRACM, i.e., Local Gaussian Distribution Fitting (LGDF), localized Chan-Vese (C-V) and Localized Active Contour Model with Background Intensity Compensation (LACM-BIC), is proposed. Twelve visual features are extracted to properly select the method that may process a given input image. The system is based on a supervised approach. Applied specifically to Magnetic Resonance Imaging (MRI) images, the experiments showed that the proposed system is able to correctly select the suitable LRACM to handle a specific image. Consequently, the selection framework achieves better accuracy performance than the three LRACM separately.
Display omitted
•Automatic selection of the Localized Region-based Active Contour Model (LRACM).•Statistical moment-based features as image descriptors.•Automatic Brain tumor segmentation framework.•LRACM performance depends on the image content.•Fast and reliable MRI data analysis.
This paper presents a Localized Active Contour Model (LACM) integrating an additional step of background intensity compensation. The region-based active contour models that use statistical intensity ...information are more sensitive to the high mean intensity distance between consecutive regions. In Magnetic Resonance Imaging (MRI) this distance is great between the foreground and the background, hence it leads to an incorrect delineation of the target. In order to resolve this problem, an automatic process is introduced in our model for balancing the mean intensity distance between an image foreground and its background. The aim is to minimize the attraction effect of the active contour model to the undesired borderlines defined by these two mentioned image regions. By using this approach not only the obtained accuracy outperforms the traditional localized mean separation active contour model, but also it reduces the computation time of the segmentation task. In addition, this method was efficiently applied on automatic brain tumor segmentation in multimodal MRI data. The Hierarchical Centroid Shape Descriptor (HCSD) was used for detecting the region of interest i.e. abnormal tissue so as to automatically initialize the active contour. The validation of experiments was carried out on synthetic images and the quantitative evaluation was performed on the BRATS2012 database. Finally, the accuracy achieved by the proposed method was compared to the localized mean separation intensity, the localized Chan-Vese, the local Gaussian distribution fitting and the local binary fitting models by using the Dice coefficient, Sensitivity, Specificity and the Hausdorff distance. The computation time of the methods was also measured for comparison purposes. The obtained results show that the proposed model outperforms the accuracy of the selected state of the art methods. Moreover, it is also faster than the comparative methods in the medical image segmentation task.
Despite advances in Deep Learning, the Convolutional Neural Networks methods still manifest limitations in medical applications because datasets are usually restricted in the number of samples or ...include poorly contrasted images. Such a case is found in stenosis detection using X-rays coronary angiography. In this study, the emerging field of quantum computing is applied in the context of hybrid neural networks. So, a hybrid transfer-learning paradigm is used for stenosis detection, where a quantum network drives and improves the performance of a pre-trained classical network. An intermediate layer between the classical and quantum network post-processes the classical features by mapping them into a hypersphere of fixed radius through a hyperbolic tangent function. Next, these normalized features are processed in the quantum network, and through a SoftMax function, the class probabilities are obtained: stenosis and non-stenosis. Furthermore, a distributed variational quantum circuit is implemented to split the data into multiple quantum circuits within the quantum network, improving the training time without compromising the stenosis detection performance. The proposed method is evaluated on a small X-ray coronary angiography dataset containing 250 image patches (50%–50% of positive and negative stenosis cases). The hybrid classical–quantum network significantly outperformed the classical network. Evaluation results showed a boost concerning the classical transfer learning paradigm in the accuracy of 9%, recall of 20%, and F1-score of 11%, reaching 91.8033%, 94.9153%, and 91.8033%, respectively.
•A quantum network boosts the performance of classical neural architecture.•An L2 hyperbolic tangent layer bounds the features between classical and quantum stages.•The X-ray angiography images are analyzed to develop a robust stenosis detector system.•Transfer learning and quantum network substantially improved stenosis detection.•An efficient hybrid classical–quantum architecture is focused on stenosis detection.
Nowadays, timely maintenance of electric motors is vital to keep up the complex processes of industrial production. There are currently a variety of methodologies for fault diagnosis. Usually, the ...diagnosis is performed by analyzing current signals at a steady-state motor operation or during a start-up transient. This method is known as motor current signature analysis, which identifies frequencies associated with faults in the frequency domain or by the time–frequency decomposition of the current signals. Fault identification may also be possible by analyzing acoustic sound and vibration signals, which is useful because sometimes this information is the only available. The contribution of this work is a methodology for detecting faults in induction motors in steady-state operation based on the analysis of acoustic sound and vibration signals. This proposed approach uses the Complete Ensemble Empirical Mode Decomposition for decomposing the signal into several intrinsic mode functions. Subsequently, the frequency marginal of the Gabor representation is calculated to obtain the spectral content of the IMF in the frequency domain. This proposal provides good fault detectability results compared to other published works in addition to the identification of more frequencies associated with the faults. The faults diagnosed in this work are two broken rotor bars, mechanical unbalance and bearing defects.
•Fault detection in induction motors with vibrations and acoustic signals is shown.•Broken rotor bars, bearing defects and unbalance in induction motors are analyzed.•The Complete Ensemble Empirical Mode Decomposition method is used.•The frequency marginal of the Gabor is used for spectral estimation.
This article presents an attractive and straightforward computational strategy for estimating the anisotropic thermal conductivity in a wide range of materials. It results in a reliable and efficient ...approach with many potential applications. The proposed method is based on the mathematical model solution of a thermal process to generate some synthetic measurements simulating sensors located at the center of each face of a body under study. This work implements three optimization techniques for solving the formulated inverse thermal problem: Levenberg-Marquardt Algorithm, Particle Swarm Optimization, and Symbiotic Organism Search. Plus, we use an anisotropic cubic piece of solid material as a demonstrative case. Results show an excellent agreement between the estimated anisotropic thermal conductivities and the proposed solutions for the model. Furthermore, we notice a strong impact of the noise level on the measurement system, which affects the precision of the estimated conductivities.
In recent decades, the eye diseases have become the leading causes of blindness in young adults. Most of the cases can be prevented if detected in the early stages. For instance, the analysis of ...retinal blood vessels can help the physician to detect and prescribe appropriate treatment to the diabetic patient as a special case. This work describes a novel framework for blood vessels detection in retinal images. In the proposed methodology, the noise present in the green channel of the RGB image is reduced by a Low-Pass Radius Filter, subsequently, a 30-element Gabor filter and a Gaussian fractional derivative are used to remarkably enhance both the blood vessels structure and its contours. Thereafter, a threshold and a series of morphology-based decision rules are applied to isolate the blood vessels and reduce the incidence of false positive pixels. Additionally, our method can be used to detect the Optic Disc in the original image and remove it from the threshold result. The proposed method was assessed using the public DRIVE database, for the Test image set and the 1st manual delineations. In this database, our method is able to obtain an average accuracy of 0.9503, an average specificity of 0.7854, and an average balanced accuracy of 0.8758. Moreover, the proposed method shows a better performance than comparative methods, such as the threshold for a Frangi filter, Adaptive Threshold, and multiple classes Otsu method. After the analysis of the computer simulations, it was concluded that the proposed method is a competitive and reliable methodology for blood vessels segmentation.
In this paper, a method of vascular structure identification in intraoperative 3D Contrast-Enhanced Ultrasound (CEUS) data is presented. Ultrasound imaging is commonly used in brain tumor surgery to ...investigate in real time the current status of cerebral structures. The use of an ultrasound contrast agent enables to highlight tumor tissue, but also surrounding blood vessels. However, these structures can be used as landmarks to estimate and correct the brain shift. This work proposes an alternative method for extracting small vascular segments close to the tumor as landmark. The patient image dataset involved in brain tumor operations includes preoperative contrast T1MR (cT1MR) data and 3D intraoperative contrast enhanced ultrasound data acquired before (3D-iCEUS(start) and after (3D-iCEUS(end) tumor resection. Based on rigid registration techniques, a preselected vascular segment in cT1MR is searched in 3D-iCEUS(start) and 3D-iCEUS(end) data. The method was validated by using three similarity measures (Normalized Gradient Field, Normalized Mutual Information and Normalized Cross Correlation). Tests were performed on data obtained from ten patients overcoming a brain tumor operation and it succeeded in nine cases. Despite the small size of the vascular structures, the artifacts in the ultrasound images and the brain tissue deformations, blood vessels were successfully identified.
Segmentation of brain tumour in 3D Intraoperative Ultrasound imaging Angel‐Raya, Erick; Chalopin, Claire; Avina‐Cervantes, Juan Gabriel ...
The international journal of medical robotics + computer assisted surgery,
December 2021, 2021-12-00, 20211201, Letnik:
17, Številka:
6
Journal Article
Recenzirano
Background
Intraoperative ultrasound (iUS), using a navigation system and preoperative magnetic resonance imaging (pMRI), supports the surgeon intraoperatively in identifying tumour margins. ...Therefore, visual tumour enhancement can be supported by efficient segmentation methods.
Methods
A semi‐automatic and two registration‐based segmentation methods are evaluated to extract brain tumours from 3D‐iUS data. The registration‐based methods estimated the brain deformation after craniotomy based on pMRI and 3D‐iUS data. Both approaches use the normalised gradient field and linear correlation of linear combinations metrics. Proposed methods were evaluated on 66 B‐mode and contrast‐mode 3D‐iUS data with metastasis and glioblastoma.
Results
The semi‐automatic segmentation achieved superior results with dice similarity index (DSI) values between 85.34, 86.79% and contour mean distance values between 1.05, 1.11 mm for both modalities and tumour classes.
Conclusions
Better segmentation results were obtained for metastasis detection than glioblastoma, preferring 3D‐intraoperative B‐mode over 3D‐intraoperative contrast‐mode.
PDF
