相关参考文献
注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article
Energy & Fuels
Xiaomei Zhang et al.
Summary: In this study, the graphitization of coal is examined from the perspective of carbon nanostructures. The analysis reveals the coexistence of various carbon nanostructures in coal-based graphite, including amorphous, graphite-like, polygonal concentric, and pyrolytic graphitic nanostructures. The findings provide valuable insights into the utilization of coal resources and the preparation of high-quality graphite.
Article
Engineering, Mechanical
Julian N. Heidenreich et al.
Summary: The use of micromechanics and homogenization theory allows for predicting the effective mechanical properties of materials based on microstructural information. The microstructural information is encoded in images using convolutional neural networks (CNN), through which geometric information is reduced to ten characteristic features. A fully connected neural network model is introduced to predict the effective yield surfaces based on the encoded information, resulting in a computationally efficient CNN-FCNN model.
INTERNATIONAL JOURNAL OF PLASTICITY
(2023)
Review
Biology
Tao Zhou et al.
Summary: This paper reviews the image fusion methods based on deep learning from five aspects: the principle and advantages, the classification of methods, the application in medical image field, the evaluation metrics, and the challenges faced. It provides a systematic summary and guidance for the study of multi-modal medical images.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Materials Science, Multidisciplinary
Pingluo Zhao et al.
Summary: This study designs a neural network-based model for material microstructure recognition and semantic segmentation. It overcomes the challenges of efficient recognition and extraction of multiple structures by automatically identifying and classifying titanium alloy structures and adaptively processing images to extract features.
MATERIALS & DESIGN
(2023)
Article
Materials Science, Multidisciplinary
Yevgeny Rakita et al.
Summary: In this study, the use of scanning electron diffraction coupled with electron atomic pair distribution function analysis was explored to understand the local order in a complex multicomponent system. The experiments provided insights into the chemistry and ordering tendencies in different regions of the sample with high spatial resolution. The findings are valuable for understanding the formation and structure of the material. Rating: 8 out of 10.
Article
Computer Science, Artificial Intelligence
Antonio Manuel Duran-Rosal et al.
Summary: The study proposes a randomized-based feedforward neural network approach for regression and classification problems. It suggests an alternative optimization model and presents different models to address the drawbacks of the existing approach. The proposed methods show competitive performance in classification accuracy and separability index, and particularly excel in deep models with direct links.
APPLIED SOFT COMPUTING
(2023)
Article
Automation & Control Systems
Ismail Enes Parlak et al.
Summary: High-pressure aluminum die-casting parts are widely used in the automotive industry due to their unique properties. This study presents a novel approach using deep learning-based object detection methods to detect internal defects in these parts using X-ray images, eliminating the need for time-consuming visual inspection by human specialists.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Materials Science, Multidisciplinary
Da Ren et al.
Summary: A deep learning strategy is implemented to predict the tensile property of dual-phase steel by using microstructure images as direct inputs. Compared with traditional physical models, this method can overcome the difficulty in quantifying complex microstructural information and has high portability and applicability. Moreover, an important visualization heat map analysis is used to quantitatively identify the key microstructural factors that influence tensile properties, which further improves the explicability of this method.
COMPUTATIONAL MATERIALS SCIENCE
(2023)
Article
Computer Science, Artificial Intelligence
Emmanuel Pintelas et al.
Summary: In this study, a Multi-View-CNN framework is proposed to enhance the performance of pre-trained CNN models, and a robust image representation is created using PCA dimension reduction. The findings show that this framework significantly improves the performance of CNN models.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2023)
Article
Electrochemistry
Pan Deng et al.
Article
Materials Science, Multidisciplinary
Yihao Tang et al.
Summary: The study found that adding Cr/Mo significantly improved the corrosion resistance and wear resistance of Fe-Mn-Al-C lightweight steel. This improvement can be attributed to the formation of protective oxide film in the solution, reducing the generation of harmful oxides and increasing the compactness and charge transfer resistance of the material.
MATERIALS CHARACTERIZATION
(2023)
Article
Computer Science, Artificial Intelligence
Anusha Aswath et al.
Summary: This review summarizes the progress of deep learning-based segmentation techniques in large-scale cellular electron microscopy (EM) over the past six years. It discusses the application of deep learning in EM segmentation, including supervised, unsupervised, and self-supervised learning methods, and examines their adaptability in segmenting cellular and sub-cellular structures. Evaluation measures for benchmarking EM datasets in various segmentation tasks are also provided. Finally, the current trends and future prospects of EM segmentation with large-scale models and unlabeled images are discussed.
MEDICAL IMAGE ANALYSIS
(2023)
Article
Materials Science, Multidisciplinary
Claudia Gorynski et al.
Summary: Using region-based convolutional neural networks (R-CNNs), this study presents a novel approach to accurately quantify various microstructural characteristics of polycrystalline microstructures, such as Feret diameter, axis length, area, circumference, dihedral angle, and coordination number. A two-step method is employed, involving a semi-automatic annotation tool for generating training data and a fully automated R-CNN for quantitative evaluation of images. The R-CNN performs well in evaluating grain size characteristics, even in images with low contrast, and can differentiate between uni- and bimodal grain size distributions on the sub-micron and nanoscale. The innovative solution makes grain size measuring more accessible, time-effective, less biased, consistent, and statistically more precise.
Article
Chemistry, Physical
Pascal Vincent et al.
Summary: In this study, we observed in real time the aligning effect of electric fields during the synthesis of carbon nanotubes using an environmental transmission electron microscope. The nanotubes showed excellent alignment and allowed for accurate determination of growth rates. Different growth behaviors were observed, including constant growth rates and acceleration. The mechanisms behind these behaviors, as well as the balance between electrostatic and adhesion forces, were discussed.
Review
Materials Science, Multidisciplinary
Shao-bin Bai et al.
Summary: The rapid development of automotive industry has led to a series of increasingly serious problems such as energy consumption and environmental pollution. Therefore, developing automotive steels with high-strength and low-density is crucial for energy conservation and emission reduction. In this paper, the Fe-Mn-C-Al system steel is discussed, which has been favored by researchers for its low density and excellent combination of strength and ductility. The composition design, production process, strengthening and strain hardening mechanisms, microstructure evolution, service performance, existing problems, and future challenges are systematically expounded.
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T
(2023)
Article
Medicine, General & Internal
Yini Huang et al.
Summary: A deep learning radiopathomics model was developed to predict the molecular subtypes of early-stage breast cancers using preoperative ultrasound images and biopsy slides. The model showed excellent diagnostic performance in both internal validation and external testing, outperforming other deep learning models based on ultrasound images or biopsy slides alone.
Article
Ergonomics
Angus McKerral et al.
Summary: Vehicle automation aims to make driving less fatiguing, more convenient, and safer. However, Level 3 automated vehicles require the driver to be ready to resume control, which relies on effectively reconstructed situation awareness (SA). This study compared AV operators who passively monitored the vehicle with those engaging in non-driving-related tasks (NDRTs) and found that operators engaging with NDRTs had better SA construction, suggesting implications for regulating NDRT use in AVs.
ACCIDENT ANALYSIS AND PREVENTION
(2023)
Article
Computer Science, Artificial Intelligence
Julian Luengo et al.
Summary: This paper reviews and categorizes computer vision techniques for metallographic image segmentation, introduces deep learning-based ensemble techniques utilizing pixel similarity, and conducts thorough comparisons in real-world datasets to discuss strengths, weaknesses, and application frameworks. The paper also addresses open challenges in the field to provide guidance for future research to fill existing gaps.
INFORMATION FUSION
(2022)
Article
Materials Science, Multidisciplinary
S. Breumier et al.
Summary: In this study, a U-Net model was trained to segment bainite, ferrite, and martensite on EBSD maps using the kernel average misorientation and the pattern quality index as input. The introduction of an unknown class during training simplified the manual labeling process. The investigation of providing maps with different acquisition steps, indexation quality, and constituent content to the model highlighted the significance of training the model with a diverse range of configurations. The model achieved a 92% mean accuracy in differentiating the three constituents. The inclusion of an additional channel containing the map acquisition step aided the model in generalizing to various EBSD acquisition steps.
MATERIALS CHARACTERIZATION
(2022)
Article
Chemistry, Physical
Mehran Dadsetan et al.
Summary: Carbon black oxidation is a post-treatment method that controls its properties for different applications. The study investigates the effect of particle size on oxidation pathway and rate by oxidizing three different sizes of carbon blacks. The diffusion-controlled burning model is validated for all samples oxidized at 800 degrees C in the presence of oxygen molecules. Under electron-beam irradiation, larger particles show a reduction in oxidation rate due to the breaking of atomic bonds and transformation to the graphitic structure. However, surface burning remains the dominant mode under electron-beam irradiation.
Article
Computer Science, Information Systems
Yetian Fan et al.
Summary: This paper proposes a BP algorithm with graph regularization (BPGR) to optimize the parameters and improve the generalization performance of BP neural networks. The proposed method enforces the latent features of the hidden layer to be more concentrated, enhancing the network's generalization capability. The modified graph regularization simplifies gradient calculation and better penalizes extreme weight values. Additionally, the graph regularization can be integrated with deep neural networks to further improve their generalization performance.
INFORMATION SCIENCES
(2022)
Article
Nanoscience & Nanotechnology
Michiel Larmuseau et al.
Summary: This study investigates the potential of using features from deep learning models to predict hardness and composition information of complex martensitic steels based on SEM images.
SCRIPTA MATERIALIA
(2022)
Article
Materials Science, Multidisciplinary
Ryan Jacobs
Summary: Deep learning-based object detection models have been widely used in materials science, especially in the analysis of features in electron microscopy images. This review highlights the key findings and limitations of recent studies using object detection in characterizing defects in metal alloys, segmenting and analyzing micro and nanoparticles, detecting individual atoms, and tracking objects in in situ videos. The opportunities and challenges faced by the materials community are discussed, along with best practices for model assessment and potential improvements in model training.
COMPUTATIONAL MATERIALS SCIENCE
(2022)
Article
Biology
Shuojia Zou et al.
Summary: Detecting tiny objects in microscopic videos is challenging, especially in large-scale experiments. In this paper, we propose a convolutional neural network (TOD-CNN) for tiny object detection, which is trained on a high-quality sperm microscopic video dataset and incorporates a graphical user interface (GUI) for effective application and testing. TOD-CNN achieves high accuracy, with 85.60% AP50 in real-time sperm detection in microscopic videos. By comparing with diagnosis results from medical doctors, the importance of sperm detection technology in sperm quality analysis is demonstrated.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Computer Science, Hardware & Architecture
Hao Wang et al.
Summary: This paper proposes a new surface defect detection network based on Mask R-CNN to detect rail defects, achieving high accuracy in defect location through multi-scale fusion, a new evaluation metric, and data augmentation.
COMPUTERS & ELECTRICAL ENGINEERING
(2022)
Article
Automation & Control Systems
Quan Jiang et al.
Summary: Engineering rock mass quality assessment requires the identification and counting of core features. In this study, an efficient automated application using the Faster R-CNN algorithm and a self-designed program was developed. The results showed significant improvements in identification accuracy and processing speed, making it a valuable tool for evaluating technical conditions in mining deposits.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Materials Science, Multidisciplinary
Marc Ackermann et al.
Summary: This study utilized deep learning to quantify the martensite-austenite (M-A) islands in bainite. The research found that the ratio of constituent to image size during data pre-processing is a crucial parameter affecting the accuracy of subsequently trained models.
MATERIALS CHARACTERIZATION
(2022)
Review
Computer Science, Artificial Intelligence
Claudine Badue et al.
Summary: The research survey examined literature on self-driving cars, focusing on the architecture of autonomy system, perception, and decision-making methods. It also provided a detailed description of the autonomy system of the self-driving car developed at the Universidade Federal do Espirito Santo (UFES). Additionally, prominent self-driving car research platforms developed by academia and technology companies were listed.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Engineering, Multidisciplinary
Ehsan Haghighat et al.
Summary: SciANN is a Python package for scientific computing and physics-informed deep learning. It utilizes TensorFlow and Keras to build deep neural networks and optimization models, allowing for solving partial differential equations with flexibility in setting complex functional forms.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2021)
Article
Materials Science, Multidisciplinary
Mingren Shen et al.
Summary: This study discusses the use of machine learning approaches to locate and analyze defect clusters in irradiated steels, showing the promising potential of deep learning to assist in the development of automated microscopy data analysis systems. The research demonstrates that deep learning can achieve comparable performance to human analysis even with small training data sets, paving the way for fast, scalable, and reliable analysis of massive amounts of modern electron microscopy data.
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Article
Materials Science, Multidisciplinary
Malgorzata Warmuzek et al.
Summary: This work details the application of the deep learning approach to recognizing specific morphological forms in the alloy microstructure, showcasing its effectiveness and potential value in research.
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Article
Engineering, Chemical
Dangfu Yang et al.
Summary: This study developed a systematic tool based on deep learning and computational geometry to evaluate and identify the shape of granular materials. By establishing image datasets with labeled masks and employing the Mask R-CNN model, successful identification and shape analysis of particles were achieved.
Article
Nanoscience & Nanotechnology
Hsin-Mei Lu et al.
Summary: The formation of TiSiGex-SL is related to factors such as a localized strain field and gradual segregation of germanium atoms. This phenomenon could be explained by thermodynamic preference, with germanium segregation pathway based on where substitution occurs. Ultimately, excluded germanium atoms tend to accumulate at the boundary of TiSiGex-SL, forming a discontinuous thin film layer.
SCRIPTA MATERIALIA
(2021)
Article
Materials Science, Multidisciplinary
Juwon Na et al.
Summary: This study proposes a deep learning-based refocusing method for SEM images, using improved convolutional neural networks to address out-of-focus issues. The method can not only refocus low-quality SEM images, but also selectively perform tasks in unfocused regions within the images.
Article
Materials Science, Multidisciplinary
Mingren Shen et al.
Summary: An automated TEM video analysis system utilizing the YOLO model was developed for accurate and efficient analysis of microstructural features, achieving human-comparable performance. The system enables detailed analysis of both static and dynamic properties, showing potential for evaluating materials dynamics and defect evolution in TEM videos.
COMPUTATIONAL MATERIALS SCIENCE
(2021)
Article
Biology
Hasib Zunair et al.
Summary: Sharp U-Net architecture addresses the issues of blurred feature maps and over-/under-segmented target regions by employing a depthwise convolution before merging encoder and decoder features. The model consistently outperforms recent baselines in both binary and multi-class biomedical image segmentation tasks, while adding no extra learnable parameters and surpassing baselines with more than three times the number of parameters.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Fotios Logothetis et al.
Summary: Retrieving accurate 3D reconstructions of objects from the reflections of light is a challenging task in computer vision. Recent approaches combining deep learning and computer graphics have shown success in coping with the need for vast amounts of training data, achieving state-of-the-art performance in various datasets.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Article
Materials Science, Multidisciplinary
Arun Baskaran et al.
COMPUTATIONAL MATERIALS SCIENCE
(2020)
Article
Multidisciplinary Sciences
Lianwei Chen et al.
Article
Physics, Applied
W. Ma et al.
JOURNAL OF APPLIED PHYSICS
(2020)
Article
Materials Science, Multidisciplinary
Elizabeth A. Holm et al.
METALLURGICAL AND MATERIALS TRANSACTIONS A-PHYSICAL METALLURGY AND MATERIALS SCIENCE
(2020)
Article
Microscopy
Chris M. Anderson et al.
Article
Computer Science, Information Systems
Xiaoyan Chen et al.
Article
Materials Science, Multidisciplinary
Brian L. DeCost et al.
MICROSCOPY AND MICROANALYSIS
(2019)
Article
Multidisciplinary Sciences
Graham Roberts et al.
SCIENTIFIC REPORTS
(2019)
Article
Engineering, Multidisciplinary
Xiang Li et al.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2019)
Article
Materials Science, Multidisciplinary
Zijiang Yang et al.
COMPUTATIONAL MATERIALS SCIENCE
(2018)
Article
Chemistry, Multidisciplinary
Kevin Ryan et al.
JOURNAL OF THE AMERICAN CHEMICAL SOCIETY
(2018)
Article
Physics, Multidisciplinary
Tian Xie et al.
PHYSICAL REVIEW LETTERS
(2018)
Article
Multidisciplinary Sciences
Seyed Majid Azimi et al.
SCIENTIFIC REPORTS
(2018)
Article
Multidisciplinary Sciences
Weike Ye et al.
NATURE COMMUNICATIONS
(2018)
Article
Multidisciplinary Sciences
Dipendra Jha et al.
SCIENTIFIC REPORTS
(2018)
Article
Computer Science, Artificial Intelligence
Evan Shelhamer et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Article
Computer Science, Artificial Intelligence
Shaoqing Ren et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2017)
Review
Engineering, Electrical & Electronic
Peter D. Nellist
MATERIALS SCIENCE IN SEMICONDUCTOR PROCESSING
(2017)
Article
Materials Science, Multidisciplinary
Matthew D. Hecht et al.
METALLURGICAL AND MATERIALS TRANSACTIONS A-PHYSICAL METALLURGY AND MATERIALS SCIENCE
(2017)
Review
Materials Science, Multidisciplinary
Shangping Chen et al.
PROGRESS IN MATERIALS SCIENCE
(2017)
Article
Materials Science, Multidisciplinary
Brian L. DeCost et al.
Proceedings Paper
Computer Science, Artificial Intelligence
Kaiming He et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Materials Science, Multidisciplinary
Matthew D. Hecht et al.
MATERIALS CHARACTERIZATION
(2016)
Article
Materials Science, Multidisciplinary
Mark S. Bailly et al.
Review
Biochemistry & Molecular Biology
Hans Blom et al.
CURRENT OPINION IN CHEMICAL BIOLOGY
(2014)
Article
Computer Science, Information Systems
Esther Guerra et al.
INFORMATION AND SOFTWARE TECHNOLOGY
(2009)
Article
Materials Science, Multidisciplinary
V Sundararaghavan et al.
Article
Nanoscience & Nanotechnology
M Elmadagli et al.
MATERIALS SCIENCE AND ENGINEERING A-STRUCTURAL MATERIALS PROPERTIES MICROSTRUCTURE AND PROCESSING
(2003)
Article
Computer Science, Artificial Intelligence
L Breiman