Search results

The purpose of this study is to introduce a novel approach for seam pucker analysis based on wave shape parameters.

In this method the uneven wavy curve along the puckered seam line was put into a deconvolution process and broken into several simple Gaussian curves using residual mathematical analysis method. First puckered samples with five different grades were produced and scanned by laser triangulated technology. After implementation of deconvolution method, the key geometrical parameters of the decomposed waves such as number of waves and their shape parameters like wave's area, amplitude and wave length were extracted. In addition, an objective method was developed and five indexes were introduced.

Analysis showed that there is a high linear relation with high correlation between all pucker indexes and subjective pucker evaluation.

The goal of this research was to analyse the five grades of seam puckered samples and extract the basic structural parameters to solidify the characteristic of each puckered grade, in order to exclude the influence of human perception.

Simulating the behavior of clothing has always been of interest in the apparel, fashion and computer game industries. With the development of these industries, there is a need to increase the accuracy of clothing simulation techniques. A garment contains many seams whose behavior affects its final appearance. In this study, a numerical model is presented to simulate seam puckers in single- and double-layer fabrics.

A yarn-level simulation technique has been used for this purpose. Based on this technique, the individual threads in the fabric structure and the sewing threads are modeled separately. Then, their behavior and interaction with each other are considered in the seam pucker model.

The model is used to simulate the real samples. The results show that the proposed model is able to simulate the degree of seam puckering for a single-layer fabric with an average error of 7.9% and for a double-layer fabric with an average error of 8.5%.

The behavior of the seam is affected by the properties, behavior and interaction of the sewing threads and yarns in the fabric structure. In previous studies, the parameters related to seams and fabrics were not fully considered. In this study, a new yarn-level model is presented to simulate seam puckering in woven fabrics. The most important advantage of this type of simulation is the ability to examine the interaction of fabric threads as well as the interaction of sewing threads with each other and with the threads of the fabric structure.

The purpose of this paper is to propose a novel method using support vector machine (SVM) classifiers for objective seam pucker evaluation. Features are extracted using wavelet analysis and gray-level co-occurrence matrix (GLCM), and the samples are evaluated using SVM classifiers. The study aims to solve the problem of inappropriate parameters and large required samples in objective seam pucker evaluation.

Initially, seam pucker image was captured, and Edge detection and Hough transform were utilized to normalize the seam position and orientation. After cropping the image, the intensity was adjusted to the same identical level through histogram specification. Then, the standard deviations of the horizontal image and diagonal image, reconstructed using wavelet decomposition and reconstruction, were calculated based on parameter optimization. Meanwhile, GLCM was extracted from the restructured horizontal detail image, then the contrast and correlation of GLCM were calculated. Finally, these four features were imported to SVM classifiers based on genetic algorithm for evaluation.

The four extracted features reflected linear relationships among five grades. The experimental results showed that the classification accuracy was 96 percent, which catches up to the performance of human vision, and resolves ambiguity and subjective of the manual evaluation.

There are large required samples in current research. This paper provides a novel method using finite samples, and the parameters of the methods were discussed for parameter optimization. The evaluation results can provide references for analyzing the reason of wrinkles during garment manufacturing.

This paper aims to characterize the mineral composition of Martian surfaces based on Thermal Emission Spectrometer (TES; Mars Global Surveyor) as measured in the infrared thermal range. It presents modeling and interpreting of TES spectral data from selected Martian regions from which the atmospheric influences had been removed using radiative transfer algorithm and deconvolution algorithm. The spectra from the dark area of Cimmeria Terra and the bright Isidis Planitia were developed in Philip Christensen’s and Joshua Bandfield’s publications, where these spectra were subjected to spectral deconvolution to estimate the mineral composition of the Martian surface. The results of the analyses of these spectra were used for the modeling of dusty and non-dusty surface of Mars. As an additional source, the mineral compositions of Polish basalts and mafic rocks were used for these surfaces as well as for modeling Martian meteorites Shergottites, Nakhlites and Chassignites. Finally, the spectra for the modeling of the Hellas region were obtained from the Planetary Fourier Spectrometer (PFS) – (Mars Express) and the mineralogical compositions of basalts from the southern part of Poland were used for this purpose. The Hellas region was modeled also using simulated Martian soil samples Phyllosilicatic Mars Regolith Simulant and Sulfatic Mars Regolith Simulant, showing as a result that the composition of this selected area has a high content of sulfates. Linear spectral combination was chosen as the best modeling method. The modeling was performed using PFSLook software written in the Space Research Centre of the Polish Academy of Sciences. Additional measurements were made with an infrared spectrometer in thermal infrared spectroscopy, for comparison with the measurements of PFS and TES. The research uses a kind of modeling that successfully matches mineralogical composition to the measured spectrum from the surface of Mars, which is the main goal of the publication. This method is used for areas where sample collection is not yet possible. The areas have been chosen based on public availability of the data.

The infrared spectra of the Martian surface were modeled by applying the linear combination of the spectra of selected minerals, which then are normalized against the measured surface area with previously separated atmosphere. The minerals for modeling are selected based on the expected composition of the Martian rocks, such as basalt. The software used for this purpose was PFSLook, a program written in C++ at the Space Research Centre of the Polish Academy of Sciences, which is based on adding the spectra of minerals in the relevant percentage, resulting in a final spectrum containing 100 per cent of the minerals.

The results of this work confirmed that there is a relationship between the modeled, altered and unaltered, basaltic surface and the measured spectrum from Martian instruments. Spectral deconvolution makes it possible to interpret the measured spectra from areas that are potentially difficult to explore or to choose interesting areas to explore on site. The method is described for mid-infrared because of software availability, but it can be successfully applied to shortwave spectra in near-infrared (NIR) band for data from the currently functioning Martian spectroscopes.

This work is the only one attempting modeling the spectra of the surface of Mars with a separated atmosphere and to determine the mineralogical composition.

The aim of the present study is to consider the influence of the tensile behavior of fabric and sewing thread on the seam appearance.

In this study, the formation of seam puckering on two elastic and normal woven fabrics was explored. In order to prepare samples, various sewing threads were applied. Test specimens were sewn under five different thread tension levels. Then the appearance of samples was evaluated subjectively to determine their seam puckering grade before and after the laundering process.

The obtained outcomes of this study present that although sewing thread tension increment decreases the seam pucker ranking in the similar sewing condition, elastic fabrics have a greater seam pucker grade compared to the normal fabric due to the fabric extension and contraction during sewing and after sewing process, respectively. In addition, the elastic strain of the sewing thread is the key factor that determined sewing thread's tendency to make seam puckering. Moreover, the laundry process due to the relaxation of the sewing thread decreases the seam pucker grade.

The consistency of the tensile property of fabric and sewing thread is a crucial parameter in improving the seam appearance and obtaining a smooth seam.

We develop a Bayesian approach for modeling brain activation and connectivity from functional magnetic resonance image (fMRI) data. Our approach simultaneously estimates local hemodynamic response functions (HRFs) and activation parameters, as well as global effective and functional connectivity parameters. Existing methods assume identical HRFs across brain regions, which may lead to erroneous conclusions in inferring activation and connectivity patterns. Our approach addresses this limitation by estimating region-specific HRFs. Additionally, it enables neuroscientists to compare effective connectivity networks for different experimental conditions. Furthermore, the use of spike and slab priors on the connectivity parameters allows us to directly select significant effective connectivities in a given network.

We include a simulation study that demonstrates that, compared to the standard generalized linear model (GLM) approach, our model generally has higher power and lower type I error and bias than the GLM approach, and it also has the ability to capture condition-specific connectivities. We applied our approach to a dataset from a stroke study and found different effective connectivity patterns for task and rest conditions in certain brain regions of interest (ROIs).

This paper aims to determine the crystallite size and microstrain values of AgSiN thin films using potential approach called approximation method. This method can be used as a replacement for other determination methods such as Williamson-Hall (W-H) plot and Warren-Averbach analysis.

The monolayer AgSiN thin films on Ti6Al4V alloy were fabricated using magnetron sputtering technique. To evaluate the crystallite size and microstrain values, the thin films were deposited under different bias voltage (−75, −150 and −200 V). X-ray diffraction (XRD) broadening profile along with approximation method were used to determine the crystallite size and microstrain values. The reliability of the method was proved by comparing it with scanning electron microscopy graph and W-H plot method. The second parameters’ microstrain obtained was used to project the residual stress present in the thin films. Further discussion on the thin films was done by relating the residual stress with the adhesion strength and the thickness of the films.

XRD-approximation method results revealed that the crystallite size values obtained from the method were in a good agreement when it is compared with Scherer formula and W-H method. Meanwhile, the calculations for thin films corresponding residual stresses were correlated well with scratch adhesion critical loads with the lowest residual stress was noted for sample with lowest microstrain and has thickest thickness among the three samples.

The fabricated thin films were intended to be used in antibacterial applications.

Up to the knowledge from literature review, there are no reports on depositing AgSiN on Ti6Al4V alloy via magnetron sputtering to elucidate the crystallite size and microstrain properties using the approximation method.

This paper primarily aims to focus on a review of convolutional neural network (CNN)-based eye control systems. The performance of CNNs in big data has led to the development of eye control systems. Therefore, a review of eye control systems based on CNNs is helpful for future research.

In this paper, first, it covers the fundamentals of the eye control system as well as the fundamentals of CNNs. Second, the standard CNN model and the target detection model are summarized. The eye control system’s CNN gaze estimation approach and model are next described and summarized. Finally, the progress of the gaze estimation of the eye control system is discussed and anticipated.

The eye control system accomplishes the control effect using gaze estimation technology, which focuses on the features and information of the eyeball, eye movement and gaze, among other things. The traditional eye control system adopts pupil monitoring, pupil positioning, Hough algorithm and other methods. This study will focus on a CNN-based eye control system. First of all, the authors present the CNN model, which is effective in image identification, target detection and tracking. Furthermore, the CNN-based eye control system is separated into three categories: semantic information, monocular/binocular and full-face. Finally, three challenges linked to the development of an eye control system based on a CNN are discussed, along with possible solutions.

This research can provide theoretical and engineering basis for the eye control system platform. In addition, it also summarizes the ideas of predecessors to support the development of future research.

The purpose of this paper is to demonstrate that by utilizing the relationship between redundant hardware components, inherent in parallel machinery, vibration-based fault detection methods can be made more robust to changes in operational conditions. This work reports on a study of fault detection on bearings operating in two parallel subsystems that experience identical changes in speed and load.

This study was carried out using two identical subsystems that operate on the same duty cycle. The systems were run with both healthy and a variety of common bearing faults. The faults were detected by analyzing the residual between the features of the two vibration signatures from the two subsystems.

This work found that by utilizing this relationship in parallel operating machinery the fault detection process can be improved. The study looked at several different types of feature vector and found that, in this case, features based on envelope analysis or autoregressive model work the best, whereas basic statistical features did not work as well.

The proposed method can be a computationally efficient and simple solution to monitoring non-stationary machinery where there is hardware redundancy present. This method is shown to have some advantages over non-parallel approaches.

The defect detection problem of color-patterned fabric is still a huge challenge due to the lack of manual defect labeling samples. Recently, many fabric defect detection algorithms based on feature engineering and deep learning have been proposed, but these methods have overdetection or miss-detection problems because they cannot adapt to the complex patterns of color-patterned fabrics. The purpose of this paper is to propose a defect detection framework based on unsupervised adversarial learning for image reconstruction to solve the above problems.

The proposed framework consists of three parts: a generator, a discriminator and an image postprocessing module. The generator is able to extract the features of the image and then reconstruct the image. The discriminator can supervise the generator to repair defects in the samples to improve the quality of image reconstruction. The multidifference image postprocessing module is used to obtain the final detection results of color-patterned fabric defects.

The proposed framework is compared with state-of-the-art methods on the public dataset YDFID-1(Yarn-Dyed Fabric Image Dataset-version1). The proposed framework is also validated on several classes in the MvTec AD dataset. The experimental results of various patterns/classes on YDFID-1 and MvTecAD demonstrate the effectiveness and superiority of this method in fabric defect detection.

It provides an automatic defect detection solution that is convenient for engineering applications for the inspection process of the color-patterned fabric manufacturing industry. A public dataset is provided for academia.