Feature Extraction Algorithm Research Articles

Supporting ANFIS interpolation for image super resolution with fuzzy rough feature selection

Image Super-Resolution (ISR) is utilised to generate a high-resolution image from a low-resolution one. However, most current techniques for ISR confront three main constraints: i) the assumption that there is sufficient data available for training, ii) the presumption that areas of the images concerned do not involve missing data, and iii) the development of a computationally efficient model that does not compromise performance. In addressing these issues, this study proposes a novel lightweight approach termed Fuzzy Rough Feature Selection-based ANFIS Interpolation (FRFS-ANFISI) for ISR. Popular feature extraction algorithms are employed to extract the potentially significant features from images, and population-based search mechanisms are utilised to implement effective FRFS methods that assist in selecting the most important features among them. Subsequently, the processed data is entered into the ANFIS interpolation model to execute the ISR operation. To tackle the sparse data challenge, two adjacent ANFIS models are trained with sufficient data where appropriate, intending to position the ANFIS model of sparse data in the middle. This enables the two neighbouring ANFIS models to be interpolated to produce the otherwise missing knowledge or rules for the model in between, thereby estimating the corresponding outcomes. Conducted on standard ISR benchmark datasets while considering both sufficient and sparse data scenarios, the experimental studies demonstrate the efficacy of the proposed approach in helping deal with the aforementioned challenges facing ISR.

Music Recommendation System based on Facial Expressions by using CNN

Abstract: In today's world, the integration of emotion detection and personalized music recommendation has become increasingly prevalent across diverse fields. This project endeavors to develop a cutting-edge music recommendation system that tailors playlists to users' emotional states, as discerned from their facial expressions in real-time. Leveraging the Facial Expression Recognition 2013 (FER 2013) dataset, which encompasses a wide array of emotional expressions including happiness, sadness, anger, fear, disgust, neutrality, and surprise, serves as the foundation for training our model. The project employs the Mediapipe algorithm for feature extraction from facial expressions and utilizes a Convolutional Neural Network (CNN) to classify these emotions accurately. For seamless integration and user interaction, streamlit web browser frameworks are harnessed to facilitate music recommendations within an intuitive interface. Furthermore, the proposed system capitalizes on real-time face detection through camera input using OpenCV, ensuring timely and responsive interaction. By automatically generating music playlists based on the user's current emotional state, our system aims to significantly reduce computational time and overall costs compared to existing literature. In essence, this project presents a comprehensive solution that combines real-time facial expression analysis with personalized music recommendation, offering enhanced efficiency and accuracy while minimizing computational overhead.

Cardiac Multi-Frequency Vibration Signal Sensor Module and Feature Extraction Method Based on Vibration Modeling.

Cardiovascular diseases pose a long-term risk to human health. This study focuses on the rich-spectrum mechanical vibrations generated during cardiac activity. By combining Fourier series theory, we propose a multi-frequency vibration model for the heart, decomposing cardiac vibration into frequency bands and establishing a systematic interpretation for detecting multi-frequency cardiac vibrations. Based on this, we develop a small multi-frequency vibration sensor module based on flexible polyvinylidene fluoride (PVDF) films, which is capable of synchronously collecting ultra-low-frequency seismocardiography (ULF-SCG), seismocardiography (SCG), and phonocardiography (PCG) signals with high sensitivity. Comparative experiments validate the sensor's performance and we further develop an algorithm framework for feature extraction based on 1D-CNN models, achieving continuous recognition of multiple vibration features. Testing shows that the recognition coefficient of determination (R2), mean absolute error (MAE), and root mean square error (RMSE) of the 8 features are 0.95, 2.18 ms, and 4.89 ms, respectively, with an average prediction speed of 60.18 us/point, meeting the re-quirements for online monitoring while ensuring accuracy in extracting multiple feature points. Finally, integrating the vibration model, sensor, and feature extraction algorithm, we propose a dynamic monitoring system for multi-frequency cardiac vibration, which can be applied to portable monitoring devices for daily dynamic cardiac monitoring, providing a new approach for the early diagnosis and prevention of cardiovascular diseases.

Improved Diagnostic Approach for BRB Detection and Classification in Inverter-Driven Induction Motors Employing Sparse Stacked Autoencoder (SSAE) and LightGBM

This study introduces an innovative approach to diagnostics, employing a unique combination of techniques including a stratified group K-fold cross-validation method and a sparse stacked autoencoder (SSAE) alongside LightGBM. By examining signatures derived from motor current, voltage, speed, and torque, the framework aims to effectively detect and classify broken rotor bars (BRBs) within inverter-fed induction machines. In this kind of cross-validation method, class labels and grouping factors are spread out across folds by distributing motor operational data attributes equally over target label stratification and extra grouping information. By integrating SSAE and LightGBM, a gradient-boosting framework, we elevate the precision and efficacy of defect diagnosis. The SSAE feature extraction algorithm proves to be particularly effective in identifying small BRB signatures within motor operational data. Our approach relies on comprehensive datasets collected from motor systems operating under diverse loading conditions, ranging from 0% to 100%. Using a sparse stacked autoencoder, the model lowers the dimensionality and noise of the motor fault data. It then sends the cleaned data to the LightGBM network for fault diagnosis. LightGBM leverages the attributes of the sparse stacked autoencoder to showcase the distinctive qualities associated with BRBs. This integration offers the potential to improve defect identification by furnishing input representations that are both more precise and more concise. The proposed model (SSAE with LightGBM) was trained using 80% of the data, while the remaining 20% was used for testing. To validate the proposed architecture, we evaluate the accuracy, precision, recall, and F1-scores of the results using motor global signals, with the help of confusion matrices with receiver operating characteristic (ROC) curves. Following the training of a new LightGBM model with refined hyperparameters through Bayesian optimization, we proceed to conduct the final classification utilizing the optimal feature subset. Evaluation of the test dataset indicates that the BRBs diagnostic framework facilitates the detection and classification of issues with induction motor BRBs, achieving accuracy rates of up to 99% across all loading conditions.

Sustainable Urban Drainage Systems (2014-2023) by Using Bibliometric Analysis Method

Sustainable urban drainage systems (SUDS) are increasingly crucial for stormwater management. This bibliometric review analyses research trends on sustainable urban drainage systems over the past decade (2014- 2023) using data from Scopus. The analysis found 705 articles, 192 conference papers, 85 book chapters, and 64 reviews on sustainable urban drainage systems. Publication volume increased by 66% during the study period, indicating rising research interest. The most cited article (294 citations) was a 2019 review by Andrés-Doménech et al. on innovations in sustainable urban drainage systems. Analysis of author keywords revealed 8 clusters of research topics, with "sustainable urban drainage systems" being the dominant term with 889 keywords. Although general sustainable urban drainage system terms prevail, the use of keywords related to network visualization methods like VOS viewer is rapidly increasing. The United Kingdom published the most SUDS research (315 articles), followed by China (149), Spain (135), the United States (126), and Italy (107 articles). Research was concentrated in the environmental science and engineering fields. However, this bibliometric analysis provides insights into SUDS research trends, the most active countries and institutions, and emerging topic areas. The rapid increase in publications and use of network visualization techniques demonstrates SUDS' growing importance in urban stormwater management. The results can help inform future research directions, such as applying advanced data analytics to improve SUDS design and performance. Expanding bibliometric analyses with additional techniques like VOS viewer could further enhance understanding of this critical area of urban environmental research. Developing bibliometric methods and adding feature extraction algorithms when selecting features used to model data can increase the efficiency and accuracy of the data on sustainable urban drainage systems. The development of research data using Vos viewers images with this type of data processing research can also be maximized for research related to the sustainable urban drainage system.

Monitoring of chlorophyll content in local saltwort species Suaeda salsa under water and salt stress based on the PROSAIL-D model in coastal wetland

As the invasion of alien species intensifies, the native salt marsh vegetation, especially the ecosystem of Suaeda salsa (S. salsa), in Chinese coastal wetlands has been severely disrupted, significantly impeding its functionality within coastal wetland ecosystems. Chlorophyll content (Cab) is an important parameter for monitoring the growth and health status of vegetation. However, the remote sensing mechanism of Cab for different phenotypes of green and red vegetation influenced by betacyanin under different water and salt conditions is not clear. Therefore, to further clarify the remote sensing mechanism of S. salsa and improve the generality of Cab prediction for different phenotypes under different water and salt conditions, we designed a growth experiment under different groundwater levels and salt concentrations. This experiment was used to simulate the growth of S. salsa in different habitats in nature and investigate the relationship between their physicochemical parameters, spectra, and environmental stress. We propose using the specific absorption coefficient of betacyanin (Beta) to adjust PROSAIL-D to better fit the spectral characteristics of S. salsa. The relationship between Beta and Cab was utilized to further optimize the simulation accuracy of the PROSAIL-D model in different environments. Feature extraction algorithms, including differential enhancement of two-dimensional correlation spectroscopy (FD-2DCOS) and three-band models, were introduced to construct multiple spectral features for establishing a Cab prediction model for S. salsa. The research results showed that: (1) S. salsa had the best response of Cab and spectra to salinity under a higher groundwater level and showed a gradual reddening trend. (2) The spectral curves simulated by the adjusted PROSAIL-D model were more consistent with the spectral characteristics of S. salsa under different water-salt environments, and the simulation effect could be further optimized by using the relationship between Beta and Cab. (3) The FD-2DCOS analysis method we proposed could highlight the useful spectral information related to Cab better than the original 2DCOS algorithm. The final eight spectral features of (1/R701–1/R540)R540, Mean(D590–600), Mean(D660–670), Mean(D677–685), FDVI_NRG, FDVI_NIR, Skewness (D677–750) and Position(D677–750) had the best response to Cab of S. salsa, and had the least influence on LAI and soil background. (4) The particle swarm optimization random forest regression (PSO-RFR) model based on eight spectral features and adding 70% measured spectral data performed the best in predicting the actual Cab of S. salsa, with an RMSE of 2.326 μg·cm−2. Although further optimization and calibration of the adjusted PROSAIL-D model and Cab prediction model of S. salsa are needed in the future, this study extended its application to S. salsa, a special local salt marsh vegetation, and promoted the development of Cab monitoring of salt marsh vegetation in coastal wetlands.

Robust image descriptor for machine learning based data reduction in serial crystallography.

Serial crystallography experiments at synchrotron and X-ray free-electron laser (XFEL) sources are producing crystallographic data sets of ever-increasing volume. While these experiments have large data sets and high-frame-rate detectors (around 3520 frames per second), only a small percentage of the data are useful for downstream analysis. Thus, an efficient and real-time data classification pipeline is essential to differentiate reliably between useful and non-useful images, typically known as 'hit' and 'miss', respectively, and keep only hit images on disk for further analysis such as peak finding and indexing. While feature-point extraction is a key component of modern approaches to image classification, existing approaches require computationally expensive patch preprocessing to handle perspective distortion. This paper proposes a pipeline to categorize the data, consisting of a real-time feature extraction algorithm called modified and parallelized FAST (MP-FAST), an image descriptor and a machine learning classifier. For parallelizing the primary operations of the proposed pipeline, central processing units, graphics processing units and field-programmable gate arrays are implemented and their performances compared. Finally, MP-FAST-based image classification is evaluated using a multi-layer perceptron on various data sets, including both synthetic and experimental data. This approach demonstrates superior performance compared with other feature extractors and classifiers.

Comparison of machine learning algorithms and feature extraction techniques for the automatic detection of surface EMG activation timing

This paper presents a methodology for automatically detecting muscular activity by denoising, extracting features, and classifying surface electromyography (sEMG) signals. The proposed methodology utilizes the Discrete Wavelet Transform (DWT) and Willison’s Amplitude Algorithm (WAMP) for feature extraction. Five classification methods, including Neural Networks (NN), Classification Vector, XGBoost, Light Gradient Boosting Machine (LGBM), and ExtraTree, were evaluated using F-Measure, Precision, and Recall as performance metrics. Through k-fold cross-validation, the XGBoost algorithm, when combined with the Eigen values feature, achieved the highest training performance with an F1-Score of 98.71 %. For the test group, the LGBM classifier using WAMP, and NN with both WAMP and Eigen values as features, demonstrated the best average performance with F1-Scores of 96.52 ± 3.45 % and 96.52 ± 3.07 %, respectively. These results highlight the precision and performance of the proposed approach in detecting EMG signals. Moreover, the framework has the potential to support clinicians in diagnosing neuromuscular disorders and developing human–machine interfaces.

Radiomics analysis for distinctive identification of COVID-19 pulmonary nodules from other benign and malignant counterparts

This observational study investigated the potential of radiomics as a non-invasive adjunct to CT in distinguishing COVID-19 lung nodules from other benign and malignant lung nodules. Lesion segmentation, feature extraction, and machine learning algorithms, including decision tree, support vector machine, random forest, feed-forward neural network, and discriminant analysis, were employed in the radiomics workflow. Key features such as Idmn, skewness, and long-run low grey level emphasis were identified as crucial in differentiation. The model demonstrated an accuracy of 83% in distinguishing COVID-19 from other benign nodules and 88% from malignant nodules. This study concludes that radiomics, through machine learning, serves as a valuable tool for non-invasive discrimination between COVID-19 and other benign and malignant lung nodules. The findings suggest the potential complementary role of radiomics in patients with COVID-19 pneumonia exhibiting lung nodules and suspicion of concurrent lung pathologies. The clinical relevance lies in the utilization of radiomics analysis for feature extraction and classification, contributing to the enhanced differentiation of lung nodules, particularly in the context of COVID-19.

PHE-SICH-CT-IDS: A benchmark CT image dataset for evaluation semantic segmentation, object detection and radiomic feature extraction of perihematomal edema in spontaneous intracerebral hemorrhage

Background and objective:Intracerebral hemorrhage is one of the diseases with the highest mortality and poorest prognosis worldwide. Spontaneous intracerebral hemorrhage (SICH) typically presents acutely, prompt and expedited radiological examination is crucial for diagnosis, localization, and quantification of the hemorrhage. Early detection and accurate segmentation of perihematomal edema (PHE) play a critical role in guiding appropriate clinical intervention and enhancing patient prognosis. However, the progress and assessment of computer-aided diagnostic methods for PHE segmentation and detection face challenges due to the scarcity of publicly accessible brain CT image datasets. Methods:This study establishes a publicly available CT dataset named PHE-SICH-CT-IDS for perihematomal edema in spontaneous intracerebral hemorrhage. The dataset comprises 120 brain CT scans and 7,022 CT images, along with corresponding medical information of the patients. To demonstrate its effectiveness, classical algorithms for semantic segmentation, object detection, and radiomic feature extraction are evaluated. The experimental results confirm the suitability of PHE-SICH-CT-IDS for assessing the performance of segmentation, detection and radiomic feature extraction methods. Results:This study conducts numerous experiments using classical machine learning and deep learning methods, demonstrating the differences in various segmentation and detection methods on the PHE-SICH-CT-IDS. The highest precision achieved in semantic segmentation is 76.31%, while object detection attains a maximum precision of 97.62%. The experimental results on radiomic feature extraction and analysis prove the suitability of PHE-SICH-CT-IDS for evaluating image features and highlight the predictive value of these features for the prognosis of SICH patients. Conclusion:To the best of our knowledge, this is the first publicly available dataset for PHE in SICH, comprising various data formats suitable for applications across diverse medical scenarios. We believe that PHE-SICH-CT-IDS will allure researchers to explore novel algorithms, providing valuable support for clinicians and patients in the clinical setting. PHE-SICH-CT-IDS is freely published for non-commercial purpose at https://figshare.com/articles/dataset/PHE-SICH-CT-IDS/23957937.

Image Analysis and Classification Using HRSVM-CNN for Land-Cover Classification by Using Remote Sensing Images

Objective: To effectively analyze diverse satellite images and derive valuable insights, it's crucial to employ efficient methods for classification and image processing. However, due to imperfections in image formats and sensor data, satellite imagery often contains flaws and inaccuracies, requiring extra steps to enhance its quality. The proposed solution involves two key techniques: segmenting the input image using a Hybrid HRSVM-CNN and classifying the resulting high-resolution remote sensing image using a Convolutional Neural Network. This combined approach addresses the challenges posed by image inconsistencies and aims to improve the accuracy and efficiency of current methods for satellite image analysis. Methods: In this research, a high-resolution Support Vector Machine-Convolutional Neural Network (Hybrid HRSVM-CNN) and texture characteristics are used to create an automated land identification method for satellite Remote sensing (RS) images. This approach's main focus is segmentation using the Bendlet Transform and Improved Chan-Vese, and it also does classification using a Hybrid HRSVM-CNN based on feature extraction and gray-level co-occurrence matrix algorithm. Findings: The proposed classification method's accuracy was evaluated against several other classification algorithms, including Semi-Supervised Graph Based Method (SSG), Conditional Random Fields (CRF), k-Nearest Neighbor (KNN), and Bi-layer Graph-based Learning (BLGL), Support Vector Machine (SVM), and Artificial Neural Networks (ANN). When compared with existing methods, the findings of the proposed method display excellent accuracy of 98.83%. Novelty: To start, an adaptive median filter is used to pre-process the satellite Remote sensing images, removing unwanted noises and other impacts. Following pre-processing, the image is segmented using the Bendlet Transform and Improved Chan-Vese algorithms. Gray-level co-occurrence matrix is utilized to extract texture information, and the Hybrid HRSVM-CNN is then used to categorize the various types of land. These applications frequently have a variety of issues that affect the categorization accuracy. A few significant factors, like location, irregularity, form, and diameter, reduce the process's overall accuracy. This research focuses on presenting a unique Land-Cover classification model in order to address such problems. The UC Merced Land Use dataset was considered in this research. Keywords: Bendlet Transform and Improved Chan­Vese Segmentation, Hybrid HRSVM­CNN, Land detection system, Satellite remote sensing images, Adaptive median filter, Gray­ level co­occurrence matrix

Random subsequence forests

The random forest classifier is widely used in different fields due to its accuracy and robustness. Since its invention, the random forest algorithm is naturally developed for multi-dimensional vectorial data since features can be directly sampled during the decision tree construction procedure. In the context of discrete sequence classification, an explicit feature set is not readily available and we need to employ a feature extraction algorithm before building the random forest. However, such a predefined feature subset may limit the diversity of decision trees since the set of candidate features is composed of all subsequences. As a result, the predictive accuracy of constructed random forest classifier may be reduced. To address this, we propose a new algorithm that is able to directly build a random forest by choosing features from the set of all subsequences adaptively. To improve the running efficiency of our algorithm, the count-suffix tree is utilized to facilitate the fast frequency counting of subsequences so as to accelerate the generation of each randomized decision tree. The experimental results on 15 real datasets show that our method can outperform those state-of-the-art classification algorithms in terms of the predictive accuracy. The source code of our method can be found at: https://github.com/JiaqiWang-dlut/RSForest.

An enhanced mechanism for detection of spam emails by deep learning technique with bio-inspired algorithm

This study aims to create a highly effective system for classifying email spam, with the key objective of improving performance and accuracy in classification. Rigorous pre-processing techniques, including lemmatization and tokenization, are applied to refine the dataset. The impact of optimal feature selection on deep learning algorithm stability with varying training datasets is investigated and to improve classifier performance, pre-stages such as feature extraction and selection using bag of words are utilized. The hybrid model is further enhanced by combining feature extraction and classification algorithms with optimization. The inclusion of multiple features, such as n-gram features, addresses the 'Curse of Dimensionality,' and optimal feature selection is employed to improve the spam detection process. The proposed system undergoes three main modifications: multiple feature extraction, feature selection, and an enhanced hybrid model, all aimed at improving spam detection accuracy. The e-mail classification phase involves mapping between training and testing sets, with deep learning algorithms utilized for feature extraction and classification.The recently introduced Sand Cat Swarm Optimization algorithm is employed to refine weights during each epoch, enhancing accuracy and minimizing loss. The proposed system extends its capabilities to identify phishing attacks within the network, offering a comprehensive approach to email security.

Accurate semantic segmentation of small-body craters for navigation

Feature extraction and matching play integral roles in autonomous vision navigation. As a typical morphological feature, craters can be used as navigation landmarks. However, the spin of small bodies introduces substantial variations in illumination and viewing angles within acquired images, thereby posing challenges to feature extraction and matching algorithms. Addressing these challenges, a deep learning-based approach emerges as pivotal in mitigating the limitations of existing navigation algorithms. This paper presents an algorithm designed to segment noteworthy craters and irregular regions on such small bodies, thereby furnishing crucial autonomous navigation data for missions involving uncharted terrains. By seamlessly integrating deep learning techniques with conventional computer vision-based feature description methods, the algorithm achieves matching segmentation results of noteworthy precision. The experimental results show that the algorithm has better results compared to the existing mainstream segmentation networks. And it can achieve the accurate matching of segmentation results.

An Integrated Monitoring, Diagnostics, and Prognostics System for Aero-Engines under Long-Term Performance Deterioration

In the field of aircraft engine diagnostics, many advanced algorithms have been proposed over the last few years. However, there is still wide room for improvement, especially in the development of more integrated and complete engine health management systems to detect, identify, and forecast complex faults in a short time. Furthermore, it is necessary to ensure that these systems preserve their capabilities over time despite engine deterioration. This paper addresses these necessities by proposing an integrated system that considers the joint operation of feature extraction, anomaly detection, fault identification, and prognostic algorithms for engines with long operation times. To effectively reveal the actual engine condition, light adaptive degraded engine models are computed along with different health indicators that are used as inputs to train and test recognition and prediction models. The system is developed and evaluated using a specialized NASA platform which provides data from a turbofan engine fleet simultaneously experiencing long-term performance deterioration and faults. Contrary to other compared solutions, our results show that the proposed system is robust against the effects of engine deterioration, maintaining its level of detection, recognition, and prediction accuracy over a total engine service life. The low computational cost algorithms has generally fast performance in all stages, making the system suitable for online applications.

A high-performance conical-neck helmholtz resonator-based piezoelectric self-powered system for urban transportation

As urbanization accelerates, the issue of traffic noise escalates. Efficiently harnessing this prevalent acoustic energy and facilitating its collection and conversion has emerged as a notable challenge in contemporary research. This paper introduces a piezoelectric self-powered system anchored on a Conical-Neck Helmholtz Resonator-Based Piezoelectric Self-Powered System (CNHR-PSS) which places the piezoelectric device inside a Conical-Neck Helmholtz resonator. This system amalgamates acoustic energy harvesting, traffic noise abatement, and traffic condition discernment. It combines by two parts, including a Piezoelectric Self-Powered Node (PSN) and a machine learning algorithm. The PSN, employing the Conical Neck Helmholtz Resonator and piezoelectric module, seizes noise and transmutes it into electrical energy, showcasing robust scalability. Multiple PSNs coalesce to form a sound barrier for traffic noise mitigation. Concurrently, the voltage signals emanated by the PSN also encapsulate traffic status information. The algorithm extracts feature from the output signal and employs machine learning to decipher traffic conditions. Simulative and theoretical analyses affirm that the system can efficaciously harvest acoustic energy from urban traffic noise and attenuate noise, with a pinnacle output power of 0.52mW and an average noise reduction of 13.16 %. The recognition accuracy of traffic conditions via SVM attained 100 %. The investigative outcomes underscore the exemplary performance of this self-powered system, rendering it a viable solution for applications in traffic noise mitigation and intelligent transportation.

OMR Sheet Evaluation using Image Processing

Optical Mark Recognition (OMR) technology has revolutionized the grading and assessment processes in educational institutions, surveys, and various other fields. OMR sheets, designed with predefined bubbles or checkboxes, are scanned and processed to extract relevant data. This paper presents a comprehensive review of the methodologies and advancements in OMR sheet evaluation using image processing techniques. The review begins with an overview of traditional OMR systems and their limitations, such as susceptibility to errors due to variations in scanning quality, paper orientation, and noise interference. Subsequently, it delves into the evolution of image processing algorithms tailored for OMR sheet evaluation. Several key components of OMR sheet evaluation are discussed, including image pre-processing techniques for enhancing readability, segmentation methods for isolating individual marks, feature extraction algorithms for capturing relevant data, and classification techniques for accurate identification of marked responses. The review highlights recent trends and innovations in OMR sheet evaluation, such as the integration of machine learning and deep learning algorithms for improved accuracy and robustness. Additionally, it addresses challenges such as handling skewed or distorted images, multi-page OMR sheets, and real-time processing requirements. Furthermore, the paper discusses benchmark datasets and evaluation metrics commonly used to assess the performance of OMR systems. It also examines practical considerations such as scalability, cost-effectiveness, and usability in diverse settings..

Detection and quantification of corrosion defects in CFRP-strengthened steel structures based on low-power vibrothermography

ABSTRACT For CFRP-strengthened steel structures, corrosion defects in steel are incredibly hazardous, but there is a lack of effective non-destructive testing methods. Based on the low-power vibrothermography (LVT) technique, this study proposes a quantitative detection framework for corrosion defects of CFRP-strengthened steel structures, including feature extraction algorithms for improving the defect detectability, and a feature enhancement method for reducing the quantification error. First, a finite element model is built to simulate the heat generation under ultrasonic excitation and to obtain the temperature distribution on the specimen surface. The processing results of the simulated thermal images show that feature extraction algorithms (FFT, PCA, and PLSR) effectively extract defect features. Subsequently, the LVT experimental setup was established to detect corrosion defects in CFRP-strengthened steel specimens. The experimental results demonstrate that the LVT technique can selectively heat corrosion defects, and processing results prove that the FFT and PLSR can further enhance the defect detectability. Finally, we propose a feature enhancement method based on gravitational calculation and double-threshold segmentation to reduces the quantification error. The quantitative evaluation relative errors of defects with diameters of 10 mm, 8 mm, and 6 mm are 5.26%, 5.26%, and 10.09%, respectively.

A study on the application of discrete curvature feature extraction and optimization algorithms to battery health estimation

A study on the application of discrete curvature feature extraction and optimization algorithms to battery health estimation

Effects of camera external parameters error on measurement accuracy in monocular vision

Monocular vision is widely employed in industrial measurement scenarios due to its low cost, flexibility, mature algorithms, and high reliability. However, in actual production line monocular vision measurement systems, the measured plane may be affected by motion mechanisms or device vibrations, causing it to deviate from the system calibration plane and resulting in measurement errors. Current research primarily focuses on analyzing the influence of camera internal parameters and feature extraction algorithms on measurement errors, with limited quantitative analysis of the impact of camera external parameters. To address this issue, our paper derives a mathematical expression for measurement error when rotational and translational motion occurs between the measurement and calibration planes. Theoretical analysis reveals that when the camera optical axis is perpendicular to the measurement plane, measurement error is independent of the main point coordinates of the camera’s optical axis, translation component in the measurement plane, and rotation angle around the camera’s optical axis. Instead, it exhibits a linear relationship with the translation component in the direction of the camera’s optical axis and is inversely proportional to the normalized focal length of the camera. When the optical axis of the camera is not perpendicular to the calibration plane, the measurement error exhibits a nonlinear relationship with camera’s internal and external parameters. To verify our theoretical derivation’s accuracy, we conduct measurement experiments using both industrial and telecentric lenses and analyzed rotation and translation of the measured plane separately. The measurement data was evaluated by Root Mean Square Error and Pearson Correlation Coefficient, which demonstrates that experimental and theoretical function images exhibit consistent trends, verifying our theoretical derivation’s correctness and providing a theoretical guide for improving actual visual measurement accuracy.