Article
Engineering, Multidisciplinary
Subhashree Mohapatra, Girish Kumar Pati, Manohar Mishra, Tripti Swarnkar
Summary: This study proposes an intelligent method using empirical wavelet transform (EWT) and convolutional neural network (CNN) to classify alimentary canal diseases. The method achieves high accuracy and performance metrics in disease classification. A comparative study with other contemporary techniques is conducted to validate the efficacy of the proposed method.
AIN SHAMS ENGINEERING JOURNAL
(2023)
Article
Spectroscopy
Maryam Valizadeh, Melika Sohrabi, Zahra Ameri Braki, Rashed Rashidi, Maryam Pezeshkpur
Summary: This study investigated the simultaneous absorption of SAL and FLU in Seroflo spray using CWT and RBF-NN methods. The RMSE and LOD/LOQ values obtained showed the accuracy and sensitivity of the chemometrics methods, which were comparable to HPLC as a reference method for drug analysis in pharmaceutical quality control laboratories.
SPECTROCHIMICA ACTA PART A-MOLECULAR AND BIOMOLECULAR SPECTROSCOPY
(2021)
Article
Computer Science, Information Systems
Pan Zhen, Bangning Zhang, Zhibo Chen, Daoxing Guo, Wenfeng Ma
Summary: In this letter, a spectrum sensing method called WT-ResNet is proposed, which is based on wavelet transform and residual network. This method effectively addresses the issues of non-stationary signals and low SNR. It is data-driven and does not require any prior knowledge about the signal. Simulation results show that the method outperforms other spectrum sensing methods.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2022)
Article
Computer Science, Hardware & Architecture
Shui-Hua Wang, Jin Zhou, Yu-Dong Zhang
Summary: This study proposes a novel method for more efficient and accurate recognition of community-acquired pneumonia. The method uses wavelet entropy as the feature extractor and cat swarm optimization to train an artificial neural network. Experimental results demonstrate that this method outperforms four state-of-the-art approaches in terms of performance.
MOBILE NETWORKS & APPLICATIONS
(2022)
Article
Thermodynamics
Ruan Luzia, Lihki Rubio, Carlos E. Velasquez
Summary: Several studies have focused on improving forecasting techniques for capturing multiple patterns in time series. The advancement in computing hardware has made it possible to solve complex equations using large amounts of data, such as neural networks. However, time series methods like ARIMA can also provide good approximations with low computational resources. To enhance ARIMA approximations, they can be combined with techniques like Wavelet Transform or Fourier Transform. This study evaluates the suitability of using artificial neural networks, ARIMA combined with Wavelet Transform, or Fourier Transform to make predictions for different time horizons and frequencies. The results indicate that artificial neural networks perform better for short-term horizons, ARIMA with Fourier Transform provides the best approximation for monthly time series and any time horizon, and ARIMA with Wavelet Transform offers the best approximation for medium-term and long-term periods at any time frequency.
Article
Environmental Sciences
Hadi Fattahi, Nastaran Zandy Ilghani
Summary: This study utilizes a hybrid model of wavelet transform and artificial neural network to estimate shear wave velocity. Preprocessing of input variables using wavelet transform enhances the accuracy of model calculations, which is validated using field data from Marun reservoir in Iran.
ENVIRONMENTAL EARTH SCIENCES
(2021)
Article
Chemistry, Analytical
Andrey Stepanov
Summary: This paper introduces a modified wavelet synthesis algorithm for continuous wavelet transform, which provides a guaranteed approximation of the maternal wavelet to the sample and a formalized representation of the wavelet. The method distinguishes itself by using splines and artificial neural networks to achieve higher accuracy.
Article
Psychology, Multidisciplinary
Chengjin Xu, Zhe Zhang
Summary: This study examines the entrepreneurial psychology of college students and its effects, summarizing the four aspects of entrepreneurial psychology, reviewing the research status, and proposing a combined model of wavelet transform and Neural Network. The research found that male students have significantly higher self-efficacy than female students, and entrepreneurial psychology is highly correlated with gender and education levels.
FRONTIERS IN PSYCHOLOGY
(2021)
Article
Engineering, Multidisciplinary
Hao Dong, Yufeng Nie, Junzhi Cui, Wenbo Kou, Minqiang Zou, Junyan Han, Xiaofei Guan, Zihao Yang
Summary: An innovative wavelet-based learning approach assisted multiscale analysis is developed to predict the effective thermal conductivities of particulate composites with heterogeneous conductivity, combining the advantages of multiscale modeling, wavelet transform, and artificial neural network.
COMPUTER METHODS IN APPLIED MECHANICS AND ENGINEERING
(2021)
Article
Engineering, Multidisciplinary
Mantang Hu, Guofeng Wang, Kaile Ma, Zenghuan Cao, Shuai Yang
Summary: A method for bearing performance degradation assessment is proposed, using optimized empirical wavelet transform and fuzzy C-means model to improve the sensitivity and stability of the assessment method in extracting fault information.
Article
Computer Science, Information Systems
Xiangyu Zhao, Peng Huang, Xiangbo Shu
Summary: This paper investigates the issues in feature learning methods based on CNN and proposes a new module based on wavelet attention for image classification. Experimental results demonstrate significant improvements in accuracy using this approach.
MULTIMEDIA SYSTEMS
(2022)
Article
Computer Science, Information Systems
Seung-Kwan Kang, Si-Young Yie, Jae-Sung Lee
Summary: In this study, the Noise2Noise framework and trainable wavelet transform were used to reduce noise in PET images, achieving good results in artifact suppression and abnormal uptake preservation. Quantitative analysis showed that the proposed method outperformed the original Noise2Noise technique and improved image contrast.
Article
Engineering, Electrical & Electronic
Sudip Modak, Sayanjit Singha Roy, Rohit Bose, Soumya Chatterjee
Summary: In this study, a novel approach for automated detection and classification of focal EEG signals was proposed, utilizing cross wavelet transform and a customized CNN model. The experiment showed promising results, with 100% accuracy achieved for the delta rhythm and significantly reduced training time compared to existing CNN models.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Chemical
Jindong Zhang, Zhangjianing Cheng
Summary: In this study, a model combining wavelet noise reduction and radial basis neural network (XW-RBF) is proposed to reduce noise interference in monitoring data. The XW-RBF model predicts an average relative error of 0.77 and a root average square error of 0.13, which outperforms the original data prediction results with noise structure and shows higher prediction accuracy. The wavelet noise reduction method can remove noise data caused by construction interference and the surrounding environment, reducing the discreteness of the original data by 30%. The XW-RBF model can reflect the law of data change and predict future data trends with high credibility. These findings suggest that the XW-RBF model can optimize the deep foundation pit settlement prediction model for high accuracy and has potential application in deep foundation pit engineering.
Article
Acoustics
Shaul Hameed Syed, V. Muralidharan
Summary: This study investigates the fault diagnosis of planetary gearbox using discrete wavelet analysis combined with Artificial Neural Network and Support Vector Machine. The research finds that the mean square energy of detailed coefficients of Discrete Wavelet Transform shows excellent fault diagnosing characteristics.
Article
Engineering, Civil
Elham Rajabi, Gholamreza Ghodrati Amiri
Summary: This study proposes the control of ductility demands of reinforced concrete frames under critical-successive earthquakes using artificial neural networks and empirical equations. The research finds that critical record sequences decrease the capacity of frames, emphasizing the importance of determining the value of R factors based on actual conditions.
SUSTAINABLE AND RESILIENT INFRASTRUCTURE
(2022)
Article
Acoustics
Hamed Keikha, Gholamreza Ghodrati Amiri
Summary: This study combines the equivalent lateral force procedure with the capacity spectrum method to evaluate the performance of quintuple friction pendulum isolators in isolated structures. The accuracy of the simplified method is assessed by comparing its results with nonlinear response history analysis under different earthquake motions and site conditions, providing guidance for practical design.
JOURNAL OF VIBRATION AND CONTROL
(2023)
Article
Engineering, Civil
Mohammadreza Jalalinia, Gholamreza Ghodrati Amiri, Seyed Ali Seyed Razzaghi
Summary: This article proposes a baseline-free method for accurately locating damage, specifically cracks, in plates with a circular hole. By using guided ultrasonic waves and analyzing the response signals with wavelet transform, actionable damage-sensitive features are extracted to calculate damage indexes and locate the damage.
IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF CIVIL ENGINEERING
(2022)
Article
Engineering, Civil
Hossein Rezaei, Panam Zarfam, Emadaldin Mohammadi Golafshani, Gholamreza Ghodrati Amiri
Summary: This study develops seismic response prediction models and fragility curves for concrete box-girder bridges using Symbolic Regression analysis. By considering geometrical, material, ground motion, and structural uncertainties, the reliability of the models is improved. The results demonstrate that the prediction models are effective and accurate.
Article
Engineering, Mechanical
Mohammadreza Jalalinia, Gholamreza Ghodrati Amiri, Seyed Ali Seyed Razzaghi
Summary: This article presents a baseline-free damage detection method based on guided ultrasonic waves and signal processing, which can accurately detect multiple damage locations at the edge of a circular hole in a plate-like structure. The method is also effective in detecting damage near the plate edge.
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2023)
Article
Engineering, Civil
Mohammad Bavandi, Gholamreza Ghodrati Amiri, Elham Rajabi, Abdolreza S. Moghadam
Summary: Natural hazards can become crises without reduction systems, and quantitative estimation of hazards is crucial for prevention. Structural resilience encompasses different dimensions, and qualitatively involves predicting factors to restore damaged structures quickly. This study evaluates the resilience of 3-story buildings with post-tensioned self-centering connections through six models, developing a seismic resilience index and a quantitative assessment index for self-centering structures. One significant finding is that resilience and structural performance decrease with increasing event occurrences. Higher indices indicate greater building resilience.
Article
Engineering, Civil
Hossein Babajanian Bisheh, Gholamreza Ghodrati Amiri
Summary: This paper proposes a novel method for structural damage detection, which combines the advantages of variational mode decomposition algorithm and kernel principal component analysis in the presence of environmental effects. The method decomposes vibration response data using the variational mode decomposition algorithm, extracts spectral centroid feature from selected intrinsic mode functions, and performs kernel principal component analysis to obtain damage-sensitive indices for condition monitoring. The proposed method is validated through numerical and full-scale studies, and the results show its accuracy in identifying structural damage under varying environmental conditions.
ENGINEERING STRUCTURES
(2023)
Article
Engineering, Civil
Seyed Amir Hashemi Amiri, Gholamreza Ghodrati Amiri, Maysam Ghasemi Naghibdehi, Mobin Afzalirad
Summary: In this research, numerical modeling of a 3D reinforced concrete column was conducted in three different conditions, including non-retrofitted state, steel plates retrofitted state, and CFRP retrofitted state. The effects of retrofits and heat on the cyclic lateral behavior of the columns were studied and compared through coupled temperature-displacement analysis under cyclic lateral loading at various heat levels.
PERIODICA POLYTECHNICA-CIVIL ENGINEERING
(2023)
Article
Computer Science, Interdisciplinary Applications
Hossein Rezaei, Panam Zarfam, Emadaldin Mohammadi Golafshani, Gholamreza Ghodrati Amiri
Summary: This paper introduces interpretable, reliable, and fast prediction models for estimating the seismic responses of curved bridges. These models are developed using two novel branches of the symbolic regression approach and consider various uncertainties. The most influential parameters for seismic demands are identified using the evolutionary correlation coefficient, and closed-form mathematical expressions are generated to predict seismic demands.
COMPUTERS & STRUCTURES
(2023)
Article
Engineering, Civil
Mohammad Hossein Afsharmovahed, Gholamreza Ghodrati Amiri, Ehsan Darvishan
Summary: This paper proposes a new method for damage detection of structures using specific sensors and feature-sensors to improve accuracy. The method is validated with real data from a cable-stayed bridge, demonstrating an accuracy of almost 98% in distinguishing damaged and healthy states.
IRANIAN JOURNAL OF SCIENCE AND TECHNOLOGY-TRANSACTIONS OF CIVIL ENGINEERING
(2023)
Article
Engineering, Mechanical
Arghavan Asghari, Gholamreza Ghodrati Amiri, Ehsan Darvishan, Arian Asghari
Summary: This study proposes a novel deep ensemble learning approach based on the stacked generalization method for detecting damages in structural health monitoring. The method utilizes a multi-headed deep artificial neural network architecture and combines predictions using the stacking ensemble method to enhance result accuracy. Experimental results verify the potential of this method in the field of structural health monitoring and damage detection.
JOURNAL OF VIBRATION ENGINEERING & TECHNOLOGIES
(2023)
Article
Engineering, Multidisciplinary
Mohtasham Khanahmadi, Borhan Mirzaei, Gholamreza Ghodrati Amiri, Majid Gholhaki, Omid Rezaifar
Summary: This study introduces a damage identification method to diagnose damaged regions in 3D sandwich panels using modal dynamic data. By defining an Irregularity Detection Index, it is possible to identify damaged locations, and the index value increases with the severity of the damage.
Article
Engineering, Civil
Bahador Adel Sanjideh, Azadeh Ghadimi Hamzehkolaei, Ali Zare Hosseinzadeh, Gholamreza Ghodrati Amiri
Summary: This paper proposes an optimization-based Finite Element model updating approach for structural damage identification and quantification. It introduces a modal flexibility-based error function and formulates the updating problem as an optimization problem using modal assurance criterion. The paper also proposes a new multi-stage Selective Particle Swarm Optimization (SPSO) algorithm to solve the optimization problem and verifies its performance and precision.
STRUCTURAL ENGINEERING AND MECHANICS
(2022)
Article
Engineering, Civil
Mohammadreza Ahadpour Khaneghah, Esmaeil Mohammadi, Vahid Broujerdian, Gholamreza Ghodrati Amiri
Summary: The goal of this research was to find the best design for a self-centering buckling restrained brace (SC-BRB) system by balancing self-centering capability and energy dissipation. Three, six, and nine-story structures were investigated using OpenSees software and the TCL programming language. The results showed that the SC-BRB system can significantly reduce the residual deformation of framed buildings while maintaining acceptable energy dissipation reduction.
EARTHQUAKES AND STRUCTURES
(2022)
Article
Engineering, Civil
Hossein Babajanian Bisheh, Gholamreza Ghodrati Amiri
Summary: This paper proposes a data-driven methodology for online early damage identification under changing environmental conditions. The proposed method relies on two data analysis methods: feature-based method and hybrid PCA-KPCA. The results demonstrate that the proposed method can accurately detect structural damage and reduce false alarms by suppressing the effects of environmental variations.
STRUCTURAL MONITORING AND MAINTENANCE, AN INTERNATIONAL JOURNAL
(2022)