Search results
1 – 10 of 373Sara El-Ateif, Ali Idri and José Luis Fernández-Alemán
COVID-19 continues to spread, and cause increasing deaths. Physicians diagnose COVID-19 using not only real-time polymerase chain reaction but also the computed tomography (CT…
Abstract
Purpose
COVID-19 continues to spread, and cause increasing deaths. Physicians diagnose COVID-19 using not only real-time polymerase chain reaction but also the computed tomography (CT) and chest x-ray (CXR) modalities, depending on the stage of infection. However, with so many patients and so few doctors, it has become difficult to keep abreast of the disease. Deep learning models have been developed in order to assist in this respect, and vision transformers are currently state-of-the-art methods, but most techniques currently focus only on one modality (CXR).
Design/methodology/approach
This work aims to leverage the benefits of both CT and CXR to improve COVID-19 diagnosis. This paper studies the differences between using convolutional MobileNetV2, ViT DeiT and Swin Transformer models when training from scratch and pretraining on the MedNIST medical dataset rather than the ImageNet dataset of natural images. The comparison is made by reporting six performance metrics, the Scott–Knott Effect Size Difference, Wilcoxon statistical test and the Borda Count method. We also use the Grad-CAM algorithm to study the model's interpretability. Finally, the model's robustness is tested by evaluating it on Gaussian noised images.
Findings
Although pretrained MobileNetV2 was the best model in terms of performance, the best model in terms of performance, interpretability, and robustness to noise is the trained from scratch Swin Transformer using the CXR (accuracy = 93.21 per cent) and CT (accuracy = 94.14 per cent) modalities.
Originality/value
Models compared are pretrained on MedNIST and leverage both the CT and CXR modalities.
Details
Keywords
Amirul Syafiq, Vengadaesvaran Balakrishnan and Nasrudin Abd. Rahim
This paper aims to design the nano-titanium dioxide (TiO2) coating system which has superhydrophilic property, self-cleaning mechanism and antifog property as well as strong…
Abstract
Purpose
This paper aims to design the nano-titanium dioxide (TiO2) coating system which has superhydrophilic property, self-cleaning mechanism and antifog property as well as strong adhesion on glass substrate.
Design/methodology/approach
Two hydrophilic materials have been used such as TiO2 nanoparticles as fillers and hydrophilic copolymer, Pluronic F-127 by using simple sol–gel approach. The prepared solution was applied onto glass through dip- and spray-coating techniques and then left for drying at ambient temperature.
Findings
The nano-TiO2 superhydrophilic coating has achieved the water contact angle of 4.9° ± 0.5°. The superhydrophilic coating showed great self-cleaning effect against concentrated syrup and methylene blue where thin layer of water washes the dirt contaminants away. The nano-TiO2 coating exhibits great antifog performance that maintains high transparency of around 89% when the coated glass is placed above hot-fog vapor for 10 min. The fog droplets were condensed into water film which allowed the transmission of light through the glass. The strong adhesion of coated glass shows no total failure at scratch profile when impacted with scratch load of 500, 800 and 1,200 mN.
Research limitations/implications
Findings will be useful in the development of self-cleaning superhydrophilic coating that is applicable on building glass and photovoltaic panel.
Practical implications
The developed nano-TiO2 coating is developed by the combination of hydrophilic organic copolymer–inorganic TiO2 network to achieve great superhydrophilic property, optimum self-cleaning ability and supreme antifog performance.
Social implications
The findings will be useful for residents in building glass window where the application will reduce dust accumulation and keep the glass clean for longer period.
Originality/value
The synthesis of nano-TiO2 superhydrophilic coating which can be sprayed on large glass panel and cured at ambient temperature.
Details
Keywords
Wang Zhang, Lizhe Fan, Yanbin Guo, Weihua Liu and Chao Ding
The purpose of this study is to establish a method for accurately extracting torch and seam features. This will improve the quality of narrow gap welding. An adaptive deflection…
Abstract
Purpose
The purpose of this study is to establish a method for accurately extracting torch and seam features. This will improve the quality of narrow gap welding. An adaptive deflection correction system based on passive light vision sensors was designed using the Halcon software from MVtec Germany as a platform.
Design/methodology/approach
This paper proposes an adaptive correction system for welding guns and seams divided into image calibration and feature extraction. In the image calibration method, the field of view distortion because of the position of the camera is resolved using image calibration techniques. In the feature extraction method, clear features of the weld gun and weld seam are accurately extracted after processing using algorithms such as impact filtering, subpixel (XLD), Gaussian Laplacian and sense region for the weld gun and weld seam. The gun and weld seam centers are accurately fitted using least squares. After calculating the deviation values, the error values are monitored, and error correction is achieved by programmable logic controller (PLC) control. Finally, experimental verification and analysis of the tracking errors are carried out.
Findings
The results show that the system achieves great results in dealing with camera aberrations. Weld gun features can be effectively and accurately identified. The difference between a scratch and a weld is effectively distinguished. The system accurately detects the center features of the torch and weld and controls the correction error to within 0.3mm.
Originality/value
An adaptive correction system based on a passive light vision sensor is designed which corrects the field-of-view distortion caused by the camera’s position deviation. Differences in features between scratches and welds are distinguished, and image features are effectively extracted. The final system weld error is controlled to 0.3 mm.
Details
Keywords
Guihang Liu, Runxia Guo and Jiusheng Chen
Maintenance stands are the most valuable maintenance resources and provide the necessary maintenance space and maintenance facilities for aircraft maintenance. To expand the…
Abstract
Purpose
Maintenance stands are the most valuable maintenance resources and provide the necessary maintenance space and maintenance facilities for aircraft maintenance. To expand the maintenance market, maintenance, repair and overhaul (MRO) urgently need to achieve a reasonable schedule between aircraft maintenance requirements and maintenance stand capability to improve aircraft maintenance continuity and reduce the risk of scratching due to aircraft movement. This study aims to design a maintenance stand scheduling (MSS) model based on spatiotemporal constraints to solve the problem of maintenance stand schedules.
Design/methodology/approach
To address the problem of maintenance stand schedules, this study introduces mixed-integer programming algorithm to design the MSS model on the basis of classical hybrid flow shop structure. When designing the optimization objective function of MSS modeling, the spatiotemporal constraints are mainly considered. Specifically, first, the spatial constraints between maintenance stands are fully considered so that more aircraft can be parked in the workshop. Second, the optimization objective is designed to minimize the number of aircraft movements by defining multiple maintenance capabilities of the stand. Finally, a solution based on spatiotemporal constraints is proposed in the solving process.
Findings
A set of MRO production data from Guangzhou is used as a test data set to demonstrate the effectiveness of the proposed MSS model.
Originality/value
The types of maintenance stands are defined and divided into four categories: fixed stand, temporary stand, half-body stand and engine ground test stand, which facilitates optimal modeling; a new scheduling model is designed considering both temporal constraints and spatial constraints, which can improve both the utilization of maintenance stand and safety (reduce the risk of scratching between aircraft).
Details
Keywords
Zonglin Lei, Zunge Li and Yangyi Xiao
This study aims to investigate the surface modification on 20CrMnTi gear steel individually treated by diamond-like carbon films and nitride coatings.
Abstract
Purpose
This study aims to investigate the surface modification on 20CrMnTi gear steel individually treated by diamond-like carbon films and nitride coatings.
Design/methodology/approach
For this purpose, the mechanical properties of a-C:H, ta-C and AlCrSiN coatings are characterized by nano-indentation and scratch tests. The friction and wear behaviors of these three coatings are evaluated by ball-on-disc tribological experiments under dry contact conditions.
Findings
The results show that the a-C:H coating has the highest coating-substrate adhesion strength (495 mN) and the smoothest surface (Ra is about 0.045 µm) compared with the other two coatings. The AlCrSiN coating shows the highest mean coefficient of friction (COF), whereas the ta-C coating exhibits the lowest one (steady at about 0.16). The carbon-based coatings possess excellent self-lubricating properties compared with nitride ceramic ones, which effectively reduce the COF by about 64%. The major failure mode of carbon-based coatings in dry contact is slight abrasive wear. The damage of AlCrSiN coating is mainly adhesive wear and abrasive wear.
Originality/value
It is suggested that the carbon-based film can effectively improve the friction-reducing and wear resistance performance of the gear steel surface, which has a promising application prospect in the mechanical transmission field.
Peer review
The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-05-2023-0129/
Details
Keywords
Eliza Rossiter, T.J. Thomson and Rachel Fitzgerald
The purpose of this study is to evaluate the use and effectiveness of a bespoke mobile learning resource, Pocket Tutor. This resource responds to a number of teaching and learning…
Abstract
Purpose
The purpose of this study is to evaluate the use and effectiveness of a bespoke mobile learning resource, Pocket Tutor. This resource responds to a number of teaching and learning challenges within the tertiary education context. These include those related to the number and type of learning activities that can be offered, class pacing, subject-specific content considerations and the availability and quality of off-the-shelf learning resources. Educators have to potentially contend with all of these amidst mounting institutional constraints and external pressures. Yet, a supplemental, from-scratch online learning resource can help mitigate some of these challenges.
Design/methodology/approach
This study presents the successes and challenges of introducing a mobile learning resource, Pocket Tutor, to bolster autonomous learning in a supported university learning environment. Pocket Tutor was designed and developed in 2019 and integrated in 2020 and 2021 into a multimedia design class offered at a large university in the Asia-Pacific. The resource’s effectiveness is measured against common technology acceptance factors – including self-efficacy, enthusiasm and enjoyment in relation to contextual purpose and class learning outcomes – through a multi-pronged approach consisting of a class-wide survey, developed specifically for this purpose and analysis of usage data. Deeper context was also provided through a small pool of follow-up interviews.
Findings
Evidence from this study’s data suggests that a bespoke, mobile-learning resource can provide greater consistency, more relevance, more flexibility for when and where students learn and more efficiency with limited opportunities for synchronous interaction. At the same time, a bespoke mobile-learning resource represents a significant investment of skill and time to develop and maintain.
Originality/value
This study responds to calls from scholars who argue that more research (especially that is qualitative and discipline-specific) is needed to investigate students’ willingness to use learning apps on their mobile devices. This study pairs such research about student willingness with actual usage data and student reflections to more concretely address the role of mobile learning resources in higher education contexts. This study also, importantly, does not just assess perceptions and attitudes about mobile learning resources in the abstract but assesses attitudes and usage patterns for specific generic and bespoke mobile learning resources available for students in a specific university class (thereby providing discipline-specific insights). This study also provides a unique contribution by including multiple years of data and, thus, offers a longitudinal view on how mobile-learning resources are perceived and used in a particular higher education context.
Details
Keywords
Zhicai Du, Qiang He, Hengcheng Wan, Lei Zhang, Zehua Xu, Yuan Xu and Guotao Li
This paper aims to improve the tribological properties of lithium complex greases using nanoparticles to investigate the tribological behavior of single additives (nano-TiO2 or…
Abstract
Purpose
This paper aims to improve the tribological properties of lithium complex greases using nanoparticles to investigate the tribological behavior of single additives (nano-TiO2 or nano-CeO2) and composite additives (nano-TiO2–CeO2) in lithium complex greases and to analyze the mechanism of their influence using a variety of characterization tools.
Design/methodology/approach
The morphology and microstructure of the nanoparticles were characterized by scanning electron microscopy and an X-ray diffractometer. The tribological properties of different nanoparticles, as well as compounded nanoparticles as greases, were evaluated. Average friction coefficients and wear diameters were analyzed. Scanning electron microscopy and three-dimensional topography were used to analyze the surface topography of worn steel balls. The elements present on the worn steel balls’ surface were analyzed using energy-dispersive spectroscopy and X-ray photoelectron spectroscopy.
Findings
The results showed that the coefficient of friction (COF) of grease with all three nanoparticles added was low. The grease-containing composite nanoparticles exhibited a lower COF and superior anti-wear properties. The sample displayed its optimal tribological performance when the ratio of TiO2 to CeO2 was 6:4, resulting in a 30.5% reduction in the COF and a 29.2% decrease in wear spot diameter compared to the original grease. Additionally, the roughness of the worn spot surface and the maximum depth of the wear mark were significantly reduced.
Originality/value
The main innovation of this study is the first mixing of nano-TiO2 and nano-CeO2 with different sizes and properties as compound lithium grease additives to significantly enhance the anti-wear and friction reduction properties of this grease. The results of friction experiments with a single additive are used as a basis to explore the synergistic lubrication mechanism of the compounded nanoparticles. This innovative approach provides a new reference and direction for future research and development of grease additives.
Peer review
The peer review history for this article is available at: https://publons.com/publon/10.1108/ILT-09-2023-0291/
Details
Keywords
Tao Pang, Wenwen Xiao, Yilin Liu, Tao Wang, Jie Liu and Mingke Gao
This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the…
Abstract
Purpose
This paper aims to study the agent learning from expert demonstration data while incorporating reinforcement learning (RL), which enables the agent to break through the limitations of expert demonstration data and reduces the dimensionality of the agent’s exploration space to speed up the training convergence rate.
Design/methodology/approach
Firstly, the decay weight function is set in the objective function of the agent’s training to combine both types of methods, and both RL and imitation learning (IL) are considered to guide the agent's behavior when updating the policy. Second, this study designs a coupling utilization method between the demonstration trajectory and the training experience, so that samples from both aspects can be combined during the agent’s learning process, and the utilization rate of the data and the agent’s learning speed can be improved.
Findings
The method is superior to other algorithms in terms of convergence speed and decision stability, avoiding training from scratch for reward values, and breaking through the restrictions brought by demonstration data.
Originality/value
The agent can adapt to dynamic scenes through exploration and trial-and-error mechanisms based on the experience of demonstrating trajectories. The demonstration data set used in IL and the experience samples obtained in the process of RL are coupled and used to improve the data utilization efficiency and the generalization ability of the agent.
Details
Keywords
Shuliu Wang, Qianqian Liu, Jin Wang, Nana Chen, JunHang Chen, Jialiang Song, Xin Zhang and Kui Xiao
This study aims to investigate the role of aluminium (Al) in marine environment and the corrosion mechanism of galvalume coatings by conducting accelerated experiments and data…
Abstract
Purpose
This study aims to investigate the role of aluminium (Al) in marine environment and the corrosion mechanism of galvalume coatings by conducting accelerated experiments and data analysis.
Design/methodology/approach
Samples were subjected to accelerated corrosion for 136 days via salt spray tests to simulate the natural conditions of marine environment and consequently accelerate the experiments. Subsequently, the samples were examined using various test methods, such as EDS, scanning electron microscopy (SEM), X-ray diffraction (XRD) and electrochemical impedance spectroscopy (EIS), and the obtained data were analysed.
Findings
Galvalume coatings comprised interdigitated zinc (Zn)-rich and dendritic Al-rich phases. Corrosion was observed to begin with a Zn-rich phase. The primary components of the corrosion product film were Al2O3 and Zn5(OH)8Cl2·H2O. It was confirmed that the role of Al was to form a dense protective film, thereby successfully blocking the entry of corrosive media and protecting the iron substrate.
Originality/value
This study provides a clearer understanding of the corrosion mechanism and kinetics of galvalume coatings in a simulated marine environment. In addition, the role of Al, which is rarely mentioned in the literature, was investigated.
Details
Keywords
However, its key provision -- an increase in the system’s defined contribution -- was rejected by the Lower House. The government will have to negotiate key parts of the bill…