Feature Extraction Algorithm Research Articles

Convolutional neural network augmented soft-sensor for autonomous microfluidic production of uniform bubbles

Microfluidics has emerged as a foundational process for creating highly uniform emulsions and bubbles. To enable integration of microfluidic platforms into industrial processes, achieving precise control over the size uniformity of microfluidic-generated bubbles and emulsions is crucial. Even if the external variables such as flow rates or pressures are kept constant, microfluidic processes can be easily disturbed by unknown factors that would substantially compromise the uniformity of resulting emulsions and bubbles. In this study, we introduce a two-step soft-sensor approach that combines a convolutional neural network (CNN) and an image recognition algorithm for feature extraction to detect both the flow regime and the size and uniformity of resulting bubbles. By using a CNN to detect flow regimes, our controller is able to restore the bubble-producing flow regime in response to disturbances. Beyond self-recovery, our controller actively adjusts to minimize errors, maintain setpoints, mitigate disturbances, and ensure system stability over extended periods. 99.2% of bubbles produced during an 8-hour period remain within 5% of the setpoint with our controller acting. By leveraging the soft sensor and artificial intelligence-assisted feedback control, our work presents a widely applicable approach for precise and automated control of microfluidics in diverse applications.

Time-series water prediction based on feature clustering fusion and XGboost

Abstract. The time series prediction problem has a very wide range of applications in many fields. Most scholars use the LSTM class of algorithms for prediction. However, this method consumes a significant amount of computational power and presents several challenges. To address this issue, this paper proposes a time series forecasting method based on feature fusion and XGBoost. Specifically, we first utilize holiday information and the K-Means algorithm for feature extraction to expand the feature dimensions of the dataset, and then employ XGBoost as a model for training and prediction. Experiments demonstrate that the method proposed in this paper significantly reduces error compared to other traditional machine learning and deep learning methods, while the training time is much shorter than these methods. For example, compared with LSTM, the MSLE of this model decreases by 1.42%, while the training time is only 0.15% of that of LSTM. This greatly saves on training costs and computational power consumption. This confirms the effectiveness of using machine learning and clustering algorithms in time series prediction and provides new methods and practical application directions for future time series prediction models.

Robotic MAG welding defects and quality assessment with a defect threshold decision model-driven method

The use of machine vision and deep learning methods for online monitoring and evaluation of welding quality during the welding process and timely detection and correction of welding defects is essential for intelligent welding manufacturing. In this paper, with the goal of online monitoring of the welding quality of the robotic arc welding for the excavator boom, we established a multi-source sensing system for robotic arc welding processes. We have developed various feature extraction algorithms for extracting information about welding pools, arc sounds, currents, voltages, and other features. We proposed to extract welding pool image features using Res2-MobileNetV3 to obtain a 12-dimensional welding pool feature, which enabled good inter-class discrimination among different welding defects. We designed a welding defect threshold decision (DD) strategy model using the responsive machine learning and lightweight network Res2-MobileNetV3 method, achieving a welding defect recognition accuracy of 96.59%. Finally, we tested the accuracy and reliability of the welding defect recognition model on an actual welding scene for the robotic welding of the excavator boom. It provided valuable scientific methods and technological approaches for intelligent welding in complex scenes.

Unlocking the potential of simulated hyperspectral imaging in agro environmental analysis: a comprehensive study of algorithmic approaches

This study focuses on identifying and evaluating the severity of powdery mildew disease in tomato plants. The uniqueness of this work lies in combining the imaging and advanced deep learning methods to develop a technique that transforms Red Green Blue (RGB) images into Simulated Hyperspectral Images (SHSI) to perform spectral and spatial analysis for precise detection and assessment of powdery mildew severity, thereby enhancing disease management. Furthermore, this research evaluates three advanced pre-trained VGG16 models, ResNet50 and EfficientNet-B7 algorithms for image preprocessing and feature extraction. Extracted features are passed to a neural network generator model to convert RGB image features into SHSIs, providing insights into the spectrum. This method enables the image analysis to perform assessments from SHSIs for health classification using Normalized Difference Vegetation Index (NDVI) values, which are meticulously compared with accurate hyperspectral data using metrics like mean absolute error (MAE) and root mean squared error (RMSE). This strategy enhances precision farming, environmental monitoring, and remote sensing accuracy. Results show that ResNet50’s architecture offers a robust framework for this study’s spectral and spatial analysis, making it a suitable choice over VGG16 and EfficientNet-B7 for transforming RGB images into SHSI. These simulated hyperspectral images offer a scalable and affordable approach for precise assessment of crop disease severity.

Adaptive probe position correction for automated complex weld inspection based on structural signal monitoring

ABSTRACT To ensure comprehensive coverage of welds, multi-axis motions are necessary for the probe during the automatic detection of complex welds. Guaranteeing the effectiveness of ultrasonic data during this process is crucial for ensuring detection accuracy and reliability. Taking tubular Y-joints as an example, this paper presents an adaptive probe posture correction method based on structural signal monitoring: (1) The structural and acoustic model of tubular Y-joints is established to select and predict the target structural signal. (2) Feature extraction and signal tracking algorithms are developed to achieve real-time monitoring of signals. (3) A posture correction method is proposed based on signal characteristics: time-domain characteristics correspond to position adjustments, while amplitudes correspond to orientation corrections. Building upon this, a feedback mechanism for probe posture is established. The effectiveness of the developed method is verified through underwater automatic detection experiments of tubular Y-joints. Results demonstrate that, with the assistance of the probe posture correction method, the coverage of the effective area increases to more than 95%, and embedded defects are fully detected through a single scan. In conclusion, the adaptive probe posture correction method based on structural signal monitoring presents a promising approach for the automatic ultrasonic examination of complex welds.

Explainable artificial intelligence in web phishing classification on secure IoT with cloud-based cyber-physical systems

IoT is the technology that aids the interconnection of all kinds of devices over the internet to replace data, monitor devices and enhance actuators to create outcomes. Cyber-physical systems (CPS) contain control and computation components, which are compactly assured with physical procedures. The internet plays a prominent role in modern lives, and the cybersecurity challenge caused by phishing attacks is significant. This research presents a novel approach to address this problem using machine learning (ML) methods for phishing website classification. Leveraging feature extraction and innovative algorithms, the projected method aims to distinguish between malicious and legitimate websites by features of phishing attempts and analyzing inherent patterns. Phishing is a significant threat that causes extensive financial losses for internet users yearly. This fraudulent act includes identity hackers utilizing clever approaches to deceive individuals into revealing sensitive data. Generally, phishers use strategies such as advanced phishing software and fake emails to illegally acquire confidential details like usernames and passwords from financial accounts. This article develops an Explainable Artificial Intelligence with Aquila Optimization Algorithm in Web Phishing Classification (XAIAOA-WPC) approach on secure Cyber-Physical Systems. The developed XAIAOA-WPC approach mainly emphasizes the effectual classification and recognition of web phishing based on CPS. In the first phase, preprocessing is carried out on three levels: data cleaning, text preprocessing, and standardization. Furthermore, the Harris' Hawks optimization-based feature selection (HHO-FS) method is applied to derive feature subsets. The XAIAOA-WPC method utilizes a multi-head attention-based long short-term memory (MHA-LSTM) model for web phishing recognition. Besides, the detection outcomes of the MHA-LSTM approach are enhanced by using the Aquila optimization algorithm (AOA) model. At last, the XAIAOA-WPC method incorporates the XAI model LIME for superior perception and explainability of the black-box process for precise identification of intrusions. The simulation outcome of the XAIAOA-WPC method is examined on a benchmark database. The experimental validation of the XAIAOA-WPC method exhibited a superior accuracy value of 99.29 % over existing techniques.

An Enhanced LBPH Algorithm for Robust Face Feature Extraction

From security systems to human-computer interaction, face recognition technology is a key component in many different applications. In this domain, the local binary pattern histogram (lbph) algorithm has shown great promise due to its ability in texture-based feature extraction and robustness. In this study, the performance of lbph algorithm is improved by optimising important parameters: radius, number of neighbours and grid configuration. Tweaking these parameters systematically enable us to get the most success out of this algorithm. Lbph algorithm parameters has been tuned into a 5x7 dimensional matrix, which gives us total of 35 grids with equal width and height pixels. In other words, one central pixel plus 34 neighbouring pixels where the radii of 3 square neighbourhoods can be adjusted. The study combines the experimental exploration with fine-tuning via machine learning approaches to optimize lbph algorithm. Finally, we have provided experimental results on intra-class and inter-class feature distribution analysis conducted on selected images taken under constraints and unconstraint environments. The performance of our novel 34N-LBPH algorithm showed very low values by obtaining intra-class average means of 0.031, 0.078, and 0.101 for three classes under constraint environment indicating the proposed 34n-lbph is robust for facial feature extraction. The findings suggest that our enhanced algorithm, 34 neighbour linear binary pattern Histogram (34N-LBPH) can effectively handle variations in lighting, expressions and occlusions, contributing to the advancement of facial feature extraction for face recognition.

Automated vision-based concrete crack measurement system

Maintaining and ensuring the safety of ageing infrastructures is becoming of uttermost importance. This is particularly critical in Europe, where several infrastructures like tunnels and bridges are approaching their end-of-life. Such a condition justifies the need for a prompt recognition of the deterioration status of these structures as well as the identification of strategies for effective inspection and monitoring operations. This paper focuses on cracks, and proposes a vision-based measurement system aimed at precisely and accurately detecting cracks on concrete surfaces and measuring their geometric features. The system mainly leverages RGB-D cameras to make the pixel to real world measurement units conversion possible (by assessing the camera to target relative distance and pose), and exploits an image processing pipeline consisting of the following steps: (a) an artificial intelligence-based semantic segmentation model for identifying cracks on the target structure; (b) a ridge detection algorithm for identifying the centre line of the cracks; (c) a geometric feature extraction algorithm to extract key metrics of the crack, like its width and length. Variance analysis of the crack mean width measurement shows a repeatability standard deviation of 0.01 mm and a reproducibility standard deviation of 0.02 mm, with a Type A expanded uncertainty of 0.004 mm. The system performance is discussed in the paper referring both to lab testing activities, targeted to the assessment of its metrological characteristics, and to a real field application, i.e. concrete inspection in a tunnel. This latter application is of particular interests as it is targeted to demonstrate the robustness of the approach in harsh environments (i.e., strong presence of dust, total absence of natural light) and on surfaces whose roughness generates important light gradients and shadows (e.g., sprayed concrete).

Application of terahertz time-domain spectroscopy and chemometrics-based crested porcupine algorithm in identification of different medicinal parts of Angelica sinensis

ObjectiveAngelica sinensis is one of the commonly used Chinese herbal medicine in traditional Chinese medicine clinic, exhibits different pharmacological characteristics due to variations in the content of active ingredients in its head, body, and tail. Therefore, research on the identification methods of different medicinal parts of Angelica sinensis is of great practical significance. Terahertz Time-Domain Spectroscopy (THz-TDS) technology is widely used in the field of nondestructive testing because of its unique electromagnetic wave characteristics. This study explores the feasibility of combining THz-TDS with chemometrics to identify different medicinal parts of Angelica sinensis. MethodsBy comparing the spectral response characteristics of different parts of Angelica sinensis to various optical parameters, the absorption coefficient spectrum in the 0.6–3.0 THz range was selected, and three types of feature extraction algorithms, namely, joint Competitive Adaptive Reweighted Sampling (CARS), Uninformative Variable Elimination (UVE), and Successive Projections Algorithm (SPA), were used to establish the classification models of Extreme Learning Machine (ELM), Random Forest (RF), and Support Vector Machine (SVM) in turn, and optimize the models by using the crown porcupine algorithm (Crested Porcupine Optimizer (CPO) to optimize the model. ResultsThe research results indicate that the CPO optimizer significantly improved the classification accuracy of the models, with the accuracy of the ELM, RF, and SVM models increasing by 4.36%, 1.11%, and 12.22%, respectively. The SPA-CPO-SVM model exhibited the best overall performance, achieving accuracies of 96.11% and 97.96% on the prediction and training sets, respectively, while the number of input features was only 5% of the total feature set. ConclusionThe results show that the fully joint feature extraction strategy and optimization algorithm can play a powerful synergistic effect in model construction, confirming the feasibility of THz-TDS technology to correctly identify different medicinal parts of Angelica sinensis, and providing an important reference for the application of terahertz technology in the identification of Chinese herbal medicines.

A Hybrid Approach for Face Morphing Detection

Background: In biometrics, one of the most popular study topics is the detection of face morphing attacks. However, because present methods are unable to capture significant feature changes, they are unable to strike the correct balance between accuracy and complexity. Survey investigation and analysis have shown that the existing method of face morphing detection take a bit longer time to detect the image attack due to the high computation required by facial feature extraction approaches. Conversely, further study is needed to develop a model to enhance the computational time and accuracy of the current face morphing recognition methods. The paper developed a hybrid model for face morphing detection. The FERET database was created to aid in the evaluation and development of algorithms. Local Binary Pattern (LBP) was used as feature extraction algorithm and Residue Number System (RNS) was introduced to reduce the lengthy computational time of LBP during the extraction of images. The classification accuracy of 98% was achieved for the FERET database, while an accuracy of 96% was achieved for the FRGCv2 database. An average training time of 0.0532seconds was recorded for the FERET database, while an average training time of 0.0582seconds was achieved for the FRGCv2 database. The study concluded that the high dimensionality of LBP was well reduced and optimized by the RNS algorithm, which improved the performance of face morphing recognition.

Study on detection of pesticide residues in tobacco based on hyperspectral imaging technology.

Tobacco is a critical economic crop, yet its cultivation heavily relies on chemical pesticides, posing health risks to consumers, therefore, monitoring pesticide residues in tobacco is conducive to ensuring food safety. However, most current research on pesticide residue detection in tobacco relies on traditional chemical methods, which cannot meet the requirements for real-time and rapid detection. This study introduces an advanced method that combines hyperspectral imaging (HSI) technology with machine learning algorithms. Firstly, a hyperspectral imager was used to obtain spectral data of tobacco samples, and a variety of spectral pre-processing technologies such as mean centralization (MC), trend correction (TC), and wavelet transform (WT), as well as feature extraction methods such as competitive adaptive reweighted sampling (CARS) and least angle regression (LAR) were used to process the spectral data, and then, grid search algorithm (GSA) is used to optimize the support sector machine (SVM). The optimized MC-LAR-SVM model achieved a pesticide classification accuracy of 84.1%, which was 9.5% higher than the original data model. The accuracy of the WT-TC-CARS-GSA-SVM model in the fenvalerate concentration classification experiment was as high as 91.8 %, and it also had excellent performance in other metrics. Compared with the model based on the original data, the accuracy, precision, recall, and F1-score are improved by 8.3 %, 8.2 %, 7.5 %, and 0.08, respectively. The results show that combining spectral preprocessing and feature extraction algorithms with machine learning models can significantly enhance the performance of pesticide residue detection models and provide robust, efficient, and accurate solutions for food safety monitoring. This study provides a new technical means for the detection of pesticide residues in tobacco, which is of great significance for improving the efficiency and accuracy of food safety detection.

Comparative analysis of electroencephalogram (EEG) data gathered from the frontal region with other brain regions affected by attention deficit hyperactivity disorder (ADHD) through multiresolution analysis and machine learning techniques

Attention deficit hyperactivity disorder (ADHD) is a neurodevelopmental disorder characterized by repeated patterns of hyperactivity, impulsivity, and inattention that limit daily functioning and development. Electroencephalography (EEG) anomalies correspond to changes in brain connection and activity. The authors propose utilizing empirical mode decomposition (EMD) and discrete wavelet transform (DWT) for feature extraction and machine learning (ML) algorithms to categorize ADHD and control subjects. For this study, the authors considered freely accessible ADHD data obtained from the IEEE data site. Studies have demonstrated a range of EEG anomalies in ADHD patients, such as variations in power spectra, coherence patterns, and event-related potentials (ERPs). Some of the studies claimed that the brain’s prefrontal cortex and frontal regions collaborate in intricate networks, and disorders in either of them exacerbate the symptoms of ADHD. , Based on the research that claimed the brain’s prefrontal cortex and frontal regions collaborate in intricate networks, and disorders in either of them exacerbate the symptoms of ADHD, the proposed study examines the optimal position of EEG electrode for identifying ADHD and in addition to monitoring accuracy on frontal/ prefrontal and other regions of brain our study also investigates the position groupings that have the highest effect on accurateness in identification of ADHD. The results demonstrate that the dataset classified with AdaBoost provided values for accuracy, precision, specificity, sensitivity, and F1-score as 1.00, 0.70, 0.70, 0.75, and 0.71, respectively, whereas using random forest (RF) it is 0.98, 0.64, 0.60, 0.81, and 0.71, respectively, in detecting ADHD. After detailed analysis, it is observed that the most accurate results included all electrodes. The authors believe the processes can detect various neurodevelopmental problems in children utilizing EEG signals.

Multi-channel depth segmentation network based on 3D graph convolution algorithm and its application in point cloud segmentation

At the current stage, 3D graph convolutional algorithms face the following issues: (1) The problem of determining the neighborhood in graph convolution. (2) The issue of fusing features at different depths in deep graph convolutional algorithms. (3) The challenge of feature fusion and recognition in multi-path deep graph convolutional algorithms. Based on these, the paper "Multi-Path Deep Segmentation Network Based on 3D Graph Convolutional Algorithm and Its Application in Point Cloud Segmentation" is proposed. Inspired by visual computing theory, the neighborhood for 3D graph convolution is determined based on the receptive field theory, and a 3D graph convolutional algorithm based on visual selectivity is proposed; A single-link deep feature extraction algorithm for 3D graph convolution based on visual selectivity is proposed, it achieve the fusion of features at different depths learned by the graph convolutional algorithm by a pyramid learning method; A multi-link feature extraction algorithm for 3D graph convolution based on visual selectivity is proposed, and achieve multi-link feature fusion and segmentation to utilize the RPN calculation method. compared with algorithms such as PointNet, PointNet++, KPConv deform, 3D GCN, and My Algorithm, The segmentation performance and geometric invariance of the proposed algorithm are validated on the ShapeNetPart dataset and the custom Mortise_and_Tenon_DB dataset, and Experiments demonstrate that the proposed algorithm is correct and feasible, offers superior 3D point cloud segmentation performance, and exhibits strong geometric invariance.

EEG FEATURE EXTRACTION AND RECOGNITION BASED ON MULTI-FEATURE FUSION

In response to the issue of insufficient information and low classification accuracy in single-channel feature extraction algorithms for EEG signals, the paper proposed a method based on Adaptive Noise-assisted Complete Ensemble Empirical Mode Decomposition (CEEMDAN) and multi-feature fusion. Firstly, we acquired multi-channel motor imagery EEG data and preprocessed it. Next, utilized CEEMDAN with adaptive noise to adaptively decompose the channel data. Secondly, extracted features from the Intrinsic Mode Functions (IMFs) which we obtained after CEEMDAN decomposition for different feature layers and fused them, obtaining the original feature matrices for each feature layer. Finally, we fused and reduced the dimensionality of the original feature matrices from each layer, input the resulting matrix into a classification model for classification, and output the classification results. We achieve an average classification accuracy of 88.59% on the BCI Competition II Data Set III, and validate the results on self-collected single-channel motor imagery EEG data, achieving a classification accuracy of 89.72%. Experimental results indicate that multi-feature fusion outperforms single features, and the combination of CEEMDAN decomposition with multi-feature fusion achieves higher classification accuracy.

Research on the Cable-to-Terminal Connection Recognition Based on the YOLOv8-Pose Estimation Model

Substations, as critical nodes for power transmission and distribution, play a pivotal role in ensuring the stability and security of the entire power grid. With the ever-increasing demand for electricity and the growing complexity of grid structures, traditional manual inspection methods for substations can no longer meet the requirements for efficient and safe operation and maintenance. The advent of automated inspection systems has brought revolutionary changes to the power industry. These systems utilize advanced sensor technology, image processing techniques, and artificial intelligence algorithms to achieve real-time monitoring and fault diagnosis of substation equipment. Among these, the recognition of cable-to-terminal connection relationships is a key task for automated inspection systems, and its accuracy directly impacts the system’s diagnostic capabilities and fault prevention levels. However, traditional methods face numerous limitations when dealing with complex power environments, such as inadequate recognition performance under conditions of significant perspective angles and geometric distortions. This paper proposes a cable-to-terminal connection relationship recognition method based on the YOLOv8-pose model. The YOLOv8-pose model combines object detection and pose estimation techniques, significantly improving detection accuracy and real-time performance in environments with small targets and dense occlusions through optimized feature extraction algorithms and enhanced receptive fields. The model achieves an average inference time of 74 milliseconds on the test set, with an accuracy of 92.8%, a recall rate of 91.5%, and an average precision mean of 90.2%. Experimental results demonstrate that the YOLOv8-pose model performs excellently under different angles and complex backgrounds, accurately identifying the connection relationships between terminals and cables, providing reliable technical support for automated substation inspection systems. This research offers an innovative solution for automated substation inspection systems, with significant application prospects.

Optimizing Real-Time MI-BCI Performance in Post-Stroke Patients: Impact of Time Window Duration on Classification Accuracy and Responsiveness.

Brain-computer interfaces (BCIs) are promising tools for motor neurorehabilitation. Achieving a balance between classification accuracy and system responsiveness is crucial for real-time applications. This study aimed to assess how the duration of time windows affects performance, specifically classification accuracy and the false positive rate, to optimize the temporal parameters of MI-BCI systems. We investigated the impact of time window duration on classification accuracy and false positive rate, employing Linear Discriminant Analysis (LDA), Multilayer Perceptron (MLP), and Support Vector Machine (SVM) on data acquired from six post-stroke patients and on the external BCI IVa dataset. EEG signals were recorded and processed using the Common Spatial Patterns (CSP) algorithm for feature extraction. Our results indicate that longer time windows generally enhance classification accuracy and reduce false positives across all classifiers, with LDA performing the best. However, to maintain the real-time responsiveness, crucial for practical applications, a balance must be struck. The results suggest an optimal time window of 1-2 s, offering a trade-off between classification performance and excessive delay to guarantee the system responsiveness. These findings underscore the importance of temporal optimization in MI-BCI systems to improve usability in real rehabilitation scenarios.

Hyperspectral imaging and artificial intelligence enhance remote phenotyping of grapevine rootstock influence on whole vine photosynthesis.

Rootstocks are gaining importance in viticulture as a strategy to combat abiotic challenges, as well as enhancing scion physiology. Photosynthetic parameters such as maximum rate of carboxylation of RuBP (Vcmax) and the maximum rate of electron transport driving RuBP regeneration (Jmax) have been identified as ideal targets for potential influence by rootstock and breeding. However, leaf specific direct measurement of these photosynthetic parameters is time consuming, limiting the information scope and the number of individuals that can be screened. This study aims to overcome these limitations by employing hyperspectral imaging combined with artificial intelligence (AI) to predict these key photosynthetic traits at the canopy level. Hyperspectral imaging captures detailed optical properties across a broad range of wavelengths (400 to 1000 nm), enabling use of all wavelengths in a comprehensive analysis of the entire vine's photosynthetic performance (Vcmax and Jmax). Artificial intelligence-based prediction models that blend the strength of deep learning and machine learning were developed using two growing seasons data measured post-solstice at 15 h, 14 h, 13 h and 12 h daylengths for Vitis hybrid 'Marquette' grafted to five commercial rootstocks and 'Marquette' grafted to 'Marquette'. Significant differences in photosynthetic efficiency (Vcmax and Jmax) were noted for both direct and indirect measurements for the six rootstocks, indicating that rootstock genotype and daylength have a significant influence on scion photosynthesis. Evaluation of multiple feature-extraction algorithms indicated the proposed Vitis base model incorporating a 1D-Convolutional neural Network (CNN) had the best prediction performance with a R2 of 0.60 for Vcmax and Jmax. Inclusion of weather and chlorophyll parameters slightly improved model performance for both photosynthetic parameters. Integrating AI with hyperspectral remote phenotyping provides potential for high-throughput whole vine assessment of photosynthetic performance and selection of rootstock genotypes that confer improved photosynthetic performance potential in the scion.

Second-order Spatial Measures Low Overlap Rate Point Cloud Registration Algorithm Based On FPFH Features1

When the sensor dynamically collects point cloud data for object or map reconstruction, the registration effect is poor and reconstruction application is difficult with a too low overlap rate of the collected point cloud data. The reason is that the objects are covered, the sensor rotation angle is too large and the speed of movement is too fast. Because of these problems, this paper proposes a point cloud registration algorithm based on FPFH feature matching, combined with second-order spatial measures. Firstly, using the FPFH feature extraction algorithm, the features of each point are extracted, and then feature matching is performed to generate the set of feature point pairs. Secondly, the second-order spatial measure is used to calculate the set of feature point pairs to obtain the second-order spatial measure matrix scores and sort them. Finally, the dichotomy method is used to find the appropriate second-order spatial measure scores for distinguishing the inner points (points in the overlap region) from the outer points (points that do not belong to the overlap region as well as the mismatched points and some disturbances). The contrast experiments between this algorithm and three common point cloud registration algorithms, FPFH-ICP, 4PCS-ICP, and NDT-ICP, on the Stanford dataset and 3DMatch dataset shows that the registration accuracy of the other algorithms decreases significantly with a low overlap rate. But this algorithm still has a high registration accuracy and is less affected by outliers than the other algorithms. Besides, this algorithm can still maintain a good registration effect on different data sets.

A dimensionality reduction assisted evolutionary algorithm for high-dimensional expensive multi/many-objective optimization

Surrogate-assisted multi/many-objective evolutionary algorithms (SA-MOEAs) have shown significant progress in tackling expensive optimization problems. However, existing research primarily focuses on low-dimensional optimization problems. The main reason lies in the fact that some surrogate techniques used in SA-MOEAs, such as the Kriging model, are not applicable for exploring high-dimensional decision space. This paper introduces a surrogate-assisted multi-objective evolutionary algorithm with dimensionality reduction to address high-dimensional expensive optimization problems. The proposed algorithm includes two key insights. Firstly, we propose a dimensionality reduction framework containing three different feature extraction algorithms and a feature drift strategy to map the high-dimensional decision space into a low-dimensional decision space; this strategy helps to improve the robustness of surrogates. Secondly, we propose a sub-region search strategy to define a series of promising sub-regions in the high-dimensional decision space; this strategy helps to improve the exploration ability of the proposed SA-MOEA. Experimental results demonstrate the effectiveness of our proposed algorithm in comparison to several state-of-the-art algorithms.

Bayesian optimized multimodal deep hybrid learning approach for tomato leaf disease classification

Manual identification of tomato leaf diseases is a time-consuming and laborious process that may lead to inaccurate results without professional assistance. Therefore, an automated, early, and precise leaf disease recognition system is essential for farmers to ensure the quality and quantity of tomato production by providing timely interventions to mitigate disease spread. In this study, we have proposed seven robust Bayesian optimized deep hybrid learning models leveraging the synergy between deep learning and machine learning for the automated classification of ten types of tomato leaves (nine diseased and one healthy). We customized the popular Convolutional Neural Network (CNN) algorithm for automatic feature extraction due to its ability to capture spatial hierarchies of features directly from raw data and classical machine learning techniques [Random Forest (RF), XGBoost, GaussianNB (GNB), Support Vector Machines (SVM), Multinomial Logistic Regression (MLR), K-Nearest Neighbor (KNN)], and stacking for classifications. Additionally, the study incorported a Boruta feature filtering layer to capture the statistically significant features. The standard, research-oriented PlantVillage dataset was used for the performance testing, which facilitates benchmarking against prior research and enables meaningful comparisons of classification performance across different approaches. We utilized a variety of statistical classification metrics to demonstrate the robustness of our models. Using the CNN-Stacking model, this study achieved the highest classification performance among the seven hybrid models. On an unseen dataset, this model achieved average precision, recall, f1-score, mcc, and accuracy values of 98.527%, 98.533%, 98.527%, 98.525%, and 98.268%, respectively. Our study requires only 0.174 s of testing time to correctly identify noisy, blurry, and transformed images. This indicates our approach's time efficiency and generalizability in images captured under challenging lighting conditions and with complex backgrounds. Based on the comparative analysis, our approach is superior and computationally inexpensive compared to the existing studies. This work will aid in developing a smartphone app to offer farmers a real-time disease diagnosis tool and management strategies.