Two hidden layer neural network-based rotation forest ensemble for hyperspectral image classification

In this paper, we propose a new spectral-spatial classification strategy to enhance the classification performances obtained on hyperspectral images by integrating rotation forests and Markov random fields (MRFs). First, rotation forests are performed to obtain the class probabilities based on spectral information. Rotation forests create diverse base learners using feature extraction and subset features. The feature set is randomly divided into several disjoint subsets; then, feature extraction is performed separately on each subset, and a new set of linear extracted features is obtained. The base learner is trained with this set. An ensemble of classifiers is constructed by repeating these steps several times. The weak classifier of hyperspectral data, classification and regression tree (CART), is selected as the base classifier because it is unstable, fast, and sensitive to rotations of the axes. In this case, small changes in the training data of CART lead to a large change in the results, generating high diversity within the ensemble. Four feature extraction methods, including principal component analysis (PCA), neighborhood preserving embedding (NPE), linear local tangent space alignment (LLTSA), and linearity preserving projection (LPP), are used in rotation forests. Second, spatial contextual information, which is modeled by MRF prior, is used to refine the classification results obtained from the rotation forests by solving a maximum a posteriori problem using the α-expansion graph cuts optimization method. Experimental results, conducted on three hyperspectral data with different resolutions and different contexts, reveal that rotation forest ensembles are competitive with other strong supervised classification methods, such as support vector machines. Rotation forests with local feature extraction methods, including NPE, LLTSA, and LPP, can lead to higher classification accuracies than that achieved by PCA. With the help of MRF, the proposed algorithms can improve the classification accuracies significantly, confirming the importance of spatial contextual information in hyperspectral spectral-spatial classification.

Classifier ensemble construction with rotation forest to improve medical diagnosis performance of machine learning algorithms

Exploring sex classification from earprints - A comparison of supervised machine learning algorithms and conventional linear discriminant analysis.

Often, previous knowledge about the classes on the ground may assist in the improvement of a land cover classification from remote sensing data. There are many ways in which the previous information in the form of a priori probabilities can be included in the training stage of a supervised classification process. The inclusion of a priori probabilities may be useful to classify the images dominated by mixed pixels. In this paper, an approach to incorporate a priori probabilities in back propagation neural network (BPNN) algorithm, by way of replicating the training data (consisting of pure pixels) of a class according to its proportional area coverage has been implemented. By doing this, the abundant classes are assigned more weights than the other classes in the image. The results show a significant improvement in classification accuracy by 20% over the case when the a priori probabilities are not included. However, the major limitation of this approach is that it depends on the use of pure pixels, which may often be hard to find in images dominated by mixed pixels. We therefore suggest an alternative approach that incorporates mixed pixels in the training stage of BPNN algorithm. The results from this approach also reflect a significant improvement in classification accuracy by 14%. Further, both the approaches produce significantly higher accuracy than the most widely used maximum likelihood classifier (MLC). However, the second approach, which does not depend on identification of pure pixels in the image and their replication, appears more attractive to produce meaningful and accurate land cover classification from remote sensing data.

Magnetic Resonance Imaging plays a vital part in diagnosis of mutant cells in the endometrial layer of women reproductive system. This Endometrial carcinoma (EC) is one among the type of uterine cancer acts as a major challenge for the medical practitioners for early diagnosis and classification. This study explores advanced imaging techniques and artificial intelligence (AI) for improved EC identification. The Methodology incudes, an approach of extracting texture features using Local Binary Patterns (LBP), Histogram of Oriented Gradients (HOG), Gray Level Co-occurrence Matrix (GLCM), and Gray Level Run Length Matrix (GLRLM) from the image data. These features are fused using a hybrid approach to capture complementary information. Machine learning classifiers including Random Forest (RF), Radial Basis Function (RBF), Artificial Neural Network (ANN), Support Vector Machine (SVM), Extreme Learning Machine (ELM), and Adaptive Neuro-Fuzzy Inference System (ANFIS) are trained and evaluated. Results demonstrate significant improvements in classification accuracy, with the hybrid feature extraction method achieving significant accuracy. Explainable AI (XAI) techniques are employed to interpret and visualize classifier decisions, providing details into the discriminative features contributing to EC classification.. The findings support the potential of integrating advanced imaging and machine learning, facilitated by XAI, for precise EC diagnosis and therapeutic planning.

Document forgery has increased enormously due to the progression of information technology and image processing software. Critical documents are protected using watermarks or signatures, i.e., active approach. Other documents need passive approach for document forensics. Most of the passive techniques aim to detect and fix the source of the printed document. Other techniques look for the irregularities present in the document. This paper aims to fix the document source printer using passive approach. Hand-crafted features based on key printer noise features (KPNF), speeded up robust features (SURF) and oriented FAST rotated and BRIEF (ORB) are used. Then, feature-based classifiers are implemented using K-NN, decision tree, random forest and majority voting. The document classifier proposed model can efficiently classify the questioned documents to their respective printer class. Further, adaptive boosting and bootstrap aggregating methodologies are used for the improvement in classification accuracy. The proposed model has achieved the best accuracy of 95.1% using a combination of KPNF + ORB + SURF with random forest classifier and adaptive boosting methodology.

Chronic kidney disease (CKD) involves numerous variables, but only a few significantly impact the classification task. The statistically equivalent signature (SES) method, inspired by constraint-based learning of Bayesian networks, is employed to identify essential features in CKD. Unlike conventional feature selection methods, which typically focus on a single set of features with the highest predictive potential, the SES method can identify multiple predictive feature subsets with similar performance. However, most feature selection (FS) classifiers perform suboptimally with strongly correlated data. The FS approach faces challenges in identifying crucial features and selecting the most effective classifier, particularly in high-dimensional data. This study proposes using the Least Absolute Shrinkage and Selection Operator (LASSO) in conjunction with the SES method for feature selection in CKD identification. Following this, an ensemble deep-learning model combining long short-term memory (LSTM) and gated recurrent unit (GRU) networks is proposed for CKD classification. The features selected by the hybrid feature selection method are fed into the ensemble deep-learning model. The model’s performance is evaluated using accuracy, precision, recall, and F1 score metrics. The experimental results are compared with individual classifiers, including decision tree (DT), Random Forest (RF), logistic regression (LR), and support vector machine (SVM). The findings indicate a 2% improvement in classification accuracy when using the proposed hybrid feature selection method combined with the LSTM and GRU ensemble deep-learning model. Further analysis reveals that certain features, such as HEMO, POT, bacteria, and coronary artery disease, contribute minimally to the classification task. Future research could explore additional feature selection methods, including dynamic feature selection that adapts to evolving datasets and incorporates clinical knowledge to enhance CKD classification accuracy further.

Background/Objectives: Recent studies emphasized on using ensemble models over single ones to solve credit scoring problems. The objective of this study is to build a heterogeneous ensemble classifier model with an improved classification accuracy. Methods: This study focuses on developing a heterogeneous ensemble classifier using Logistic Regression, K-nearest neighbor, Decision tree, Random Forest, Naïve Base and Support vector machine as base classifiers and Random Forest, Logistic Regression and Support vector machine as meta-classifiers. The proposed model is built using these six base classifiers for ensemble aggregation. A feature selection algorithm based on the random forest technique is used for selecting the best features. A stacking and voting method are used for building ensemble model. Findings: The ensemble classifier gives superior predictive performance than single classifiers SVM, DT, RF, NB, KNN and LR with an accuracy of 91.56% for Australian dataset and 84.35% for German dataset. Novelty: The proposed model uses stacking and majority voting method for ensemble classification. Initially, stacking is applied to the base classifiers. This is done in two levels. First the training dataset is split into 10 folds for cross validation. The output of each classifier is taken, and the dataset is updated with the meta-features. In the second level, three meta-classifiers (MC), namely LR, SVM and RF are used. Majority voting is applied to the output of these meta-classifiers for the prediction. Keywords: Credit scoring; ensemble model; SVM; DT; RF; NB; KNN; LR

Ensemble classification based on generalized additive models

Introduction: In order to assess how well conventional and hybrid pitch detection techniques perform in speech processing applications, a comparative analysis of the two types of methods is conducted. Method: A proposed hybrid approach, Proposed PEF+CEP, is examined alongside five traditional algorithms, namely Normalized Correlation Function (NCF), Pitch Estimation Filter (PEF), Log- Harmonic Summation (LHS), Summation of Residual Harmonics (SRH) and Cepstrum Pitch Determination (CEP). The effectiveness is evaluated using performance metrics like accuracy, specificity, sensitivity, and Gross Pitch Error (GPE). Results and Discussion: Our findings show that the accuracy and specificity of the traditional methods are impressive; the accuracy and sensitivity of the suggested hybrid method surpass their performance, with an astounding 98.8% accuracy and 99.2% sensitivity. Conclusion: Furthermore, the Proposed PEF+CEP method is a promising solution for accurate and dependable pitch detection in speech processing applications because it strikes a strong balance between computational efficiency and robustness. These results open up new avenues for research in the field of speech processing and demonstrate the potential of hybrid approaches.

Capturing images in thousands of contiguous spectral bands has been made simpler with the emergence of technology in the field of hyperspectral remote sensing. Despite of these huge data available for analysis, Hyperspectral images (HSI) face many challenges due to high dimensionality, noise, spectral mixing and computational complexity. Several preprocessing methods can be used to overcome the above mentioned issues. In this paper, an enhancement technique using 2D-Empirical Wavelet Transform (EWT) is used as a preprocessing step for the HSI reconstruction prior to sparsity based classification (Subspace Pursuit and Orthogonal Matching Pursuit). The effectiveness of the proposed method is proved by comparing the classification results obtained with and without applying preprocessing. Experimental analysis shows a significant improvement in the classification accuracies i.e., for 40 $$\%$$ of training samples, OMP shows an improvement in overall classification accuracy from 66.12 $$\%$$ to 93.20 $$\%$$ and SP shows an improvement from 66.36 $$\%$$ to 92.74 $$\%$$ .

.The aim of this work is to develop an effective brain–computer interface (BCI) method based on functional near-infrared spectroscopy (fNIRS). In order to improve the performance of the BCI system in terms of accuracy, the ability to discriminate features from input signals and proper classification are desired. Previous studies have mainly extracted features from the signal manually, but proper features need to be selected carefully. To avoid performance degradation caused by manual feature selection, we applied convolutional neural networks (CNNs) as the automatic feature extractor and classifier for fNIRS-based BCI. In this study, the hemodynamic responses evoked by performing rest, right-, and left-hand motor execution tasks were measured on eight healthy subjects to compare performances. Our CNN-based method provided improvements in classification accuracy over conventional methods employing the most commonly used features of mean, peak, slope, variance, kurtosis, and skewness, classified by support vector machine (SVM) and artificial neural network (ANN). Specifically, up to 6.49% and 3.33% improvement in classification accuracy was achieved by CNN compared with SVM and ANN, respectively.

Application of neural machine interface in individuals with chronic hemiparetic stroke is regarded as a great challenge, especially for classification of the hand opening and grasping during a functional upper extremity movement such as reach-to-grasp. The overall accuracy of classifying hand movements, while actively lifting the paretic arm, is subject to a significant reduction compared to the accuracy when the arm is fully supported. Such a reduction is believed to be due to the expression of flexion synergy, which couples shoulder abduction (SABD) with elbow/wrist and finger flexion, and is common in up to 60% of the stroke population. Little research has been done to develop methods to reduce the impact of flexion synergy on the classification of hand opening and grasping. In this study, we proposed a novel approach to classify hand opening and grasping in the context of the flexion synergy using a wavelet coherence-based filter. We first identified the frequency ranges where the coherence between the SABD muscle and wrist/finger flexion muscles is significant in each participant, and then removed the synergy-induced electromyogram (EMG) component with a subject-specific and muscle-specific coherence-based filter. The new approach was tested in 21 stroke individuals with moderate to severe motor impairments. Employing the filter, 14 participants gained improvement in classification accuracy with a range of 0.1 to 14%, while four showed 0.3 to 1.2% reduction. The remaining three participants were excluded from comparison due to the lack of significant coherence, thus no filters were applied. The improvement in classification accuracy is significant (p = 0.017) when the SABD loading equals 50% of the maximal torque. Our findings suggest that the coherence-based filters can reduce the impact of flexion synergy by removing the synergy-induced EMG component and have the potential to improve the overall classification accuracy of hand movements in individuals with poststroke flexion synergy.

Observation of broadband acoustic scatter from fish at multiple angles has the potential to offer advantages for remote classification in cases where the species exhibit differences in size and or body shape, and animal orientation is unknown or difficult to estimate. However, the total angular coverage of the observations, available bandwidth, and the inter- and intra-species variability in size can significantly influence classification accuracy. These parameters are investigated using laboratory data collected from ten different fish species using a linear array of receivers and a single transmitter with an effective angular coverage of up to 25 degrees with a 3 degree sampling increment. Results indicate that when the species exhibit significant differences in length, even two observations covering only 10 degrees are sufficient to obtain an 80 percent improvement in classification accuracy over a single observation angle. This holds true for a wide range of animal orientations. As inter-species size similarity increases, and intra-species size variability increases, more observations covering a larger range of angles are required to maintain a similar improvement in classification accuracy.

Monitoring riparian vegetation with up-to-date technologies, such as remote sensing and machine learning, is emphasized by their extensive and dynamic nature. This study evaluates the spatiotemporal dynamics of vegetation in the Slovak Danube riparian zone from 2004 to 2022 using a multi-sensor approach (Landsat-5/8 and Sentinel-2). We integrated seasonal vegetation indices, textural, and morphological patterns to enhance Land Cover (LC) classification accuracy. Using Random Forest within a spectral–spatial framework, we achieved notable improvement in classification accuracy. We evaluated ecological processes, spatial errors, misclassification, and the spatial distribution of LC changes within the riparian zone. Our core-area analysis revealed that only 52% of the riparian zone remains stable over time. Crucially, we quantified the impact of spatial misclassifications at class boundaries, finding that edge-related errors account for 0.24% to 2.85% of the detected change. The classification distinguished 1,076 ha of managed plantations and 1,236 ha of natural forest. Overall, the results demonstrated the effectiveness of various feature combinations for classifying different satellite datasets and assessing the temporal evolution of riparian zones in regulated river systems, while highlighting the critical importance of incorporating uncertainty analysis to ensure robust interpretation of detected LC changes.