☆ 4.6 Article

ANN Prediction Model of Concrete Fatigue Life Based on GRW-DBA Data Augmentation

APPLIED SCIENCES-BASEL (2023)

Related references

Note: Only part of the references are listed.

Article Energy & Fuels

A Deep-Learning intelligent system incorporating data augmentation for Short-Term voltage stability assessment of power systems

Yang Li et al.

Summary: This paper proposes an intelligent system for short-term voltage stability assessment (STVSA) in power systems using data augmentation and deep learning. Semi-supervised cluster learning and conditional least squares generative adversarial networks (LSGAN) are used for labeled sample generation and data augmentation on a small dataset. An assessment model with attention mechanism is established to extract temporal dependencies. Experimental results demonstrate that this approach achieves higher accuracy and faster response time on small datasets.

APPLIED ENERGY (2022)

Add to Collection

Article Pharmacology & Pharmacy

Power priors with entropy balancing weights in data augmentation of partially controlled randomized trials

Guanglei Yu et al.

Summary: In pediatric or orphan diseases, conducting randomized and controlled clinical trials is often not feasible. To address this issue, real-world data can be used to complement the current trial. The entropy balancing weighting technique is a useful method for balancing covariates and augmenting the trial with external control data.

JOURNAL OF BIOPHARMACEUTICAL STATISTICS (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

An Adaptive Learning Rate Schedule for SIGNSGD Optimizer in Neural Networks

Kang Wang et al.

Summary: A novel adaptive learning rate schedule for neural network training via SIGNSGD optimizer is proposed, which automatically obtains learning rates in different training stages and outperforms the standard SGD in terms of faster convergence rate and better performance with fewer gradient communication bits. Three numerical simulations on three public datasets are conducted to demonstrate the efficiency of the proposed approach.

NEURAL PROCESSING LETTERS (2022)

Add to Collection

Article Physics, Applied

Prediction models establishment and comparison for guiding force of high-temperature superconducting maglev based on deep learning algorithms

Zhihao Ke et al.

Summary: This paper presents the prediction of guiding force in high-temperature superconducting (HTS) maglev using different neural network models. The results show that the deep neural network (DNN) model has the best fitting goodness, while the long short-term memory (LSTM) model displays the smoothest fitting curve. Additionally, adaptive iterative algorithms are proposed to optimize the parameters and learning rate, reducing computing time and unnecessary iterations.

SUPERCONDUCTOR SCIENCE & TECHNOLOGY (2022)

Add to Collection

Article Chemistry, Physical

Predicting the Mechanical Properties of RCA-Based Concrete Using Supervised Machine Learning Algorithms

Meijun Shang et al.

Summary: Environment-friendly concrete is gaining popularity due to its low energy consumption and minimal environmental damage. However, the increasing population and demand for construction result in a decrease in natural resources and an increase in construction waste. Therefore, the use of recycled materials and recycled coarse aggregate in concrete is crucial for addressing environmental issues.

MATERIALS (2022)

Add to Collection

Article Chemistry, Multidisciplinary

Application of Neural Network and Time-Domain Feature Extraction Techniques for Determining Volumetric Percentages and the Type of Two Phase Flow Regimes Independent of Scale Layer Thickness

Abdullah K. Alanazi et al.

Summary: This innovative non-invasive system uses a dual-energy gamma source and two detectors, along with artificial intelligence, to determine the flow pattern and volume percentage of two-phase flow by considering the thickness of scales in the pipelines.

APPLIED SCIENCES-BASEL (2022)

Add to Collection

Article Construction & Building Technology

Virtual mix design: Prediction of compressive strength of concrete with industrial wastes using deep data augmentation

Ning Chen et al.

Summary: The study utilized virtual material design approach, deep learning, and deep data augmentation to predict the compressive strength of concrete with industrial wastes, demonstrating that deep learning methods have higher accuracy. A lightweight deep convolutional neural network was designed to improve computational efficiency and prediction accuracy.

CONSTRUCTION AND BUILDING MATERIALS (2022)

Add to Collection

Article Construction & Building Technology

Residual strength of concrete subjected to fatigue based on machine learning technique

Wei Zhang et al.

Summary: This study employs machine learning techniques to address the complex fatigue problem of concrete materials. Various learning algorithms were trained using experimental data to estimate fatigue life, and a concrete strength degradation model was proposed.

STRUCTURAL CONCRETE (2022)

Add to Collection

Article Agronomy

A Reversible Automatic Selection Normalization (RASN) Deep Network for Predicting in the Smart Agriculture System

Xuebo Jin et al.

Summary: This paper proposes a Reversible Automatic Selection Normalization (RASN) network to improve the performance of deep learning prediction networks widely used in smart agriculture. By integrating normalization and renormalization layers, and scaling and translating the input with learnable parameters, the accuracy of the prediction has been effectively improved. The application results show that the model has good prediction ability and adaptability for greenhouses in smart agriculture system.

AGRONOMY-BASEL (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Integrated ANN-Bayes-based travel time prediction modeling for signalized corridors with probe data acquisition paradigm

Wei Lin et al.

Summary: This study proposed an innovative methodological framework that combines exponential smoothing technique, Artificial Neural Network (ANN) techniques, and Bayes algorithms for predicting travel time along a signalized corridor. The results showed that the developed models can effectively capture travel time patterns and perform well on real-world travel time datasets.

EXPERT SYSTEMS WITH APPLICATIONS (2022)

Add to Collection

Article Biophysics

Impact of deep learning architectures on accelerated cardiac T1 mapping using MyoMapNet

Amine Amyar et al.

Summary: The study investigated the performance of various deep learning architectures in the MyoMapNet model for T-1 estimation. The U-Net and FC DL models were found to enable fast myocardial T-1 mapping with good image quality and accuracy.

NMR IN BIOMEDICINE (2022)

Add to Collection

Article Biology

Multi-task multi-scale learning for outcome prediction in 3D PET images

Amine Amyar et al.

Summary: In this study, a multi-task, multi-scale learning framework is proposed to predict patient survival and treatment response. The results show that this framework can extract meaningful and powerful features, improving the performance of radiomics. The subsidiary tasks provide an inductive bias, enabling the model to better generalize.

COMPUTERS IN BIOLOGY AND MEDICINE (2022)

Add to Collection

Article Imaging Science & Photographic Technology

Weakly Supervised Tumor Detection in PET Using Class Response for Treatment Outcome Prediction

Amine Amyar et al.

Summary: It is proven that radiomic characteristics extracted from the tumor region are predictive. However, the segmentation of the lesion is time consuming and requires a highly trained physician. This study proposes a prediction framework for tumor segmentation and outcome prediction using weakly supervised deep learning. The proposed approach achieves state-of-the-art prediction results with a small data set and weak segmentation ground truth.

JOURNAL OF IMAGING (2022)

Add to Collection

Article Computer Science, Artificial Intelligence

Improving the accuracy of global forecasting models using time series data augmentation

Kasun Bandara et al.

Summary: Global Forecasting Models (GFM) trained across multiple time series have shown promising results in forecasting competitions and real-world applications. A novel data-augmentation based framework has been proposed to improve the accuracy of GFM models in less data-abundant settings, using techniques such as GRATIS, MBB, and DBA. The proposed variants significantly outperform state-of-the-art univariate forecasting methods in competition and real-world datasets.

PATTERN RECOGNITION (2021)

Add to Collection

Article Polymer Science

Prediction of Geopolymer Concrete Compressive Strength Using Novel Machine Learning Algorithms

Ayaz Ahmad et al.

Summary: The study utilizes supervised machine learning algorithms to predict the mechanical properties of concrete, with ensemble ML approaches like AdaBoost and Boosting showing higher effectiveness compared to individual ML techniques, with Boosting performing the best.

POLYMERS (2021)

Add to Collection

Article Engineering, Environmental

Monitoring the effect of surface functionalization on the CO2 capture by graphene oxide/methyl diethanolamine nanofluids

Zongming Zhou et al.

Summary: Research shows that stable suspensions of graphene oxide (GO) nanosheets in MDEA solutions can serve as a potential medium for CO2 absorption. Experimental analyses reveal that GO surface functionalization positively affects CO2 absorption by MDEA-based nanofluids. AI models are designed to predict CO2 solubility in GO/MDEA nanofluids.

JOURNAL OF ENVIRONMENTAL CHEMICAL ENGINEERING (2021)

Add to Collection

Article Computer Science, Artificial Intelligence

Approach for fault prognosis using recurrent neural network

Qianhui Wu et al.

JOURNAL OF INTELLIGENT MANUFACTURING (2020)

Add to Collection

Article Engineering, Civil

Damage detection in steel-concrete composite bridge using vibration characteristics and artificial neural network

Zhi Xin Tan et al.

STRUCTURE AND INFRASTRUCTURE ENGINEERING (2020)

Add to Collection

Article Computer Science, Hardware & Architecture

Grow and Prune Compact, Fast, and Accurate LSTMs

Xiaoliang Dai et al.

IEEE TRANSACTIONS ON COMPUTERS (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

LLR: Learning learning rates by LSTM for training neural networks

Changyong Yu et al.

NEUROCOMPUTING (2020)

Add to Collection

Article Construction & Building Technology

Determination and assessment of fatigue stresses on concrete bridges

Michael Hansen

STRUCTURAL CONCRETE (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

GRATIS: GeneRAting TIme Series with diverse and controllable characteristics

Yanfei Kang et al.

STATISTICAL ANALYSIS AND DATA MINING (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

Learning discriminative features via weights-biased softmax loss

Xiaobin Li et al.

PATTERN RECOGNITION (2020)

Add to Collection

Article Construction & Building Technology

New damage evolution law for modeling fatigue life of asphalt concrete surfacing of long-span steel bridge

Xun Qian Xu et al.

CONSTRUCTION AND BUILDING MATERIALS (2020)

Add to Collection

Proceedings Paper Computer Science, Information Systems

Heterogeneous Private Information Retrieval

Hamid Mozaffari et al.

27TH ANNUAL NETWORK AND DISTRIBUTED SYSTEM SECURITY SYMPOSIUM (NDSS 2020) (2020)

Add to Collection

Article Computer Science, Artificial Intelligence

diffGrad: An Optimization Method for Convolutional Neural Networks

Shiv Ram Dubey et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2020)

Add to Collection

Article Computer Science, Interdisciplinary Applications

Conversion of Mersenne Twister to double-precision floating-point numbers

Shin Harase

MATHEMATICS AND COMPUTERS IN SIMULATION (2019)

Add to Collection

Review Clinical Neurology

Artificial intelligence for assisting diagnostics and assessment of Parkinson's disease-A review

Minja Belic et al.

CLINICAL NEUROLOGY AND NEUROSURGERY (2019)

Add to Collection

Article Engineering, Mechanical

Experimental validation of an ANN model for random loading fatigue analysis

S. Ramachandra et al.

INTERNATIONAL JOURNAL OF FATIGUE (2019)

Add to Collection

Article Engineering, Multidisciplinary

Wasserstein GAN-Based Small-Sample Augmentation for New-Generation Artificial Intelligence: A Case Study of Cancer-Staging Data in Biology

Yufei Liu et al.

ENGINEERING (2019)

Add to Collection

Article Construction & Building Technology

Compressive strength prediction of recycled concrete based on deep learning

Fangming Deng et al.

CONSTRUCTION AND BUILDING MATERIALS (2018)

Add to Collection

Article Engineering, Mechanical

Density and velocity determination for single-phase flow based on radiotracer technique and neural networks

G. H. Roshani et al.

FLOW MEASUREMENT AND INSTRUMENTATION (2018)

Add to Collection

Article Computer Science, Artificial Intelligence

shapeDTW: Shape Dynamic Time Warping

Jiaping Zhao et al.

PATTERN RECOGNITION (2018)

Add to Collection

Article Chemistry, Multidisciplinary

Fatigue Life Prediction of High Modulus Asphalt Concrete Based on the Local Stress-Strain Method

Mulian Zheng et al.

APPLIED SCIENCES-BASEL (2017)

Add to Collection

Article Engineering, Civil

Multiple linear regression, artificial neural network, and fuzzy logic prediction of 28 days compressive strength of concrete

Faezehossadat Khademi et al.

FRONTIERS OF STRUCTURAL AND CIVIL ENGINEERING (2017)

Add to Collection

Article Construction & Building Technology

Fatigue life prediction method of concrete based on energy dissipation

Dong Lei et al.

CONSTRUCTION AND BUILDING MATERIALS (2017)

Add to Collection

Article Construction & Building Technology

Interactive Effect of Mechanical Fatigue Load and the Fatigue Effect of Freeze-Thaw on Combined Damage of Concrete

Wenting Li et al.

JOURNAL OF MATERIALS IN CIVIL ENGINEERING (2015)

Add to Collection

Article Construction & Building Technology

Prediction of Fatigue Life of Rubberized Asphalt Concrete Mixtures Containing Reclaimed Asphalt Pavement Using Artificial Neural Networks

Feipeng Xiao et al.

JOURNAL OF MATERIALS IN CIVIL ENGINEERING (2009)

Add to Collection

Article Environmental Sciences

The National Human Activity Pattern Survey (NHAPS): a resource for assessing exposure to environmental pollutants

NE Klepeis et al.

JOURNAL OF EXPOSURE ANALYSIS AND ENVIRONMENTAL EPIDEMIOLOGY (2001)

Add to Collection

© Peeref 2019-2024. All rights reserved.