课程文献中心 更多>>

关键词： CAD   multi-modal method   recurrence plot   deep learning   feature extraction  

摘要： Coronary artery disease (CAD) is an irreversible and fatal disease. It necessitates timely and precise diagnosis to slow CAD progression. Electrocardiogram (ECG) and phonocardiogram (PCG), conveying abundant disease-related information, are prevalent clinical techniques for early CAD diagnosis. Nevertheless, most previous methods have relied on single-modal data, restricting their diagnosis precision due to suffering from information shortages. To address this issue and capture adequate information, the development of a multi-modal method becomes imperative. In this study, a novel multi-modal learning method is proposed to integrate both ECG and PCG for CAD detection. Along with deconvolution operation, a novel ECG-PCG coupling signal is evaluated initially to enrich the diagnosis information. After constructing a modified recurrence plot, we build a parallel CNN network to encode multi-modal information, involving ECG, PCG and ECG-PCG coupling deep-coding features. To remove irrelevant information while preserving discriminative features, we add an autoencoder network to compress feature dimension. Final CAD classification is conducted by combining support vector machine and optimal multi-modal features. The experiment is validated on 199 simultaneously recorded ECG and PCG signals from non-CAD and CAD subjects, and achieves high performance with accuracy, sensitivity, specificity and f1-score of 98.49%, 98.57%,98.57% and 98.89%, respectively. The result demonstrates the superiority of the proposed multi-modal method in overcoming information shortages of single-modal signals and outperforming existing models in CAD detection. This study highlights the potential of multi-modal deep-coding information, and offers a wider insight to enhance CAD diagnosis.

关键词： Bearing fault diagnosis   Explainable artificial intelligence   Feature extraction   Vibration   Condition monitoring  

摘要： This study aims to enhance bearing fault diagnosis by integrating eXplainable Artificial Intelligence technology, emphasizing improved accuracy and interpretability in vibration data analysis. In the initial phase, vibration data undergo transformation into spectrograms through short time Fourier transform analysis, followed by the application of the Grad-CAM algorithm to extract interpretable features, thus enhancing diagnostic precision. Subsequently, the second phase capitalizes on data that have undergone inverse transformation, highlighting features through reduced variance for outlier detection and bearing fault differentiation. The validity of this method is corroborated by analysis of datasets from the University of Ottawa and CWRU, affirming its versatility across diverse fault scenarios. The outcomes validate the methodology's capability in accurately differentiating between healthy and fault conditons, linking outlier frequencies to fault severity, and enhancing model interpretability through Grad-CAM visualizations. Despite certain constraints, this methodology signifies a progressive stride in precise and interpretable bearing fault diagnosis, heralding advancements in its application to industrial contexts.

关键词： Nonlinear subsidiary system   Ultralow frequency vibration isolation   Ultralow dynamic stiffness  

摘要： Quasi-zero-stiffness (QZS) isolator with high-static-low-dynamic stiffness can withstand heavy loads and effectively isolate vibration with low frequency. However, the ultralow frequency vibration isolation is still a challenge for the existing QZS isolators. This paper proposes an innovative design of parabolic cam-roller QZS isolators by use of nonlinear subsidiary systems to achieve ultralow dynamic stiffness and ultralow frequency vibration isolation. The theoretical formulations of the proposed QZS isolators are derived. The effects of structural parameters on stiffness characteristics are analyzed and then an optimal design are presented. The vibration isolation of the proposed QZS isolators under harmonic excitation is investigated using the averaging method, and dynamic response under impact load is studied using the Runge-Kutta algorithm. The bifurcation analysis for the designed QZS isolator is briefly presented. In comparison with the previous parabolic cam-roller QZS isolator with the linear subsidiary system and the existing QZS isolators with the nonlinear subsidiary systems, the present QZS isolators have lower stiffness in a wider displacement region, which makes them be able to isolate harmonic excitations with larger amplitude and have better isolation performance for harmonic excitations and impact loading. A prototype of the proposed QZS isolator is designed, fabricated and tested. Experimental results show that the measured force-displacement curves are in good agreement with those predicted by theory, and isolation performance of the proposed QZS isolators for vibration with ultralow frequency significantly outperforms the existing QZS isolator.

关键词： CAD/CAM abutments   clinical performance   implant-prosthetic rehabilitation   pen-implant soft tissues   single crowns  

摘要： Purpose: To evaluate the clinical performance of implant-prosthetic rehabilitations carried out using ceramic-coated CAD/ CAM titanium abutments. Materials and Methods: Thirty implants were placed in 30 patients and rehabilitated with 30 single crowns attached to CAD/CAM titanium abutments. A conventional procedure was applied, implants were placed after postextraction socket healing, and prosthetic restorations were placed after implant healing. Implant lengths ranged from 6 to 15 mm, and widths were 3.6, 4.2, and 4.8 mm. At the time of prosthesis delivery (TO), after 2 years (T1), and after 5 years (T2), the Plaque Index (PI), bleeding on probing (BoP), pocket probing depth (PPD), marginal bone level (MBL), and pink/white esthetic scores (PES/WES) were evaluated for each implant. Results: No patient dropped out of the study during the follow-up period. All 30 implants were clinically successful 5 years after prosthesis delivery (survival rate: 100%) and showed no signs of pen-implant infection. Pen-implant soft tissues were in good health (BoP at T2: 0% in 73% of patients;25% in 13% of patients;50% in 10% of patients;and 75% in 3% of patients). The mean PPD was 2.05 +/- 0.56 mm at TO, 1.992 +/- 0.6 mm at T1, and 1.867 +/- 0.439 mm at T2. The mean MBL was 0.413 +/- 0.440 mm at TO, 0.306 +/- 0.388 mm at T1, and 0.263 +/- 0.368 mm at T2. The mean PES, WES, and PES/WES indices (7.43 +/- 1.04, 7.57 +/- 0.82, and 15.00 +/- 1.17, respectively) indicate good integration of soft tissues, satisfactory esthetics, and overall positive outcomes. Conclusions: The success rates, maintenance of MBLs, and periodontal and esthetic indices suggest the validity of implant-prosthetic rehabilitations with CAD/CAM abutments in cases of single crowns.

关键词： LP-DED   CAM   Laser cladding   offline programming   industrial robot  

摘要： Directed energy deposition (DED) for additive manufacturing applications is commonly realized by the usage of industrial robots. The DED processing end effectors are usually mounted on industrial robot systems and can, therefore, be moved and oriented in up to many degrees of freedom. However, the design of the powder nozzle and the programming of the robot can limit the movement options. For this reason, translational movements, as with conventional 3D printers, are still common today. The end effector is usually guided horizontal over the component surface although welding in position (PA) is preferred in general. It may be necessary to tilt the end effector in order to gain advantages during processing due to the constrained position. This is particularly advantageous for overhang structures and is often realized with the help of a turn-tilt positioning table in combination with an industrial robot. However, this approach is, in some cases, not possible due to geometrical constrains. To extend applications in this direction, advanced methods for slicing the components and programming the robot movements are necessary. The main aspect of this work is the development, testing, and evaluation of a multidimensional DED manufacturing approach. This is tested on a thin-walled component with defined overhang areas and compared with conventional approaches. Different strategies are assessed in terms of the geometrical match of the target geometry. Influences of strategies on the results are evaluated. It can be shown that multidimensional path planning approaches lead to a better match of the target geometry.

关键词： mammogram   breast cancer   breast tumor   computer-aided diagnosis systems   conventional neural network   machine learning   multi-layer perceptron   disease diagnoses   classification   deep CNN   breast cancer diagnosis   soft voting  

摘要： Breast cancer has been one of the main causes of death among women recently, and it has been the focus of attention of many specialists and researchers in the health field. Because of its seriousness and spread speed, breast cancer-resisting methods, early diagnosis, diagnosis, and treatment have been the points of research discussion. Many computers-aided diagnosis (CAD) systems have been proposed to reduce the load on physicians and increase the accuracy of breast tumor diagnosis. To the best of our knowledge, combining patient information, including medical history, breast density, age, and other factors, with mammogram features from both breasts in craniocaudal (CC) and mediolateral oblique (MLO) views has not been previously investigated for breast tumor classification. In this paper, we investigated the effectiveness of using those inputs by comparing two combination approaches. The soft voting approach, produced from statistical information-based models (decision tree, random forest, K-nearest neighbor, Gaussian naive Bayes, gradient boosting, and MLP) and an image-based model (CNN), achieved 90% accuracy. Additionally, concatenating statistical and image-based features in a deep learning model achieved 93% accuracy. We found that it produced promising results that would enhance the CAD systems. As a result, this study finds that using both sides of mammograms outperformed the result of using only the infected side. In addition, integrating the mammogram features with statistical information enhanced the accuracy of the tumor classification. Our findings, based on a novel dataset, incorporate both patient information and four-view mammogram images, covering multiple classes: normal, benign, and malignant.

关键词： systematic review   CAD/CAM   polycaprolactone   beta-TCP   hydroxyapatite  

摘要： The objective of this work is to review the literature on the use of three-dimensional scaffolds obtained by printing for the regeneration of bone defects in the maxillofacial area. The research question asked was: what clinical experiences exist on the use of bone biomaterials manufactured by CAD/CAM in the maxillofacial area? Prospective and retrospective studies and randomized clinical trials in humans with reconstruction area in the maxillofacial and intraoral area were included. The articles had to obtain scaffolds for bone reconstruction that were designed by computer processing and printed in different materials. Clinical cases, case series, in vitro studies and those that were not performed in humans were excluded. Six clinical studies were selected that met the established inclusion criteria. The selected studies showed heterogeneity in their objectives, materials used and types of regenerated bone defects. A high survival rate was found for dental implants placed on 3D-printed scaffolds, with rates ranging from 94.3% to 98%. The materials used included polycaprolactone, coral-derived hydroxyapatite, biphasic calcium phosphate (BCP) and bioceramics. The use of CAD/CAM technology is seen as key for satisfying variations in the shapes and requirements of different fabrics and size variations between different individuals. Furthermore, the possibility of using the patient's own stem cells could revolutionize the way bone defects are currently treated in oral surgery. The results indicate a high survival rate of dental implants placed on 3D-printed scaffolds, suggesting the potential of this technology for bone regeneration in the maxillofacial mass.

关键词： agricultural biotechnology   C2 photosynthesis   C3-C4 intermediates   C4 photosynthesis   CAM   climate change   crop nutrition   elevated CO2  

摘要： Societal Impact Statement Climate change continues to intensify the challenges of food production as agricultural systems face more variable and extreme weather. Coupled with increasing human population, growers must balance increasing crop yields with nutrient content to prevent global malnutrition. Photosynthetic diversity may permit some crops to tolerate climate change and elevated CO2 whilst maintaining both crop yield quantity and quality. This review examines how photosynthetic diversity interacts with crop production and nutritional stability under elevated CO2 and climate change, and highlights opportunities for photosynthetic diversity to inspire agricultural solutions. Summary Innovative agricultural solutions are desperately needed to achieve food security for a growing human population amidst the imminent pressures of climate change that threaten more variable and extreme weather, placing additional pressures on already precarious agricultural systems. Not only are crop yields at risk under climate change but rising global atmospheric CO2 concentrations are concurrently driving a carbon dilution effect that threatens to reduce the nutritional quality of our crops to further global malnutrition. Plants using different photosynthetic metabolisms, however, experience these negative impacts to yield and nutrition to different degrees. Thus, photosynthetic diversity may offer solutions to combat malnutrition under climate change and elevated CO(2 )concentrations, whether that be through targeting existing resilient species for agricultural programmes or applying agricultural biotechnology to engineer photosynthetic diversity into existing crops. Here, we discuss how each major photosynthetic type is predicted to fare under elevated CO2 concentrations and climate change and explore agricultural opportunities to maintain both yield and nutrient stability.

关键词： appendix segmentation   deep learning   CT imaging   mask R-CNN   grad-CAM   Detectron  

摘要： Background: A leading cause of emergency abdominal surgery, appendicitis is a common condition affecting millions of people worldwide. Automatic and accurate segmentation of the appendix from medical imaging is a challenging task, due to its small size, variability in shape, and proximity to other anatomical structures. Methods: In this study, we propose a backbone-enriched Mask R-CNN architecture (MaskAppendix) on the Detectron platform, enhanced with Gradient-weighted Class Activation Mapping (Grad-CAM), for precise appendix segmentation on computed tomography (CT) scans. In the proposed MaskAppendix deep learning model, ResNet101 network is used as the backbone. By integrating Grad-CAM into the MaskAppendix network, our model improves feature localization, allowing it to better capture subtle variations in appendix morphology. Results: We conduct extensive experiments on a dataset of abdominal CT scans, demonstrating that our method achieves state-of-the-art performance in appendix segmentation, outperforming traditional segmentation techniques in terms of both accuracy and robustness. In the automatic segmentation of the appendix region in CT slices, a DSC score of 87.17% was achieved with the proposed approach, and the results obtained have the potential to improve clinical diagnostic accuracy. Conclusions: This framework provides an effective tool for aiding clinicians in the diagnosis of appendicitis and other related conditions, reducing the potential for diagnostic errors and enhancing clinical workflow efficiency.

关键词： Cam profile optimization   jerk minimization   optimization of a polynomial   metaheuristic optimization  

摘要： Polynomials of a degree higher than 8th used for the rise phase of displacement curve of a cam profile were optimized for gaining minimal jerk using the search and rescue optimization algorithm. The algorithm was used to obtain the polynomial coefficients for the polynomials of the higher degree that cannot be calculated by using the analytical approach without adding additional boundary conditions other than displacement, velocity and acceleration in characteristic positions. The degree of the polynomial from which the optimal value of jerk using the optimization algorithm can be obtained was determined, as well as the degree after which the results of the optimization give worse values of the jerk.