Search or ask a question

How to use bayesian statistics in the field of crack concrete information?

Probabilistic logic

Convolutional neural network

Log-normal distribution

Best insight from top research papers

Bayesian statistics is used in the field of crack concrete information to quantify and assess the geometric properties of cracks. A novel crack quantification framework has been proposed that utilizes a set of unordered inspection images. Cracks in the images are detected using an instance segmentation convolutional neural network, and the crack segmentations from multiple separate images are aggregated through voxel-based reconstruction and Bayesian data fusion. This framework outputs a crack model that can retrieve accurate geometric properties of each crack segment by recognizing the crack's inherent branching patterns . Additionally, a Bayesian method has been developed to estimate the initial crack length distribution for probabilistic risk analysis of repaired structural details. The method updates a non-informative prior using a likelihood function based on inspection capability, structural geometry, and material properties .

Answers from top 5 papers

PDF

Open Access

More filters

Papers (5)	Insight
Open access•Book Chapter•DOI Bayesian Updating of a Cracking Model for Reinforced Concrete Structures Subjected to Static and Cyclic Loadings Henriette Marlaine Imounga, Emilio Bastidas-Arteaga, Moutou Pitti Rostand, Serge Ekomy Ango - Show less +3 more 01 Jan 2021	The paper proposes a Bayesian network-based methodology to propagate uncertainties in a damage model for reinforced concrete structures subjected to cyclic loading.
Journal Article•DOI Bayesian method for estimating initial crack size distribution for probabilistic risk analysis of repairable structural details Doo-Sun Lee, D. S. Lim, Hwasoo Kim, Seil Baek - Show less +3 more 31 May 2022-Fatigue & Fracture of Engineering Materials & Structures 3 Citations	The provided paper does not specifically mention the field of crack concrete information.
Journal Article•DOI Concrete Crack Quantification Using Voxel-Based Reconstruction and Bayesian Data Fusion Chaobo Zhang, Maziar Jamshidi, Chih-Chen Chang, Xiaojun Liang, Zhiwen Chen, Weihua Gui - Show less +5 more 01 Nov 2022-IEEE Transactions on Industrial Informatics	The paper proposes a crack quantification framework that utilizes Bayesian data fusion to aggregate crack segmentations from multiple images and retrieve accurate geometric properties of each crack segment.
Journal Article•DOI Concrete Crack Quantification Using Voxel-Based Reconstruction and Bayesian Data Fusion 01 Nov 2022-IEEE Transactions on Industrial Informatics 1 Citations	The paper proposes a crack quantification framework that utilizes Bayesian data fusion to aggregate crack segmentations from multiple images and retrieve accurate geometric properties of each crack segment.
Journal Article•DOI Probabilistic structural identification and condition assessment of prestressed concrete bridges based on Bayesian inference using deflection measurements Siyi Jia, Mitsuyoshi Akiyama, Bing An Han, Dan M. Frangopol - Show less +3 more 31 Mar 2023-Structure and Infrastructure Engineering 1 Citations	The provided paper does not specifically discuss the use of Bayesian statistics in the field of crack concrete information.

My columns

Related Questions

How Bayesian Analysis is used and explain briefly.?5 answersBayesian analysis is a statistical approach that focuses on evaluating the probability of outcomes based on data and prior knowledge. It involves constructing a model, incorporating prior information, and estimating the posterior distribution of parameters. The posterior distribution is then used to estimate quantities of interest about the parameters. Bayesian analysis has advantages over traditional statistical significance testing, such as providing a more flexible and intuitive framework for inference. It has been applied in various fields, including operations and supply chain management (OSCM), strategic management research, medical literature, and high-energy polarimetry. The use of Bayesian methods is becoming more popular due to advancements in computing power, which allows for simulation-based approximations of the posterior distribution.

How does Bayesian Analysis is use illustration?5 answersBayesian analysis is used as a method for data analysis in various fields, including social sciences, cardiovascular medicine, strategic management research, and occupational exposure analysis. It offers several advantages such as better understanding of uncertainty, incorporation of previous research, straightforward interpretation of findings, high-quality inferences with small samples, and the ability to work with complex data structures. In social sciences, Bayesian modeling can be used to analyze couple, marriage, and family therapy research. In cardiovascular medicine, Bayesian analysis integrates new trial information with existing knowledge to reduce uncertainty and change attitudes about treatments. In strategic management research, Bayesian methods provide an alternative to traditional statistical significance testing and offer advantages in conducting and reporting analyses. In occupational exposure analysis, Bayesian analysis methods can quantify plausible values for exposure parameters of interest and provide insight into the exposure distribution.

What is the crack velocity in concrete?5 answersThe crack velocity in concrete can vary depending on various factors such as loading rate, fiber content, and strain rate. In some cases, crack velocities can reach several hundred meters per second. The crack propagation speed can be influenced by the presence of steel fibers, with higher fiber content resulting in higher crack velocities, even reaching speeds close to the theoretically predicted terminal crack velocity. Additionally, the crack speed in ultra-high performance concrete (UHPC) has been found to increase asymptotically as the crack initiation strain rate increases. The loading rate also plays a significant role, with crack branching observed at higher loading rates and a critical crack velocity at the onset of crack branching. Experimental methods such as spalling tests and digital image correlation coupled with ultra-high-speed cameras have been used to determine crack speeds in concrete.

How can Bayesian statistical models be used to improve image analysis?5 answersBayesian statistical models can be used to improve image analysis in several ways. Firstly, they allow for the modeling of complex problems such as image noise-reduction, de-blurring, feature enhancement, and object detection. Secondly, Bayesian model selection provides a framework for selecting the most appropriate model directly from the observed data, without reference to ground truth data. Additionally, variational inference methods based on conditional normalizing flows offer a promising alternative to traditional MCMC methods, enabling fast approximation of point estimates and uncertainty quantification. Furthermore, score-based diffusion models can be used for Bayesian image reconstruction, providing efficient tools for generative modeling and solving image reconstruction problems. Overall, Bayesian statistical models offer a flexible and powerful approach to improve image analysis by addressing computational difficulties, allowing for model selection, enabling fast approximation, and providing uncertainty quantification.

What is Bayesian inference in artificial intelligence?5 answers

What is Bayesian probabilistic inference in artificial intelligence?4 answers

See what other people are reading

What is pros and cons of using plasmonic nanoparticle as biomarker?

Plasmonic nanoparticles offer significant advantages as biomarkers, including ultrasensitive detection capabilities and versatility. They enable the detection of biomarkers at extremely low concentrations, down to the single-molecule level, enhancing early diagnosis of diseases like cancer and neurological disorders. Additionally, plasmonic nanoparticles can be integrated into digital imaging immunoassays, improving selectivity and sensitivity for precise biomarker quantification. However, challenges such as reproducibility issues and high background noise exist with amplification-based methods using plasmonic nanoparticles. Despite these limitations, the development of plasmonic nanoparticle-based biosensors continues to progress, offering promising solutions for rapid and accurate biomarker detection in various diseases, potentially revolutionizing clinical diagnosis and drug discovery.What is aesthetic attire choices?

Aesthetic attire choices encompass the selection of clothing and accessories based on aesthetic considerations rather than purely practical ones. These choices serve as vehicles of identity, allowing individuals to express confidence, identity, status, aspirations, and affiliations through their appearance. The aesthetic features of clothing play a crucial role in consumer decision-making, as users often base their choices on whether the clothing aligns with their personal aesthetics. Dressing the body is a form of communication, used to attract attention, convey messages, or conform to societal norms. Aesthetic attire choices are influenced by cultural perceptions, personal preferences, and the desire to represent oneself in a particular way.How can digital image processing be used to detect neurodegenerative changes in the brain?

Digital image processing can aid in detecting neurodegenerative changes in the brain by utilizing advanced techniques such as computer vision and deep learning algorithms. Techniques like segmentation and color detection algorithms can track structural abnormalities in MRI images to assess neural atrophy, indicating the presence and extent of dementia. Additionally, unsupervised generative modeling techniques, like Deep Convolutional Adversarial Networks (DCGANs), can be employed to produce synthetic images from limited neuroimaging data, increasing dataset size and variety for more accurate diagnosis of neurodegenerative diseases like Alzheimer's Disease and Mild Cognitive Impairment. These methods enhance the analysis of neuroimaging data, enabling better detection of biomarkers associated with neurodegenerative diseases, ultimately aiding clinicians in diagnosis and treatment.How Machine Learning Algorithms work in Face Recognition System? A Review and Comparative Study?

Machine learning algorithms play a crucial role in face recognition systems by extracting facial features and identifying individuals. Various studies have evaluated the performance of machine learning algorithms in facial expression recognition (FER) tasks. These algorithms, such as support vector machine, random forest, logistic regression, and AdaBoost, have been tested on datasets like FER2013 to assess their accuracy and robustness. The goal is to enhance the effectiveness of these algorithms in recognizing facial expressions accurately, despite challenges like aging, beard, and different poses. By comparing different algorithms and their performance, researchers aim to improve the overall efficiency and reliability of face recognition systems.What are some traditional methods other than machine and deep learning for detection brain abnormalities?

Traditional methods for detecting brain abnormalities, apart from machine and deep learning, include nuclear magnetic resonance (MRI) imaging. MRI scans are commonly used to identify abnormal tissue growth in the brain, such as tumors, by providing detailed information about the brain's structure. Additionally, human investigation has been a traditional technique for detecting abnormalities in the brain, although it is limited by the vast amount of data and human error. These methods have been essential in diagnosing brain conditions before the advent of advanced technologies like machine learning and deep learning. While machine learning and deep learning algorithms have shown promise in improving detection accuracy and efficiency, traditional methods like MRI imaging and human investigation remain fundamental in the field of brain abnormality detection.How AI is impacting Security Management and Assessment of Smart Grid?

AI is significantly impacting Security Management and Assessment of Smart Grids by enhancing cybersecurity measures. Utilizing AI-based security controls, such as machine learning algorithms, improves intrusion detection and malware prevention. AI enables the development of advanced security mechanisms like the AI-ADP scheme, combining artificial intelligence for attack detection and prevention with cryptography-driven recommender systems for data security. Furthermore, AI facilitates the implementation of deep learning algorithms, like convolutional neural networks, for intelligent operation and maintenance in power terminals, ensuring comprehensive protection at both device and network levels. Overall, AI's integration in Smart Grid security management enhances risk assessment, transparency, and interpretability of security controls, ultimately strengthening the resilience of critical infrastructures against cyber threats.What are the specific neuroimaging techniques used to investigate dyslexia and identify potential biomarkers?

Neuroimaging techniques such as functional MRI (fMRI), EEG, and MRI data analysis methods like Convolutional Neural Networks (CNNs) and Time Distributed Convolutional Long-Short Term Memory Neural networks are utilized to investigate dyslexia and identify potential biomarkers. These techniques aid in examining neuronal response properties related to reading difficulties, screening reading ability through physiological assessments, and detecting dyslexia based on anatomical and functional MRI data. Additionally, methods like modified histogram normalization (MHN) and Gaussian smoothing are employed to enhance the interpretation of dyslexia neural-biomarkers from MRI datasets, improving image features and tissue volume estimations for accurate dyslexia classification. The combination of these advanced neuroimaging approaches offers a comprehensive understanding of dyslexia and facilitates the early identification of reading impairments in children.Domain adaptation for generating compound fault signals

Domain adaptation techniques are crucial for generating compound fault signals in fault diagnosis. Various studies propose innovative methods to address the challenge of limited labeled data and diverse working conditions. One approach involves utilizing multichannel domain adaptation graph convolutional networks to extract domain-invariant features for fault diagnosis under varying conditions. Another method leverages simulation-driven domain adaptation using physical-based simulations to align source and target domain data for high classification accuracy with minimal real data, particularly beneficial for industrial applications. Additionally, a multilayer domain adaptation (MLDA) method is designed to diagnose compound and single faults of various sizes simultaneously, effectively extracting domain-invariant features for improved fault diagnosis performance. These approaches collectively demonstrate the significance of domain adaptation in generating compound fault signals for enhanced fault diagnosis.Is this true: incorporating self-attention mechanisms (SAM) into hybrid models has emerged as a focal point in load forecasting?

Yes, incorporating self-attention mechanisms (SAM) into hybrid models has indeed emerged as a focal point in load forecasting, as evidenced by recent research across various studies. The integration of SAM into hybrid models like CNN-GRU and LSTM has been shown to significantly enhance the accuracy and efficiency of load forecasting models. For instance, the CNN-GRU-DAM model, which combines convolutional neural networks (CNN), gated recurrent units (GRU), and dual attention mechanisms, demonstrates improved forecasting accuracy with a mean absolute percentage error (MAPE) reduction, highlighting the effectiveness of attention mechanisms in capturing temporal dynamics and feature correlations within load data. Further, the application of SAM in a model based solely on load data, without the need for additional features like weather or time, has shown to outperform traditional LSTM and CNN-GRU models by a significant margin, indicating the power of attention mechanisms in enhancing model performance even with minimal input data. Similarly, the integration of attention layers in non-intrusive load monitoring (NILM) models has been found to improve the extraction of appliance-level power consumption data, which is crucial for accurate load forecasting. Moreover, the use of attention mechanisms in SEQ2SEQ frameworks with BIGRU (Bidirectional GRU) has been validated through simulation experiments, further confirming the utility of attention mechanisms in making the decoder's predictive value more targeted across different time periods. Additionally, the development of hierarchical self-attention models like LTSNet for long-term load trend forecasting showcases the capability of attention mechanisms to mine high-dimensional features and maintain stable forecasting performance over extended periods. Research also highlights the effectiveness of multi-scale feature attention hybrid networks in capturing multi-scale features and important parameters of multi-factor input sequences, thereby enhancing the accuracy and robustness of short-term load forecasting. Lastly, the DCNN-LSTM-AE-AM framework combines various deep learning techniques with attention mechanisms to improve prediction results, especially in capturing oscillation characteristics of low-load data, underscoring the comprehensive benefits of incorporating SAM into hybrid models for load forecasting. In summary, the integration of self-attention mechanisms into hybrid models for load forecasting is a significant trend that has been proven to enhance model performance across various dimensions of forecasting accuracy, robustness, and applicability to different forecasting scenarios.What are the urgency of prediction of solar irradiation for pv using wrf model?

Prediction of solar irradiation for photovoltaic (PV) systems using the Weather Research and Forecasting (WRF) model is crucial for maintaining power balance and ensuring the secure operation of power systems. The accuracy of solar irradiance forecasts is essential for integrating non-conventional energy sources into the grid effectively. The WRF-Solar model is specifically designed to meet the increasing demand for accurate solar irradiance forecasting, offering flexibility in representing aerosol-cloud-radiation processes. By utilizing ensemble techniques like random forest and extreme gradient boosting, the accuracy of solar radiation prediction can be significantly enhanced, making them ideal models for solar energy prediction. Additionally, the WRF-Solar ensemble prediction system, coupled with calibration methods, improves forecast quality by considering the uncertainty of each ensemble member, leading to reduced bias and enhanced probabilistic attributes.How to classifier breed horse?

To classify horse breeds, various methods have been explored in recent research. One effective approach is the use of deep learning techniques, specifically pre-trained deep convolutional neural networks, which have shown promising results in automatic breed classification of horses. Another method involves utilizing a neuro-fuzzy classifier (NFC) of the Takagi-Sugeno-Kang (TSK) type, combined with wavelet packet (WP) transformed data, to classify different horse gaits based on rider's hip motion data collected by inertial sensors. Additionally, genetic information and classification algorithms have been employed to investigate genetic relationships and population structure among different horse breeds, demonstrating the utility of machine learning algorithms like Naive Bayes and IB1 for breed discrimination tasks. Furthermore, a study utilized a combination of wireless motion sensors and machine learning to automatically classify horse gaits with high accuracy, enabling detailed biomechanical studies and genetic research in gait classification.