Optimizing deep learning architectures for SEM image classification using advanced dimensionality reduction techniques

Breast cancer remains a critical global health concern, requiring advanced and reliable diagnostic methods for early detection and effective intervention. This work introduces an integrated ensemble framework that combines multiple dimensionality reduction (DR) techniques, including Principal Component Analysis (PCA), Non-negative Matrix Factorization (NMF), and Singular Value Decomposition (SVD), with robust machine learning (ML) classifiers for improved breast cancer detection. The publicly available Wisconsin Breast Cancer Dataset (WBCD) was utilized, with rigorous data preprocessing performed to address missing values, anomalies, and class imbalance through stratified sampling and median imputation. To mitigate overfitting and underfitting, dimensionality reduction was coupled with cross-validation and ensemble strategies. The predictive performance of Logistic Regression (LR), Support Vector Machine (SVM), Random Forest (RF), Decision Tree (DT), and Multi-Layer Perceptron (MLP) was systematically evaluated. Experimental results show that SVM consistently achieves a maximum accuracy of 97.9 % across all applied DR techniques, while MLP and LR also reach 97.9 % accuracy with PCA and NMF, though MLP exhibits performance variability depending on the selected DR method. The findings provide practical guidance for healthcare practitioners and researchers, supporting the adoption of explainable and scalable AI-driven diagnostic tools. Limitations include the reliance on a single dataset and the need for further validation on larger and more diverse clinical cohorts. Future work will focus on enhancing model interpretability, external validation, and real-world deployment in resource-constrained settings.

Matrix factorization plays an important role in scientific computation. The widely used one is singular value decomposition (SVD) which approximates the original data matrix with three lower rank matrices with orthogonality constraints. Recently nonnegative matrix factorization (NMF) considering the nonnegativity of data makes the results more interpretable than those of SVD. However NMF finds only two factor matrices and there is no significant index as singular values of SVD which can be used for sorting learned basis vectors. In this paper we take into account the nonnegativity for SVD and propose nonnegative SVD (NNSVD). The preliminary results on the microarray data of spermatogenesis show that NNSVD has advantages of both SVD and NMF.

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.

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.

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.

A recommendation system is a method that provides suggestions of items that might users like. There are many domains that can be recommended, one of the most demanded domains by users today is food. In the era of big data, food choices from the large amount of data make it difficult for users to choose the right food for them. The collaborative filtering (CF) approach is considered capable of providing accurate and high quality item suggestions. One of the algorithms that can provide good performance results from the CF approach is Matrix Factorization (MF). This study aims to test a dataset that contains product ratings of food items using three MF algorithms, which are Singular Value Decomposition (SVD), SVD with Implicit Ratings (SVD++), and Non-Negative Matrix Factorization (NMF). Different latent factors are also used for the purpose of improving the performance of the proposed recommendation system algorithm. The dataset used is Amazon Fine Food Reviews. The study shows NMF and SVD++ as the best algorithm for generating user rating predictions for items. NMF has the smallest average prediction error as measured by MAE which is 0.7311. While SVD++ obtains the smallest prediction error value of 1.0607 as measured using RMSE. In addition to these results, the top-n evaluation also shows that the proposed algorithm performs quite well. The hit ratio value for each different n-item always increases proportionally to the number of recommended n-items. The highest hit ratio value is generated from the SVD++ algorithm of 0.0025 on n-item recommendations of 25 items. Overall it can be said that the proposed algorithm has good performance in providing item recommendations.

This paper deals with detecting fetal electrocardiogram FECG signals from single-channel abdominal lead. It is based on the Convolutional Neural Network (CNN) combined with advanced mathematical methods, such as Independent Component Analysis (ICA), Singular Value Decomposition (SVD), and a dimension-reduction technique like Nonnegative Matrix Factorization (NMF). Due to the highly disproportionate frequency of the fetus's heart rate compared to the mother's, the time-scale representation clearly distinguishes the fetal electrical activity in terms of energy. Furthermore, we can disentangle the various components of fetal ECG, which serve as inputs to the CNN model to optimize the actual FECG signal, denoted by FECGr, which is recovered using the SVD-ICA process. The findings demonstrate the efficiency of this innovative approach, which may be deployed in real-time.

A majorization–minimization based solution to penalized nonnegative matrix factorization with orthogonal regularization

Image representation is a fundamental issue in signal processing, pattern recognition, and computer vision. An efficient image representation can lead to the development of effective algorithms for the interpretation of images. Since Marr proposed the fundamental principle of the primary sketch concept of a scene, many image representations have been developed based on this concept. The primary sketch refers to the edges, lines, regions, and others in an image. These are characteristic features, which can be extracted from an image by transforming an image from the pixel-level to a higher level representation for image understanding. Many techniques developed for pattern recognition can be used for image transform and resulted in efficiently representing the characteristic features (or called intrinsic dimension). Dimensionality reduction (DR) and sparse representation (SR) are two representative schemes frequently used in the transform for reducing the dimension of a dataset. These transformations include principle component analysis (PCA), singular value decomposition (SVD), non-negative matrix factorization (NMF), and sparse coding (SC). The study of the mammal brain suggests that only a small number of active neurons encode sensory information at any given point. This finding has led to the rapid development of sparse coding which refers to a small number of nonzero entries in a feature vector. Hence, it is important to represent the sparsity for the dataset by eliminating the data redundancy for applications. The ultimate goal is to have a compact, efficient, and compressed representation of the input data.

The construction of literature-based networks of gene-gene interactions is one of the most important applications of text mining in bioinformatics. Extracting potential gene relationships from the biomedical literature may be helpful in building biological hypotheses that can be explored further experimentally. In this paper, we explore the utility of singular value decomposition (SVD) and non-negative matrix factorization (NMF) to extract unrecognized gene relationships from the biomedical literature by taking advantage of known gene relationships. We introduce a way to incorporate a priori knowledge of gene relationships into LSI/SVD and NMF. In addition, we propose a gene retrieval method based on NMF (GR/NMF), which shows comparable performance with latent semantic indexing based on SVD.

Non-negative matrix factorization (NMF) has been one of the most popular methods for feature learning in the field of machine learning and computer vision. Most existing works directly apply NMF on high-dimensional image datasets for computing the effective representation of the raw images. However, in fact, the common essential information of a given class of images is hidden in their low rank parts. For obtaining an effective low-rank data representation, we in this paper propose a non-negative low-rank matrix factorization (NLMF) method for image clustering. For the purpose of improving its robustness for the data in a manifold structure, we further propose a graph regularized NLMF by incorporating the manifold structure information into our proposed objective function. Finally, we develop an efficient alternating iterative algorithm to learn the low-dimensional representation of low-rank parts of images for clustering. Alternatively, we also incorporate robust principal component analysis into our proposed scheme. Experimental results on four image datasets reveal that our proposed methods outperform four representative methods.

In this paper we compare the performance of several dimension reduction techniques which are used as a tool for feature extraction. The tested methods include singular value decomposition, semi-discrete decomposition, non-negative matrix factorization, novel neural network based algorithm for Boolean factor analysis and two cluster analysis methods as well. So called bars problem is used as the benchmark. Set of artificial signals generated as a Boolean sum of given number of bars is analyzed by these methods. Resulting images show that Boolean factor analysis is upmost suitable method for this kind of data.

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

The field of data mining increasingly adapts methods and algorithms from advanced matrix computations, graph theory and optimization. In these methods, the data is described using matrix representations (graphs are represented by their adjacency matrices) and the data mining problem is formulated as an optimization problem with matrix variables. With these, the data mining task becomes a process of minimizing or maximizing a desired objective function of matrix variables. Prominent examples include spectral clustering, non-negative matrix factorization, Principal Component Analysis (PCA) and Singular Value Decomposition (SVD) related clustering and dimension reduction, tensor analysis and L-1 regularization. These matrix-formulated optimization-centric methodologies are rapidly becoming a significant part of data mining, and have evolved into a popular and rapidlyexpanding research area for solving challenging data mining problems. First, they are amenable to vigorous analysis and benefit from the well-established knowledge in linear algebra, graph theory and optimization accumulated through centuries. Second, they can be efficiently computed thanks to the mature software tools developed by scientific computing communities. Third, they are simple to implement and easy to

Enhancing microplastic classification through filter-interfered FTIR spectra using dimensionality reduction and deep learning in low-dimensional spaces.