scholarly journals Estimating mechanical properties of cloth from videos using dense motion trajectories: human psychophysics and machine learning

2018 ◽  
Author(s):  
Wenyan Bi ◽  
Peiran Jin ◽  
Hendrikje Nienborg ◽  
Bei Xiao
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Bending Stiffness ◽  
Motion Trajectories ◽  
Spatiotemporal Information ◽  
Machine Learning Model ◽  
Scaling Methods ◽  
Estimation System ◽  
Highly Correlated ◽  
Frame Motion

Humans can visually estimate the mechanical properties of deformable objects (e.g. cloth stiffness). While much of the recent work on material perception has focused on static image cues (e.g., textures and shape), little is known whether humans can integrate information over time to make a judgment. Here, we investigate the effect of spatiotemporal information across multiple frames (multi-frame motion) on estimating the bending stiffness of cloth. Using high-fidelity cloth animations, we first examined how the perceived bending stiffness changed as a function of the physical bending stiffness defined in the simulation model. Using maximum likelihood difference scaling methods (MLDS) we found that the perceived stiffness and the physical bending stiffness were highly correlated. A second experiment in which we scrambled the frame sequences diminished this correlation. This suggests that multi-frame motion plays an important role. To provide further evidence for this finding, we extracted dense motion trajectories from the videos across 15 consecutive frames and used the trajectory descriptors to train a machine-learning model with the measured perceptual scales. The model can predict human perceptual scales in new videos with varied winds, optical properties of cloth, and scene setups. When the correct multi-frame was removed (using either scrambled videos or 2-frame optical flow to train the model), the predictions significantly worsened. Our findings demonstrate that multi-frame motion information is important for both humans and machines to estimate the mechanical properties. In addition, we show that dense motion trajectories are effective features to build a successful automatic cloth estimation system.

scholarly journals Gut Microbiota May Underlie the Predisposition of Healthy Individuals to COVID-19-Sensitive Proteomic Biomarkers

2020 ◽  
Author(s):  
Wanglong Gou ◽  
Yuanqing Fu ◽  
Liang Yue ◽  
Geng-dong Chen ◽  
Xue Cai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gut Microbiota ◽  
Risk Score ◽  
Proinflammatory Cytokines ◽  
Healthy Individuals ◽  
The Core ◽  
Machine Learning Model ◽  
Core Set ◽  
Highly Correlated ◽  
Metabolomics Analysis

Abstract Background: The COVID-19 pandemic is spreading globally with high disparity in the susceptibility of the disease severity. Identification of the key underlying factors for this disparity is highly warranted. Results: Here we describe constructing a proteomic risk score (PRS) based on 20 blood proteomic biomarkers which related to the progression to severe COVID-19. Among COVID-19 patients, per 10% increment in the PRS was associated with a 57% higher risk of progressing to clinically severe phase (RR=1.57; 95% CI, 1.35-1.82). We demonstrate that in our own cohort of 990 individuals without infection, this proteomic risk score is positively associated with proinflammatory cytokines mainly among older, but not younger, individuals. We further discovered that a core set of gut microbiota could accurately predict the blood proteomic biomarkers of COVID-19 using a machine learning model. The core OTU-predicted PRS had a significant correlation with actual PRS both cross-sectionally (n=132, p<0.001) and prospectively (n=169, p<0.05). Most of the core OTUs were highly correlated with proinflammatory cytokines. Fecal metabolomics analysis suggested potential amino acid-related pathways linking the above core gut microbiota to inflammation.Conclusions: Our study suggests that gut microbiota may underlie the predisposition of healthy individuals to COVID-19-sensitive proteomic biomarkers.

scholarly journals Prediction of Mechanical Properties of Artificially Weathered Wood by Color Change and Machine Learning

Materials ◽  
2021 ◽  
Vol 14 (21) ◽  
pp. 6314
Author(s):  
Vahid Nasir ◽  
Hamidreza Fathi ◽  
Arezoo Fallah ◽  
Siavash Kazemirad ◽  
Farrokh Sassani ◽  
...  
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
Color Change ◽  
Learning Model ◽  
Measuring System ◽  
Mechanical Degradation ◽  
Tree Model ◽  
Clear Wood ◽  
Color Parameters ◽  
Machine Learning Model

Color parameters were used in this study to develop a machine learning model for predicting the mechanical properties of artificially weathered fir, alder, oak, and poplar wood. A CIELAB color measuring system was employed to study the color changes in wood samples. The color parameters were fed into a decision tree model for predicting the MOE and MOR values of the wood samples. The results indicated a reduction in the mechanical properties of the samples, where fir and alder were the most and least degraded wood under weathering conditions, respectively. The mechanical degradation was correlated with the color change, where the most resistant wood to color change exhibited less reduction in the mechanical properties. The predictive machine learning model estimated the MOE and MOR values with a maximum R2 of 0.87 and 0.88, respectively. Thus, variations in the color parameters of wood can be considered informative features linked to the mechanical properties of small-sized and clear wood. Further research could study the effectiveness of the model when analyzing large-sized timber.

scholarly journals Gut microbiota may underlie the predisposition of healthy individuals to COVID-19

2020 ◽  
Author(s):  
Wanglong Gou ◽  
Yuanqing Fu ◽  
Liang Yue ◽  
Geng-dong Chen ◽  
Xue Cai ◽  
...  
Keyword(s):  
Machine Learning ◽  
Gut Microbiota ◽  
Risk Score ◽  
Proinflammatory Cytokines ◽  
Metabolomic Analysis ◽  
Healthy Individuals ◽  
Machine Learning Model ◽  
Normal Individuals ◽  
Core Set ◽  
Highly Correlated

SUMMARYThe COVID-19 pandemic is spreading globally with high disparity in the susceptibility of the disease severity. Identification of the key underlying factors for this disparity is highly warranted. Here we describe constructing a proteomic risk score based on 20 blood proteomic biomarkers which predict the progression to severe COVID-19. We demonstrate that in our own cohort of 990 individuals without infection, this proteomic risk score is positively associated with proinflammatory cytokines mainly among older, but not younger, individuals. We further discovered that a core set of gut microbiota could accurately predict the above proteomic biomarkers among 301 individuals using a machine learning model, and that these gut microbiota features are highly correlated with proinflammatory cytokines in another set of 366 individuals. Fecal metabolomic analysis suggested potential amino acid-related pathways linking gut microbiota to inflammation. This study suggests that gut microbiota may underlie the predisposition of normal individuals to severe COVID-19.

scholarly journals Predicting Mechanical Properties of 3D Printed Lattice Structures

2021 ◽  
Author(s):  
Shuai Ma ◽  
Qian Tang ◽  
Ying Liu ◽  
Qixiang Feng
Keyword(s):  
Machine Learning ◽  
Mechanical Properties ◽  
3D Printing ◽  
Unit Length ◽  
3D Models ◽  
Design Stage ◽  
Geometric Feature ◽  
Support Vector ◽  
Lattice Structures ◽  
Machine Learning Model

Abstract Lattice structures (LS) manufactured by 3D printing are widely applied in many areas, such as aerospace and tissue engineering, due to their lightweight and adjustable mechanical properties. It is necessary to reduce costs by predicting the mechanical properties of LS at the design stage since 3D printing is exorbitant at present. However, predicting mechanical properties quickly and accurately poses a challenge. To address this problem, this study proposes a novel method that is applied to different LS and materials to predict their mechanical properties through machine learning. First, this study voxelised 3D models of the LS units and then calculated the entropy vector of each model as the geometric feature of the LS units. Next, the porosity, material density, elastic modulus, and unit length of the lattice unit are combined with entropy as the inputs of the machine learning model. The sample set includes 57 samples collected from previous studies. Support vector regression was used in this study to predict the mechanical properties. The results indicate that the proposed method can predict the mechanical properties of LS effectively and is suitable for different LS and materials. The significance of this work is that it provides a method with great potential to promote the design process of lattice structures by predicting their mechanical properties quickly and effectively.

scholarly journals Machine learning model estimating number of COVID-19 infection cases over coming 24 days in every province of South Korea (XGBoost and MultiOutputRegressor)

2020 ◽  
Author(s):  
Yoshiro Suzuki ◽  
Ayaka Suzuki
Keyword(s):  
Machine Learning ◽  
South Korea ◽  
Binary Classification ◽  
False Positive Rate ◽  
Learning Model ◽  
Control Measures ◽  
Economic Activities ◽  
Machine Learning Model ◽  
Other Information ◽  
Highly Correlated

We built a machine learning model (ML model) which input the number of daily infection cases and the other information related to COVID-19 over the past 24 days in each of 17 provinces in South Korea, and output the total increase in the number of infection cases in each of 17 provinces over the coming 24 days. We employ a combination of XGBoost and MultiOutputRegressor as machine learning model (ML model). For each province, we conduct a binary classification whether our ML model can classify provinces where total infection cases over the coming 24 days is more than 100. The result is Sensitivity = 3/3 = 100%, Specificity = 11/14 = 78.6%, False Positive Rate = 3/11 = 21.4%, Accuracy = 14/17 = 82.4%. Sensitivity = 100% means that we did not overlook the three provinces where the number of COVID-19 infection cases increased by more than100. In addition, as for the provinces where the actual number of new COVID-19 infection cases is less than 100, the ratio (Specificity) that our ML model can correctly estimate was 78.6%, which is relatively high. From the above all, it is demonstrated that there is a sufficient possibility that our ML model can support the following four points. (1) Promotion of behavior modification of residents in dangerous areas, (2) Assistance for decision to resume economic activities in each province, (3) Assistance in determining infectious disease control measures in each province, (4) Search for factors that are highly correlated with the future increase in the number of COVID-19 infection cases.

A Study on Polymer Particle Flow in a Disk Zone of a Screw-Disk Extruder

2014 ◽  
Vol 35 (1) ◽  
pp. 121-135 ◽  
Author(s):  
Tomasz Rydzkowski ◽  
Iwona Michalska-Pożoga
Keyword(s):  
Mechanical Properties ◽  
Computer Simulations ◽  
Particle Motion ◽  
Polymer Melt ◽  
Experimental Tests ◽  
Polymer Particle ◽  
Particle Flow ◽  
Material Particle ◽  
Motion Trajectories ◽  
Stretching Effect

Abstract The paper presents the summary of research on polymer melt particle motion trajectories in a disc zone of a screw-disk extruder. We analysed two models of its structure, different in levels of taken simplifications. The analysis includes computer simulations of material particle flow and results of experimental tests to determine the properties of the resultant extrudate. Analysis of the results shows that the motion of melt in the disk zone of a screw-disk extruder is a superposition of pressure and dragged streams. The observed trajectories of polymer particles and relations of mechanical properties and elongation of the molecular chain proved the presence of a stretching effect on polymer molecular chains.

Sign in / Sign up

Export Citation Format

Share Document