scholarly journals Leaf Counting: Fusing Network Components for Improved Accuracy

2021 ◽  
Vol 12 ◽  
Author(s):  
Guy Farjon ◽  
Yotam Itzhaky ◽  
Faina Khoroshevsky ◽  
Aharon Bar-Hillel
Keyword(s):  
Regression Model ◽  
Multiple Scales ◽  
Multiple Scale ◽  
Plant Phenotyping ◽  
Learning Approaches ◽  
Potted Plants ◽  
Multiple Resolutions ◽  
Banana Leaves ◽  
Improved Accuracy ◽  
Direct Regression

Leaf counting in potted plants is an important building block for estimating their health status and growth rate and has obtained increasing attention from the visual phenotyping community in recent years. Two novel deep learning approaches for visual leaf counting tasks are proposed, evaluated, and compared in this study. The first method performs counting via direct regression but using multiple image representation resolutions to attend leaves of multiple scales. The leaf count from multiple resolutions is fused using a novel technique to get the final count. The second method is detection with a regression model that counts the leaves after locating leaf center points and aggregating them. The algorithms are evaluated on the Leaf Counting Challenge (LCC) dataset of the Computer Vision Problems in Plant Phenotyping (CVPPP) conference 2017, and a new larger dataset of banana leaves. Experimental results show that both methods outperform previous CVPPP LCC challenge winners, based on the challenge evaluation metrics, and place this study as the state of the art in leaf counting. The detection with regression method is found to be preferable for larger datasets when the center-dot annotation is available, and it also enables leaf center localization with a 0.94 average precision. When such annotations are not available, the multiple scale regression model is a good option.

Non-Linear Dynamic Analysis of a Cable-Stayed Beam

2005 ◽  
Author(s):  
Carlos E. N. Mazzilli ◽  
Franz Rena´n Villarroel Rojas
Keyword(s):  
Multiple Scales ◽  
Equations Of Motion ◽  
Multiple Scale ◽  
Local Mode ◽  
Numerical Application ◽  
Global Mode ◽  
Lower Mode ◽  
Reduced Equations ◽  
External Resonance ◽  
Non Linear

The dynamic behaviour of a simple clamped beam suspended at the other end by an inclined cable stay is surveyed in this paper. The sag due to the cable weight, as well as the non-linear coupling between the cable and the beam motions are taken into account. The formulation for in-plane vibration follows closely that of Gattulli et al. [1] and confirms their findings for the overall features of the equations of motion and the system modal properties. A reduced non-linear mathematical model, with two degrees of freedom, is also developed, following again the steps of Gattulli and co-authors [2,3]. Hamilton’s Principle is evoked to allow for the projection of the displacement field of both the beam and the cable onto the space defined by the first two modes, namely a “global” mode (beam and cable) and a “local” mode (cable). The method of multiple scales is then applied to the analysis of the reduced equations of motion, when the system is subjected to the action of a harmonic loading. The steady-state solutions are characterised in the case of internal resonance between the local and the global modes, plus external resonance with respect to either one of the modes considered. A numerical application is presented, for which multiple-scale results are compared with those of numerical integration. A reasonable qualitative and quantitative agreement is seen to happen particularly in the case of external resonance with the higher mode. Discrepancies should obviously be expected due to strong non-linearities present in the reduced equations of motion. That is specially the case for external resonance with the lower mode.

Forecasting Of Covid-19 Cases Using Machine Learning Approach

2021 ◽  
Vol 17 ◽  
Author(s):  
Sachin Kumar ◽  
Karan Veer
Keyword(s):  
Machine Learning ◽  
Regression Model ◽  
Model Performance ◽  
Real Data ◽  
Absolute Error ◽  
Viral Disease ◽  
Support Vector ◽  
Family Welfare ◽  
Accuracy Score ◽  
Learning Approaches

Aims: The objective of this research is to predict the covid-19 cases in India based on the machine learning approaches. Background: Covid-19, a respiratory disease caused by one of the coronavirus family members, has led to a pandemic situation worldwide in 2020. This virus was detected firstly in Wuhan city of China in December 2019. This viral disease has taken less than three months to spread across the globe. Objective: In this paper, we proposed a regression model based on the Support vector machine (SVM) to forecast the number of deaths, the number of recovered cases, and total confirmed cases for the next 30 days. Method: For prediction, the data is collected from Github and the ministry of India's health and family welfare from March 14, 2020, to December 3, 2020. The model has been designed in Python 3.6 in Anaconda to forecast the forecasting value of corona trends until September 21, 2020. The proposed methodology is based on the prediction of values using SVM based regression model with polynomial, linear, rbf kernel. The dataset has been divided into train and test datasets with 40% and 60% test size and verified with real data. The model performance parameters are evaluated as a mean square error, mean absolute error, and percentage accuracy. Results and Conclusion: The results show that the polynomial model has obtained 95 % above accuracy score, linear scored above 90%, and rbf scored above 85% in predicting cumulative death, conformed cases, and recovered cases.

scholarly journals High-fidelity optical diffraction tomography of multiple scattering samples

2019 ◽  
Vol 8 (1) ◽  
Author(s):  
Joowon Lim ◽  
Ahmed B. Ayoub ◽  
Elizabeth E. Antoine ◽  
Demetri Psaltis
Keyword(s):  
Beam Propagation Method ◽  
Ground Truth ◽  
Dipole Approximation ◽  
Optical Diffraction ◽  
Superior Performance ◽  
Diffraction Tomography ◽  
Learning Approaches ◽  
Optical Diffraction Tomography ◽  
Evaluation Of Learning ◽  
Improved Accuracy

Abstract We propose an iterative reconstruction scheme for optical diffraction tomography that exploits the split-step non-paraxial (SSNP) method as the forward model in a learning tomography scheme. Compared with the beam propagation method (BPM) previously used in learning tomography (LT-BPM), the improved accuracy of SSNP maximizes the information retrieved from measurements, relying less on prior assumptions about the sample. A rigorous evaluation of learning tomography based on SSNP (LT-SSNP) using both synthetic and experimental measurements confirms its superior performance compared with that of the LT-BPM. Benefiting from the accuracy of SSNP, LT-SSNP can clearly resolve structures that are highly distorted in the LT-BPM. A serious limitation for quantifying the reconstruction accuracy for biological samples is that the ground truth is unknown. To overcome this limitation, we describe a novel method that allows us to compare the performances of different reconstruction schemes by using the discrete dipole approximation to generate synthetic measurements. Finally, we explore the capacity of learning approaches to enable data compression by reducing the number of scanning angles, which is of particular interest in minimizing the measurement time.

scholarly journals Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping

2016 ◽  
Author(s):  
Michael P. Pound ◽  
Alexandra J. Burgess ◽  
Michael H. Wilson ◽  
Jonathan A. Atkinson ◽  
Marcus Griffiths ◽  
...  
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Data Analysis ◽  
Paradigm Shift ◽  
State Of The Art ◽  
Plant Phenotyping ◽  
Learning Approaches ◽  
Challenging Problem ◽  
Feature Identification ◽  
Art Performance

AbstractDeep learning is an emerging field that promises unparalleled results on many data analysis problems. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping, and demonstrate state-of-the-art results for root and shoot feature identification and localisation. We predict a paradigm shift in image-based phenotyping thanks to deep learning approaches.

He’s Multiple-Scale Solution for the Three-dimensional Nonlinear KH Instability of Rotating Magnetic Fluids

2019 ◽  
Vol 9 (1) ◽  
pp. 52-69 ◽  
Author(s):  
Yusry Osman El-Dib ◽  
Amal A Mady
Keyword(s):  
Multiple Scales ◽  
Velocity Ratio ◽  
Three Dimensional ◽  
Multiple Scale ◽  
Stability Criteria ◽  
Helmholtz Instability ◽  
Vertical Field ◽  
Horizontal Flux ◽  
The Stability ◽  
Transition Curves

This paper elucidates a trend in solving nonlinear oscillators of the rotating Kelvin-Helmholtz instability. The system is constituted by the vertical flux or the horizontal flux. He’s multiple-scales perturbation methodology has been applied and therefore the system is represented by a generalized homotopy equation. This approach ends up in a periodic answer to a nonlinear oscillator with high nonlinearity. The cubic-quintic nonlinear Duffing equation is obligatory as a condition to uniformly answer. This equation is employed to derive the stability criteria. The transition curves are plotted to investigate the stability image. It's shown that the angular velocity suppresses the instability. The tangential flux plays a helpful role, whereas the vertical field encompasses a destabilizing influence. Within the existence of the rotation, the velocity ratio reduces stability configuration.

scholarly journals Plant phenotyping: increasing throughput and precision at multiple scales

2017 ◽  
Vol 44 (1) ◽  
pp. v ◽  
Author(s):  
Malcolm J. Hawkesford ◽  
Argelia Lorence
Keyword(s):  
Multiple Scales ◽  
Field Trials ◽  
Plant Biology ◽  
Plant Phenotyping ◽  
Form And Function ◽  
Technological Advances ◽  
Basic Plant ◽  
Plant Form ◽  
And Function ◽  
Invasive Techniques

In this special issue of Functional Plant Biology, we present a perspective of the current state of the art in plant phenotyping. The applications of automated and detailed recording of plant characteristics using a range of mostly non-invasive techniques are described. Papers range from tissue scale analysis through to aerial surveying of field trials and include model plant species such as Arabidopsis as well as commercial crops such as sugar beet and cereals. The common denominators are high throughput measurements, data rich analyses often utilising image based data capture, requirements for validation when proxy measurement are employed and in many instances a need to fuse datasets. The outputs are detailed descriptions of plant form and function. The papers represent technological advances and important contributions to basic plant biology, and these studies are commonly multidisciplinary, involving engineers, software specialists and plant physiologists. This is a fast moving area producing large datasets and analytical requirements are often common between very diverse platforms.

scholarly journals Contribution of collaborative skill toward construction drawing skill for developing vocational course

2021 ◽  
Vol 11 (1) ◽  
pp. 755-771
Author(s):  
Abdul Haris Setiawan ◽  
Ryo Takaoka ◽  
Agusti Tamrin ◽  
Roemintoyo ◽  
Eko Supri Murtiono ◽  
...  
Keyword(s):  
Regression Model ◽  
Student Performance ◽  
Civil Engineering ◽  
Positive Influence ◽  
Learning Approaches ◽  
Study Program ◽  
Education Study ◽  
Vocational High Schools ◽  
Collaborative Skills ◽  
Future Work

Abstract This study aims to support developing research in designing a vocational lesson and learning model for civil engineering education study program by examining students’ collaborative skills toward construction drawing skills as a substantial skill in civil engineering. This study investigated student performance for proposing collaborative learning approaches to improve student skills as needed by industry. It is an ex-post-facto study using 130 samples from several vocational high schools in Indonesia with descriptive statistics and regression for the data analysis. The results show that the collaborative skill is in a fair category of 60.00 and the construction drawing skill is in a good category of 67.49 on a 100 scale. There is a significant and positive influence of collaborative skill (X) toward construction drawing skill (Y) with a linear regression model Ŷ = 31.443 + 1.952X. Furthermore, it presented a correlation coefficient of 0.644, a determination coefficient (R 2) of 0.415, and an adjusted R 2 of 0.410, where it can be concluded that the collaborative skill variable (X) as a predictor in the regression model includes the moderate category, which gives a 41% contribution in explaining the variants of the construction drawing skill (Y) as the dependent variable. It needs special attention to the specific behavioral details of the collaborative skill. The future work is needed to improve collaborative skills that emphasize prioritizing collaboration between peers and learning interdependence.

scholarly journals A Comparison of Machine Learning Approaches to Improve Free Topography Data for Flood Modelling

2021 ◽  
Vol 13 (2) ◽  
pp. 275
Author(s):  
Michael Meadows ◽  
Matthew Wilson
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Spatial Patterns ◽  
Large Scale ◽  
Multiple Scales ◽  
Flood Hazard ◽  
Training Data ◽  
Learning Approaches ◽  
Testing Dataset ◽  
Topography Data

Given the high financial and institutional cost of collecting and processing accurate topography data, many large-scale flood hazard assessments continue to rely instead on freely-available global Digital Elevation Models, despite the significant vertical biases known to affect them. To predict (and thereby reduce) these biases, we apply a fully-convolutional neural network (FCN), a form of artificial neural network originally developed for image segmentation which is capable of learning from multi-variate spatial patterns at different scales. We assess its potential by training such a model on a wide variety of remote-sensed input data (primarily multi-spectral imagery), using high-resolution, LiDAR-derived Digital Terrain Models published by the New Zealand government as the reference topography data. In parallel, two more widely used machine learning models are also trained, in order to provide benchmarks against which the novel FCN may be assessed. We find that the FCN outperforms the other models (reducing root mean square error in the testing dataset by 71%), likely due to its ability to learn from spatial patterns at multiple scales, rather than only a pixel-by-pixel basis. Significantly for flood hazard modelling applications, corrections were found to be especially effective along rivers and their floodplains. However, our results also suggest that models are likely to be biased towards the land cover and relief conditions most prevalent in their training data, with further work required to assess the importance of limiting training data inputs to those most representative of the intended application area(s).

A Time-Varying Stiffness Rotor Active Magnetic Bearings Under Combined Resonance

2008 ◽  
Vol 75 (1) ◽  
Author(s):  
U. H. Hegazy ◽  
M. H. Eissa ◽  
Y. A. Amer
Keyword(s):  
Multiple Scales ◽  
Nonlinear Oscillations ◽  
Equations Of Motion ◽  
Multiple Scale ◽  
Magnetic Bearings ◽  
Time Varying ◽  
Active Magnetic Bearings ◽  
Gyroscopic Effects ◽  
Nonlinear Equations Of Motion ◽  
Combined Resonance

This paper is concerned with the nonlinear oscillations and dynamic behavior of a rigid disk-rotor supported by active magnetic bearings (AMB), without gyroscopic effects. The nonlinear equations of motion are derived considering a periodically time-varying stiffness. The method of multiple scales is applied to obtain four first-order differential equations that describe the modulation of the amplitudes and the phases of the vibrations in the horizontal and vertical directions. The stability and the steady-state response of the system at a combination resonance for various parameters are studied numerically, applying the frequency response function method. It is shown that the system exhibits many typical nonlinear behaviors, including multiple-valued solutions, jump phenomenon, hardening, and softening nonlinearity. A numerical simulation using a fourth-order Runge-Kutta algorithm is carried out, where different effects of the system parameters on the nonlinear response of the rotor are reported and compared to the results from the multiple scale analysis. Results are compared to available published work.

Linking Genes to Shape in Plants Using Morphometrics

2020 ◽  
Vol 54 (1) ◽  
pp. 417-437
Author(s):  
Hao Xu ◽  
George W. Bassel
Keyword(s):  
Multiple Scales ◽  
Computational Simulation ◽  
Plant Phenotyping ◽  
Biological Complexity ◽  
Phenotypic Analysis ◽  
Mechanical Signals ◽  
Whole Plant ◽  
Plant Form ◽  
Morphological Phenotype ◽  
Quantitative Approaches

A transition from qualitative to quantitative descriptors of morphology has been facilitated through the growing field of morphometrics, representing the conversion of shapes and patterns into numbers. The analysis of plant form at the macromorphological scale using morphometric approaches quantifies what is commonly referred to as a phenotype. Quantitative phenotypic analysis of individuals with contrasting genotypes in turn provides a means to establish links between genes and shapes. The path from a gene to a morphological phenotype is, however, not direct, with instructive information progressing both across multiple scales of biological complexity and through nonintuitive feedback, such as mechanical signals. In this review, we explore morphometric approaches used to perform whole-plant phenotyping and quantitative approaches in capture processes in the mesoscales, which bridge the gaps between genes and shapes in plants. Quantitative frameworks involving both the computational simulation and the discretization of data into networks provide a putative path to predicting emergent shape from underlying genetic programs.

Sign in / Sign up

Export Citation Format

Share Document