Jun Xiang, Ruru Pan and Weidong Gao
The paper aims to propose a novel method based on deep sparse convolutional neural network (CNN) for clothing recognition. A CNN based on inception module is applied to bridge…
Abstract
Purpose
The paper aims to propose a novel method based on deep sparse convolutional neural network (CNN) for clothing recognition. A CNN based on inception module is applied to bridge pixel-level features and high-level category labels. In order to improve the robustness accuracy of the network, six transformation methods are used to preprocess images. To avoid representational bottlenecks, small-sized convolution kernels are adopted in the network. This method first pretrains the network on ImageNet and then fine-tune the model in clothing data set.
Design/methodology/approach
The paper opts for an exploratory study by using the control variable comparison method. To verify the rationality of the network structure, lateral contrast experiments with common network structures such as VGG, GoogLeNet and AlexNet, and longitudinal contrast tests with different structures from one another are performed on the created clothing image data sets. The indicators of comparison include accuracy, average recall, average precise and F-1 score.
Findings
Compared with common methods, the experimental results show that the proposed network has better performance on clothing recognition. It is also can be found that larger input size can effectively improve accuracy. By analyzing the output structure of the model, the model learns a certain “rules” of human recognition clothing.
Originality/value
Clothing analysis and recognition is a meaningful issue, due to its potential values in many areas, including fashion design, e-commerce and retrieval system. Meanwhile, it is challenging because of the diversity of clothing appearance and background. Thus, this paper raises a network based on deep sparse CNN to realize clothing recognition.
Details
Keywords
The purpose of the paper is researching on the motion law of fiber in the vortex field inside the nozzle.
Abstract
Purpose
The purpose of the paper is researching on the motion law of fiber in the vortex field inside the nozzle.
Design/methodology/approach
A three-dimensional calculation model was established using the MVS861 (Muratec Vortex Spinning) air-jet vortex-spinning nozzle as the prototype, and the fluid–solid coupling calculation module in the finite element calculation software ADINA (Adina System) was used to numerically analyze the fiber-air flow two-phase coupling. At the same time, the effect of the air pressure at the nozzle on the two-phase flow is studied.
Findings
The results show that after the air flow ejected through the nozzle, a vortex field will be generated in the flow field to push the internal fiber to move toward the nozzle outlet in a wave motion; as the air pressure at the nozzle increases, the fiber movement period becomes shorter and the oscillation frequency becomes higher; increasing the air pressure at the spray hole can improve the working efficiency of fiber twisting and wrapping.
Originality/value
The research present an effective and feasible theoretical model and method for the motion law of fiber in the vortex field inside the nozzle based on ADINA fluid–structure coupling model.
Details
Keywords
Ning Zhang, Ruru Pan, Lei Wang, Shanshan Wang, Jun Xiang and Weidong Gao
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…
Abstract
Purpose
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.
Design/methodology/approach
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.
Findings
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.
Originality/value
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.
Details
Keywords
Yuzheng Lu, Weidong Gao and Hongbo Wang
This paper seeks to build a mathematical model to deduct the twists distribution in the slub‐yarn.
Abstract
Purpose
This paper seeks to build a mathematical model to deduct the twists distribution in the slub‐yarn.
Design/methodology/approach
The model, considering the shearing modulus and polar moment of inertia of the yarn, influenced by the yarn density, is established based on the bar torsion model. The twists distribution in the slub‐yarn is concluded based on the analysis of the results. The rules were verified via an indirect method, by testing the breaking strength of the slub‐yarn.
Findings
The results of the analysis showed that twists in every section of the slub‐yarn are in inverse proportion to the square of the line density of the corresponding section. Slub length is a key factor to the twist in the base yarn, and the increase of the slub length will increase the twist; while the multiple is the key factor to the slub twist, and the enhancement of the multiple will decrease the twist significantly.
Research limitations/implications
The analysis cannot be verified via a direct method. A new, more conceivable direct method should be utilized to test the result.
Originality/value
The paper builds a base for the research of the mechanical properties of slub‐yarn and gives directions to the slub‐yarn production.
Details
Keywords
Jihong Liu, Itsuo Yamaura and Weidong Gao
This paper deals with the reflecting rays of yarn.
Abstract
Purpose
This paper deals with the reflecting rays of yarn.
Design/methodology/approach
The modeling, assuming that the fibers are arranged around the surface of elliptic yarn and reflecting rays of yarn are consisted of reflecting rays of fibers, is established using mathematical method. We can get a distributional curve of reflecting rays by this method.
Findings
It was found that because resolution was an important parameter in measurement equipment, the result of modeling must be filtered. It gives fundamental theory for selecting resolution and we also provide other useful value for selecting equipment of image processing. Resolution is an important parameter for measurement equipment. We have provided the minimum resolution for yarn. When we do image processing for yarn, we can get correct information of yarn by image processing with the minimum resolution and over.
Research limitations/implications
The result using different measurement equipment does not show the same result, therefore, the model must be filtered according to resolution.
Orginality/value
Although previous researches have used the reflecting property of yarn, little work that analyzed the reflecting model of yarn and the relationship between resolution and reflecting property has been achieved. We present a method of analyzing reflection of yarn.
Details
Keywords
Examines the fifthteenth published year of the ITCRR. Runs the whole gamut of textile innovation, research and testing, some of which investigates hitherto untouched aspects…
Abstract
Examines the fifthteenth published year of the ITCRR. Runs the whole gamut of textile innovation, research and testing, some of which investigates hitherto untouched aspects. Subjects discussed include cotton fabric processing, asbestos substitutes, textile adjuncts to cardiovascular surgery, wet textile processes, hand evaluation, nanotechnology, thermoplastic composites, robotic ironing, protective clothing (agricultural and industrial), ecological aspects of fibre properties – to name but a few! There would appear to be no limit to the future potential for textile applications.
Details
Keywords
Yuzhen Long, Chunli Yang, Xiangchun Li, Weidong Lu, Qi Zhang and Jiaxing Gao
Coal is the basic energy and essential resource in China, which is crucial to the economic lifeline and energy security of the country. Coal mining has been ever exposed to…
Abstract
Purpose
Coal is the basic energy and essential resource in China, which is crucial to the economic lifeline and energy security of the country. Coal mining has been ever exposed to potential safety risks owing to the complex geologic environment. Effective safety supervision is a vital guarantee for safe production in coal mines. This paper aims to explore the impacts of the internet+ coal mine safety supervision (CMSS) mode that is being emerged in China.
Design/methodology/approach
In this study, the key factors influencing CMSS are identified by social network analysis. They are used to develop a multiple linear regression model of law enforcement frequency for conventional CMSS mode, which is then modified by an analytical hierarchy process to predict the law enforcement frequency of internet+ CMSS mode.
Findings
The regression model demonstrated high accuracy and reliability in predicting law enforcement frequency. Comparative analysis revealed that the law enforcement frequency in the internet+ mode was approximately 40% lower than the conventional mode. This reduction suggests a potential improvement in cost-efficiency, and the difference is expected to become even more significant with an increase in law enforcement frequency.
Originality/value
To the best of the authors’ knowledge, this is one of the few available pieces of research which explore the cost-efficiency of CMSS by forecasting law enforcement frequency. The study results provide a theoretical basis for promoting the internet+ CMSS mode to realize the healthy and sustainable development of the coal mining industry.
Details
Keywords
Cloud-based technologies are reliably improving Information Technology (IT) environment incorporating changes and modifications to the present business structure. Cloud computing…
Abstract
Purpose
Cloud-based technologies are reliably improving Information Technology (IT) environment incorporating changes and modifications to the present business structure. Cloud computing enables small and medium-sized businesses (SMBs) to organize and exchange pertinent data and information in real time. This study checks out the influence of cloud-based services (IT infrastructure, expenses of cloud services, cloud data security and IT knowledge of human resources) on customers' satisfaction in SMBs.
Design/methodology/approach
Cloud computing offers a way to coordinate and share organizational and personal information and data. The adoption of cloud services is one of the most emerging technological advances in the current competitive business environment. Cloud-based services allow start-ups or SMBs to take advantage of technological advancements and respond more quickly to changing consumer demands. In the available literature, cloud computing has received a lot of attention. However, there is also a research gap in creating a paradigm that links the value development drivers in the electronic industry with the leveraging impact of cloud and intercloud computing resources for start-ups and SMBs. A hypothetical model was constructed based on a literature review, and the associations between the latent variables were investigated utilizing structural equations.
Findings
Findings from the study confirmed the validity of the proposed model for customer satisfaction assessment. Besides, the results showed that customer satisfaction is affected by cloud-based services in SMBs. The results illustrated that IT infrastructure influences customer satisfaction significantly and positively, with a T-value of 2.42. Also, the results confirmed that the cost of cloud services with a T-value of 2.68 affects customer satisfaction significantly and positively. Cloud data security also impacts customer satisfaction with a T-value of 5.20. The results also showed that the IT knowledge of human resources affects customer satisfaction with a T-value of 3.01.
Originality/value
The main originality of this research is proposing a new conceptual model to assess the impact of cloud-based services on the satisfaction of the customers in SMBs.
Details
Keywords
Wenrui Gao, Weidong Wang, Hongbiao Zhu, Shunping Zhao, Guofu Huang and Zhijiang Du
The paper aims to improve the radiation-proof capability of the self-designed mobile robot with a 7-DOF manipulator, enabling the long-playing inspection and intervention under…
Abstract
Purpose
The paper aims to improve the radiation-proof capability of the self-designed mobile robot with a 7-DOF manipulator, enabling the long-playing inspection and intervention under high-dose radiation environment. In this context, gamma-ray irradiation test for electronic components and specific hardness design have also been specifically presented and discussed.
Design/methodology/approach
The study’s hardness design mainly focuses on shielding protection, distance protection and time protection. Irradiation test is first carried out to investigate irradiation resistance of each electronic module. Then, modular deployment and shielding calculation are completed for the point-type nuclear accidents, respectively, to achieve a robust anti-radiation design scheme. Finally, the field experiment is conducted to validate system effectiveness and good mobility, and operational practices are acquired for the realization of time protection.
Findings
Coupled with modular redeployment and shielding design, irradiation results illustrate the effectiveness of robotic anti-radiation design. Meanwhile, experiences and reformed measures from the field exercise implement efficient operation and radiological time protection.
Research limitations/implications
Considering the huge risks of high-dose source exposure, the radiation-resistance of the overall system cannot be verified in the field experiment. Fortunately, irradiation test and modular shielding calculation are conducted as a minimal validation.
Practical implications
The proposed anti-radiation design methods and the irradiated results can be applied to many other nuclear vehicles and manipulators for the feasible multi-layer protection and excellent mobility.
Originality/value
A nuclear intervention robot with specific hardness design is presented in detail in this paper. Enlightened by the idea of shielding and distance protection, a large number of electronic modules with multiple types and structures are treated and compared in irradiation experiments, while modular redeployment and retrofitting are completed to reduce irradiated damages. To achieve the effect of time protection, mobility performance and operational practices are discussed and validated in the field experiment based on the mobile system.
Details
Keywords
Weidong Wang, Wenrui Gao, DongMei Wu and Zhijiang Du
The paper aims to present a tracked robot comprised of several biochemical sampling instruments and a universal control architecture. In addition, a dynamic motion planning…
Abstract
Purpose
The paper aims to present a tracked robot comprised of several biochemical sampling instruments and a universal control architecture. In addition, a dynamic motion planning strategy and autonomous modules in sampling tasks are designed and illustrated at length.
Design/methodology/approach
Several sampling instruments with position tolerance and sealing property are specifically developed, and a robotic operation system (ROS)-based universal control architecture is established. Then, based on the system, two typical problems in sampling tasks, i.e. arm motion planning in unknown environment and autonomous modules, are discussed, implemented and tested. Inspired by the idea of Gaussian process classification (GPC) and Gaussian process (GP) information entropy, three-dimensional (3D) geometric modeling and arm obstacle avoidance strategy are implemented and proven successfully. Moreover, autonomous modules during sampling process are discussed and realized.
Findings
Smooth implementations of the two experiments justify the validity and extensibility of the robot control scheme. Furthermore, the former experiment proves the efficiency of arm obstacle avoidance strategy, while the later one demonstrates the time reduction and accuracy improvement in sampling tasks as the autonomous actions.
Practical implications
The proposed control architecture can be applied to more mobile and industrial robots for its feasible and extensible scheme, and the utility function in arm path planning strategy can also be utilized for other information-driven exploration tasks.
Originality/value
Several specific biochemical sampling instruments are presented in detail, while ROS and Moveit! are integrated into the system scheme, making the robot extensible, achievable and real-time. Based on the control scheme, an information-driven path planning algorithm and automation in sampling tasks are conceived and implemented.