课程文献中心 更多>>

摘要： Studies on the fracture performance of a recently introduced computer-aided design and computer-aided manufacturing (CAD-CAM) lithium disilicate ceramic containing virgilite with different cements are lacking.

关键词： Edge Impulse   Machine Learning   Smart Agriculture   Sustainability  

摘要： Accurate classification of tomatoes is crucial for efficient sorting, packaging, and overall agricultural management. Classifying tomatoes using an ESP32-CAM in an Internet of Things (IoT) platform can enhance sustainability by optimizing resources. By employing image recognition algorithms on the ESP32-CAM, the tomatoes can be classified based on various factors like size, ripeness, and quality. This data can be transmitted to the IoT platform, enabling real-time monitoring and management of tomato production. With this information, farmers can make informed decisions, reduce waste, and increase efficiency, contributing to sustainable agriculture practices. In the proposed system, the tomato classification system that integrates with the Edge Impulse platform is presented. In this paper, a case study on utilizing IoT for tomato classification using the ESP32-CAM microcontroller and the ResNet deep learning model is presented. We discuss the setup, implementation, challenges, and results of the project, highlighting the potential of IoT in improving agricultural processes. The aim is to create a sustainable solution that maximizes agricultural productivity while minimizing waste. The proposed system employs machine learning algorithms for real-time image processing and classification, offering a cost-effective and scalable approach to smart farming. Leveraging the Edge-Impulse cloud-based platform, ESP32-CAM, and servo motors, the system demonstrates an efficient workflow for automated sorting based on tomato ripeness and color. This approach features its potential for enhancing sustainability in agriculture.

摘要： Purpose / Aim: The aim of the current study is to compare the 2-year clinical performance of lithium disilicate and hybrid resin nano-ceramic onlays restorations. Materials & Methods: All cavities were prepared according to preparation rules of in...

关键词： acute coronary syndrome(s)   coronary computed tomography angiography   high-risk plaque   obstructive stenosis   pericoronary adipose tissue attenuation   CAD   coronary artery disease   CTA   computed tomography angiography   HRP   high-risk plaque   LAD   left anterior descending artery   LCX   left circumflex coronary artery   MACE   major adverse cardiac event(s)   PCATA   pericoronary adipose tissue attenuation   RCA   right coronary artery  

摘要： Pericoronary adipose tissue attenuation (PCATA) is a novel imaging biomarker of pericoronary inflammation associated with coronary artery disease. Several studies have reported the usefulness of PCATA among people of European ethnicity; however, data are lacking concerning those of Asian ethnicity.

关键词： FXG Score-CAM   CNNs   visual explanation techniques   interpretability   Score-CAM   FullGrad   XGrad-CAM  

摘要： Convolutional Neural Networks (CNNs) have shown impressive performance on solving vision problems, but their limited interpretability is a concern, especially in high-stakes applications where trust and clarity are essential. Among post-hoc visual explanation techniques, Score-CAM is widely used, but has notable limitations. It relies solely on activation maps, ignoring input and per-neuron sensitivity. Additionally, this method typically extracts information from a single layer (usually the final convolutional layer) making its output highly dependent on layer selection while disregarding valuable contributions from other layers. Score-CAM also applies uniform spatial weighting within feature maps, failing to capture variations in importance across individual spatial locations. To address these shortcomings, we propose FXG (FullXGrad) Score-CAM, a novel interpretability method that integrates FullGrad, XGrad-CAM, and Score-CAM. FXG Score-CAM integrates activation, input, and bias attribution into the saliency map using the Score-CAM weighting method, aggregating information across all layers via the FullGrad framework while leveraging XGrad-CAM for spatially adaptive feature weighting. Our experimental evaluations on benchmark datasets demonstrate that FXG Score-CAM consistently outperforms Score-CAM and other state-of-the-art explainability methods in both qualitative and quantitative assessments. It also passes standard sanity checks, confirming explanation reliability. Code is available at https://***/quannguyen2153/fxg-score-cam

关键词： Eye care   Integrative medicine   Ophthalmology   Yoga   LMICs   low- and middle-income countries   CAM   complementary and alternative medicine   IOP   intraocular pressure   RCTs   randomized controlled trials  

摘要： Yoga is widely practiced as a complementary, alternative, and integrative therapy to manage various health conditions. Existing literature indicates that yoga may play a role in eye care. The objective of this review was to investigate the available evidence of yoga in eye care.

摘要： Early detection of oral squamous cell carcinoma (OSCC) is crucial for reducing its high mortality rates. Deep learning (DL) artificial models have shown promise in recognizing patterns in complex samples, which can be valuable for improving the diagnosis of malignant and potentially malignant oral lesions.

关键词： Breast Cancer   Inflammatory breast cancer   Mammography   Biomarkers   Diagnosis   IBC   Inflammatory breast cancer   AJCC   The American Joint Committee on Cancer   IARC   International Agency for Research on Cancer   CC   Craniocaudal   MLO   Mediolateral oblique   PNL   Posterior nipple line   GLCM   Gray-level co-occurrence matrices   ANOVA   Analysis of variance   CAD   Computer-aided detection   DICOM   Digital Imaging and Communications in Medicine  

摘要： Inflammatory breast cancer (IBC) is a rare and aggressive type of breast cancer, as many physicians may not be aware of it in terms of symptoms and diagnosis. Mammography is the first choice in breast screenings and diagnosis. Because of a lack of expertise and imaging datasets, IBC portrayal and machine learning-based diagnosis systems have not yet been studied thoroughly. Developing scanning and diagnosis tools can close the knowledge gap and barriers to a timely IBC diagnosis.

关键词： Model-based Systems Engineering   Heterogeneous Models   Model Management   API   SysML   CAD  

摘要： Model-based Systems Engineering emphasises the use of semi-formal models to describe the overall system behaviour and structure. In addition to these domain-independent models, an efficient engineering process for mechatronic systems requires domain-specific models, like CAD models, to define the detailed design. This contribution introduces heterogeneous models, as product models integrating SysML and CAD model elements, and describes their technical implementation. Therefore, an implementation concept and its technical realisation will be presented. Key elements of this contribution are the realised API to link SysML and CAD tools and its application to develop heterogeneous models.

关键词： CAD   Chest pain   Current density vector maps   Data interpretation   Inverse solution   Magnetocardiography   Multicenter studies  

摘要： Magnetocardiography undoubtedly has exceptionally high sensitivity to electrophysiological changes in the myocardium. This is an absolutely non-invasivemethod with no contraindications. However, several barriers exist to the widespread adoption of this technique into clinical routine. One of the most important is the lack of a clear and consistent medical algorithm for interpreting magnetocardiographic data, leading to a clinically significant decision.