Improvements on Learning Kernel Extended Dictionary for Face Recognition

Kernel extended dictionary learning model (KED) is a new type of Sparse Representation for Classification (SRC), which represents the input face image as a linear combination of dictionary set and extended dictionary set to determine the input face image class label. Extended dictionary is created based on the differences between the occluded images and non-occluded training images. There are four defaults to make about KED: (1) Similar weights are assigned to the principle components of occlusion variations in KED model, while the principle components of the occlusion variations have different weights, which are proportional to the principle components Eigen-values. (2) Reconstruction of an occluded image is not possible by combining only non-occluded images and the principle components (or the directions) of occlusion variations, but it requires the mean of occlusion variations. (3) The importance and capability of main dictionary and extended dictionary in reconstructing the input face image is not the same, necessarily. (4) KED Runtime is high. To address these problems or challenges, a novel mathematical model is proposed in this paper. In the proposed model, different weights are assigned to the principle components of occlusion variations; different weights are assigned to the main dictionary and extended dictionary; an occluded image is reconstructed by non-occluded images and the principle components of occlusion variations, and also the mean of occlusion variations; and collaborative representation is used instead of sparse representation to enhance the runtime. Experimental results on CAS-PEAL subsets showed that the runtime and accuracy of the proposed model is about 1% better than that of KED.

Download Full-text

Huber collaborative representation for robust multiclass classification

International Journal of Wavelets Multiresolution and Information Processing ◽

10.1142/s0219691319500206 ◽

2019 ◽

Vol 17 (04) ◽

pp. 1950020 ◽

Cited By ~ 1

Author(s):

Cuiming Zou ◽

Yuan Yan Tang ◽

Yulong Wang ◽

Zhenghua Luo

Keyword(s):

Robust Statistics ◽

Classification Problem ◽

Multiclass Classification ◽

Classification Performance ◽

Collaborative Representation ◽

Proposed Model ◽

The Mean ◽

Classification Tasks ◽

Real World Datasets ◽

The Cost

Recent advances have shown a great potential of collaborative representation (CR) for multiclass classification. However, conventional CR-based classification methods adopt the mean square error (MSE) criterion as the cost function, which is sensitive to gross corruption and outliers. To address this limitation, inspired by the success of robust statistics, we develop a Huber collaborative representation-based classification (HCRC) method for robust multiclass classification. Concretely, we cast the classification problem as a Huber collaborative representation problem with the Huber estimator. Our another contribution is to design an efficient half-quadratic (HQ) algorithm with guaranteed convergence to solve the proposed model efficiently. Furthermore, we also give a theoretical analysis of the classification performance of HCRC. Experiments on real-world datasets corroborate that HCRC is an effective and robust algorithm for multiclass classification tasks.

Download Full-text

Simple explicit model of liquid mean flow in region above axial impeller

Collection of Czechoslovak Chemical Communications ◽

10.1135/cccc19852396 ◽

1985 ◽

Vol 50 (11) ◽

pp. 2396-2410

Author(s):

Miloslav Hošťálek ◽

Ivan Fořt

Keyword(s):

Vortex Flow ◽

Flow Model ◽

Quantitative Agreement ◽

Mean Flow ◽

Flat Bottom ◽

Proposed Model ◽

Minimum Number ◽

The Mean ◽

Model Equations ◽

Radial Circulation

The study describes a method of modelling axial-radial circulation in a tank with an axial impeller and radial baffles. The proposed model is based on the analytical solution of the equation for vortex transport in the mean flow of turbulent liquid. The obtained vortex flow model is tested by the results of experiments carried out in a tank of diameter 1 m and with the bottom in the shape of truncated cone as well as by the data published for the vessel of diameter 0.29 m with flat bottom. Though the model equations are expressed in a simple form, good qualitative and even quantitative agreement of the model with reality is stated. Apart from its simplicity, the model has other advantages: minimum number of experimental data necessary for the completion of boundary conditions and integral nature of these data.

Download Full-text

Modeling the Excess Velocity of Low-Viscous Taylor Droplets in Square Microchannels

Fluids ◽

10.3390/fluids4030162 ◽

2019 ◽

Vol 4 (3) ◽

pp. 162 ◽

Cited By ~ 2

Author(s):

Thorben Helmers ◽

Philip Kemper ◽

Jorg Thöming ◽

Ulrich Mießner

Keyword(s):

High Speed ◽

Process Intensification ◽

Continuous Phase ◽

Channel Cross Section ◽

Optimization Approach ◽

Mean Flow ◽

Bypass Flow ◽

Wall Film ◽

Proposed Model ◽

The Mean

Microscopic multiphase flows have gained broad interest due to their capability to transfer processes into new operational windows and achieving significant process intensification. However, the hydrodynamic behavior of Taylor droplets is not yet entirely understood. In this work, we introduce a model to determine the excess velocity of Taylor droplets in square microchannels. This velocity difference between the droplet and the total superficial velocity of the flow has a direct influence on the droplet residence time and is linked to the pressure drop. Since the droplet does not occupy the entire channel cross-section, it enables the continuous phase to bypass the droplet through the corners. A consideration of the continuity equation generally relates the excess velocity to the mean flow velocity. We base the quantification of the bypass flow on a correlation for the droplet cap deformation from its static shape. The cap deformation reveals the forces of the flowing liquids exerted onto the interface and allows estimating the local driving pressure gradient for the bypass flow. The characterizing parameters are identified as the bypass length, the wall film thickness, the viscosity ratio between both phases and the C a number. The proposed model is adapted with a stochastic, metaheuristic optimization approach based on genetic algorithms. In addition, our model was successfully verified with high-speed camera measurements and published empirical data.

Download Full-text

A Deep Learning Approach to Predict Autism Spectrum Disorder Using Multisite Resting-State fMRI

Applied Sciences ◽

10.3390/app11083636 ◽

2021 ◽

Vol 11 (8) ◽

pp. 3636

Author(s):

Faria Zarin Subah ◽

Kaushik Deb ◽

Pranab Kumar Dhar ◽

Takeshi Koshiba

Keyword(s):

Autism Spectrum Disorder ◽

Resting State ◽

State Of The Art ◽

Resting State Fmri ◽

Autism Spectrum ◽

Spectrum Disorder ◽

Bootstrap Analysis ◽

Proposed Model ◽

Art Methods ◽

The Mean

Autism spectrum disorder (ASD) is a complex and degenerative neuro-developmental disorder. Most of the existing methods utilize functional magnetic resonance imaging (fMRI) to detect ASD with a very limited dataset which provides high accuracy but results in poor generalization. To overcome this limitation and to enhance the performance of the automated autism diagnosis model, in this paper, we propose an ASD detection model using functional connectivity features of resting-state fMRI data. Our proposed model utilizes two commonly used brain atlases, Craddock 200 (CC200) and Automated Anatomical Labelling (AAL), and two rarely used atlases Bootstrap Analysis of Stable Clusters (BASC) and Power. A deep neural network (DNN) classifier is used to perform the classification task. Simulation results indicate that the proposed model outperforms state-of-the-art methods in terms of accuracy. The mean accuracy of the proposed model was 88%, whereas the mean accuracy of the state-of-the-art methods ranged from 67% to 85%. The sensitivity, F1-score, and area under receiver operating characteristic curve (AUC) score of the proposed model were 90%, 87%, and 96%, respectively. Comparative analysis on various scoring strategies show the superiority of BASC atlas over other aforementioned atlases in classifying ASD and control.

Download Full-text

Impedance Modeling and Stability Analysis of DFIG-Based Wind Energy Conversion System Considering Frequency Coupling

Energies ◽

10.3390/en14113243 ◽

2021 ◽

Vol 14 (11) ◽

pp. 3243

Author(s):

Shaojian Song ◽

Peichen Guan ◽

Bin Liu ◽

Yimin Lu ◽

HuiHwang Goh

Keyword(s):

Stability Analysis ◽

Coupling Effect ◽

Impedance Model ◽

Wind Energy Conversion ◽

Proposed Model ◽

New Type ◽

Impedance Modeling ◽

Frequency Coupling ◽

Bus Voltage ◽

Voltage Dynamics

Impedance-based stability analysis is an effective method for addressing a new type of SSO accidents that have occurred in recent years, especially those caused by the control interaction between a DFIG and the power grid. However, the existing impedance modeling of DFIGs is mostly focused on a single converter, such as the GSC or RSC, and the influence between the RSC and GSC, as well as the frequency coupling effect inside the converter are usually overlooked, reducing the accuracy of DFIG stability analysis. Hence, the entire impedance is proposed in this paper for the DFIG-based WECS, taking coupling factors into account (e.g., DC bus voltage dynamics, asymmetric current regulation in the dq frame, and PLL). Numerical calculations and HIL simulations on RT-Lab were used to validate the proposed model. The results indicate that the entire impedance model with frequency coupling is more accurate, and it is capable of accurately predicting the system’s possible resonance points.

Download Full-text

Cotton Stand Counting from Unmanned Aerial System Imagery Using MobileNet and CenterNet Deep Learning Models

Remote Sensing ◽

10.3390/rs13142822 ◽

2021 ◽

Vol 13 (14) ◽

pp. 2822

Author(s):

Zhe Lin ◽

Wenxuan Guo

Keyword(s):

Deep Learning ◽

Cotton Plant ◽

Unmanned Aerial System ◽

Learning Models ◽

Training Images ◽

Testing Dataset ◽

Cotton Plants ◽

Detection And Counting ◽

Different Dimensions ◽

The Mean

An accurate stand count is a prerequisite to determining the emergence rate, assessing seedling vigor, and facilitating site-specific management for optimal crop production. Traditional manual counting methods in stand assessment are labor intensive and time consuming for large-scale breeding programs or production field operations. This study aimed to apply two deep learning models, the MobileNet and CenterNet, to detect and count cotton plants at the seedling stage with unmanned aerial system (UAS) images. These models were trained with two datasets containing 400 and 900 images with variations in plant size and soil background brightness. The performance of these models was assessed with two testing datasets of different dimensions, testing dataset 1 with 300 by 400 pixels and testing dataset 2 with 250 by 1200 pixels. The model validation results showed that the mean average precision (mAP) and average recall (AR) were 79% and 73% for the CenterNet model, and 86% and 72% for the MobileNet model with 900 training images. The accuracy of cotton plant detection and counting was higher with testing dataset 1 for both CenterNet and MobileNet models. The results showed that the CenterNet model had a better overall performance for cotton plant detection and counting with 900 training images. The results also indicated that more training images are required when applying object detection models on images with different dimensions from training datasets. The mean absolute percentage error (MAPE), coefficient of determination (R2), and the root mean squared error (RMSE) values of the cotton plant counting were 0.07%, 0.98 and 0.37, respectively, with testing dataset 1 for the CenterNet model with 900 training images. Both MobileNet and CenterNet models have the potential to accurately and timely detect and count cotton plants based on high-resolution UAS images at the seedling stage. This study provides valuable information for selecting the right deep learning tools and the appropriate number of training images for object detection projects in agricultural applications.

Download Full-text

Quantitative analysis of static equilibrium in women after mastectomy

International Journal on Disability and Human Development ◽

10.1515/ijdhd-2013-0041 ◽

2014 ◽

Vol 14 (1) ◽

pp. 81-87

Author(s):

Maciej Rachwał ◽

Justyna Drzał-Grabiec ◽

Katarzyna Walicka-Cupryś ◽

Aleksandra Truszczyńska

Keyword(s):

Mean Amplitude ◽

Control Group ◽

Foot Pressure ◽

Locomotor System ◽

Center Of Foot Pressure ◽

The Mean ◽

Almost All ◽

Posture Stability ◽

Mastectomy Group ◽

Better Than

Abstract Background: The post-mastectomy changes to the locomotor system are related to the scar and adhesion or to the lymphatic edema after amputation which, in turn, lead to local and global distraction of the work of the muscles. These changes lead to body statics disturbance that changes the projection of the center of gravity and worsens motor response due to changing of the muscle sensitivity. Objective: The aim of the study was to evaluate the static balance of women after undergoing mastectomy. Methods: The study included 150 women, including 75 who underwent mastectomy (mean age: 60±7.6) years, mean body mass index (BMI): 26 (±3.6) kg/m2) and 75 who were placed in the control group with matched age and BMI. The study was conducted using a tensometric platform. Results: Statistically significant differences were found for almost all parameters between the post-mastectomy group and group of healthy women, regarding center of foot pressure (COP) path length in the Y and X axes and the mean amplitude of COP. Conclusions: First, the findings revealed that balance in post-mastectomy women is significantly better than in the control group. Second, physiotherapeutic treatment of post-mastectomy women may have improved their posture stability compared with their peers.

Download Full-text

Heterobeltiosis in French Marigold (Tagetes patula L.)

Journal of Agricultural Science ◽

10.5539/jas.v8n8p182 ◽

2016 ◽

Vol 8 (8) ◽

pp. 182

Author(s):

Kanwar Priyanaka ◽

Y. C. Gupta ◽

S. R. Dhiman ◽

R. K. Dogra ◽

Sharma Madhu ◽

...

Keyword(s):

Rainy Season ◽

Quantitative Traits ◽

Block Design ◽

Tagetes Patula ◽

Male Sterile ◽

Randomized Block Design ◽

Parental Material ◽

The Mean ◽

Parental Lines ◽

Better Than

The studies on heterosis were carried with four male sterile lines namely; ms7, ms8, ms9, ms10 and 18 diverse pollinators as tester by using line × tester crossing programme. The 72 F1 hybrids were produced and evaluated along with 22 parental lines during summer 2009 and rainy season 2009 in Randomized Block Design. Observations were recorded on nine quantitative traits during both the seasons. Highly significant variances for all the traits indicated the sufficient variability in the parental material for all the characters under study. The performance of F1 hybrids was much better than the mean performance of parents during both the crop seasons. Appreciable heterosis was observed in all the characters, except flower weight in summer and plant height in rainy season.

Download Full-text

Stability and Stabilization for Discrete System With Probabilistic Nonlinearities

Journal of Dynamic Systems Measurement and Control ◽

10.1115/1.4024305 ◽

2013 ◽

Vol 135 (5) ◽

Cited By ~ 2

Author(s):

Xia Zhao ◽

Engang Tian

Keyword(s):

Sufficient Conditions ◽

Discrete Systems ◽

System Model ◽

Linear Matrix ◽

Time Varying Delay ◽

Mean Square Stability ◽

New Type ◽

Stability And Stabilization ◽

The Mean ◽

Varying Delay

This paper investigates stability and stabilization of discrete systems with probabilistic nonlinearities and time-varying delay. New characters of the nonlinearities, the probability of the nonlinearities happening between different bounds, are used to build new type of system model, which can help us make a full use of the inner variation information of the nonlinearities. With the help of the new characters, new system model is proposed. Then, sufficient conditions for the mean square stability of the system can be obtained by using the Lyapunov functional approach and linear matrix inequalities technique. An example is proposed to illustrate the efficiency of the proposed method.

Download Full-text

Material Considerations in the Microfabrication of Grating Microstructures for use in a Laser-Powered Linear Accelerator

MRS Proceedings ◽

10.1557/proc-76-129 ◽

1986 ◽

Vol 76 ◽

Cited By ~ 2

Author(s):

John B. Warren

Keyword(s):

Linear Accelerator ◽

Material Selection ◽

Collaborative Work ◽

Fused Silica ◽

Image Analyzer ◽

Metrological Analysis ◽

Field Gradients ◽

New Type ◽

Specialized Form ◽

Better Than

ABSTRACTCollaborative work between Brookhaven and Los Alamos National Laboratories is developing a new type of linear accelerator that uses a high-power, picosecond pulse CO2 laser to irradiate a specialized form of grating with a pitch of 10.6 microns. The electromagnetic field that results can be used to accelerate electrons at field gradients of several GeV/m with potential efficiencies much better than current accelerators. The grating must be conductive to minimize resistive losses, be able to withstand high fields without damage, and requires dimensional tolerances in the sub-micron range. These requirements focus attention on grating material selection, microfabrication methods, and metrological methods used for quality control. At present, several types of gratings have been manufactured by reactive ion etching of fused silica in CHF 3/Ar or etching silicon with KOH/H 2O or ethylenediamine-pyrocatechol solutions. Metrological analysis of the gratings has begun with a Tracor Northern 5700 digital image analyzer.

Download Full-text