Fused deposition modeling (FDM) is a form of additive manufacturing where three-dimensional (3D) models are created by depositing melted thermoplastic polymer filaments in layers. Although FDM is a ...mature process, defects can occur during printing. Therefore, an image-based quality inspection method for 3D-printed objects of varying geometries was developed in this study. Transfer learning with pretrained models, which were used as feature extractors, was combined with ensemble learning, and the resulting model combinations were used to inspect the quality of FDM-printed objects. Model combinations with VGG16 and VGG19 had the highest accuracy in most situations. Furthermore, the classification accuracies of these model combinations were not significantly affected by differences in color. In summary, the combination of transfer learning with ensemble learning is an effective method for inspecting the quality of 3D-printed objects. It reduces time and material wastage and improves 3D printing quality.
The support vector machine (SVM) is a widely used tool in classification problems. The SVM trains a classifier by solving an optimization problem to decide which instances of the training data set ...are support vectors, which are the necessarily informative instances to form the SVM classifier. Since support vectors are intact tuples taken from the training data set, releasing the SVM classifier for public use or shipping the SVM classifier to clients will disclose the private content of support vectors. This violates the privacy-preserving requirements for some legal or commercial reasons. The problem is that the classifier learned by the SVM inherently violates the privacy. This privacy violation problem will restrict the applicability of the SVM. To the best of our knowledge, there has not been work extending the notion of privacy preservation to tackle this inherent privacy violation problem of the SVM classifier. In this paper, we exploit this privacy violation problem, and propose an approach to postprocess the SVM classifier to transform it to a privacy-preserving classifier which does not disclose the private content of support vectors. The postprocessed SVM classifier without exposing the private content of training data is called Privacy-Preserving SVM Classifier (abbreviated as PPSVC). The PPSVC is designed for the commonly used Gaussian kernel function. It precisely approximates the decision function of the Gaussian kernel SVM classifier without exposing the sensitive attribute values possessed by support vectors. By applying the PPSVC, the SVM classifier is able to be publicly released while preserving privacy. We prove that the PPSVC is robust against adversarial attacks. The experiments on real data sets show that the classification accuracy of the PPSVC is comparable to the original SVM classifier.
Clustering is a common task for organizing data into clusters. The kernel
k
-means identifies clusters of nonlinearly separable data by applying the kernel trick to the commonly used
k
-means ...clustering to group data in the kernel-induced feature space. Since the kernel
k
-means is costly in computation due to the quadratic complexity, outsourcing the computations of kernel
k
-means to external computing service providers can benefit the data owner who has only limited computing resources. However, data privacy is a critical concern in outsourcing since the data may contain sensitive information. Existing works of privacy-preserving outsourcing for general kernel methods based on distance preservation are weak in security. We propose a privacy-preserving outsourcing scheme for the kernel
k
-means based on the randomly linear transformation and the random perturbation of the kernel matrix. The data sent to the service provider are encrypted, and the service provider solves the kernel
k
-means from the encrypted data. The proposed scheme is much stronger in security than existing works, and the experimental results show that the proposed privacy-preserving kernel
k
-means method has similar clustering performance with a normal large-scale kernel
k
-means algorithm and imposes very little overhead on the data owner.
Dental laboratories require manpower resources for manufacturing prostheses and inventory management. In this paper, we developed an automated inventory management system for dental laboratories to ...improve the production efficiency. A sensing system was developed based on the framework of Internet of things to collect the information of cobalt-chromium disks both in the storage room and manufacturing area, and an expert system was developed to automatically conduct inventory management based on the established rules. The proposed system can reduce the time of recording data and also assist the manager in configuring and managing material orders. The experimental results showed that a large amount of working time is reduced, resulting in the benefits of saving money and improving efficiency in dental manufacturing.
The systems modeling technique is used for developing an abstract model to help analyze and understand the functionality of a system. In this paper, we introduce a new approach for general-purpose ...systems modeling called structure-behavior coalescence (SBC), which supports the integration of modeling both structural and behavioral aspects of a system in a single diagram. Process algebra is utilized to describe the interactions between the components of the system. SBC combines graphical notation and process algebra to provide formalism and an intuitive representation in the development of the conceptual model. The SBC model can clearly describe the interactions between system components and precisely specify the execution order of an entire system via algebraic operations.
The breast ultrasound is not only one of major devices for breast tissue imaging, but also one of important methods in breast tumor screening. It is non-radiative, non-invasive, harmless, simple, and ...low cost screening. The American College of Radiology (ACR) proposed the Breast Imaging Reporting and Data System (BI-RADS) to evaluate far more breast lesion severities compared to traditional diagnoses according to five-criterion categories of masses composition described as follows: shape, orientation, margin, echo pattern, and posterior features. However, there exist some problems, such as intensity differences and different resolutions in image acquisition among different types of ultrasound imaging modalities so that clinicians cannot always identify accurately the BI-RADS categories or disease severities. To this end, this article adopted three different brands of ultrasound scanners to fetch breast images for our experimental samples. The breast lesion was detected on the original image using preprocessing, image segmentation, etc. The breast tumor’s severity was evaluated on the features of the breast lesion via our proposed classifiers according to the BI-RADS standard rather than traditional assessment on the severity; i.e., merely using benign or malignant. In this work, we mainly focused on the BI-RADS categories 2–5 after the stage of segmentation as a result of the clinical practice. Moreover, several features related to lesion severities based on the selected BI-RADS categories were introduced into three machine learning classifiers, including a Support Vector Machine (SVM), Random Forest (RF), and Convolution Neural Network (CNN) combined with feature selection to develop a multi-class assessment of breast tumor severity based on BI-RADS. Experimental results show that the proposed CAD system based on BI-RADS can obtain the identification accuracies with SVM, RF, and CNN reaching 80.00%, 77.78%, and 85.42%, respectively. We also validated the performance and adaptability of the classification using different ultrasound scanners. Results also indicate that the evaluations of F-score based on CNN can obtain measures higher than 75% (i.e., prominent adaptability) when samples were tested on various BI-RADS categories.
The popularity and development of mobile devices and mobile apps have dramatically changed human life. Due to the tremendous and still rapidly growing number of mobile apps, helping users find apps ...that satisfy their demands remains a difficult task. To address this problem, we propose a personalized mobile app recommender system based on the textual data of user reviews on the app store. Topic modeling techniques are applied to extract hidden topics of user reviews, and the probability distributions of the topics are utilized to represent the features of the apps. Then, the user profile is constructed based on the user's installed apps to capture user preferences. Both the topic distributions of the apps and user preferences are taken into account to produce recommendation scores to generate recommendation lists for target users. We crawl real-world data sets from app stores to evaluate the performance. The experimental results show that user reviews are effective for deriving the features of apps, and the proposed user-review-based app recommender system improves the performance of existing approaches. We conclude that the user reviews on the app store effectively represent the features of apps and play a significant role in personalized app recommender systems.
The development of a heterogeneous catalyst for use in environmental remediation remains a challenging and attractive research endeavor. Specifically, for Fenton reactions, most research approaches ...have focused on the preparation of iron-containing heterostructures as photo-Fenton catalysts that utilize visible light for enhancing the degradation efficiency. Herein, the synthesis and novel application of C,N-doped iron borates are demonstrated as single-component heterogeneous photo-Fenton catalysts with high Fenton activity under visible light. Under the optimal conditions, 10 mg of the catalyst is shown to achieve effective degradation of 10 ppm methylene blue (MB) dye, Rhodamine B (RhB) dye, and tetracycline (TC) under simulated solar irradiation with a first-order rate constant of k = 0.218 min−1, 0.177 min−1, and 0.116 min−1, respectively. Using MB as a model system, the C,N-doped iron borate exhibits 10- and 26-fold increases in catalytic activity relative to that of the 50 nm hematite nanoparticles and that of the non-doped iron borate, respectively, in the presence of H2O2 under the simulated solar irradiation. Furthermore, the optimum reaction conditions used only 320 equivalents of H2O2 with respect to the concentration of dye, rather than the several thousand equivalents of H2O2 used in conventional heterogeneous Fenton catalysts. In addition, the as-prepared C,N-doped iron borate achieves 75% MB degradation after 20 min in the dark, thus enabling the continuous degradation of pollutants at night and in areas with poor light exposure. The stability and recyclability of C,N-doped iron borate for the oxidation of MB was demonstrated over three cycles with insignificant loss in photo-Fenton activity. The high Fenton activity of the C,N-doped iron borate is considered to be due to the synergistic action between the negatively-charged borate ligands and the metal center in promoting the Fenton reaction. Moreover, carbon and nitrogen doping are shown to be critical in modifying the electronic structure and increasing the conductivity of the catalyst. In view of its synthetic simplicity, high efficiency, low cost of reagents, and minimal cost of operation (driven by natural sunlight), the as-prepared heterogeneous single-component metal borate catalyst has potential application in the industrial treatment of wastewater.