Latest Publications on Examples of Fast Fourier Transform (FFT)
This is our latest selection of worldwide publications on Examples of Fast Fourier Transform (FFT), between many scientific online journals, classified and focused on fast fourier, FFT, discrete fourier and Cooley–Tukey.
Tip: Further to this selection on Examples of Fast Fourier Transform (FFT), you can search and filter our > publication database < by author, topic, keywords, date or journal.
Point Cloud Vibration Compensation Algorithm Based on an Improved Gaussian–Laplacian Filter
On 2025-01-31 by Wanhe Du, Xianfeng Yang, Jinghui Yang @MDPI
Keywords: Gaussian-Laplacian Filter, Vibration Compensation Algorithm, Point Cloud, Industrial environments, Steel plate surface inspection
AI summary: Novel algorithm improves vibration compensation for industrial steel plate surface inspection. FFT-based vibration factor extraction, adaptive windowing strategy, weighted compensation mechanism. Algorithm shows significant improvements in signal-to-noise ratio. Practical solution for surface inspection in industrial environments.
Abstract: In industrial environments, steel plate surface inspection plays a crucial role in quality control. However, vibrations during laser scanning can significantly impact measurement accuracy. While traditional vibration compensation methods rely on complex dynamic modeling, they often face challenges in practical implementation and generalization. This paper introduces a novel point cloud vibration compensation algorithm that combines an improved Gaussian&ndash;Laplacian filter with adaptiv[...]
Publication
Predicting the Dynamic Response of Transmission Tower–Line Systems Under Wind–Rain Loads
On 2025-01-30 by Bo Yang, Yifan Luo, Yingna Li, Lulu Wang, Jiawen Zhang @MDPI
Keywords: surrogate model, dynamic response, transmission tower, wind-rain loads, deep learning
AI summary: Study predicts tower-line system response under wind-rain loads using TimesNet. Numerical model generates dynamic response data. FFT transforms input signals for accurate predictions. Surrogate model provides precise results under complex conditions.
Abstract: This study, based on existing research on the dynamic response of transmission tower&ndash;line systems under wind and rain loads, proposes a method for predicting these responses using the TimesNet deep learning surrogate model. Initially, a numerical model of the tower&ndash;line system is developed to generate dynamic response time series data under the influence of wind velocity and rainfall forces. Wind velocity and precipitation intensity are used as inputs for the surrogat[...]
Publication
Vibration-Based Anomaly Detection for Induction Motors Using Machine Learning
On 2025-01-27 by Ihsan Ullah, Nabeel Khan, Sufyan Ali Memon, Wan-Gu Kim, Jawad Saleem, Sajjad Manzoor @MDPI
Keywords: machine learning, vibration-based, anomaly detection, induction motors, predictive maintenance
AI summary: Study uses machine learning for fault diagnosis in induction motors. Three algorithms tested for accuracy. Results show promise with highest accuracy achieved using deep neural networks and FFT-based features.
Abstract: Predictive maintenance of induction motors continues to be a significant challenge in ensuring industrial reliability and minimizing downtime. In this study, machine learning techniques are utilized to enhance fault diagnosis through the use of the Machinery Fault Database (MAFAULDA). A detailed extraction of statistical features was performed on multivariate time-series data to capture essential patterns that could indicate potential faults. Three machine learning algorithms&mdash;deep [...]
Publication
Radar Signal Processing and Its Impact on Deep Learning-Driven Human Activity Recognition
On 2025-01-25 by Fahad Ayaz, Basim Alhumaily, Sajjad Hussain, Muhamamd Ali Imran, Kamran Arshad, Khaled Assaleh, Ahmed Zoha @MDPI
Keywords: radar signal processing, deep learning, human activity recognition, convolutional neural networks, CNN architectures
AI summary: Integration of radar signal processing and deep learning for improved human activity recognition. Evaluation of radar processing techniques and CNN architectures for efficient HAR. MobileNetV2 with STFT preprocessing achieves high accuracy and computational efficiency. Visual features from radar-generated maps enhance applicability in resource-constrained environments.
Abstract: Human activity recognition (HAR) using radar technology is becoming increasingly valuable for applications in areas such as smart security systems, healthcare monitoring, and interactive computing. This study investigates the integration of convolutional neural networks (CNNs) with conventional radar signal processing methods to improve the accuracy and efficiency of HAR. Three distinct, two-dimensional radar processing techniques, specifically range-fast Fourier transform (FFT)-based time-range[...]
Publication
A Hybrid Dynamic Principal Component Analysis Feature Extraction Method to Identify Piston Pin Wear for Binary Classifier Modeling
On 2025-01-18 by Hao Yang, Yubin Zhai, Mengkun Zheng, Tan Wang, Dongliang Guo, Jianhui Liang, Xincheng Li, Xianliang Liu, Mingtao Jia, Rui Zhang @MDPI
Keywords: dynamic principal component analysis, feature extraction, piston pin wear, binary classifier modeling, signal processing
AI summary: A hybrid method for identifying piston pin wear through dynamic feature extraction. An effective algorithm using DPCA, VMD, and SVD. Validation with SVM binary classifiers shows improved accuracy. A significant improvement in noise reduction and feature extraction for efficient wear identification.
Abstract: The wear condition of a piston pin is a main factor in determining the operational continuity and life cycle of a diesel engine; identifying its vibration feature is of paramount importance in carrying out necessary maintenance in the early wear stage. As the dynamic vibration features are susceptible to environmental disturbance during operation, an effective signal processing method is necessary to improve the accuracy and fineness of the extracted features, which is essential to build a relia[...]
Publication
Automatic Configuration Search for Parameter-Efficient Fine-Tuning
On 2024-05-25 by Han Zhou, Xingchen Wan, Ivan Vuli?, Anna Korhonen @MIT
Keywords: automatic configuration search, parameter-efficient fine-tuning, neural architecture search, pretrained language models, task-specific fine-tuning
AI summary: Efficient fine-tuning method achieved with fewer parameters. AutoPEFT uses Bayesian optimization to discover optimal configurations. Outperforms existing methods on GLUE and SuperGLUE tasks. Pareto-optimal set balances performance and cost.
Abstract: Large pretrained language models are widely used in downstream NLP tasks via task-specific fine-tuning, but such procedures can be costly. Recently, Parameter-Efficient Fine-Tuning (PEFT) methods have achieved strong task performance while updating much fewer parameters than full model fine-tuning (FFT). However, it is non-trivial to make informed design choices on the PEFT configurations, such as their architecture, the number of tunable parameters, and even the layers in which the PEFT modules[...]
Publication
