scholarly journals Parallel Calculation Method of Patch Area Landscape Art Index Based on Surface Coverage Data

2021 ◽  
Vol 2021 ◽  
pp. 1-10
Author(s):  
Zhihua Xu
Keyword(s):  
Calculation Method ◽  
Vertical Axis ◽  
Absolute Error ◽  
Convergence Time ◽  
Characteristic Analysis ◽  
Patch Area ◽  
Parallel Calculation ◽  
Area Index ◽  
Patch Type ◽  
Landscape Art

Aiming at the problem of slow convergence in the parallel calculation of patch area landscape art index, a parallel calculation method of patch area landscape art index based on land cover data was proposed. Firstly, patch type area index, patch connectivity index, patch number index, and fragmentation index were selected as patch area landscape art spatial staggered pattern indexes to conduct characteristic analysis and establish a 3D visual reconstruction model with actual colors. Then, the coordinate points of the landscape space staggered pattern are transformed into three-dimensional visual coordinate points to realize the reconstruction of landscape art space staggered pattern in patch area. The aerial landscape image of patch area is preprocessed and input into GPU to build a Gaussian difference pyramid model. The feature points of the patch area in the aerial landscape image are calculated by the parallel computing process, and the patch boundary in the aerial landscape image is determined. The landscape perimeter of the patch area was calculated according to the boundary. The experimental results show that the complete convergence time of the horizontal axis error and the vertical axis error is 2.13 s and 1.81 s, respectively, and the absolute error and relative error of the perimeter measurement are controlled below 0.60 m and 1.00%, respectively.

Static and Dynamic Characteristic Analysis of the Tower for Vertical Axis Wind Turbine Based on Finite Element Method

2012 ◽  
Vol 229-231 ◽  
pp. 613-616
Author(s):  
Yan Jue Gong ◽  
Yuan Yuan Zhang ◽  
Fu Zhao ◽  
Hui Yu Xiang ◽  
Chun Ling Meng ◽  
...  
Keyword(s):  
Finite Element Method ◽  
Finite Element ◽  
Wind Turbine ◽  
Dynamic Characteristic ◽  
Optimization Design ◽  
Vertical Axis ◽  
Vertical Axis Wind Turbine ◽  
Characteristic Analysis ◽  
Support Structure ◽  
Element Method

As an important part of the vertical axis wind turbine, the support structure should have high strength and stiffness. This article adopts finite element method to model a kind of tower structure of the vertical axis wind turbine and carry out static and modal analysis. The static and dynamic characteristic results of tower in this paper provide reference for optimization design the support structure of wind turbine further.

scholarly journals Estimating Physical Activity Energy Expenditure Using an Ensemble Model-Based Patch-Type Sensor Module

Electronics ◽  
2021 ◽  
Vol 10 (7) ◽  
pp. 861
Author(s):  
Kyeung Ho Kang ◽  
Mingu Kang ◽  
Siho Shin ◽  
Jaehyo Jung ◽  
Meina Li
Keyword(s):  
Physical Activity ◽  
Energy Expenditure ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Ensemble Model ◽  
Direct Calorimetry ◽  
Patch Type ◽  
Mortality And Morbidity ◽  
Squared Error ◽  
Sensor Module

Chronic diseases, such as coronary artery disease and diabetes, are caused by inadequate physical activity and are the leading cause of increasing mortality and morbidity rates. Direct calorimetry by calorie production and indirect calorimetry by energy expenditure (EE) has been regarded as the best method for estimating the physical activity and EE. However, this method is inconvenient, owing to the use of an oxygen respiration measurement mask. In this study, we propose a model that estimates physical activity EE using an ensemble model that combines artificial neural networks and genetic algorithms using the data acquired from patch-type sensors. The proposed ensemble model achieved an accuracy of more than 92% (Root Mean Squared Error (RMSE) = 0.1893, R2 = 0.91, Mean Squared Error (MSE) = 0.014213, Mean Absolute Error (MAE) = 0.14020) by testing various structures through repeated experiments.

scholarly journals A Systematic Study of the Best Fitting Line Problem

2021 ◽  
Author(s):  
Giorgio Gambirasio
Keyword(s):  
Center Of Mass ◽  
Vertical Axis ◽  
Absolute Error ◽  
Optimization Method ◽  
Least Square ◽  
Absolute Value ◽  
Meeting Point ◽  
Best Fitting ◽  
The Subject ◽  
Comprehensive Study

AbstractThe classical approach for tackling the problem of drawing the 'best fitting line' through a plot of experimental points (here called a scenario) is the least square process applied to the errors along the vertical axis. However, more elaborate processes exist or may be found. In this report, we present a comprehensive study on the subject. Five possible processes are identified: two of them (respectively called VE, HE) measure errors along one axis, and the remaining three (respectively called YE, PE, and AE) take into consideration errors along both axes. Since the axes and their corresponding errors may have different physical dimensions, a procedure is proposed to compensate for this difference so that all processes could express their answers in the same consistent dimensions. As usual, to avoid mutual cancellation, errors are squared or taken in their absolute value. The two cases are separately studied.In the case of squared errors, the five processes are tested in many scenarios of experimental points, both analytically (using the software Mathematica) and numerically (with programs written on Python platform employing the Nelder-Mead optimization method). The investigation showed the possible existence of multiple solutions. Different answers originating from different starting points in Nelder?Mead correspond to solutions revealed by analytic search with Mathematica. For each scenario of experimental points, it was found that the best lines of the five processes intercept at a common point. Furthermore, the point of intercept happens to coincide with the 'center of mass' of the scenario. This fact is described by stating the existence of an empirical 'Meeting Point Law'. The case of absolute errors is only treated numerically, with Nelder?Mead minimizer. As expected, the absolute error option shows greater robustness against outliers than the square error option, for all processes. The Meeting Point Law is not valid in this case.By taking the value of minimized error as a criterion, the five processes are compared for efficiency. On average, processes PE and AE, that consider errors along both axes, resulted in the smallest minimized error and may be considered the best processes. Processes that rely on errors along a single axis (VE, HE) stay at the second place. In all cases, YE is the process that results in the largest minimized errors

Spatial Dynamic Analysis of a Mangeove Patch Based on Unmanned Aerial Vehicle: A Case Study in Pear Bay in Guangxi, China

2021 ◽  
Author(s):  
Xin Lin ◽  
Chungan Li ◽  
Mei Zhou ◽  
Wenhai Liang ◽  
Biao Li
Keyword(s):  
Unmanned Aerial Vehicle ◽  
Spatial Dynamics ◽  
Absolute Error ◽  
Maximum Error ◽  
Canopy Height ◽  
Accurate Information ◽  
Maximum Absolute Error ◽  
Patch Area ◽  
Maximum Increase ◽  
Aerial Vehicle

Abstract This study investigated the short-term spatial variability of an mangrove patch, located in the Pearl Bay in Guangxi, China. Unmanned aerial vehicle (UAV) imagery covering the period from March 2015 to October 2017 were used and the following models were developed: two annual ultra-high resolution spatial resolution digital orthophoto maps (DOMs), two digital elevation models (DEMs), two digital surface models (DSMs), two canopy height models (CHMs), and a canopy height difference model (d-CHM). Using these models, the spatial dynamics of the extent and canopy height of the patch were analyzed. The resolution of the DOMs was 0.1 m, with an average geometrical error of 0.17 m and a maximum error of 0.44 m. The resolutions of DEMs, DSMs, CHMs, d-CHM were all 1 m. The average elevation errors of CHM in 2015 and 2017 were 0.002 m and -0.001 m, respectively, with maximum absolute errors of 0.034 m and 0.030 m, respectively. The average elevation error of d-CHM was -0.003 m and the maximum absolute error was 0.036 m, and the data quality were rated as good. From 2015 to 2017, the area of the mangrove patch increased from 8.16 ha to 8.79 ha, with an average annual increase of 3.7%. Specifically, the areas of expansion, shrinkage, and maximum seaward expansion were 6356 m2, 19 m2, and 24 m, respectively. The driving factor for the variability was natural processes. Stand canopy height exhibited a particular trend of decrease from northwest to southeast (horizontal; parallel to the seawall) and from the land to the sea (vertically; perpendicular to the seawall). From 2015 to 2017, 88.2% of the patch area showed increased canopy height, with an average increase of 0.78 m and a maximum increase of 3.2 m. In contrast, 11.8% of the patch area showed decreased canopy height with a maximum decrease of 3.1 m. The main reason for the decrease in canopy height was the death of trees caused by serious insect plagues. On the other hand, the reason for the increase in height could be attributed to the natural growth of mangrove trees, but further studies are required to verify the cause. UAV remote sensing has an incomparable advantage over traditional methods in that it provides extremely detailed and highly accurate information for in-depth study of the spatial evolution of mangrove patches, which would significantly contribute towards the protection and management of mangroves.

scholarly journals Machine Learning-Based Gully Erosion Susceptibility Mapping: A Case Study of Eastern India

Sensors ◽  
2020 ◽  
Vol 20 (5) ◽  
pp. 1313 ◽  
Author(s):  
Sunil Saha ◽  
Jagabandhu Roy ◽  
Alireza Arabameri ◽  
Thomas Blaschke ◽  
Dieu Tien Bui
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Absolute Error ◽  
Gully Erosion ◽  
Machine Learning Techniques ◽  
Weight Of Evidence ◽  
Validation Dataset ◽  
Boosted Regression Tree ◽  
Area Index ◽  
Statistical Measures

Gully erosion is a form of natural disaster and one of the land loss mechanisms causing severe problems worldwide. This study aims to delineate the areas with the most severe gully erosion susceptibility (GES) using the machine learning techniques Random Forest (RF), Gradient Boosted Regression Tree (GBRT), Naïve Bayes Tree (NBT), and Tree Ensemble (TE). The gully inventory map (GIM) consists of 120 gullies. Of the 120 gullies, 84 gullies (70%) were used for training and 36 gullies (30%) were used to validate the models. Fourteen gully conditioning factors (GCFs) were used for GES modeling and the relationships between the GCFs and gully erosion was assessed using the weight-of-evidence (WofE) model. The GES maps were prepared using RF, GBRT, NBT, and TE and were validated using area under the receiver operating characteristic (AUROC) curve, the seed cell area index (SCAI) and five statistical measures including precision (PPV), false discovery rate (FDR), accuracy, mean absolute error (MAE), and root mean squared error (RMSE). Nearly 7% of the basin has high to very high susceptibility for gully erosion. Validation results proved the excellent ability of these models to predict the GES. Of the analyzed models, the RF (AUROC = 0.96, PPV = 1.00, FDR = 0.00, accuracy = 0.87, MAE = 0.11, RMSE = 0.19 for validation dataset) is accurate enough for modeling and better suited for GES modeling than the other models. Therefore, the RF model can be used to model the GES areas not only in this river basin but also in other areas with the same geo-environmental conditions.

Fire-created patchiness in Australian savannas

2003 ◽  
Vol 12 (4) ◽  
pp. 323 ◽  
Author(s):  
A. Malcolm Gill ◽  
Grant Allan ◽  
Cameron Yates
Keyword(s):  
Landsat Imagery ◽  
First Year ◽  
Patch Area ◽  
Patch Type ◽  
Frequency Distributions ◽  
Fire Area ◽  
The Individual ◽  
Negative Exponential ◽  
Log Linear ◽  
Landsat Tm Imagery

Models of ecosystem disturbances have been based on either points or patches. In this study, three types of fire-created patch were distinguished: the unburned 'islands' within a fire area; the patches with individual times-since-fire, those of the first year being the individual fire areas; and, patches with individual intervals between fires. Frequency distributions of patch areas were simulated using two randomly filled square grids (with a probability of 0.5, corresponding to 50% burnt each year) with two levels of aggregation—'none' and 'clumped'. Fires were represented by clusters of filled cells on each single grid; years were represented by a set of similar, independent, grids. Results from the simulations were compared to those from Bradshaw Station in the savanna region of the northern part of the Northern Territory using a decade of Landsat MSS and Landsat TM imagery. Maps of times since fire (years) and intervals between fires (years) were constructed. Proportions of the maps with different times since fire and intervals between fires followed negative exponential curves. All frequency distributions of patch area, irrespective of patch type, were found to be log–log linear when data were logged and 'binned' (i.e. placed in categories). In both the simulations and at Bradshaw Station, the numbers of single cell patches first rose then declined as times since fire increased while the largest fire patches rapidly decreased in size. Between-fire interval patches decreased in size with increasing intervals but small-patch number did not increase as it did for times since fire. Errors in accuracy of Landsat imagery could heighten the apparent conformity between interpreted imagery and the simulations.

scholarly journals Artificial Intelligence for Automatic Measurement of Sagittal Vertical Axis Using ResUNet Framework

2019 ◽  
Vol 8 (11) ◽  
pp. 1826 ◽  
Author(s):  
Chi-Hung Weng ◽  
Chih-Li Wang ◽  
Yu-Jui Huang ◽  
Yu-Cheng Yeh ◽  
Chen-Ju Fu ◽  
...  
Keyword(s):  
Automatic Measurement ◽  
Vertical Axis ◽  
Absolute Error ◽  
Superior Performance ◽  
Chang Gung Memorial Hospital ◽  
Sagittal Vertical Axis ◽  
Automated Method ◽  
High Consistency ◽  
Whole Spine ◽  
Clinical Conditions

We present an automated method for measuring the sagittal vertical axis (SVA) from lateral radiography of whole spine using a convolutional neural network for keypoint detection (ResUNet) with our improved localization method. The algorithm is robust to various clinical conditions, such as degenerative changes or deformities. The ResUNet was trained and evaluated on 990 standing lateral radiographs taken at Chang Gung Memorial Hospital, Linkou and performs SVA measurement with median absolute error of 1.183 ± 0.166 mm. The 5-mm detection rate of the C7 body and the sacrum are 91% and 87%, respectively. The SVA calculation takes approximately 0.2 s per image. The intra-class correlation coefficient of the SVA estimates between the algorithm and physicians of different years of experience ranges from 0.946 to 0.993, indicating an excellent consistency. The superior performance of the proposed method and its high consistency with physicians proved its usefulness for automatic measurement of SVA in clinical settings.

scholarly journals Separating overstory and understory leaf area indices for global needleleaf and deciduous broadleaf forests by fusion of MODIS and MISR data

2017 ◽  
Vol 14 (5) ◽  
pp. 1093-1110 ◽  
Author(s):  
Yang Liu ◽  
Ronggao Liu ◽  
Jan Pisek ◽  
Jing M. Chen
Keyword(s):  
Leaf Area ◽  
Water Cycle ◽  
Field Measurements ◽  
Absolute Error ◽  
Mean Value ◽  
Understory Vegetation ◽  
Forest Understory ◽  
Ecosystem Functions ◽  
Canopy Reflectance ◽  
Area Index

Abstract. Forest overstory and understory layers differ in carbon and water cycle regimes and phenology, as well as ecosystem functions. Separate retrievals of leaf area index (LAI) for these two layers would help to improve modeling forest biogeochemical cycles, evaluating forest ecosystem functions and also remote sensing of forest canopies by inversion of canopy reflectance models. In this paper, overstory and understory LAI values were estimated separately for global needleleaf and deciduous broadleaf forests by fusing MISR and MODIS observations. Monthly forest understory LAI was retrieved from the forest understory reflectivity estimated using MISR data. After correcting for the background contribution using monthly mean forest understory reflectivities, the forest overstory LAI was estimated from MODIS observations. The results demonstrate that the largest extent of forest understory vegetation is present in the boreal forest zones at northern latitudes. Significant seasonal variations occur for understory vegetation in these zones with LAI values up to 2–3 from June to August. The mean proportion of understory LAI to total LAI is greater than 30 %. Higher understory LAI values are found in needleleaf forests (with a mean value of 1.06 for evergreen needleleaf forests and 1.04 for deciduous needleleaf forests) than in deciduous broadleaf forests (0.96) due to the more clumped foliage and easier penetration of light to the forest floor in needleleaf forests. Spatially and seasonally variable forest understory reflectivity helps to account for the effects of the forest background on LAI retrieval while compared with constant forest background. The retrieved forest overstory and understory LAI values were compared with an existing dataset for larch forests in eastern Siberia (40–75° N, 45–180° E). The retrieved overstory and understory LAI is close to that of the existing dataset, with an absolute error of 0.02 (0.06), relative error of 1.3 % (14.3 %) and RMSE of 0.93 (0.29) for overstory (understory). The comparisons between our results and field measurements in eight forest sites show that the R2 values are 0.52 and 0.62, and the RMSEs are 1.36 and 0.62 for overstory and understory LAI, respectively.

Sign in / Sign up

Export Citation Format

Share Document