DSpace Collection:http://hdl.handle.net/10722/387212024-03-29T02:15:30Z2024-03-29T02:15:30ZUnsupervised Fabric Defects Detection based on Spatial Domain Saliency and Features ClusteringZhao, ShuxuanZhong, Ray YWang, JunliangXu, ChuqiaoZhang, Jiehttp://hdl.handle.net/10722/3419022024-03-26T05:38:05Z2023-07-01T00:00:00ZTitle: Unsupervised Fabric Defects Detection based on Spatial Domain Saliency and Features Clustering
Authors: Zhao, Shuxuan; Zhong, Ray Y; Wang, Junliang; Xu, Chuqiao; Zhang, Jie
Abstract: <p>Fabric defects detection plays a critical role in the quality control of textile manufacturing industry. It is still a challenge to realize accurate fabric defects detection due to variations of fabric texture and the lack of defective samples. To solve this problem, this paper proposes an unsupervised learning fabric defects detection method. Firstly, a multi-level spatial domain saliency method (MSDS) is proposed to generate multi-level saliency values by convoluting color histograms with pixel values, which can greatly suppress background information via the fusion of multi-level saliency values. Secondly, fabric feature extraction method (FFE) is proposed to respectively extract geometrical features, intensity features, and texture features from potential defective regions. Finally, an adaptive fabric feature clustering algorithm (AFFC) is designed to adjust weights of fabric features and obtain final defects detection results. In the experiment section, the influence of fabric features on defects detection is discussed. And compared with other unsupervised learning methods, the proposed method can achieve over 90% accuracy fabric defects detection within small samples, which is significantly better than other methods and can meet the practical requirements of fabric defects detection.</p>2023-07-01T00:00:00ZA discrete choice experiment to examine the factors influencing consumers’ willingness to purchase health appsXie, ZhenzhenLiu, HaoOr, Calvinhttp://hdl.handle.net/10722/3416242024-03-20T06:57:50Z2023-07-03T00:00:00ZTitle: A discrete choice experiment to examine the factors influencing consumers’ willingness to purchase health apps
Authors: Xie, Zhenzhen; Liu, Hao; Or, Calvin
Abstract: <p><strong>Background: </strong>The benefits of health apps can only be realized when consumers purchase them for use. Thus, it is important to understand what factors influence consumers’ willingness to purchase health apps. Therefore, this study aimed to examine the influence of health app attributes and sociodemographic characteristics on consumers’ willingness to purchase health apps, and how the value of the health app attributes varies for individuals with different sociodemographic characteristics.</p><p><strong>Methods: </strong>A questionnaire-based discrete choice experiment (DCE) was conducted with a random sample of 561 adults. A standard logit regression was applied to assess the influence of health app attributes and sociodemographic characteristics on consumers’ willingness to purchase health apps, and marginal willingness to pay (MWTP) was calculated for each factor using regression coefficients. Interaction effects were also examined to determine how the value of health app attributes varies by sociodemographic characteristics.</p><p><strong>Results: </strong>Usefulness, ease of use, security and privacy, and attitudes of healthcare professionals toward consumers’ use of health apps were the attributes of health apps that positively influenced consumers’ willingness to purchase them. Conversely, smartphone storage consumption, mobile Internet data consumption, and app price negatively influenced consumers’ willingness to purchase the apps. For sociodemographic characteristics, being male, having a household size greater than three, having a monthly household income of HK$30,000 or more, having a lower education level (below diploma), having previously used health apps, and having previously purchased health apps were associated with a higher willingness to purchase health apps.</p><p><strong>Conclusions: </strong>Health app attributes that influenced consumers’ willingness to purchase the apps and populations that were less willing to purchase health apps were identified. Efforts should be made to improve health app attributes and enhance the promotion of health apps among these underserved populations.</p>2023-07-03T00:00:00ZInterpolation and difference optimized machine learning model for accurate prediction of silicon etching depth with small sample datasetYang, YeXu, Yanghttp://hdl.handle.net/10722/3414162024-03-13T08:42:39Z2023-01-01T00:00:00ZTitle: Interpolation and difference optimized machine learning model for accurate prediction of silicon etching depth with small sample dataset
Authors: Yang, Ye; Xu, Yang
Abstract: A novel interpolation and difference optimized (IDO) machine learning model to predict the depth of silicon etching is proposed, which is particularly well-suited to addressing small sample problems. Our approach involves dividing both experimental and simulation data obtained from the Technology Computer-Aided Design (TCAD) software into training and testing sets. Both experimental data and TCAD simulation data are used as inputs to machine learning module 1 (ML1), while ML2 takes the actual experimental data as inputs and then learns the difference between the experimental data and the TCAD simulation data, outputting the difference. The outputs generated by ML1 and ML2 serve as input parameters to machine learning module 3 (ML3), and the weights of ML3 are updated through its own learning process to produce the final prediction results. We demonstrate that our IDO model, which contains three basic ML algorithms, achieves higher prediction accuracy compared to the basic ML algorithm alone. Moreover, through ablation studies, we establish that the three components of the IDO prediction model are inseparable. The IDO model exhibits improved generalization performance, making it particularly suitable for small sample datasets in the semiconductor processing domain.2023-01-01T00:00:00ZHybrid Multimaterial 3D Printing Using Photocuring-While-DispensingJin, JieZhang, FangzhouYang, YulongZhang, ChengqianWu, HaidongXu, YangChen, Yonghttp://hdl.handle.net/10722/3414152024-03-13T08:42:38Z2023-01-01T00:00:00ZTitle: Hybrid Multimaterial 3D Printing Using Photocuring-While-Dispensing
Authors: Jin, Jie; Zhang, Fangzhou; Yang, Yulong; Zhang, Chengqian; Wu, Haidong; Xu, Yang; Chen, Yong
Abstract: Three-dimensional (3D) printing methods, such as vat photopolymerization (VPP) and direct-ink-writing (DIW) processes, are known for their high-resolution and multimaterial capabilities, respectively. Here a novel hybrid 3D printing technique that combines the strengths of VPP and DIW processes to achieve multimaterial and high-resolution printing of functional structures and devices, is presented. The method involves dispensing liquid-like materials via syringes into a photocurable matrix material and subsequently using a Galvano mirror-controlled laser beam to selectively photocure the dispensed material trace or the matrix material surrounding the trace. The laser beam scanning and syringe dispensing are synchronized with a set delay to control liquid diffusion and in situ fixture. The versatility of the method is demonstrated by fabricating intricate 3D ant and wheel prototypes using various materials available for VPP and DIW technologies. The proposed photocuring-while-dispensing strategy offers advantages over conventional multimaterial 3D printing methods, such as integrating materials regardless of photocurability and viscosity, and fabricating heterogeneous structures with complex geometries and high resolution. With its principle demonstrated, this multimaterial 3D printing process will open up a wide range of potential applications with diverse functionalities and materials.2023-01-01T00:00:00Z