Classification Performance Research Articles

Search for Young Stellar Objects within 4XMM-DR13 Using CatBoost and SPE

Classifying and summarizing large data sets from different sky survey projects is essential for various subsequent scientific research. By combining data from 4XMM-DR13, Sloan Digital Sky Survey (SDSS) DR18, and CatWISE, we formed an XMM-WISE-SDSS sample that included information in the X-ray, optical, and infrared bands. By cross matching this sample with data sets from known spectral classifications from SDSS and LAMOST, we obtained a training data set containing stars, galaxies, quasars, and young stellar objects (YSOs). Two machine learning methods, CatBoost and Self-Paced Ensemble (SPE), were used to train and construct machine learning models through training sets to classify the XMM-WISE-SDSS sample. Notably, the SPE classifier showed excellent performance in YSO classification, identifying 1102 YSO candidates from 160,545 sources, including 258 known YSOs. Then we further verify whether these candidates are YSOs by the spectra in LAMOST and the identification in the SIMBAD and VizieR databases. Finally there are 412 unidentified YSO candidates. The discovery of these new YSOs is an important addition to existing YSO samples and will deepen our understanding of star formation and evolution. Moreover we provided a classification catalog for the whole XMM-WISE-SDSS sample.

DMCCT: Dual-Branch Multi-Granularity Convolutional Cross-Substitution Transformer for Hyperspectral Image Classification

In the field of hyperspectral image classification, deep learning technology, especially convolutional neural networks, has achieved remarkable progress. However, convolutional neural network models encounter challenges in hyperspectral image classification due to limitations in their receptive fields. Conversely, the global modeling capability of Transformers has garnered attention in hyperspectral image classification. Nevertheless, the high computational cost and inadequate local feature extraction hinder its widespread application. In this study, we propose a novel fusion model of convolutional neural networks and Transformers to enhance performance in hyperspectral image classification, namely the dual-branch multi-granularity convolutional cross-substitution Transformer (DMCCT). The proposed model adopts a dual-branch structure to separately extract spatial and spectral features, thereby mitigating mutual interference and information loss between spectral and spatial data during feature extraction. Moreover, a multi-granularity embedding module is introduced to facilitate multi-scale and multi-level local feature extraction for spatial and spectral information. In particular, the improved convolutional cross-substitution Transformer module effectively integrates convolution and Transformer, reducing the complexity of attention operations and enhancing the accuracy of hyperspectral image classification tasks. Subsequently, the proposed method is evaluated against existing approaches using three classical datasets, namely Pavia University, Kennedy Space Center, and Indian Pines. Experimental results demonstrate the efficacy of the proposed method, achieving significant classification results on these datasets with overall classification accuracies of 98.57%, 97.96%, and 96.59%, respectively. These results establish the superiority of the proposed method in the context of hyperspectral image classification under similar experimental conditions.

Transformer-based classification of visceral pain-related local field potential patterns in the brain

Neuronal ensemble activity entrained by local field potential (LFP) patterns underlies a variety of brain functions, including emotion, cognition, and pain perception. Recent advances in machine learning approaches may enable more effective methods for analyzing LFP patterns across multiple brain areas than conventional time-frequency analysis. In this study, we tested the performance of two machine learning algorithms, AlexNet and the Transformer models, to classify LFP patterns in eight pain-related brain regions before and during acetic acid-induced visceral pain behaviors. Over short time windows lasting several seconds, applying AlexNet to LFP power datasets, but not to raw time-series LFP traces from multiple brain areas, successfully achieved superior classification performance compared with simple LFP power analysis. Furthermore, applying the Transformer directly to the raw LFP traces achieved significantly superior classification performance than AlexNet when using LFP power datasets. These results demonstrate the utility of the Transformer in the analysis of neurophysiological signals, and pave the way for its future applications in the decoding of more complex neuronal activity patterns.

Wind turbine blade icing diagnosis based on k-means clustering and label propagation algorithm

ABSTRACT Wind turbine blade icing seriously affects power generation performance and fatigue life, and effective diagnosis of blade icing is critical for mitigating icing effects. Current diagnostic methods are greatly affected by unbalanced data, especially for small sample data. To effectively solve the above problems, a novel diagnostic method combining k-means clustering with a label propagation algorithm is proposed. Specifically, k-means clustering handles unlabeled SCADA data, generating initial pseudo-labels. Then, the label propagation algorithm refines these pseudo-labels, enhancing labeling accuracy and overall classification performance. Finally, the effectiveness of the proposed method is validated using four different type classifiers for two wind farms. The results show that the proposed method improves the average diagnostic accuracy by 3.38% compared to models that eliminate unlabeled data and with a 4.2% improvement in small sample scenarios. The results demonstrate that the method exhibits high accuracy and significant generalization ability in diagnosing blade icing, offering practical benefits for data analysis and fault diagnosis.

Early diagnosis of Alzheimer’s disease using a group self-calibrated coordinate attention network based on multimodal MRI

Convolutional neural networks (CNNs) for extracting structural information from structural magnetic resonance imaging (sMRI), combined with functional magnetic resonance imaging (fMRI) and neuropsychological features, has emerged as a pivotal tool for early diagnosis of Alzheimer’s disease (AD). However, the fixed-size convolutional kernels in CNNs have limitations in capturing global features, reducing the effectiveness of AD diagnosis. We introduced a group self-calibrated coordinate attention network (GSCANet) designed for the precise diagnosis of AD using multimodal data, including encompassing Haralick texture features, functional connectivity, and neuropsychological scores. GSCANet utilizes a parallel group self-calibrated module to enhance original spatial features, expanding the field of view and embedding spatial data into channel information through a coordinate attention module, which ensures long-term contextual interaction. In a four-classification comparison (AD vs. early MCI (EMCI) vs. late MCI (LMCI) vs. normal control (NC)), GSCANet demonstrated an accuracy of 78.70%. For the three-classification comparison (AD vs. MCI vs. NC), it achieved an accuracy of 83.33%. Moreover, our method exhibited impressive accuracies in the AD vs. NC (92.81%) and EMCI vs. LMCI (84.67%) classifications. GSCANet improves classification performance at different stages of AD by employing group self-calibrated to expand features receptive field and integrating coordinated attention to facilitate significant interactions among channels and spaces. Providing insights into AD mechanisms and showcasing scalability for various disease predictions.

Unrevealing the Halyomorpha halys Damage Fingerprint on Hazelnut Metabolome by Multiomic Platforms and AI-Aided Strategies.

The brown marmorated stink bug (Halyomorpha halys) poses a significant threat to hazelnut crops by affecting kernel development and causing quality defects, reducing the market value. While previous studies have identified bitter-tasting compounds in affected kernels, the impact of stink bug feeding on the hazelnut metabolome, particularly concerning aroma precursors, remains underexplored. This study aims to map the nonvolatile metabolome and volatilome of hazelnut samples obtained by caging H. halys on different cultivars in two locations to identify markers for diagnosing stink bug damage. Using a multiomic approach involving headspace solid-phase microextraction (HS-SPME), comprehensive two-dimensional gas chromatography-time-of-flight mass spectrometry (GC × GC-TOF MS), and liquid chromatography-high-resolution mass spectrometry (LC-HRMS), both raw and roasted hazelnuts are analyzed, with artificial intelligence (AI) and machine learning tools employed to explore data correlations. The study finds that the hazelnut metabolome and volatilome exhibit high chemical complexity with significant classes of compounds such as aldehydes, ketones, alcohols, and terpenes identified in both raw and roasted hazelnuts. Multivariate analysis indicates that the orchard location significantly impacts the metabolome, followed by damage type, with cultivar differences being less pronounced. Partial least-squares discriminant analysis (PLS-DA) models achieve high predictive accuracy for orchard location (99%) and damage type (≈80%), with the roasted volatilome showing the highest predictive accuracy. Correlation matrices reveal significant relationships between raw hazelnut metabolites and aroma compounds in roasted samples, suggesting potential markers for stink bug damage that could guide the quality assessment and mitigation strategies. Data fusion techniques further enhance classification performance, particularly in predicting damage type, underscoring the potential of integrating multiple data sets for comprehensive quality assessment.

Tree Species Classification from UAV Canopy Images with Deep Learning Models

Forests play a critical role in the provision of ecosystem services, and understanding their compositions, especially tree species, is essential for effective ecosystem management and conservation. However, identifying tree species is challenging and time-consuming. Recently, unmanned aerial vehicles (UAVs) equipped with various sensors have emerged as a promising technology for species identification due to their relatively low cost and high spatial and temporal resolutions. Moreover, the advancement of various deep learning models makes remote sensing based species identification more a reality. However, three questions remain to be answered: first, which of the state-of-the-art models performs best for this task; second, which is the optimal season for tree species classification in a temperate forest; and third, whether a model trained in one season can be effectively transferred to another season. To address these questions, we focus on tree species classification by using five state-of-the-art deep learning models on UAV-based RGB images, and we explored the model transferability between seasons. Utilizing UAV images taken in the summer and fall, we captured 8799 crown images of eight species. We trained five models using summer and fall images and compared their performance on the same dataset. All models achieved high performances in species classification, with the best performance on summer images, with an average F1-score was 0.96. For the fall images, Vision Transformer (ViT), EfficientNetB0, and YOLOv5 achieved F1-scores greater than 0.9, outperforming both ResNet18 and DenseNet. On average, across the two seasons, ViT achieved the best accuracy. This study demonstrates the capability of deep learning models in forest inventory, particularly for tree species classification. While the choice of certain models may not significantly affect performance when using summer images, the advanced models prove to be a better choice for fall images. Given the limited transferability from one season to another, further research is required to overcome the challenge associated with transferability across seasons.

Application of Machine Learning Models for Malware Classification With Real and Synthetic Datasets

Stacking of multiple Machine Learning (ML) classifiers have gained popularity in addressing anomalous data classification along with Deep Learning (DL) algorithms. This study compares traditional ML classifiers, multi-layer stacking ML classifiers, and DL classifiers using an open-source malware dataset-containing equal numbers of benign and malware samples. The results on the realistic dataset indicate that the DL classifier, utilizing a Bidirectional Long Short-Term Memory (BiLSTM) model, outperformed the stacked classifiers with Logistic Regression (LR) and Support Vector Machine (SVM) as Meta learners by 36.78% and 39.69%, respectively, in terms of classification accuracy and performance. The research work was extended to study the impact of Generative Adversarial Network (GAN) based synthetic dataset of relatively smaller size on deep learning models. It was observed that the Deep Learning Multi-Layer Perceptron (DLMLP) Model had relatively superior performance as compared to complex deep learning models like Long Short-Term Memory LSTM and BiLSTM

Data-adaptive binary classifiers in high dimensions using random partitioning

Classification in high dimensions has been highlighted for the past two decades since Fisher's linear discriminant analysis (LDA) is not optimal in a smaller sample size n comparing the number of covariates p, i.e. p>n, which is mostly due to the singularity of the sample covariance matrix. Rather than modifying how to estimate the sample covariance and sample mean vector in constructing a classifier, we build two types of high-dimensional classifiers using data splitting, i.e. single data splitting (SDS) and multiple data splitting (MDS). Moreover, we introduce a weighted version of MDS classifier that improves classification performance as illustrated in numerical studies. Each of the split data sets has a smaller size of covariates compared to the sample size so that LDA is applicable, and classification results can be combined with respect to minimizing the misclassification rate. We present theoretical justification backing up our proposed methods by comparing misclassification rates with LDA in high dimension. We also conduct a wide range of simulations and analyse four microarray data sets, which demonstrates that our proposed methods outperform some existing methods or at least yield comparable performances.

Explainable artificial intelligence (XAI) to find optimal in-silico biomarkers for cardiac drug toxicity evaluation

The Comprehensive In-vitro Proarrhythmia Assay (CiPA) initiative aims to refine the assessment of drug-induced torsades de pointes (TdP) risk, utilizing computational models to predict cardiac drug toxicity. Despite advancements in machine learning applications for this purpose, the specific contribution of in-silico biomarkers to toxicity risk levels has yet to be thoroughly elucidated. This study addresses this gap by implementing explainable artificial intelligence (XAI) to illuminate the impact of individual biomarkers in drug toxicity prediction. We employed the Markov chain Monte Carlo method to generate a detailed dataset for 28 drugs, from which twelve in-silico biomarkers of 12 drugs were computed to train various machine learning models, including Artificial Neural Networks (ANN), Support Vector Machines (SVM), Random Forests (RF), XGBoost, K-Nearest Neighbors (KNN), and Radial Basis Function (RBF) networks. Our study’s innovation is leveraging XAI, mainly through the SHAP (SHapley Additive exPlanations) method, to dissect and quantify the contributions of biomarkers across these models. Furthermore, the model performance was evaluated using the test set from 16 drugs. We found that the ANN model coupled with the eleven most influential in-silico biomarkers namely dVmdtrepol,dVmdtmax,APD90,APD50,APDtri,CaD90,CaD50,Catri,CaDiastole,qInward,andqNet\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\frac{dVm}{dt}_{repol}, \\frac{dVm}{dt}_{max}, {APD}_{90}, {APD}_{50}, {APD}_{tri}, {CaD}_{90}, {CaD}_{50}, {Ca}_{tri}, {Ca}_{Diastole}, qInward, and qNet$$\\end{document} showed the highest classification performance among all classifiers with Area Under the Curve (AUC) scores of 0.92 for predicting high-risk, 0.83 for intermediate-risk, and 0.98 for low-risk drugs. We also found that the optimal in silico biomarkers selected based on SHAP analysis may be different for various classification models. However, we also found that the biomarker selection only sometimes improved the performance; therefore, evaluating various classifiers is still essential to obtain the desired classification performance. Our proposed method could provide a systematic way to assess the best classifier with the optimal in-silico biomarkers for predicting the TdP risk of drugs, thereby advancing the field of cardiac safety evaluations.

Early Cervical Cancer Diagnosis with SWIN-Transformer and Convolutional Neural Networks.

Introduction: Early diagnosis of cervical cancer at the precancerous stage is critical for effective treatment and improved patient outcomes. Objective: This study aims to explore the use of SWIN Transformer and Convolutional Neural Network (CNN) hybrid models combined with transfer learning to classify precancerous colposcopy images. Methods: Out of 913 images from 200 cases obtained from the Colposcopy Image Bank of the International Agency for Research on Cancer, 898 met quality standards and were classified as normal, precancerous, or cancerous based on colposcopy and histopathological findings. The cases corresponding to the 360 precancerous images, along with an equal number of normal cases, were divided into a 70/30 train-test split. The SWIN Transformer and CNN hybrid model combines the advantages of local feature extraction by CNNs with the global context modeling by SWIN Transformers, resulting in superior classification performance and a more automated process. The hybrid model approach involves enhancing image quality through preprocessing, extracting local features with CNNs, capturing the global context with the SWIN Transformer, integrating these features for classification, and refining the training process by tuning hyperparameters. Results: The trained model achieved the following classification performances on fivefold cross-validation data: a 94% Area Under the Curve (AUC), an 88% F1 score, and 87% accuracy. On two completely independent test sets, which were never seen by the model during training, the model achieved an 80% AUC, a 75% F1 score, and 75% accuracy on the first test set (precancerous vs. normal) and an 82% AUC, a 78% F1 score, and 75% accuracy on the second test set (cancer vs. normal). Conclusions: These high-performance metrics demonstrate the models' effectiveness in distinguishing precancerous from normal colposcopy images, even with modest datasets, limited data augmentation, and the smaller effect size of precancerous images compared to malignant lesions. The findings suggest that these techniques can significantly aid in the early detection of cervical cancer at the precancerous stage.

Ensemble Learning for Stellar Classification and Radius Estimation from Multimodal Data

Abstract Stellar classification and radius estimation are crucial for understanding the structure of the universe and stellar evolution. With the advent of the era of astronomical big data, multimodal data are available and theoretically effective for stellar classification and radius estimation. A problem is how to improve the performance of this task by jointly using the multimodal data. However, existing research primarily focuses on using single-modal data. To this end, this paper proposes a model, Multi-Modal SCNet (MMSCNet), and its ensemble model Multimodal Ensemble for Stellar Classification and Regression (MESCR) for improving stellar classification and radius estimation performance by fusing two modality data. In this problem, a typical phenomenon is that the sample numbers of some type stars are evidently more than others. This imbalance has negative effects on model performance. Therefore, this work utilize a weighted sampling strategy to deal with the imbalance issues in MESCR. Some evaluation experiments are conducted on a test set for MESCR and the classification accuracy is 96.1\%, the radius estimation performance Mean of Absolute Error (MAE) and $\sigma$ are 0.084 dex and 0.149 \(R_{\odot}\) respectively. Moreover, we assessed the uncertainty of model predictions, confirming good consistency within a reasonable deviation range. Finally, we applied our model to 50,871,534 SDSS stars without spectra and published a new catalog.

EEG-based emotional valence and emotion regulation classification: a data-centric and explainable approach

Emotion classification using electroencephalographic (EEG) data is a challenging task in the field of Artificial Intelligence. While many researchers have focused on finding the best model or feature extraction technique to achieve optimal results, few have attempted to select the best methodological steps for working with the dataset. In this study, we applied two different theoretical approaches based on the noise of the dataset: curriculum learning and confident learning. Curriculum learning involves presenting training examples to the model in a specific order, starting with easier examples and gradually increasing in difficulty. This approach has been shown to improve model performance. Confident learning is a method for identifying and correcting label errors in datasets. By identifying and correcting these errors, confident learning can improve the performance of machine learning models trained on noisy datasets. We then applied the Integrated Gradient technique in order to assess the explainability of each model. Our aim was to explore the impact of different models and methods on emotion classification performance using EEG data. We collected and used an EEG dataset in which participants rated the emotional valence of positive and negative pictures while performing an emotion regulation (ER) task, comparing a control condition (Look) with two ER strategies: cognitive reappraisal and expressive suppression. We performed a multilabel classification to identify emotional neutrality or polarization of emotional valence (both positive and negative) rated by participants and the emotion regulation strategy adopted during the task. We compared the performance of models trained on three datasets selected based on label noise and evaluated their suitability for this task. Our results suggest different patterns based on the architecture used for feature importance, highlighting both advantages and criticisms.

Significant feature suppression and cross-feature fusion networks for fine-grained visual classification

The technique of extracting different distinguishing features by locating different part regions to achieve fine-grained visual classification (FGVC) has made significant improvements. Utilizing attention mechanisms for feature extraction has become one of the mainstream methods in computer vision, but these methods have certain limitations. They typically focus on the most discriminative regions and directly combine the features of these parts, neglecting other less prominent yet still discriminative regions. Additionally, these methods may not fully explore the intrinsic connections between higher-order and lower-order features to optimize model classification performance. By considering the potential relationships between different higher-order feature representations in the object image, we can enable the integrated higher-order features to contribute more significantly to the model’s classification decision-making capabilities. To this end, we propose a saliency feature suppression and cross-feature fusion network model (SFSCF-Net) to explore the interaction learning between different higher-order feature representations. These include (1) an object-level image generator (OIG): the intersection of the output feature maps of the last two convolutional blocks of the backbone network is used as an object mask and mapped to the original image for cropping to obtain an object-level image, which can effectively reduce the interference caused by complex backgrounds. (2) A saliency feature suppression module (SFSM): the most distinguishing part of the object image is obtained by a feature extractor, and the part is masked by a two-dimensional suppression method, which improves the accuracy of feature suppression. (3) A cross-feature fusion method (CFM) based on inter-layer interaction: the output feature maps of different network layers are interactively integrated to obtain high-dimensional features, and then the high-dimensional features are channel compressed to obtain the inter-layer interaction feature representation, which enriches the output feature semantic information. The proposed SFSCF-Net can be trained end-to-end and achieves state-of-the-art or competitive results on four FGVC benchmark datasets.

Classification of Garlic Varieties with Fluorescent Spectroscopy Using Machine Learning

Machine learning techniques can produce fast, accurate and objective results in the analysis of agricultural products. These artificial intelligence-based systems are frequently encountered in studies on agriculture in the literature. This study reveals the usability of machine learning algorithms in classification of garlic cultivars using fluorescent spectroscopic data. For this, six types of garlic were used: Razgradski-11, Razgradski-12, Razgradski-115, Plovdivski-120, Yambolski-99 and Topolovgradski. In the first stage, the parsing analysis made from the fluorescent spectroscopic data of the garlics was carried out with seven different machine learning. The classification results of these seven types of machine learning algorithms were obtained. In the second stage, the classification results were obtained by adjusting the hyperparameters of each Machine Learning (ML) algorithm in order to control the improvability of the classification accuracy rates. Finally, performance metrics such as Specificity, precision, MCC, F1-Score of the classification processes obtained in the two stages were compared. In general, it was observed that the classification performances increased with the hyperparameter adjustment performed in the second stage. In this study, classification results with ML showed that fluorescent spectroscopy data of garlic strongly represented garlic species and provided high performance classification accuracy of 99.93% with Neural Network (NN), one of the machine learning methods using these data.

Distinguish microphase-separated structures of diblock copolymers using local order parameters

The microphase-separated structures of block copolymers are inherently highly ordered local structures, commonly characterized by differences in domain width and curvature. By focusing on diblock copolymers, we propose local order parameters (LOPs) that accurately distinguish between adjacent microphase-separated structures on the phase diagram. We used the Molecular Assembly structure Learning package for Identifying Order parameters (MALIO) to evaluate the structure classification performance of 186 candidate LOPs. MALIO calculates the numerical values of all candidate LOPs for the input microphase-separated structures to create a dataset, and then performs supervised machine learning to select the best LOPs quickly and systematically. We evaluated the robustness of the selected LOPs in terms of classification accuracy against variations in miscibility and fraction of block. The minimum local area size required for LOPs to achieve their classification performances is closely related to the characteristic sizes of the microphase-separated structures. The proposed LOPs are potentially applicable over a large area on the phase diagram.

Employing Different Algorithms of Lightweight Convolutional Neural Network Models in Image Distortion Classification

The majority of applications use automatic image recognition technologies to carry out a range of tasks. Therefore, it is crucial to identify and classify image distortions to improve image quality. Despite efforts in this area, there are still many challenges in accurately and reliably classifying distorted images. In this paper, we offer a comprehensive analysis of models of both non-lightweight and lightweight deep convolutional neural networks (CNNs) for the classification of distorted images. Subsequently, an effective method is proposed to enhance the overall performance of distortion image classification. This method involves selecting features from the pretrained models’ capabilities and using a strong classifier. The experiments utilized the kadid10k dataset to assess the effectiveness of the results. The K-nearest neighbor (KNN) classifier showed better performance than the naïve classifier in terms of accuracy, precision, error rate, recall and F1 score. Additionally, SqueezeNet outperformed other deep CNN models, both lightweight and non-lightweight, across every evaluation metric. The experimental results demonstrate that combining SqueezeNet with KNN can effectively and accurately classify distorted images into the correct categories. The proposed SqueezeNet-KNN method achieved an accuracy rate of 89%. As detailed in the results section, the proposed method outperforms state-of-the-art methods in accuracy, precision, error, recall, and F1 score measures.

Galaxy Classification Using EWGC

The Enhanced Wide-field Galaxy Classification Network (EWGC) is a novel architecture designed to classify spiral and elliptical galaxies using Wide-field Infrared Survey Explorer (WISE) images. The EWGC achieves an impressive classification accuracy of 90.02%, significantly outperforming the previously developed WGC network and underscoring its superior performance in galaxy morphology classification. Remarkably, the network demonstrates a consistent accuracy of 90.02% when processing both multi-target and single-target images. Such robustness indicates the EWGC’s versatility and potential for various applications in galaxy classification tasks.

A study on the classification performance of water-injection hydrocyclone

Aiming at the problem of fine particles entrainment in the underflow of hydrocyclone during the metal grinding classification process, a water-injection hydrocyclone was proposed to improve the classification efficiency. Through external injection of water on the wall surface of the cone section, the particles settling in the region were loosely graded so that the fine particles settled in the wall surface returned to the inner swirl again, thus reducing their entry into the underflow. Numerical simulation was used to explore the differences in the internal flow field characteristics and separation performance of the hydrocyclone after adding the water-injection structure. Then the industrial tests were conducted on the classification performance of the water-injection hydrocyclone. Numerical results showed that compared with the conventional hydrocyclone, the static pressure, tangential and axial velocity of the fluid inside the water-injection hydrocyclone increased, while the turbulence intensity decreased. The experimental results showed that with the increase of water-injection flow rate, the content of -74 μm particles in the underflow of water-injection hydrocyclone first decreased and then increased, and the comprehensive classification efficiency increased and then decreased accordingly. Compared with the conventional hydrocyclone, the content of -74 μm particles in the underflow of the water-injection hydrocyclone was reduced from 26.34% to 23.95%, and the comprehensive classification efficiency was increased from 69.22% to 73.03%, which mitigated the phenomenon of fine particles entrainment in the underflow.

Robot terrain classification based on improved Hilbert-Huang transform and long short-term memory network

Nowadays, with the rapid development of science and technology, the innovation and application of robot technology has become an important force to promote industrial development, which requires robots to have a high degree of autonomy and adaptability. Among them, terrain classification technology is one of the key technologies to achieve this goal. In order to improve the ground adaptability of robots in complex environments, this paper proposes a terrain classification algorithm based on improved Hilbert-Huang transform(HHT) combined with ensemble empirical mode decomposition(EEMD) and long short-term memory network(LSTM). Firstly, the signal data is processed by EEMD, and then the frequency domain features of the signal are extracted by Hilbert transform to expand the feature dimension. Finally, the features are learned and classified by the LSTM model, which effectively improves the classification accuracy. In this paper, we conducted sufficient experiments to compare the effects of EMD and EEMD and the effects of different neural network models, and verified the contribution of the Hilbert-Huang transform to improve the classification performance through ablation experiments, which proves the effectiveness and reliability of our proposed algorithm, and provided powerful technical support for the robot to adapt to the ground information in the complex environment.