Subspace Ensemble Research Articles

Multi-label Random Subspace Ensemble Classification1

In this work, we develop a new ensemble learning framework, multi-label Random Subspace Ensemble (mRaSE), for multi-label classification. Given a base classifier (e.g., multinomial logistic regression, classification tree, K-nearest neighbors), mRaSE works by first randomly sampling a collection of subspaces, then choosing the best ones that achieve the minimum cross-validation errors and, finally, aggregating the chosen weak learners. In addition to its superior prediction performance, mRaSE also provides a model-free feature ranking depending on the given base classifier. An iterative version of mRaSE is also developed to further improve the performance. A model-free extension is pursued on the iterative version, leading to the so-called Super mRaSE, which accepts a collection of base classifiers as input to the algorithm. We show the proposed algorithms compared favorably with the state-of-the-art classification algorithm including random forest and deep neural network, via extensive simulation studies and two real data applications. The new algorithms are implemented in an updated version of the R package RaSEn.

Bag of Feature-Based Ensemble Subspace KNN Classifier in Muscle Ultrasound Diagnosis of Diabetic Peripheral Neuropathy

Muscle ultrasound quantification is a valuable complementary diagnostic tool for diabetic peripheral neuropathy (DPN), enhancing physicians’ diagnostic capabilities. Quantitative assessment is generally regarded as more reliable and sensitive than visual evaluation, which often necessitates specialized expertise. This work develops a computer-aided diagnostic (CAD) system based on muscle ultrasound that integrates the bag of features (BOF) and an ensemble subspace k-nearest neighbor (KNN) algorithm for DPN detection. The BOF creates a histogram of visual word occurrences to represent the muscle ultrasound images and trains an ensemble classifier through cross-validation, determining optimal parameters to improve classification accuracy for the ensemble diagnosis system. The dataset includes ultrasound images of six muscles from 53 subjects, consisting of 27 control and 26 patient cases. An empirical analysis was conducted for each binary classifier based on muscle type to select the best vocabulary tree properties or K values for BOF. The result indicates that ensemble subspace KNN classification, based on the bag of features, achieved an accuracy of 97.23%. CAD systems can effectively diagnose muscle pathology, thereby addressing limitations and identifying issues in individuals with diabetes. This research underscores muscle ultrasound as a promising diagnostic tool to aid physicians in making accurate diagnoses, streamlining workflow, and uncovering muscle-related complications in DPN patients.

Random subspace ensemble-based detection of false data injection attacks in automatic generation control systems

Automatic Generation Control (AGC) systems in smart grids are increasingly vulnerable to cyber-attacks, particularly False Data Injection (FDI) attacks, due to their reliance on information and communication technologies. These vulnerabilities pose significant threats to the reliable operation of power systems. To address this challenge, this research paper introduces the machine learning (ML) based cyberattack detection technique designed to identify FDI attacks with the highest accuracy proficiently. The study involves a comprehensive analysis of three features: the original discrete signal feature, the cycle-to-cycle-based feature, and the sample-to-sample-based feature. These features are utilized for detecting FDI attacks and distinguishing them from normal load variations. The research meticulously collects data by simulating diverse FDI attacks, including step attacks, pulse attacks, random attacks, and normal load variation cases on an AGC power system. Four ML classifiers are selected and compared for the classification task. The simulation results reveal that the sample-to-sample-based feature proves highly effective in distinguishing FDI attacks compared to the original signal and cycle-to-cycle-based features. Notably, the results indicate that the random subspace ensemble (RaSE) classifier, utilizing sample-to-sample-based features, effectively identifies and classifies all normal and FDI attacks. This research provides valuable insights into the potential of ML techniques for enhancing FDI attack detection in the AGC of power systems. It provides a potential pathway for overcoming the limitations associated with traditional model-based FDI detection methods.

Prediction of air compressor faults with feature fusion and machine learning

Air compressors are critical for many industries, but early detection of faults is crucial for keeping them running smoothly and minimizing maintenance costs. This contribution investigates the use of predictive machine learning models and feature fusion to diagnose faults in single-acting, single-stage reciprocating air compressors. Vibration signals acquired under healthy and different faulty conditions (inlet valve fluttering, outlet valve fluttering, inlet-outlet valve fluttering, and check valve fault) serve as the study’s input data. Diverse features including statistical attributes, histogram data, and auto-regressive moving average (ARMA) coefficients are extracted from the vibration signals. To identify the most relevant features, the J48 decision tree algorithm is employed. Five lazy classifiers viz. k-nearest neighbor (kNN), K-star, local kNN, locally weighted learning (LWL), and random subspace ensemble K-nearest neighbors (RseslibKnn) are then used for fault classification, each applied to the individual feature sets. The classifiers achieve commendable accuracy, ranging from 85.33% (K-star and local kNN) to 96.00% (RseslibKnn) for individual features. However, the true innovation lies in feature fusion. Combining the three feature types, statistical, histogram, and ARMA, significantly improves accuracy. When local kNN is used with fused features, the model achieves a remarkable 100% classification accuracy, demonstrating the effectiveness of this approach for reliable fault diagnosis in air compressors.

Machine Learning-Based Classification of Soil Parent Materials Using Elemental Concentration and Vis-NIR Data.

In soil science, the allocation of soil samples to their respective origins holds paramount significance, as it serves as a crucial investigative tool. In recent times, with the increasing use of proximal sensing and advancements in machine-learning techniques, new approaches have accompanied these developments, enhancing the effectiveness of soil utilization in soil science. This study investigates soil classification based on four parent materials. For this purpose, a total of 59 soil samples were collected from 12 profiles and the vicinity of each profile at a depth of 0-30 cm. Surface soil samples were analyzed for elemental concentrations using X-Ray fluorescence (XRF) and inductively coupled plasma-optical emission spectrometry (ICP-OES) and soil spectra using a visible near-infrared (Vis-NIR) spectrometer. Soil samples collected from soil profiles (12 soil samples) and surface (47 soil samples) were used to classify parent materials using machine learning-based algorithms such as Support Vector Machine (SVM), Ensemble Subspace k-Near Neighbor (ESKNN), and Ensemble Bagged Trees (EBTs). Additionally, as a validation of the classification techniques, the dataset was subjected to five-fold cross-validation and independent sample set splitting (80% calibration and 20% validation). Evaluation metrics such as accuracy, F score, and G mean were used to evaluate prediction performance. Depending on the dataset and algorithm used, the classification success rates varied between 70% and 100%. Overall, the ESKNN (99%) produced better results than other classification methods. Additionally, Relief algorithms were employed to identify key variables for each dataset (ICP-OES: CaO, Fe2O3, Al2O3, MgO, and MnO; XRF: SiO2, CaO, Fe2O3, Al2O, and MnO; Vis-NIR: 567, 571, 572, 573, and 574 nm). Subsequent soil reclassification using these reduced variables revealed reduced accuracies using Vis-NIR data, with ESKNN still yielding the best results.

COVID-19 Mental Health Impact Analysis using Ensemble-based Classifier

Introduction In the 21st century, human community witnessed a range of biological crises resulting in long-term consequences like loss of life, economic decline, trauma and social disruptions. COVID -19, named the SARs-CoV-2 virus by United Nations, was a similar outbreak in China in the year 2019, which later spread across the world. During the pandemic, as part of preventive measures, the government authorities introduced SOP (standard operating procedures) measures such as social distancing, lockdown, quarantining and closure of educational institutions imposing a great impact on mental health and well-being of humans, especially among the youth. Materials and Methods A study was performed on a public dataset containing survey records collected from 1182 students of different educational institutions. The survey data was based on age, region of residence, time spent online and health fitness. The method used in the proposed work is a classifier model based on an ensemble of decision trees called random forest to predict the consequences of online learning on student’s health. The optimum and promising features are selected by using Recursive feature elimination (RFE) method. Results Our findings reveal a notable enhancement in predicting human health during a pandemic, as indicated by a significant increase in validation accuracy based on confusion for various classifiers. Experimental validation of the developed classifier model is done through the confusion matrix and receiver operating characteristic (ROC) curve. Further, performance metrics such as accuracy, precision, recall, F1-score, specificity, and error rate were employed. The experimental results established the superiority of the proposed ensemble subspace discriminant classifier compared to traditional classifiers. Discussions The RFE feature selection method used in the proposed work helps to select the optimum features as well as more informative features. Moreover, the method employed hyper parameter tuning method to enhance the performance of the classifier model. Conclusion This study highlights the importance of taking care of the emotional and physical health of humans during any pandemic. Furthermore, our approach possesses the capacity to significantly influence the field of predicting health, facilitating the development of more effective and advanced prediction strategies in the future.

Random subspace ensemble for directly classifying high-dimensional incomplete data

Random subspace ensemble for directly classifying high-dimensional incomplete data

Detection of cardiac abnormalities from 12-lead ecg using complex wavelet sub-band features

Aim of the study. This research endeavours to optimize cardiac anomaly detection by introducing a method focused on selecting the most effective Daubechis wavelet families. The principal aim is to differentiate between cardiac states that are normal and abnormal by utilizing longer electrocardiogram (ECG) signal events based on the Apnea ECG dataset. Apnea ECG is often used to detect sleep apnea, a sleep disorder characterized by repeated interruptions in breathing during sleep. By using machine learning methods, such as Principal Component Analysis (PCA) and different classifiers, the goal is to improve the precision of cardiac irregularity identification. Used method. To extract important statistical and sub-band information from lengthy ECG signal episodes, the study uses a novel method that combines discrete wavelet transform with Principal Component Analysis (PCA) for dimension reduction. The methodology focuses on successfully categorizing ECG signals by utilizing several classifiers, including multilayer perceptron (MLP) neural network, Ensemble Subspace K-Nearest Neighbour(KNN), and Ensemble Bagged Trees, together with varied Daubechis wavelet families (db2, db3, db4, db5, db6). Brief Description of Results. The results emphasize the importance of the chosen Daubechis wavelet family, db5, and its superiority in ECG representation. The method distinguishes normal and abnormal ECG signals well on the Physionet Apnea ECG database. The Neural Network-based method accurately recognizes 100% of healthy signals and 97.8% of problematic ones with 98.6% accuracy. Findings. The Ensemble Subspace K-Nearest Neighbour (KNN) and Ensemble Bagged Trees methods got 87.1% accuracy and 0.89 and 0.87 AOC curve values on this dataset, showing that the method works. Precision values of 0.96, 0.86, and 0.86 for MLP Neural Network, KNN Subspace, and Ensemble Bagged Trees confirm their robustness. These findings suggest wavelet families and machine learning can improve cardiac abnormality detection and categorization.

Proficiency evaluation of shape and WPT radiomics based on machine learning for CT lung cancer prognosis

BackgroundLung cancer is a fatal disease which has high occurrence and mortality rates, worldwide. Computed tomography imaging is being widely used by clinicians for detection of lung cancer. Radiomics extracted from medical images together with machine learning platform has enabled automated lung cancer diagnosis. Therefore, this study is proposed with the aim to efficiently apply radiomics and ML techniques to classify pulmonary nodules in CT images. Lung Image Data Consortium is utilized which contains 1018 CT lung cancer cases.ResultsRadiomics are extracted using Shape, Gray Level Co-occurrence Method, Gray Level Difference Method, and Gray Level Run Length Matrix along with Wavelet Packet Transform. To select a relevant set of features two techniques, Analysis of variance and Chi-square test, are applied. The classification of nodule into benign or malignant is evaluated by using state-of-art models: Support vector machine, Decision Trees, Ensemble Trees (BOCET, BACET, RUSBOCET), Ensemble Subspace KNN and Ensemble Subspace Discriminant. The results show that, BACET gives best AUROC (92.9%), MGSVM gives best accuracy (90.4%), FGSVM yields the best sensitivity (97.8%), MGSVM gives best precision (94.1%) and RUSBOCET gives best specificity (84%).ConclusionsThe results show that the proposed methodology can be successfully used for the classification of pulmonary nodules based on CT images. The outcome thus can help clinicians to reach better decision, treatments and early diagnosis.

A novel approach to recognition of Alzheimer's and Parkinson's diseases: random subspace ensemble classifier based on deep hybrid features with a super-resolution image.

Artificial intelligence technologies have great potential in classifying neurodegenerative diseases such as Alzheimer's and Parkinson's. These technologies can aid in early diagnosis, enhance classification accuracy, and improve patient access to appropriate treatments. For this purpose, we focused on AI-based auto-diagnosis of Alzheimer's disease, Parkinson's disease, and healthy MRI images. In the current study, a deep hybrid network based on an ensemble classifier and convolutional neural network was designed. First, a very deep super-resolution neural network was adapted to improve the resolution of MRI images. Low and high-level features were extracted from the images processed with the hybrid deep convolutional neural network. Finally, these deep features are given as input to the k-nearest neighbor (KNN)-based random subspace ensemble classifier. A 3-class dataset containing publicly available MRI images was utilized to test the proposed architecture. In experimental works, the proposed model produced 99.11% accuracy, 98.75% sensitivity, 99.54% specificity, 98.65% precision, and 98.70% F1-score performance values. The results indicate that our AI system has the potential to provide valuable diagnostic assistance in clinical settings.

Smart polarization and spectroscopic holography for real-time microplastics identification

Optical microscopy technologies as prominent imaging methods can offer rapid, non-destructive, non-invasive detection, quantification, and characterization of tiny particles. However, optical systems generally incorporate spectroscopy and chromatography for precise material determination, which are usually time-consuming and labor-intensive. Here, we design a polarization and spectroscopic holography to automatically analyze the molecular structure and composition, namely smart polarization and spectroscopic holography (SPLASH). This smart approach improves the evaluation performance by integrating multi-dimensional features, thereby enabling highly accurate and efficient identification. It simultaneously captures the polarization states-related, holographic, and texture features as spectroscopy, without the physical implementation of a spectroscopic system. By leveraging a Stokes polarization mask (SPM), SPLASH achieves simultaneous imaging of four polarization states. Its effectiveness has been demonstrated in the application of microplastics (MP) identification. With machine learning methods, such as ensemble subspace discriminant classifier, k-nearest neighbors classifier, and support vector machine, SPLASH depicts MPs with anisotropy, interference fringes, refractive index, and morphological characteristics and performs explicit discrimination with over 0.8 in value of area under the curve and less than 0.05 variance. This technique is a promising tool for addressing the increasing public concerning issues in MP pollution assessment, MP source identification, and long-term water pollution monitoring.

Improved Contraction-Expansion Subspace Ensemble for High-Dimensional Imbalanced Data Classification

Improved Contraction-Expansion Subspace Ensemble for High-Dimensional Imbalanced Data Classification

Experimentally investigated machine learning based MPPT for PV panel systems

This manuscript uses a supervised-based machine learning algorithm to predict the maximum power point in a PV system. The PV panel has been integrated with a boost converter. The input parameters are irradiance, temperature, PV current, PV voltage, proportional–integral (PI) and Power value. Sixty thousand data have been collected using MATLAB Simulink and are applied for modelling. It has been tested on several algorithms with accuracy like, Fine tree (96%), Medium Tree (82.9%), Coarse tree (56.9%), Fine KNN (93.8%), Medium KNN (93%), Coarse KNN (90.4%), Cosine KNN (92.9%), Cubic KNN(92.6), Weighted KNN (94.3%), Ensemble Boosted Trees (94.6%), Ensemble Bagged Trees (98.1%) and Ensemble Subspace KNN (97%). The model with better accuracy is used to track the MPP (Maximum Power Point). The system has been studied using a confusion matrix, parallel coordinates plots, scattering plots and receiver operator characteristics (ROC) curve. The proposed algorithm has been tested on a hardware prototype where data have been collected using the KG045 voltage sensor and ACS712 current sensor. The ML-based MPPT is configured in MATLAB and then tested on a hardware prototype using a PV panel under varying power conditions. The system has been tested at different temperatures like 28°C, 39°C, 25°C, 32°C and 36°C. The model has been successfully tested on hardware as well as software results.

Decision support framework for predicting rate of gait recovery with optimized treatment planning

Rate of Recovery during the rehabilitation procedure is not effectively evaluated due to existing limitations of measurement tools and large human variability.The conventional way to treat lower-limb injuries is by conducting a physician-guided rehabilitation process that could take several weeks or months. But the process of estimating the rate of recovery is entirely based on the expertise of a therapist. Moreover, it remains unclear to a large extent about the factors have contributed to the success of treatment, the most effective rehabilitation duration, and recovery progression rate. To address these limitations, a random subspace ensemble k-nearest neighbor (RSEnkNN) model is proposed to predict the rehabilitation duration of an individual after initial baseline assessment of gait trajectories. The model is trained using an open-source dataset comprising 211 healthy and 2084 patients with functional gait disorders.The proposed model is able to predict rehabilitation duration with an accuracy of 88–89 % in case of ankle, calcaneus, and hip injury while the success rate of 82 % is achieved for knee disorders. Features computed from ground reaction force, measures of postural steadiness, and bilateral symmetry turn out to be effective in predicting the early, moderate, or late recovery of an individual. The significantly contributing features for each anomaly class are reported using recursive feature elimination (RFE) technique to support clinicians. Thereafter, recovery rate is determined using a novel metric Rate of Gait Recovery (RoGR) index that could be effective for treatment planning and re-scheduling of therapy sessions (if required). This work determined that the most effective rehabilitation period is 2–6 weeks post-surgery for restoration to normal walk. Thus, a prediction tool for strengthening clinical decision-making is proposed to support early rehabilitation.

Application of classification machine learning algorithms for characterizing nutrient transport in a clay plain agricultural watershed

Excess nutrients in surface water and groundwater can lead to water quality deterioration in available water resources. Thus, the classification of nutrient concentrations in water resources has gained significant attention during recent decades. Machine learning (ML) algorithms are considered an efficient tool to describe nutrient loss from agricultural land to surface water and groundwater. Previous studies have applied regression and classification ML algorithms to predict nutrient concentrations in surface water and/or groundwater, or to categorize an output variable using a limited number of input variables. However, there have been no studies that examined the application of different ML classification algorithms in agricultural settings to classify various output variables using a wide range of input variables. In this study, twenty-four ML classification algorithms were implemented on a dataset from three locations within the Upper Parkhill watershed, an agricultural watershed in southern Ontario, Canada. Nutrient concentrations in surface water were classified using geochemical and physical water parameters of surface water and groundwater (e.g., pH), climate and field conditions as the input variables. The performance of these algorithms was evaluated using four evaluation metrics (e.g., classification accuracy) to identify the optimal algorithm for classifying the output variables. Ensemble bagged trees was found to be the optimal ML algorithm for classifying nitrate concentration in surface water (accuracy of 90.9%), while the weighted KNN was the most appropriate algorithm for categorizing the total phosphorus concentration (accuracy of 87%). The ensemble subspace discriminant algorithm gave the highest overall classification accuracy for the concentration of soluble reactive phosphorus and total dissolved phosphorus in surface water with an accuracy of 79.2% and 77.9%, respectively. This study exemplifies that ML algorithms can be used to signify exceedance of recommended concentrations of nutrients in surface waters in agricultural watersheds. Results are useful for decision makers to develop nutrient management strategies.

Geographical origin identification of ginseng using near-infrared spectroscopy coupled with subspace-based ensemble classifiers

Ginseng is a well-known traditional herbal medicine and the ginseng available on the market may not actually be produced in a certain place as claimed. Traditional methods of identifying the geographical origin of Ginseng are subjective, time-consuming or destructive. A more efficient approach is desirable. The feasibility of combining near-infrared (NIR) spectroscopy with ensemble learning for discriminating ginseng producing area was explored. A total of 270 samples were collected and evenly partitioned into the training and test sets. Random subspace ensemble (RSE) that uses linear discriminant classifier (LDA) as weak learner (abbreviated RSE-LDA) was used to construct predictive models. Two parameters including the size of subspace and the number of learners in ensemble were optimized. Classic partial least algorithm (PLS) was applied to build the reference model. The sensitivity, specificity, and total accuracy of final RSE-LDA and PLS models were 97.8 %, 100 %, 99.3 %, and 93.3 %, 96.7 %, 95.6 %, respectively. In order to study the impact of training set composition on the results, the samples were randomly divided 200 times and the algorithm was run repeatedly to statistically analyze the sensitivity and specificity on the test set. Similar results were obtained. The effect of training set size was also investigated. It indicates that the combination of NIR spectroscopy with the RSE algorithm is a potential tool of discriminating the origin of Ginseng.

Development of electronic nose for detection of micro-mechanical damages in strawberries.

A self-developed portable electronic nose and its classification model were designed to detect and differentiate minor mechanical damage to strawberries. The electronic nose utilises four metal oxide sensors and four electrochemical sensors specifically calibrated for strawberry detection. The selected strawberries were subjected to simulated damage using an H2Q-C air bath oscillator at varying speeds and then stored at 4°C to mimic real-life mechanical damage scenarios. Multiple feature extraction methods have been proposed and combined with Principal Component Analysis (PCA) dimensionality reduction for comparative modelling. Following validation with various models such as SVM, KNN, LDA, naive Bayes, and subspace ensemble, the Grid Search-optimised SVM (GS-SVM) method achieved the highest classification accuracy of 0.84 for assessing the degree of strawberry damage. Additionally, the Feature Extraction ensemble classifier achieved the highest classification accuracy (0.89 in determining the time interval of strawberry damage). This experiment demonstrated the feasibility of the self-developed electronic nose for detecting minor mechanical damage in strawberries.

Statistically significant features improve binary and multiple Motor Imagery task predictions from EEGs.

In recent studies, in the field of Brain-Computer Interface (BCI), researchers have focused on Motor Imagery tasks. Motor Imagery-based electroencephalogram (EEG) signals provide the interaction and communication between the paralyzed patients and the outside world for moving and controlling external devices such as wheelchair and moving cursors. However, current approaches in the Motor Imagery-BCI system design require effective feature extraction methods and classification algorithms to acquire discriminative features from EEG signals due to the non-linear and non-stationary structure of EEG signals. This study investigates the effect of statistical significance-based feature selection on binary and multi-class Motor Imagery EEG signal classifications. In the feature extraction process performed 24 different time-domain features, 15 different frequency-domain features which are energy, variance, and entropy of Fourier transform within five EEG frequency subbands, 15 different time-frequency domain features which are energy, variance, and entropy of Wavelet transform based on five EEG frequency subbands, and 4 different Poincare plot-based non-linear parameters are extracted from each EEG channel. A total of 1,364 Motor Imagery EEG features are supplied from 22 channel EEG signals for each input EEG data. In the statistical significance-based feature selection process, the best one among all possible combinations of these features is tried to be determined using the independent t-test and one-way analysis of variance (ANOVA) test on binary and multi-class Motor Imagery EEG signal classifications, respectively. The whole extracted feature set and the feature set that contain statistically significant features only are classified in this study. We implemented 6 and 7 different classifiers in multi-class and binary (two-class) classification tasks, respectively. The classification process is evaluated using the five-fold cross-validation method, and each classification algorithm is tested 10 times. These repeated tests provide to check the repeatability of the results. The maximum of 61.86 and 47.36% for the two-class and four-class scenarios, respectively, are obtained with Ensemble Subspace Discriminant among all these classifiers using selected features including only statistically significant features. The results reveal that the introduced statistical significance-based feature selection approach improves the classifier performances by achieving higher classifier performances with fewer relevant components in Motor Imagery task classification. In conclusion, the main contribution of the presented study is two-fold evaluation of non-linear parameters as an alternative to the commonly used features and the prediction of multiple Motor Imagery tasks using statistically significant features.

ENSEMBLE LEARNING APPROACHES FOR CLASSIFICATION WITH HIGH-DIMENSIONAL DATA

Classification with high-dimensional data is a significant challenge in machine learning because the abundance of features in high-dimensional data makes it difficult to identify meaningful patterns, which leads to overfitting and reduced classification performance. Moreover, the computational cost of processing high-dimensional data is often prohibitively expensive, requiring specialized hardware or optimized algorithms. Ensemble learning is a powerful machine learning technique that combines multiple models to improve classification accuracy. By aggregating the predictions of multiple models, ensemble learning can reduce overfitting, increase robustness, and improve performance on a wide range of real-world classification problems. Ensemble learning is effective for classification with high-dimensional data because it can combine multiple models to mitigate the effects of the curse of dimensionality, reduce overfitting, and enhance generalization performance. By using different learning algorithms or subsets of features, ensemble learning can improve the diversity of the models, leading to better overall performance on high-dimensional data. This paper proposes two hybrid ensemble machine learning approaches that integrate random subspace ensemble with bagging and boosting to enhance classification performance with high-dimensional data. Experimental results demonstrate that these methods significantly improve classification accuracy with highdimensional data.

Recognition of maize seed varieties based on hyperspectral imaging technology and integrated learning algorithms.

Purity is an important factor of maize seed quality that affects yield, and traditional seed purity identification methods are costly or time-consuming. To achieve rapid and accurate detection of the purity of maize seeds, a method for identifying maize seed varieties, using random subspace integrated learning and hyperspectral imaging technology, was proposed. A hyperspectral image of the maize seed endosperm was collected to obtain a spectral image cube with a wavelength range of 400∼1,000 nm. Methods, including Standard Normal Variate (SNV), multiplicative Scatter Correction (MSC), and Savitzky-Golay First Derivative (SG1) were used to preprocess raw spectral data. Iteratively retains informative variables (IRIV) and competitive adaptive reweighted sampling (CARS) were used to reduce the dimensions of the spectral data. A recognition model of maize seed varieties was established using k-nearest neighbor (KNN), support vector machine (SVM), line discrimination analysis (LDA) and decision tree (DT). Among the preprocessing methods, MSC has the best effect. Among the dimensionality reduction methods, IRIV has the best performance. Among the base classifiers, LDA had the highest precision. To improve the precision in identifying maize seed varieties, LDA was used as the base classifier to establish a random subspace ensemble learning (RSEL) model. Using MSC-IRIV-RSEL, precision increased from 0.9333 to 0.9556, and the Kappa coefficient increased from 0.9174 to 0.9457. This study shows that the method based on hyperspectral imaging technology combined with subspace ensemble learning algorithm is a new method for maize seed purity recognition.