scholarly journals Fluorescence multi-scale endoscopy and its applications in the study and diagnosis of gastro-intestinal diseases: set-up design and software implementation

2015 ◽  
Author(s):  
Pablo Aurelio Gómez-García ◽  
Alicia Arranz ◽  
Manuel Fresno ◽  
Manuel Desco ◽  
Umar Mahmood ◽  
...  
Keyword(s):  
Software Implementation ◽  
Intestinal Diseases ◽  
Multi Scale ◽  
Set Up

scholarly journals Group and Shuffle Convolutional Neural Networks with Pyramid Pooling Module for Automated Pterygium Segmentation

Diagnostics ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 1104
Author(s):  
Siti Raihanah Abdani ◽  
Mohd Asyraf Zulkifley ◽  
Nuraisyah Hani Zulkifley
Keyword(s):  
Screening Tool ◽  
Jaccard Index ◽  
Dense Network ◽  
Multi Scale ◽  
Spatial Pyramid Pooling ◽  
Severity Levels ◽  
Set Up ◽  
Channel Variation ◽  
Mobile Phone Camera ◽  
Sunlight Radiation

Pterygium is an eye condition that is prevalent among workers that are frequently exposed to sunlight radiation. However, most of them are not aware of this condition, which motivates many volunteers to set up health awareness booths to give them free health screening. As a result, a screening tool that can be operated on various platforms is needed to support the automated pterygium assessment. One of the crucial functions of this assessment is to extract the infected regions, which directly correlates with the severity levels. Hence, Group-PPM-Net is proposed by integrating a spatial pyramid pooling module (PPM) and group convolution to the deep learning segmentation network. The system uses a standard mobile phone camera input, which is then fed to a modified encoder-decoder convolutional neural network, inspired by a Fully Convolutional Dense Network that consists of a total of 11 dense blocks. A PPM is integrated into the network because of its multi-scale capability, which is useful for multi-scale tissue extraction. The shape of the tissues remains relatively constant, but the size will differ according to the severity levels. Moreover, group and shuffle convolution modules are also integrated at the decoder side of Group-PPM-Net by placing them at the starting layer of each dense block. The addition of these modules allows better correlation among the filters in each group, while the shuffle process increases channel variation that the filters can learn from. The results show that the proposed method obtains mean accuracy, mean intersection over union, Hausdorff distance, and Jaccard index performances of 0.9330, 0.8640, 11.5474, and 0.7966, respectively.

scholarly journals Experimental evidence for inherent Lévy search behaviour in foraging animals

2015 ◽  
Vol 282 (1807) ◽  
pp. 20150424 ◽  
Author(s):  
Andrea Kölzsch ◽  
Adriana Alzate ◽  
Frederic Bartumeus ◽  
Monique de Jager ◽  
Ellen J. Weerman ◽  
...  
Keyword(s):  
Experimental Evidence ◽  
Power Laws ◽  
Size Distributions ◽  
New Paradigm ◽  
Landscape Complexity ◽  
Search Behaviour ◽  
Multi Scale ◽  
Behavioural Strategy ◽  
Lévy Walks ◽  
Set Up

Recently, Lévy walks have been put forward as a new paradigm for animal search and many cases have been made for its presence in nature. However, it remains debated whether Lévy walks are an inherent behavioural strategy or emerge from the animal reacting to its habitat. Here, we demonstrate signatures of Lévy behaviour in the search movement of mud snails ( Hydrobia ulvae ) based on a novel, direct assessment of movement properties in an experimental set-up using different food distributions. Our experimental data uncovered clusters of small movement steps alternating with long moves independent of food encounter and landscape complexity. Moreover, size distributions of these clusters followed truncated power laws. These two findings are characteristic signatures of mechanisms underlying inherent Lévy-like movement. Thus, our study provides clear experimental evidence that such multi-scale movement is an inherent behaviour rather than resulting from the animal interacting with its environment.

Scratchability of Soda-Lime Silica (SLS) Glasses: Dynamic Fracture Analysis

2005 ◽  
Vol 290 ◽  
pp. 31-38 ◽  
Author(s):  
V. Le Houérou ◽  
J.-C. Sanglebœuf ◽  
Tanguy Rouxel
Keyword(s):  
Normal Load ◽  
Soda Lime ◽  
Fracture Analysis ◽  
Float Glass ◽  
Fused Silica ◽  
Machining Process ◽  
Multi Scale ◽  
Set Up ◽  
Fused Silica Glass

Grinding and polishing are widely used for glass machining with fine finished surfaces. These processes result from abrasion due to repeated contacts between hard sliding particles and the glass surface. The study of contact mechanics problem is of fundamental interest to understand the process of material removal in glasses. In order to get insight into this problem, an experimental set up was designed which allows a monotonic loading of the indenter combined with a controlled sliding of the specimen to simulate a slow abrasive machining process. In addition, the experiments are conducted with an in-situ video monitoring that allows for the observation of the different fracture phenomena beneath the indenter. Fracture surfaces were also studied using SEM and AFM for multi-scale investigation. Fracture analysis was carried on a standard float glass, four different SLS glasses and a fused silica glass. The observed phenomena were discussed in the light of the influence of the normal load and the chemical composition.

Integrated Fracture Delineation in Volcanics, Junggar Basin, China

2014 ◽  
Vol 1073-1076 ◽  
pp. 2019-2024
Author(s):  
Fang Fang Wu ◽  
Jin Chuan Zhang ◽  
Hao Zhang ◽  
Jin Long Wu
Keyword(s):  
Junggar Basin ◽  
Dispersion Analysis ◽  
Key Factors ◽  
Vertical Wells ◽  
Surface Shear ◽  
Acoustic Reflection ◽  
Multi Scale ◽  
Set Up ◽  
Resistivity Image ◽  
Borehole Surface

Fracture effectiveness, extension and connectivity from borehole surface into deep formation are the key factors to control producibility of volcanic formations. A systematic and integrated fracture delineation approach was set up which integrated available measurements with multi-scale depth of investigation to cover borehole surface, near wellbore and deep formation. High resolution micro-resistivity image was used to identify fractures on the borehole surface; shear anisotropy enhanced by dispersion analysis was used to evaluate fractures away from the borehole; Borehole acoustic reflection survey technique was applied in vertical wells to assess probable fracture networks deep into formation up to maximal 10 meters. This multi-scale approach had been implemented in multiple wells drilled in volcanic formations in Junggar basin, which helped a lot on fracture evaluation and productivity estimation.

Mechanical Behaviour of Cement-Bound Gravels by Experiment-Based 3D Multi-Scale Modelling: Application to Non-Hazardous Waste Incineration Bottom Ashes Aggregates for Use in Road Engineering

2021 ◽  
Vol 54 ◽  
pp. 71-85
Author(s):  
Libasse Sow ◽  
Fabrice Bernard ◽  
Siham Kamali-Bernard
Keyword(s):  
Hazardous Waste ◽  
Mechanical Behaviour ◽  
Waste Incineration ◽  
Friction Angle ◽  
Multi Scale ◽  
Scale Modelling ◽  
Set Up ◽  
Definition Of ◽  
Hazardous Waste Incineration ◽  
Modelling Approach

This paper presents a hierarchical multi-scale modelling approach devoted to investigating the mechanical behaviour of cement-bound gravels. Material studied is based on Non-Hazardous Waste Incineration (NHWI) bottom ashes. The elastic moduli of NHWI particles have been previously determined by an original indentation campaign never conducted so far on these types of aggregates. The results of the experimental campaign serve as input data to the developed numerical strategy. The modelling is based on the definition of Representative Elementary Volumes (REV) considering all the heterogeneities of the material. The "virtual laboratory" set up made it possible to determine the mechanical parameters characterizing the gravel treated with 3% of cement. The high value obtained of the internal friction angle (76 °) gives the material a good bearing capacity. The classification in mechanical classes 3 and 4 when the Young's modulus of the NHWI particles varies from 20 to 80 GPa proves the feasibility of the reuse of this type of industrial by-products in this sector of activity. The present modelling approach is validated by means of comparisons with experimental results of the literature.

C haste : incorporating a novel multi-scale spatial and temporal algorithm into a large-scale open source library

2009 ◽  
Vol 367 (1895) ◽  
pp. 1907-1930 ◽  
Author(s):  
Miguel O. Bernabeu ◽  
Rafel Bordas ◽  
Pras Pathmanathan ◽  
Joe Pitt-Francis ◽  
Jonathan Cooper ◽  
...  
Keyword(s):  
Open Source ◽  
Computational Efficiency ◽  
Large Scale ◽  
Three Dimensional ◽  
Testing Procedure ◽  
Two Dimensions ◽  
Multi Scale ◽  
Bidomain Equations ◽  
Cancer Modelling ◽  
Set Up

Recent work has described the software engineering and computational infrastructure that has been set up as part of the Cancer, Heart and Soft Tissue Environment (C haste ) project. C haste is an open source software package that currently has heart and cancer modelling functionality. This software has been written using a programming paradigm imported from the commercial sector and has resulted in a code that has been subject to a far more rigorous testing procedure than that is usual in this field. In this paper, we explain how new functionality may be incorporated into C haste . Whiteley has developed a numerical algorithm for solving the bidomain equations that uses the multi-scale (MS) nature of the physiology modelled to enhance computational efficiency. Using a simple geometry in two dimensions and a purpose-built code, this algorithm was reported to give an increase in computational efficiency of more than two orders of magnitude. In this paper, we begin by reviewing numerical methods currently in use for solving the bidomain equations, explaining how these methods may be developed to use the MS algorithm discussed above. We then demonstrate the use of this algorithm within the C haste framework for solving the monodomain and bidomain equations in a three-dimensional realistic heart geometry. Finally, we discuss how C haste may be developed to include new physiological functionality—such as modelling a beating heart and fluid flow in the heart—and how new algorithms aimed at increasing the efficiency of the code may be incorporated.

scholarly journals Automatic Fabric Defect Detection Using Cascaded Mixed Feature Pyramid with Guided Localization

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 871 ◽  
Author(s):  
You Wu ◽  
Xiaodong Zhang ◽  
Fengzhou Fang
Keyword(s):  
Defect Detection ◽  
Large Scale ◽  
Region Of Interest ◽  
Feature Maps ◽  
Detection Algorithms ◽  
Multi Scale ◽  
Fabric Defect Detection ◽  
Fabric Defect ◽  
Feature Pyramid ◽  
Set Up

Generic object detection algorithms for natural images have been proven to have excellent performance. In this paper, fabric defect detection on optical image datasets is systematically studied. In contrast to generic datasets, defect images are multi-scale, noise-filled, and blurred. Back-light intensity would also be sensitive for visual perception. Large-scale fabric defect datasets are collected, selected, and employed to fulfill the requirements of detection in industrial practice in order to address these imbalanced issues. An improved two-stage defect detector is constructed for achieving better generalization. Stacked feature pyramid networks are set up to aggregate cross-scale defect patterns on interpolating mixed depth-wise block in stage one. By sharing feature maps, center-ness and shape branches merges cascaded modules with deformable convolution to filter and refine the proposed guided anchors. After balanced sampling, the proposals are down-sampled by position-sensitive pooling for region of interest, in order to characterize interactions among fabric defect images in stage two. The experiments show that the end-to-end architecture improves the occluded defect performance of region-based object detectors as compared with the current detectors.

A Multi-View Sonar Image Fusion Method Based on Nonsubsampled Contourlet Transform and Morphological Modification

2014 ◽  
Vol 530-531 ◽  
pp. 567-570 ◽  
Author(s):  
Zhi Gang Zhang ◽  
Hong Yu Bian ◽  
Zi Qi Song ◽  
Hui Xu
Keyword(s):  
Image Fusion ◽  
Contourlet Transform ◽  
Nonsubsampled Contourlet Transform ◽  
Multi Scale ◽  
Sonar Image ◽  
Morphological Modification ◽  
Morphology Modification ◽  
Sonar Images ◽  
Set Up

In underwater detection, a single image from the image sonar doesnt have the capacity to fully describe the surface of the interested target. In practice, a target is usually detected from various views, and similar contours and textures in a series of multi-view images can be employed. This work offers a novel technique for the fusion of a series of sonar images in multi-view detection of the same target, to improve the quality of images and repair the regions of target. The method takes advantage of Nonsubsampled Contourlet Transform (NSCT) to acquire coefficient matrixes of different resolutions and directions. Besides, a framework for sonar image fusion is set up based on morphology modification. The coefficient matrixes in NSCT domain are fused in the multi-scale framework and revised in decision-making. Experimental results show that target regions in the fused sonar images are effectively repaired and image quality also get improved evidently.

An improved fast segmentation algorithm for text and graphics data

2020 ◽  
Vol 39 (4) ◽  
pp. 5273-5281
Author(s):  
Zhancang Li
Keyword(s):  
Gabor Filter ◽  
Deep Level ◽  
A Priori ◽  
Video Information ◽  
Multi Scale ◽  
Extraction Step ◽  
Set Up ◽  
Edge Features ◽  
Text Location ◽  
Important Basis

The application of video and image segmentation is carried out from the aspects of improving the accuracy of segmentation and reducing the calculation time, but the segmentation result is affected by the initial curve position, so this paper proposes a new method. As an important part of the Internet, pictures are usually used to help visitors understand. The image contains a lot of deep-level video information, which is an important basis for video content retrieval and data analysis. In this paper, combining the texture and edge features of the image in the process of text location, a multi-scale Gabor filter bank is proposed to transform the original image, and a priori knowledge of the text region is used to process the non-text object in the transform result. In the part of extracting text from pictures, and improved TF-IDF algorithm, BC-TF-IDF algorithm, is proposed to extract text from pictures. To ensure the integrity of the extracted image, the Sobel algorithm is used to process the image in the edge extraction step. Finally, the above method is applied to the Weibo network, and a system of collecting and recognizing the character content of the Weibo image is set up, which completes the function of collecting and gradually recognizing the Weibo image, and verifies the proposed localization method.

Multi-Scale Analysis for Thermo-Elasticity Properties of Composite Materials with Small Periodic Configuration

2007 ◽  
Vol 334-335 ◽  
pp. 25-28 ◽  
Author(s):  
Shao Fan Tang ◽  
Fu Hua Huang ◽  
Jun Liang ◽  
Shan Yi Du
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Composite Materials ◽  
Multi Scale ◽  
Asymptotic Expressions ◽  
Refined Meshes ◽  
Set Up ◽  
Periodic Configuration ◽  
Small Periodic ◽  
Element Method

In this paper, based on the equations of coupled thermo-elasticity, two-scale asymptotic expressions of the temperature and displacement of composite materials under coupled thermo-elasticity condition are set up with the perturbation method. By the multi-scale finite element method, the temperature and 2-order displacement, strain and stress of composite materials with small periodic configuration under coupled thermo-elasticity condition are calculated. Comparing with the results calculated by finite element method with refined meshes, it’s shown that multi-scale method is an efficient method, and the calculation precision is satisfied.

Sign in / Sign up

Export Citation Format

Share Document