Redundant Information Research Articles

К вопросу о признаках инсайдерской деятельности

The work sets the task of identifying insider activities in organizations that lead to threats to in-formation security, one of the first steps of which should be a review of scientific publications in the subject area and identifying the main characteristics of insiders. The purpose of the work is to systema-tize the main characteristics of insiders used in the work of the corresponding methods; For this pur-pose, the following scientific methods were used: review of scientific publications, identification of in-sider characteristics, their analysis and systematization. The novelty of the research is determined by the fact that, in contrast to individual groups of features used by existing methods for detecting insiders, this work presents their set of 15 elements, suitable for the entire set of solutions; namely the following: greed, biography, psychology, personality, switching, predispositional, professional (working), abnormal behavior, dissemination of information, file changes, collection of information (redundant), telephone conversations, loyalty, physiognomy, illegal actions. The theoretical significance lies in the fact that a single set of insider attributes has been obtained, including all private ones used in existing methods. The practical significance lies in obtaining the characteristics of insiders, on the basis of which a unified meta-method can be built, taking into account the advantages of existing ones.

Novel discretized gravitational search algorithm for effective medical hyperspectral band selection

Medical hyperspectral imaging present a promising avenue for non-invasive diagnostic methods for diseases. Nonetheless, the sparsity of medical hyperspectral data within high-dimensional spaces introduces the “curse of dimensionality”, which diminishes the efficiency and accuracy of data processing efforts. Therefore, spectral dimensionality reduction emerges as an essential process in the analysis and utilization of MHSIs data. To retain the intrinsic properties of the spectral bands, an effective unsupervised band selection algorithm is proposed leveraging the gravitational search algorithm (GSA-UBS) to identify the optimal band subset. Taking into account the informational content and redundancy among candidate bands, a comprehensive evaluation criterion is established that incorporates a band distance matrix and an information entropy vector. Additionally, a straightforward discrete search strategy is developed that enables gravitational search algorithm to directly retrieve the original sequence numbers of the selected bands, bypassing the conventional 0–1 band weighting approach. The extensive evaluation of GSA-UBS on three publicly available invivo brain cancer MHSIs datasets and a remote sensing hyperspectral image demonstrates its superior performance compared to various state-of-the-art methods. The source code for GSA-UBS can be accessed at https://github.com/zhangchenglong1116/GSA_UBS.

BANDRP: a bilinear attention network for anti-cancer drug response prediction based on fingerprint and multi-omics.

Predicting anti-cancer drug response can help with personalized cancer treatment and is an important topic in modern oncology research. Although some methods have been used for anti-cancer drug response prediction, how to effectively integrate various features related to cancer cell lines, drugs, and their known responses is still affected by the redundant information of input features and the complex interactions between features. In this study, we propose a bilinear attention model, named BANDRP, based on multiple omics data of cancer cell lines and multiple molecular fingerprints of drugs to predict potential anti-cancer drug responses. Compared with existing models, BANDRP uses gene expression data to calculate pathway enrichment scores to enrich the features of cancer cell lines and can automatically learn the interactive information of cancer cell lines and drugs through bilinear attention networks. Benchmarking and independent tests demonstrate that BANDRP surpasses baseline models and exhibits robust generalization performance. Ablation experiments affirm the optimality of the current model architecture and feature selection scheme for our prediction task. Furthermore, analytical experiments and case studies on unknown anti-cancer drug response predictions underscore BANDRP's potential as a potent and reliable framework for predicting anti-cancer drug response.

Global and local feature extraction based on convolutional neural network residual learning for MR image denoising.

Given the different noise distribution information of global and local magnetic resonance (MR) images, this study aims to extend the current work on convolutional neural networks that preserve global structure and local details in MR image denoising tasks. This study proposed a parallel and serial network for denoising 3D MR images, called 3D-PSNet. We use the residual depthwise separable convolution block to learn the local information of the feature map, reduce the network parameters, and thus improve the training speed and parameter efficiency. In addition, we consider the feature extraction of the global image and utilize residual dilated convolution to process the feature map to expand the receptive field of the network and avoid the loss of global information. Finally, we combine both of them to form a parallel network. What's more, we integrate reinforced residual convolution blocks with dense connections to form serial network branches, which can remove redundant information and refine features to further obtain accurate noise information. The peak signal-to-noise ratio, structural similarity index measure, and root mean square error metrics of 3D-PSNet are as high as 47.79%, 99.81%, and 0.40%, respectively, achieving competitive denoising effect on three public datasets. The ablation experiments demonstrated the effectiveness of all the designed modules regarding all the evaluated metrics in both datasets. The proposed 3D-PSNet takes advantage of multi-scale receptive fields, local feature extraction and residual dense connections to more effectively restore the global structure and local fine features in MR images, and is expected to help doctors quickly and accurately diagnose patients' conditions.

Feline eye-inspired artificial vision for enhanced camouflage breaking under diverse light conditions.

Biologically inspired artificial vision research has led to innovative robotic vision systems with low optical aberration, wide field of view, and compact form factor. However, challenges persist in object detection and recognition against complex backgrounds and varied lighting. Inspired by the feline eye, which features a vertically elongated pupil and tapetum lucidum, this study introduces an artificial vision system designed for superior object detection and recognition in a monocular framework. Using a slit-like elliptical aperture and a patterned metal reflector beneath a hemispherical silicon photodiode array, the system reduces excessive light and enhances photosensitivity. This design achieves clear focus under bright light and enhanced sensitivity in dim conditions. Theoretical and experimental analyses demonstrate the system's ability to filter redundant information and detect camouflaged objects in diverse lighting, representing a substantial advancement in monocular camera technology and the potential of biomimicry in optical innovations.

Rapid SLAM Method for Star Surface Rover in Unstructured Space Environments

The space environment is characterized by unstructured features, sparsity, and poor lighting conditions. The difficulty in extracting features from the visual frontend of traditional SLAM methods results in poor localization and time-consuming issues. This paper proposes a rapid and real-time localization and mapping method for star chart surveyors in unstructured space environments. Improved localization is achieved using multiple sensor fusion to sense the space environment. We replaced the traditional feature extraction module with an enhanced SuperPoint feature extraction network to tackle the challenge of challenging feature extraction in unstructured space environments. By dynamically adjusting detection thresholds, we achieved uniform detection and description of image keypoints, ultimately resulting in robust and accurate feature association information. Furthermore, we minimized redundant information to achieve precise positioning with high efficiency and low power consumption. We established a star surface rover simulation system and created simulated environments resembling Mars and the lunar surface. Compared to the LVI-SAM system, our method achieved a 20% improvement in localization accuracy for lunar scenarios. In Mars scenarios, our method achieved a positioning accuracy of 0.716 m and reduced runtime by 18.682 s for the same tasks. Our approach exhibits higher localization accuracy and lower power consumption in unstructured space environments.

Dementia risk prediction using decision-focused content selection from medical notes

Several general-purpose language model (LM) architectures have been proposed with demonstrated improvement in text summarization and classification. Adapting these architectures to the medical domain requires additional considerations. For instance, the medical history of the patient is documented in the Electronic Health Record (EHR) which includes many medical notes drafted by healthcare providers. Direct processing of these notes may not be possible because the computational complexity of LMs imposes a limit on the length of input text. Therefore, previous applications resorted to content selection using truncation or summarization of the text. Unfortunately, these text processing techniques may lead to information loss, redundancy or irrelevance. In the present paper, a decision-focused content selection technique is proposed. The objective of this technique is to select a subset of sentences from the medical notes of a patient that are relevant to the target outcome over a predefined observation period. This decision-focused content selection methodology is then used to develop a dementia risk prediction model based on the Longformer LM architecture. The results show that the proposed framework delivers an AUC of 78.43 when the summary is restricted to 1024 tokens, outperforming previously proposed content selection techniques. This performance is notable given that the model estimates dementia risk with a one year prediction horizon, relies on an observation period of only one year and solely uses medical notes without other EHR data modalities. Moreover, the proposed techniques overcome the limitation of machine learning models that use a tabular representation of the text by preserving contextual content, enable feature engineering from raw text and circumvent the computational complexity of language models.

MT-U2Net: Lightweight detection network for high-precision magnetic tile surface defect localization

Automated surface defect localization is closely related to product quality control. Although many image segmentation models have achieved excellent results in industrial defect localization, the wide-ranging defects in magnetic tile materials and the similarity between textures and background textures make it difficult to balance detection model performance and model size. Therefore, we propose a new magnetic tile defect localization model called MT-U2Net. The model consists of three parts: Dres-Ublock, U2 structure, and attention mechanism. Dres-Ublock is used to enhance the model's feature extraction capability and reduce its size; the U2-Net structure is utilized to learn cross-scale defect information; the attention mechanism is employed to eliminate redundant information. MT-U2Net improves detection performance across various defect scales. In the test set, MT-U2Net achieves an F1 Score of 0.840 and an MAE of 0.024 and compresses the model size to 3.39 M. Extensive experimental results show that MT-U2Net outperforms existing state-of-the-art algorithms in magnetic tile defect detection performance and model size.

Evaluating the impact of improved filter-wrapper input variable selection on long-term runoff forecasting using local and global climate information

Long-term runoff forecasting (LRF) is great important for water resources management. Employing accurate local and global climate information can significantly enhance the accuracy of LRF. The filter-wrapper input variables selection (FWIVS) method can efficiently select local and global climate indices for LRF. However, binary metaheuristic algorithms (BMAs) in wrapper input variable selection (WIVS), such as golden jackal optimization (GJO) and gray wolf optimizer (GWO), frequently encounter local optima, which significantly impact LRF accuracy and remain unexplored. Additionally, previous FWIVS methods overlooked physical relationship between local and global climate information. Consequently, an improved GJO (IGJO) that considers the complementarity of local weather and global climate indices and prevents local optima was proposed. Four machine learning models and an integrated model (IM) were used as learning models for WIVS. Finally, eight BMAs, including IGJO, improved GWO and so on, were constructed and integrated with five learning models to develop forty wrappers for evaluating impact of various BMAs and models on WIVS and LRF. The Jinsha River was served as a case study. Results demonstrated that the impact of the improved BMAs on wrapper fitness and variables selection was higher than learning model. IGJO retained critical variables for WIVS, especially local weather variables. Moreover, IGJO effectively reduced redundant information and extracted more robust complementary global climate indices for WIVS. In addition, LSTM-IGJO exhibited the greatest enhancement in wrapper fitness and LRF accuracy, achieving a NSE of 0.92 and a MAE of 575.83 m3/s. Specifically, this finding indicated that selecting the key variables and selecting the stronger complementary global climate indices instead the redundant local weather variables for retaining key information, while eliminating redundant information, can efficiently improve the LRF accuracy.

Prompt-supervised dynamic attention graph convolutional network for skeleton-based action recognition

Skeleton-based action recognition is a core task in the field of video understanding. Skeleton sequences are characterized by high information density, low redundancy, and clear structural information, thereby facilitating the analysis of complex relationships among human behaviors more readily than other modalities. Although existing studies have encoded skeleton data and achieved positive outcomes, they have often overlooked the precise high-level semantic information inherent in the action descriptions. To address this issue, this paper proposes a prompt-supervised dynamic attention graph convolutional network (PDA-GCN). Specifically, the PDA-GCN incorporates a prompt supervision (PS) module that leverages a pre-trained large-scale language model (LLM) as a knowledge engine and retains the generated text features as prompts to provide additional supervision during model training, enhancing the model’s ability to discern analogous actions with negligible computational cost. In addition, for the purpose of bolstering the learning of discriminative features, a dynamic attention graph convolution (DA-GC) module is presented. This module utilizes self-attention mechanism to adaptively infer intrinsic relationships between joints and integrates dynamic convolution to strengthen the emphasis on local information. This dual focus on both global context and local details further amplifies the efficiency and effectiveness of the model. Extensive experiments, conducted on the widely-used skeleton-based action recognition datasets NTU RGB+D 60 and NTU RGB+D 120, demonstrate that the PDA-GCN surpasses known state-of-the-art methods, achieving accuracies of 93.4% on the NTU RGB+D 60 cross-subject split and 90.7% on the NTU RGB+D 120 cross-subject split.

Coarse-Fine Nested Network for Weakly Supervised Group Activity Recognition.

Weakly supervised group activity recognition (WSGAR) aims at identifying the overall behavior of multiple persons without any fine-grained supervision information (including individual position and action label). Traditional methods usually adopt a person-to-whole way: detect persons via off-the-shelf detectors, obtain person-level features, and integrate into the group-level features for training the classifier. However, these methods are unflexible due to serious reliance on the quality of detectors. To get rid of the detector, recent works learn several prototype tokens from noisy grid features with learnable weights directly, which treat all the local visual information equally and bring in redundant and ambiguous information to some extent. To this end, we propose a novel coarse-fine nested network (CFNN) to coarsely localize the key visual patches of activity and further finely learn the local features, as well as the global features. Specifically, we design a nested interactor (NI) to progressively model the spatiotemporal interactions of the learnable global token. According to the cue of spatial interaction in NI, we localize several key visual patches via a new coarse-grained spatial localizer (CSL). Then, we finally encode these localized visual patches with the help of global spatiotemporal dependency via a new fine-grained spatiotemporal selector (FSS). Extensive experiments on Volleyball and NBA datasets demonstrate the effectiveness of the proposed CFNN compared with the existing competitive methods. Code is available at: https://github.com/gexiaojingshelby/CFNN.

Consciousness: a quantum optical effect in fluorescent protein pathways

This paper presents a physical mechanism of embodied consciousness based on the dynamic organicity theory. We use the entropic pilot wave theory to describe the quantum dipole oscillations from dipole-bound delocalized (quasi-free) electrons in nonpolar nanocavities of aromatic amino acid residues (benzene moiety /cyclic hydrocarbons that contain resonance structures) and their fluorescent pathways. These pathways contain cavity quasipolariton condensates composed of quantized polarization waves of entangled photons. The behavior of oscillating molecular dipoles is influenced by the quantum nature of dynamic organicity, which causes energy fluctuations necessary to move delocalized electrons and create bare polaritons (quantized polarization waves). These waves correspond to photon quasiparticles interacting with water molecules to form quasipolaritons, softened by interacting with hydroxide ions (OH-) within crystal lattices of interfacial water H30. When [H3O+]=[OH−], the solution is neutral in hydrophobic nanocavities. In such nonpolar cavities, evanescent photons (non-radiative transitions in the absence of any source) are emitted while protons (H+) diffuse due to recombination with hydroxide (OH-) ions, acting as protonic analogs of ‘holes’ or excitons. In protein pores, proton motion strongly coupled with π-electron delocalization is a conduit for exciton-photon (polariton) and its polarization wave component. Internal energy fluctuations comprise both quantum potential energy and negative quantum kinetic energy. We explore how quantum potential energy influences the negentropic effect of a 'repulsive force' guided by entropic pilot waves through pilot wave force (negentropic force), functioning as an information-based action of the polarization wave as a conduit of the cavity quasipolariton. When the rate of change of quantum entropy is zero, and momentum of the polarization wave is zero the internal energy transduction between quantum potential energy to quantum kinetic energy manifests as the negentropic force and facilitates the movement of information-based action for information encoding when negative quantum kinetic energy happens at certain times. Experiments have shown that biphoton entanglement interferes with anaesthetics. We postulate that the disruption of cavity polaritonic condensate through its polarization wave component disrupts the decoding of information, suggesting consciousness is attributed to a quantum optical effect. Therefore, we further theorize that consciousness is attributed to the negative quantum kinetic energy of the polarization wave, which provides an informational structure of multiscale redundancy when negentropic action reduces information redundancy. This has profound implications for understanding consciousness as nonmechanical action channeled through negentropic force when the rate of change of quantum entropy is zero.

A Hybrid Feature Selection through Ensemble Rank Aggregation to Improve Perdition and Classification Accuracy

Today, extending credit is a difficult operation since credit databases contain a large quantity of data as well as redundant and useless information. The surplus and unrelated data can lower the categorization and prediction accuracy. In this case, feature selection is crucial for managing massive data. Different rank aggregation (RA) methods are there to ensemble individual feature selection. However not every dataset will perform at its best when using a single RA technique, the combination of multiple RA techniques are needed to increase the perdition accuracy. This study proposes a hybrid rank aggregation model that select features that are significant across different rank aggregation methods like MC4, Kendall tau distance and Borda. This study observed that the performance of ensemble rank aggregation techniques is better than the existing individual rank aggregation methods.

An Adaptive Spatiotemporal Decouple Graph Convolutional Network Based Quality‐Related Fault Detection Method for Complex Industrial Processes

ABSTRACTWith the rapid development of industrial technology, industrial processes become increasingly complex, presenting characteristics of large‐scale and multi‐unit collaboration. However, most current fault detection methods focus on nonlinearity, dynamics, and other characteristics, while neglecting spatiotemporal information. To address this issue, an adaptive spatiotemporal decouple graph convolutional network based quality‐related fault detection method is proposed in this article. First, the temporal graph convolutional network and spatial graph convolutional network are combined organically in the form of joint training. Second, considering that fixed graph structures cannot reflect the dynamic relationships among nodes, we proposed an adaptive weighted mask mechanism to construct dynamic correlation graph embedded with priori knowledge. Multi‐attention mechanism is used to integrate spatiotemporal information, besides, we designed a decoupling layer to avoid information redundancy. Finally, the proposed spatiotemporal graph convolutional network is used to establish a regression model, the quality‐related latent variables are extracted by the decoupling layer, and the statistic is constructed based on Kullback–Leibler divergence. The effectiveness and feasibility of the proposed method are illustrated with the hot strip mill process and the Tennessee Eastman process.

Redundancy Attributes of a Complex System: Application to Bioinformatics

In general, a complex system consists of a large number of interacting units, which when viewed in an information-theoretic perspective, could be seen to possess gross redundant features. Further, a complex system is inherently stochastical in its extensive spatiotemporal universe and hence, some of its statistical features could manifest as patterns occurring more frequently than others; and, likewise some other patterns could form rare elements of the same set. In information-theoretic perspectives (in Shannon's sense) such more (or less) probabilistic occurrences of features specify the redundant (or nonredundant) aspects of the complex system. This attribute of information redundancy in a complex system could be adopted to devise a useful complexity metric as described in this paper. The use of such a complexity metric is demonstrated in differentiating codon-noncodon domains in human and bacterial genomes (which constitute a complex system when seen at the scale of observing a DNA sequence made of vast domains of protein molecules).

A novel procedure to automate the removal of PLI and motion artifacts using mode decomposition to enhance pattern recognition of sEMG signals for myoelectric control of prosthesis

Hand Movement Recognition (HMR) with sEMG is crucial for artificial hand prostheses. HMR performance mostly depends on the feature information that is fed to the classifiers. However, sEMG often captures noise like power line interference (PLI) and motion artifacts. This may extract redundant and insignificant feature information, which can degrade HMR performance and increase computational complexity. This study aims to address these issues by proposing a novel procedure for automatically removing PLI and motion artifacts from experimental sEMG signals. This will make it possible to extract better features from the signal and improve the categorization of various hand movements. Empirical mode decomposition and energy entropy thresholding are utilized to select relevant mode components for artifact removal. Time domain features are then used to train classifiers (kNN, LDA, SVM) for hand movement categorization, achieving average accuracies of 92.36%, 93.63%, and 98.12%, respectively, across subjects. Additionally, muscle contraction efforts are classified into low, medium, and high categories using this technique. Validation is performed on data from ten subjects performing eight hand movement classes and three muscle contraction efforts with three surface electrode channels. Results indicate that the proposed preprocessing improves average accuracy by 9.55% with the SVM classifier, significantly reducing computational time.

Reconstructing hyperspectral images of textiles from a single RGB image utilizing the multihead self-attention mechanism

Hyperspectral images possess abundant information and play a pivotal role in enhancing the accuracy of color difference detection in textiles. However, traditional hyperspectral imaging methods necessitate costly equipment and intricate operational procedures. A novel deep learning model based on a multihead attention mechanism was proposed in this article to facilitate the extensive application of hyperspectral imaging technology in textile quality inspection. This model enabled the reconstruction of the hyperspectral information of plain weave textiles from a single RGB image. In this model, encoder-decoder architecture and pyramid pooling convolutional operations were employed to integrate multiscale features of plain weave cotton-linen textiles. This could capture details and contextual information in textile images more precisely, enhancing the accuracy of hyperspectral image reconstruction. Simultaneously, an attention mechanism was introduced to increase the model’s receptive field and improve its focus on key regions in the input image and feature maps. This resulted in a reduced weighting of redundant information during network learning, leading to an improved feature extraction capability of the network. Through these methods, successful reconstructions of plain weave textiles hyperspectral information from a single RGB image was achieved. Quantitative and qualitative tests were conducted on two datasets, namely, the NTIRE 2020 dataset and a self-made textile dataset, to evaluate the performance of the proposed method. The approach proposed in this article exhibited promising results on both datasets. Specifically, the reconstructed textile hyperspectral images achieved a root mean square error of 0.0344, a peak signal-to-noise ratio of 29.945, a spectral angle mapper of 3.753, and a structural similarity index measure of 0.955 on the textile dataset. In the reconstructed hyperspectral colorimetric experiment, the maximum value of average color difference was 2.641. These results demonstrate that the method can meet the requirements for textile color measurement applications.

Dynamic convolutional time series forecasting based on adaptive temporal bilateral filtering

Time series data typically contain complex dynamic patterns, which not only include linear trends and seasonal variations but also significant nonlinear changes and complex dependencies. Currently, feature extraction methods for time series data primarily employ mixed-mode extraction within the temporal domain, neglecting the effective extraction and analysis of nonlinear characteristics between different observation points and the interdependencies between variables. To address these issues, we designed an adaptive temporal bilateral filtering module that effectively preserves and highlights the nonlinear features and patterns in time series while filtering out noise and redundant information. We also designed a nonlinear feature adaptive extraction module that integrates a gating mechanism and deformable convolutions. This design allows the model to adaptively adjust the shape of the convolutional kernels according to different time steps and conditions. This enables accurate capture and extraction of nonlinear features between various time observations and dependencies between different variables. Additionally, we use stacked convolutional layers to extract local contextual features, addressing fluctuations in local features caused by changes in data distribution in real-world scenarios. In summary, we propose DCNet, a dynamic convolutional network based on an adaptive temporal bilateral filter, and evaluated its performance on twelve real-world datasets. The results indicate that DCNet consistently achieves state-of-the-art performance in both short-term and long-term forecasting tasks, with favorable runtime efficiency.

A hybrid intelligent diagnostic approach for spool jamming faults of hydraulic directional valves

Directional valves are critical functional components in hydraulic systems for diverting the flow of hydraulic oil and controlling oil pressure. Faults of the valves could lead to failure and even serious accidents in hydraulic systems. Fault diagnostic accuracy is directly influenced by the effectiveness of signal processing. Due to the harsh operating environment of hydraulic systems, the condition monitoring signal acquired from the systems contains a large amount of redundant information and environmental noise. This makes the training processes of fault diagnostic approaches time-consuming and inefficient. In this paper, a new hybrid intelligent approach to spool jamming fault diagnostics for hydraulic directional valves is presented. The approach is designed based on the combined strengths of wavelet packet decomposition (WPD), empirical mode decomposition (EMD), variable mode decomposition (VMD), and the multi-layer perceptron (MLP) to improve the efficiency and accuracy of the fault diagnostic process. Five evaluation indices, including processing time (PT), local average accuracy (LAA), stability of accuracy (SA), weighted average of the neuron number (WANN), and robustness of WANN (ROB), are applied to benchmark the approach using ablation experiments. The experimental results show that the hybrid approach has a strong capability to extract fault-related features from the signal and perform fault diagnostics with high accuracy, efficiency, and robustness.

Plant-Leaf Recognition Based on Sample Standardization and Transfer Learning

In recent years, deep-learning methods have significantly improved the classification results in the field of plant-leaf recognition. However, limited by the model input, the original image needs to be compressed to a certain size before it can be input into the convolutional neural network. This results in great changes in the shape and texture information of some samples, thus affecting the classification accuracy of the model to a certain extent. Therefore, a minimum enclosing quadrate (MEQ) method is proposed to standardize the sample datasets. First, the minimum enclosing rectangle (MER) of the leaf is obtained in the original image, and the target area is clipped. Then, the minimum enclosing quadrate of the leaf is obtained by extending the short side of the rectangle. Finally, the sample is compressed to fit the input requirements of the model. In addition, in order to further improve the classification accuracy of plant-leaf recognition, an EC-ResNet50 model based on transfer-learning strategy is proposed and further combined with the MEQ method. The Swedish leaf, Flavia leaf, and MEW2012 leaf datasets are used to test the performance of the proposed methods, respectively. The experimental results show that using the MEQ method to standardize datasets can significantly improve the classification accuracy of neural networks. The Grad-CAM visual analysis reveals that the convolutional neural network exhibits a higher degree of attention towards the leaf surface features and utilizes more comprehensive feature regions during recognition of the leaf samples processed by MEQ method. In addition, the proposed MEQ + EC-ResNet50 method also achieved the best classification results among all the compared methods. This experiment provides a widely applicable sample standardization method for leaf recognition research, which can avoid the problem of sample deformation caused by compression processing and reduce the interference of redundant information in the image to the classification results to a certain degree.