Integrated Ensemble Strategy for Breast Cancer Detection Using Dimensionality Reduction Technique

Non-negative Matrix Factorization (NMF) and Singular Value Decomposition (SVD) are widely recognized as pivotal dimensionality reduction techniques in the literature, particularly for deep learning applications involving large and high-dimensional datasets like SEM images. This study systematically evaluates the impact of SVD and NMF on the performance, efficiency, and energy consumption of four deep learning architectures: GoogleNet, AlexNet, ResNet, and SqueezeNet. By applying these techniques to reduce dataset dimensions, we observed that SVD excelled in computational efficiency, achieving up to 35% faster processing times compared to raw datasets. NMF, on the other hand, provided superior feature interpretability, which proved beneficial for tasks requiring meaningful pattern extraction. Energy consumption analysis revealed that SVD led to a 28% reduction in computational energy cost on average, making it a practical choice for resource-constrained environments. Among the evaluated models, ResNet consistently delivered the highest classification accuracy after dimensionality reduction, showing an improvement of 4-6% over models trained on non-reduced data. These findings underscore the critical role of dimensionality reduction in enhancing the scalability, energy efficiency, and classification accuracy of deep learning models, offering valuable insights for optimizing high-dimensional data applications in both academic and industrial contexts.

Worldwide breast cancer incidence has increased by more than twenty percent in the past decade. It is also known that in that time, mortality due to the affliction has increased by fourteen percent. Using optical-based diagnostic techniques, such as Raman spectroscopy, has been explored in order to increase diagnostic accuracy in a more objective way along with significantly decreasing diagnostic wait-times. In this study, Raman spectroscopy with 532-nm excitation was used in order to incite resonance effects to enhance Stokes Raman scattering from unique biomolecular vibrational modes. Seventy-two Raman spectra (41 cancerous, 31 normal) were collected from nine breast tissue samples by performing a ten-spectra average using a 500-ms acquisition time at each acquisition location. The raw spectral data was subsequently prepared for analysis with background correction and normalization. The spectral data in the Raman Shift range of 750- 2000 cm-1 was used for analysis since the detector has highest sensitivity around in this range. The matrix decomposition technique nonnegative matrix factorization (NMF) was then performed on this processed data. The resulting leave-oneout cross-validation using two selective feature components resulted in sensitivity, specificity and accuracy of 92.6%, 100% and 96.0% respectively. The performance of NMF was also compared to that using principal component analysis (PCA), and NMF was shown be to be superior to PCA in this study. This study shows that coupling the resonance Raman spectroscopy technique with subsequent NMF decomposition method shows potential for high characterization accuracy in breast cancer detection.

Mass spectrometry imaging (MSI) is a powerful scientific tool for understanding the spatial distribution of biochemical compounds in tissue structures. In this paper, we introduce three novel approaches in MSI data processing to perform the tasks of data augmentation, feature ranking, and image registration. We use these approaches in conjunction with non-negative matrix factorization (NMF) to resolve two of the biggest challenges in MSI data analysis, namely: 1) the large file sizes and associated computational resource requirements and 2) the complexity of interpreting the very high dimensional raw spectral data. There are many dimensionality reduction techniques that address the first challenge but do not necessarily result in readily interpretable features, leaving the second challenge unaddressed. We demonstrate that NMF is an effective dimensionality reduction algorithm that reduces the size of MSI datasets by three orders of magnitude with limited loss of information, yielding spatial and spectral components with meaningful correlation to tissue structure that may be used directly for subsequent data analysis without the need for additional clustering steps. This analysis is demonstrated on an MSI dataset from female Sprague-Dawley rats for an animal model of comorbid visceral pain hypersensitivity (CPH). We find that high-dimensional MSI data (∼ 100,000 ions per pixel) can be reduced to 20 spectral NMF components with < 20% loss in reconstruction accuracy. The resulting spatial NMF components are reproducible and correlate well with H&E-stained tissue images. These components may also be used to generate images with enhanced specificity for different tissue types. Small patches of NMF data (i.e., 20 spatial NMF components over 20 × 20 pixels) provide an accuracy of ∼ 87% in classifying CPH vs naïve control subjects. This paper presents the novel data processing methodologies that were used to produce these results, encompassing novel data processing pipelines for data augmentation to support training for classification, ranking of features according to their contribution to classification, and image registration to enhance tissue-specific imaging.

Classification of human hand movements based on EMG signals using nonlinear dimensionality reduction and data fusion techniques

&lt;p&gt;Breast cancer is ranked as a significant cause of mortality among females globally. Its complex nature poses principal challenges for physicians and researchers for rapid diagnosis and prognosis. Hence, machine learning algorithms are employed to forecast and identify diseases. This study discusses the comparative analysis of seven machine learning models, e.g., logistic regression (LR), support vector machine (SVM), k-nearest neighbor classifier (KNN), decision tree classifier (DT), random forest classifier (RF), Naïve Bayes (NB), and artificial neural network (ANN) to predict breast cancer using Wisconsin breast cancer and breast cancer datasets. In the Wisconsin breast cancer dataset, KNN depicted 99% accuracy, followed by RF (98%), SVM (96%), NB (96%), LR (96%), ANN (93%), and DT (92%). On the contrary, in the breast cancer (BC) dataset, the highest accuracy was achieved by LR at 83%, and the lowest was achieved by DT (65%), which depicted that the numeric dataset WBC has better accuracy than the breast cancer dataset.&lt;/p&gt;

Parkinson's disease (PD) presents a growing global health challenge, with early detection being crucial for effective management and treatment. This study seeks to develop an innovative machine learning (ML) framework for the early detection of PD by integrating advanced techniques for data preprocessing, dimensionality reduction, feature selection, and ensemble classification, aiming to significantly improve detection accuracy and timeliness. The research employs a robust ML pipeline, beginning with data preprocessing using mean imputation, standardization, min-max scaling, and SMOTE (Synthetic Minority Over-sampling Technique) to handle imbalanced data. Dimensionality reduction is achieved through Principal Component Analysis (PCA), while feature selection is performed using SelectKBest coupled with the ANOVA F-test to identify the most relevant features. Four ensemble methods—Random Forest, Gradient Boosting, XGBoost, and Support Vector Machine (SVM)—are evaluated for classification. Among the classifiers tested, the Gradient Boosting model stands out with an impressive accuracy of 0.9487, demonstrating its superior performance in PD detection. Integrating multiple preprocessing, dimensionality reduction, and feature selection techniques proves essential in optimizing model performance, highlighting the importance of a multifaceted approach in handling complex datasets. This research introduces a comprehensive ML framework that combines multiple advanced techniques in a streamlined process, significantly improving the early detection of Parkinson's disease. Ensemble methods, combined with strategic feature selection and data balancing techniques, offer a novel approach that could be applied to other neurodegenerative disorders, expanding its potential impact beyond PD detection.

Dimensionality reduction is essential for subsurface modeling, where vast datasets with millions of measurements pose computational challenges. Advanced hardware and algorithms have enabled automated rock classification, seismic interpretation, and reservoir simulation, yet high-dimensional data remain a bottleneck. Traditional feature selection helps simplify models, but dimensionality reduction techniques are often required for rapid predictions and enhanced interpretability. Inspired by computer vision, where images are compressed into meaningful features, subsurface modeling benefits from encoding techniques that extract latent representations while preserving critical information. This chapter explores popular dimensionality reduction methods, including singular value decomposition (SVD), principal component analysis (PCA), discrete wavelet transform (DWT), dictionary learning (DL), and deep learning-based autoencoders (AE). These techniques optimize storage, reduce computational costs, and improve predictive accuracy and can be applied to complex workflows such as reservoir simulation, history matching, and geologic modeling. By transforming complex geospatial data into lower-dimensional space, they enhance uncertainty quantification and accelerate machine learning workflows. Hence, the chapter provides insights on different dimensionality reduction techniques for subsurface applications, ensuring robust and scalable modeling for energy resource exploration and development.

Dimension reduction techniques, such as singular value decomposition (SVD) and nonnegative matrix factorization (NMF), have been successfully applied in image hashing by retaining the essential features of the original image matrix. However, a concern of great importance in image hashing is that no single solution is optimal and robust against all types of attacks. The contribution of this paper is threefold. First, we introduce a recently proposed dimension reduction technique, referred as Fast Johnson-Lindenstrauss Transform (FJLT), and propose the use of FJLT for image hashing. FJLT shares the low distortion characteristics of a random projection, but requires much lower computational complexity. Secondly, we incorporate Fourier-Mellin transform into FJLT hashing to improve its performance under rotation attacks. Thirdly, we propose a new concept, namely, content-based fingerprint, as an extension of image hashing by combining different hashes. Such a combined approach is capable of tackling all types of attacks and thus can yield a better overall performance in multimedia identification. To demonstrate the superior performance of the proposed schemes, receiver operating characteristics analysis over a large image database and a large class of distortions is performed and compared with the state-of-the-art image hashing using NMF.

We seek to use dimensionality reduction to simplify the difficult task of controlling a lower limb prosthesis. Though many techniques for dimensionality reduction have been described, it is not clear which is the most appropriate for human gait data. In this study, we first compare how Principal Component Analysis (PCA) and an autoencoder on poses (Pose-AE) transform human kinematics data during flat ground and stair walking. Second, we compare the performance of PCA, Pose-AE and a new autoencoder trained on full human movement trajectories (Move-AE) in order to capture the time varying properties of gait. We compare these methods for both movement classification and identifying the individual. These are key capabilities for identifying useful data representations for prosthetic control. We first find that Pose-AE outperforms PCA on dimensionality reduction by achieving a higher Variance Accounted For (VAF) across flat ground walking data, stairs data, and undirected natural movements. We then find in our second task that Move-AE significantly outperforms both PCA and Pose-AE on movement classification and individual identification tasks. This suggests the autoencoder is more suitable than PCA for dimensionality reduction of human gait, and can be used to encode useful representations of entire movements to facilitate prosthetic control tasks.

Distance similarity matrix using ensemble of dimensional data reduction techniques: Vibration and aerocoustic case studies

Non-negative subspace feature representation for few-shot learning in medical imaging

The present work strives to investigate the effect of using dimensionality reduction techniques (DRTs) on breast cancer (BC) classification problem. Primarily, we focused on the following five (DRTs): Auto-Encoders (AE), T-Distributed Stochastic Neighbor Embedding (T- SNE), Recursive Feature Elimination (RFE), Isometric Feature Mapping (Isomap), and Principle Component analysis (PCA). These methods are combined with two famous classifiers that are Support Vector Machine (SVM) and Multilayer perceptron (MLP). They are used for BC classification. Breast Cancer Wisconsin Diagnostic (WDBC) data set was used to validate the experiments of this work. The former was provided by the University of California, Irvine (UCI) machine learning repository. The results demonstrated that combining MLP with the chosen (DRTs) methods increased the classification accuracy for almost all built models by at least 0.7%. In addition, they revealed a decrease in the classification accuracy using SVM as a classifier for almost all built models.KeywordsMachine learningDeep learningDimensionality reductionNeural networksBreast cancer predictionMedical dataset

Unlike in the field of visual scene recognition, where tremendous advances have taken place due to the availability of very large datasets to train deep neural networks, inference from medical images is often hampered by the fact that only small amounts of data may be available. When working with very small dataset problems, of the order of a few hundred items of data, the power of deep learning may still be exploited by using a pre-trained model as a feature extractor and carrying out classic pattern recognition techniques in this feature space, the so-called few-shot learning problem. However, medical images are highly complex and variable, making it difficult for few-shot learning to fully capture and model these features. To address these issues, we focus on the intrinsic characteristics of the data. We find that, in regimes where the dimension of the feature space is comparable to or even larger than the number of images in the data, dimensionality reduction is a necessity and is often achieved by principal component analysis or singular value decomposition (PCA/SVD). In this paper, noting the inappropriateness of using SVD for this setting we explore two alternatives based on discriminant analysis (DA) and non-negative matrix factorization (NMF). Using 14 different datasets spanning 11 distinct disease types we demonstrate that at low dimensions, discriminant subspaces achieve significant improvements over SVD-based subspaces and the original feature space. We also show that at modest dimensions, NMF is a competitive alternative to SVD in this setting. The implementation of the proposed method is accessible via the following link.

Dimensionality reduction techniques are essential in analyzing large 'omics' datasets in biochemistry and molecular biology. Principal component analysis, t-distributed stochastic neighbor embedding, and uniform manifold approximation and projection are commonly used for data visualization. However, these methods can be challenging for students without a strong mathematical background. In this study, intuitive examples were created using COVID-19 data to help students understand the core concepts behind these techniques. In a 4-h practical session, we used these examples to demonstrate dimensionality reduction techniques to 15 postgraduate students from biomedical backgrounds. Using Python and Jupyter notebooks, our goal was to demystify these methods, typically treated as "black boxes", and empower students to generate and interpret their own results. To assess the impact of our approach, we conducted an anonymous survey. The majority of the students agreed that using computers enriched their learning experience (67%) and that Jupyter notebooks were a valuable part of the class (66%). Additionally, 60% of the students reported increased interest in Python, and 40% gained both interest and a better understanding of dimensionality reduction methods. Despite the short duration of the course, 40% of the students reported acquiring research skills necessary in the field. While further analysis of the learning impacts of this approach is needed, we believe that sharing the examples we generated can provide valuable resources for others to use in interactive teaching environments. These examples highlight advantages and limitations of the major dimensionality reduction methods used in modern bioinformatics analysis in an easy-to-understand way.

Mass spectrometry imaging (MSI) has become an important tool for 2D profiling of biological tissues, allowing for the visualization of individual compound distributions in the sample. Based on this information, it is possible to investigate the molecular organization within any particular tissue and detect abnormal regions (such as tumor regions) and many other biologically relevant phenomena. However, the large number of compounds present in the spectra hinders the productive analysis of large MSI datasets when utilizing standard tools. The heterogeneity of samples makes exploratory visualization (a presentation of the general idea of the molecular and structural organization of the inspected tissues) challenging. Here, we explore the application of various dimensionality reduction techniques that have been used extensively in the visualization of hyperspectral images and the MSI data specifically, such as principal component analysis, independent component analysis, non-negative matrix factorization, t-distributed stochastic neighbor embedding, and uniform manifold approximation and projection. Further, we propose a new approach based on a combination of structure preserving visualization with nonlinear manifold embedding of normalized spectral data. This way, we aim to preserve as much spatially overlapping signals as possible while augmenting them with information on compositional (spectral) variation. The proposed approach can be used for exploratory visualization of MSI datasets without prior deep chemical or histological knowledge of the sample. Thus, different datasets can be visually compared employing the proposed method. The proposed approach allowed for the clear visualization of the molecular layer, granular layer, and white matter in chimpanzee and macaque cerebellum slices.