Search

This paper focuses on the channel impairments separability of two histogram-based features, asynchronous amplitude histograms (AAH) and asynchronous delay-tap plot (ADTP), commonly used in direct-detection optical performance monitoring (OPM) techniques. This paper presents an in-depth study of the conditions under which these two histogram features are applicable in OPM. These high-dimensional features, AAH and ADTP, are dimensionally reduced using a state-of-the-art data visualization algorithm called Uniform Manifold Approximation and Projection (UMAP) algorithm. After data visualization, it can be found these two histogram-based features have some limitations in distinguishing between different levels of impairments in some specific cases. These features cannot achieve high accuracy in monitoring optical performance in these given situations, no matter how complex the classifier is designed. Extensive simulation experiments were performed to study the classification performance of the two histogram features in the single and multiple impairments cases. The results show that both AAH and ADTP can be used to monitor cumulative dispersion (CD) and optical signal to noise ratio (OSNR) in the case of the single impairment. In addition, the monitoring performance of both features is better for dispersion in the case of multiple impairments coexistence, while both have limitations for OSNR monitoring. However, the anti-dispersion interference ability of ADTP is better than that of AAH. The plausibility of the study results is verified by estimating the channel impairments under different conditions using a deep neural network-based (DNN) identifier. The impairments separation visualization results of UMAP are highly consistent with the estimation results of the DNN-based classifier, achieving the interconnection of usefulness and practicality. [ABSTRACT FROM AUTHOR]

An intrusion detection system (IDS) is a system that monitors network traffic for malicious activity and generates alerts. In anomaly-based detection, machine learning (ML) algorithms exploit various statistical and probabilistic methods to learn from past or historical experience and detect valuable patterns from large, unstructured, and complex datasets. ML-based network intrusion detection aims to identify malicious behavior and alert a system administrator when an intruder tries to penetrate the network. This paper deals with the study, strategic construction, and implementation of a network intrusion detection model based on ML methods. Among the available IDS datasets, five of the most relevant are chosen for the experimental analysis, which are NSL-KDD-2009, CIC-IDS2017, CIC-IDS2018, IoTID20, and UNSW-NB15 datasets. In order to reduce the computation time in the training sample and achieve computational complexity O (N 2.38 ± δ) , we propose a computationally efficient and feasible algorithmic framework for analyzing the network traffic data. The developed approach mainly consists of two phases, i.e., "Scatter Matrices and Eigenvalue Computation based feature Selection" and "Classification procedure for the reduced dimension data." Experimental evaluation of various test case scenarios for the chosen datasets is carried out in the simulation setting. It is observed that the test results outperform the existing intrusion detection methods for detecting certain attack categories. [ABSTRACT FROM AUTHOR]

This study introduces a novel approach for fault classification in bearing components utilizing raw accelerometer data. By employing various neural network models, including deep learning architectures, we bypass the traditional preprocessing and feature-extraction stages, streamlining the classification process. Utilizing the Case Western Reserve University (CWRU) bearing dataset, our methodology demonstrates remarkable accuracy, particularly in deep learning networks such as the three variant convolutional neural networks (CNNs), achieving above 98% accuracy across various loading levels, establishing a new benchmark in fault-detection efficiency. Notably, data exploration through principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) provided valuable insights into feature relationships and patterns, aiding in effective fault detection. This research not only proves the efficacy of neural network classifiers in handling raw data but also opens avenues for more straightforward yet effective diagnostic methods in machinery health monitoring. These findings suggest significant potential for real-world applications, offering a faster yet reliable alternative to conventional fault-classification techniques. [ABSTRACT FROM AUTHOR]

Currently, numerical-simulation-based slope reliability analysis (NSB-SRA) considering spatial variability is still a time-consuming task. To address this problem, this study proposed an efficient numerical-simulation-based slope reliability analysis method. Dual dimensionality reduction technique is firstly employed to greatly reduce random variables that are required for establishing a limit-equilibrium-analysis-based multivariate adaptive regression splines (MARS) model. Then, response conditioning method is used to select the failure samples predicted by MARS model as samples for performing NSB-SRA. Finally, the proposed method is validated through two spatially variable slope examples. The results show that MARS + FDM is an efficient solution to perform NSB-SRA, especially for low-probability-level NSB-SRA problem. Besides, NSB-SRA is necessary for cases of horizontal scale of fluctuation, smaller vertical of fluctuation, larger variability of undrained shear strength, and stronger positive cross-correlation between cohesion and internal friction angle because neglecting NSB-SRA will lead to an unreliable assessment on slope reliability. [ABSTRACT FROM AUTHOR]

Software effort estimation is a vital process in the software industry for successfully administering 5Ds of the software development life cycle (SDLC). The 5Ds stand for demand, development, direction, deployment, and designated cost of the software. Software development effort estimation (SDEE) is an effort prediction mechanism to calculate the effort for the development of the software product in order to minimize the challenges in the software field. Academics and practitioners are striving to identify which machine learning estimation technique yields more accurate results based on evaluation metrics, datasets, and other pertinent aspects. The feature selection techniques impact accuracy by selecting the main and relevant features in the dataset and eliminating the redundant and irrelevant features in the dataset. To achieve accurate estimations, the paper utilizes feature selection algorithms, along with various machine learning techniques, which predict the desired effort and the performance of the model has been measured in terms of prediction accuracy, R2 value, relative error, and mean absolute error. The datasets China and Maxwell are trained with the relevant features by applying feature selection algorithms, and estimation techniques are applied to predict the effort. The performance is compared with the regression models and feature selection techniques utilized by many authors previously. The result of the proposed methodology significantly gives the best performance with the combination of feature selection and estimation models than all regression models when applied alone, to both datasets. From the results, it is perceptible that random forest is performing well with the feature selection techniques and obtains the highest prediction accuracy of 99.33% with the China and 89.47% with the Maxwell datasets. [ABSTRACT FROM AUTHOR]

Background: Recent developments in single-cell RNA sequencing have opened up a multitude of possibilities to study tissues at the level of cellular populations. However, the heterogeneity in single-cell sequencing data necessitates appropriate procedures to adjust for technological limitations and various sources of noise when integrating datasets from different studies. While many analysis procedures employ various preprocessing steps, they often overlook the importance of selecting and optimizing the employed data transformation methods. Results: This work investigates data transformation approaches used in single-cell clustering analysis tools and their effects on batch integration analysis. In particular, we compare 16 transformations and their impact on the low-dimensional representations, aiming to reduce the batch effect and integrate multiple single-cell sequencing data. Our results show that data transformations strongly influence the results of single-cell clustering on low-dimensional data space, such as those generated by UMAP or PCA. Moreover, these changes in low-dimensional space significantly affect trajectory analysis using multiple datasets, as well. However, the performance of the data transformations greatly varies across datasets, and the optimal method was different for each dataset. Additionally, we explored how data transformation impacts the analysis of deep feature encodings using deep neural network-based models, including autoencoder-based models and proto-typical networks. Data transformation also strongly affects the outcome of deep neural network models. Conclusions: Our findings suggest that the batch effect and noise in integrative analysis are highly influenced by data transformation. Low-dimensional features can integrate different batches well when proper data transformation is applied. Furthermore, we found that the batch mixing score on low-dimensional space can guide the selection of the optimal data transformation. In conclusion, data preprocessing is one of the most crucial analysis steps and needs to be cautiously considered in the integrative analysis of multiple scRNA-seq datasets. [ABSTRACT FROM AUTHOR]

Background: Numerous transcriptomic-based models have been developed to predict or understand the fundamental mechanisms driving biological phenotypes. However, few models have successfully transitioned into clinical practice due to challenges associated with generalizability and interpretability. To address these issues, researchers have turned to dimensionality reduction methods and have begun implementing transfer learning approaches. Methods: In this study, we aimed to determine the optimal combination of dimensionality reduction and regularization methods for predictive modeling. We applied seven dimensionality reduction methods to various datasets, including two supervised methods (linear optimal low-rank projection and low-rank canonical correlation analysis), two unsupervised methods [principal component analysis and consensus independent component analysis (c-ICA)], and three methods [autoencoder (AE), adversarial variational autoencoder, and c-ICA] within a transfer learning framework, trained on > 140,000 transcriptomic profiles. To assess the performance of the different combinations, we used a cross-validation setup encapsulated within a permutation testing framework, analyzing 30 different transcriptomic datasets with binary phenotypes. Furthermore, we included datasets with small sample sizes and phenotypes of varying degrees of predictability, and we employed independent datasets for validation. Results: Our findings revealed that regularized models without dimensionality reduction achieved the highest predictive performance, challenging the necessity of dimensionality reduction when the primary goal is to achieve optimal predictive performance. However, models using AE and c-ICA with transfer learning for dimensionality reduction showed comparable performance, with enhanced interpretability and robustness of predictors, compared to models using non-dimensionality-reduced data. Conclusion: These findings offer valuable insights into the optimal combination of strategies for enhancing the predictive performance, interpretability, and generalizability of transcriptomic-based models. [ABSTRACT FROM AUTHOR]

Binary classification with an imbalanced dataset is challenging. Models tend to consider all samples as belonging to the majority class. Although existing solutions such as sampling methods, cost-sensitive methods, and ensemble learning methods improve the poor accuracy of the minority class, these methods are limited by overfitting or cost parameters that are difficult to decide. This paper proposes a hybrid approach with dimension reduction that consists of data block construction, dimensionality reduction, and ensemble learning with deep neural network classifiers. The performance is evaluated on eight imbalanced public datasets in terms of recall, G-mean, AUC, F-measure, and balanced accuracy. The results show that the proposed model outperforms state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Deep learning-based models are employed in computer-aided diagnosis (CAD) tools development for pediatric pneumonia (P-Pneumonia) detection. The accuracy of the model depends on the scaling of the deep learning model. A survey on deep learning shows that models with a greater number of layers achieve better performances for P-Pneumonia detection. However, the identification of the optimal models is considered to be important work for P-Pneumonia detection. This work presents a hybrid deep learning model for P-Pneumonia detection. The model leverages the EfficientNetV2 model that employs various advanced methodologies to maintain the balance between the model scaling and the performance of the model in P-Pneumonia detection. The features of EfficientNetV2 models are passed into global weighted average pooling (GWAP) which acts like an attention layer. It helps to extract the important features that point to the infected regions of the radiography image and discard all the unimportant information. The features from GWAP are high in dimension and using kernel-based principal component analysis (K-PCA), the features were reduced. Next, the reduced features are combined together and passed into a stacked classifier. The stacked classifier is a two-stage approach in which the first stage employs a support vector machine (SVM) and random forest tree (RFT) for the prediction of P-Pneumonia using the fused features and logistic regression (LRegr) on values of prediction for classification. Detailed experiments were done for the proposed method in P-Pneumonia detection using publically available benchmark datasets. Various settings in the experimental analysis are done to identify the best model. The proposed model outperformed the other methods by improving the accuracy by 4% in P-Pneumonia detection. To show that the proposed model is robust, the model performances were shown on the completely unseen dataset of P-Pneumonia. The hybrid deep learning-based P-Pneumonia model showed good performance on completely unseen data samples of P-Pneumonia patients. The generalization of the proposed P-Pneumonia model is studied by evaluating the model on similar lung diseases such as COVID-19 (CV-19) and Tuberculosis (TBS). In all the experiments, the P-Pneumonia model has shown good performances on similar lung diseases. This indicates that the model is robust and generalizable on data samples of different patients with similar lung diseases. The P-Pneumonia models can be used in healthcare and clinical environments to assist doctors and healthcare professionals in improving the detection rate of P-Pneumonia. [ABSTRACT FROM AUTHOR]

Deep learning-based models have achieved impressive results across various practical fields. However, these models are susceptible to attacks. Recent research has demonstrated that adversarial samples can significantly decrease the accuracy of deep learning models. This susceptibility poses considerable challenges for their use in security applications. Various methods have been developed to enhance model robustness by training with more effective and generalized adversarial examples. However, these approaches tend to compromise model accuracy. Currently proposed detection methods mainly focus on speech adversarial samples generated by specified white-box attack models. In this study, leveraging manifold learning technology, a method is proposed to detect whether a speech input is an adversarial sample before feeding it into the recognition model. The method is designed to detect speech adversarial samples generated by black-box attack models and achieves a detection success rate of 84.73%. It identifies the low-dimensional manifold of training samples and measures the distance of a sample under investigation to this manifold to determine its adversarial nature. This technique enables the preprocessing detection of adversarial audio samples before their introduction into the deep learning model, thereby preventing adversarial attacks without affecting model robustness. [ABSTRACT FROM AUTHOR]

In general, wireless sensor networks are used in various industries, including environmental monitoring, military applications, and queue tracking. To support vital applications, it is crucial to ensure effectiveness and security. To prolong the network lifetime, most current works either introduce energy-preserving and dynamic clustering strategies to maintain the optimal energy level or attempt to address intrusion detection to fix attacks. In addition, some strategies use routing algorithms to secure the network from one or two attacks to meet this requirement, but many fewer solutions can withstand multiple types of attacks. So, this paper proposes a secure deep learning-based energy-efficient routing (SDLEER) mechanism for WSNs that comes with an intrusion detection system for detecting attacks in the network. The proposed system overcomes the existing solutions' drawbacks by including energy-efficient intrusion detection and prevention mechanisms in a single network. The system transfers the network's data in an energy-aware manner and detects various kinds of network attacks in WSNs. The proposed system mainly comprises two phases, such as optimal cluster-based energy-aware routing and deep learning-based intrusion detection system. Initially, the cluster of sensor nodes is formed using the density peak k-mean clustering algorithm. After that, the proposed system applies an improved pelican optimization approach to select the cluster heads optimally. The data are transmitted to the base station via the chosen optimal cluster heads. Next, in the attack detection phase, the preprocessing operations, such as missing value imputation and normalization, are done on the gathered dataset. Next, the proposed system applies principal component analysis to reduce the dimensionality of the dataset. Finally, intrusion classification is performed by Smish activation included recurrent neural networks. The proposed system uses the NSL-KDD dataset to train and test it. The proposed one consumes a minimum energy of 49.67 mJ, achieves a better delivery rate of 99.92%, takes less lifetime of 5902 rounds, 0.057 s delay, and achieves a higher throughput of 0.99 Mbps when considering a maximum of 500 nodes in the network. Also, the proposed one achieves 99.76% accuracy for the intrusion detection. Thus, the simulation outcomes prove the superiority of the proposed SDLEER system over the existing schemes for routing and attack detection. [ABSTRACT FROM AUTHOR]

In intrusion detection, the curse of dimensionality and the trade-off between maintaining a low false alarm rate and achieving a high detection rate are significant challenges. This research suggests a unique strategy based on dimensionality reduction methods to improve the performance of network intrusion detection systems (NIDS). Compressing high-dimensional network traffic data using a Long Short-Term Memory Autoencoder (LSTMAE) allows the reduced characteristics to be submitted to a classifier to identify anomalies that may indicate an attack. Using standard datasets, including Network Security Laboratory - Knowledge Discovery in Datasets (NSL-KDD), UNSW-NB15, and Canadian Institute for Cyber Security - Intrusion Detection Systems (CICIDS2017), the proposed model is tested with classifiers like Random Forest (RF) and LightGBM (Light Gradient Boosting Machines). It is hoped that by adopting this method, NIDS response times may be improved while costs associated with storing and processing data are minimized. Precision, recall, F-score, accuracy, detection rate (DR), and false alarm rate (FAR) are only a few of the performance measures used to assess the quality of the suggested models. The experimental findings show that the proposed LSTMAE model reduces prediction errors more effectively than classic machine learning techniques such as Random Forest (RF), Gradient Boosting (GB), Support Vector Machines (SVM), Deep Belief Networks (DBN), Deep Neural Networks (DNN), Autoencoder (AE), and Long Short-Term Memory (LSTM). The results also show that the proposed solution outperforms the state-of-the-art methods of detection accuracy and computing complexity using accuracy, precision, recall, F1_Score, detection rate, and FAR. [ABSTRACT FROM AUTHOR]

Simple Summary: Hematopoietic stem and progenitor cells (HSPCs) play a pivotal role in maintaining the homeostasis of the blood and immune systems. Acute myeloid leukemia (AML) and myelodysplastic syndromes (MDS) represent heterogeneous hematologic malignancies resulting from genetic mutations within cells of the hematopoietic lineage, leading to the expansion of leukemic blasts including leukemic stem cells (LSCs). Using the t-distributed stochastic neighbor embedding (t-SNE) methodology, we examined the immunological phenotype of HSPCs based on the differential expression of CD34, CD38, CD45RA, CD123 and programmed death ligand 1 (PD-L1) antigens, and contrasted it with the immunophenotype of blasts and LSCs in AML and MDS. Using multi-color flow cytometry analysis, we studied the immunophenotypical differences between leukemic cells from patients with AML/MDS and hematopoietic stem and progenitor cells (HSPCs) from patients in complete remission (CR) following their successful treatment. The panel of markers included CD34, CD38, CD45RA, CD123 as representatives for a hierarchical hematopoietic stem and progenitor cell (HSPC) classification as well as programmed death ligand 1 (PD-L1). Rather than restricting the evaluation on a 2- or 3-dimensional analysis, we applied a t-distributed stochastic neighbor embedding (t-SNE) approach to obtain deeper insight and segregation between leukemic cells and normal HPSCs. For that purpose, we created a t-SNE map, which resulted in the visualization of 27 cell clusters based on their similarity concerning the composition and intensity of antigen expression. Two of these clusters were "leukemia-related" containing a great proportion of CD34+/CD38− hematopoietic stem cells (HSCs) or CD34+ cells with a strong co-expression of CD45RA/CD123, respectively. CD34+ cells within the latter cluster were also highly positive for PD-L1 reflecting their immunosuppressive capacity. Beyond this proof of principle study, the inclusion of additional markers will be helpful to refine the differentiation between normal HSPCs and leukemic cells, particularly in the context of minimal disease detection and antigen-targeted therapeutic interventions. Furthermore, we suggest a protocol for the assignment of new cell ensembles in quantitative terms, via a numerical value, the Pearson coefficient, based on a similarity comparison of the t-SNE pattern with a reference. [ABSTRACT FROM AUTHOR]

With the rapid advancement of remote-sensing technology, the spectral information obtained from hyperspectral remote-sensing imagery has become increasingly rich, facilitating detailed spectral analysis of Earth's surface objects. However, the abundance of spectral information presents certain challenges for data processing, such as the "curse of dimensionality" leading to the "Hughes phenomenon", "strong correlation" due to high resolution, and "nonlinear characteristics" caused by varying surface reflectances. Consequently, dimensionality reduction of hyperspectral data emerges as a critical task. This paper begins by elucidating the principles and processes of hyperspectral image dimensionality reduction based on manifold theory and learning methods, in light of the nonlinear structures and features present in hyperspectral remote-sensing data, and formulates a dimensionality reduction process based on manifold learning. Subsequently, this study explores the capabilities of feature extraction and low-dimensional embedding for hyperspectral imagery using manifold learning approaches, including principal components analysis (PCA), multidimensional scaling (MDS), and linear discriminant analysis (LDA) for linear methods; and isometric mapping (Isomap), locally linear embedding (LLE), Laplacian eigenmaps (LE), Hessian locally linear embedding (HLLE), local tangent space alignment (LTSA), and maximum variance unfolding (MVU) for nonlinear methods, based on the Indian Pines hyperspectral dataset and Pavia University dataset. Furthermore, the paper investigates the optimal neighborhood computation time and overall algorithm runtime for feature extraction in hyperspectral imagery, varying by the choice of neighborhood k and intrinsic dimensionality d values across different manifold learning methods. Based on the outcomes of feature extraction, the study examines the classification experiments of various manifold learning methods, comparing and analyzing the variations in classification accuracy and Kappa coefficient with different selections of neighborhood k and intrinsic dimensionality d values. Building on this, the impact of selecting different bandwidths t for the Gaussian kernel in the LE method and different Lagrange multipliers λ for the MVU method on classification accuracy, given varying choices of neighborhood k and intrinsic dimensionality d, is explored. Through these experiments, the paper investigates the capability and effectiveness of different manifold learning methods in feature extraction and dimensionality reduction within hyperspectral imagery, as influenced by the selection of neighborhood k and intrinsic dimensionality d values, identifying the optimal neighborhood k and intrinsic dimensionality d value for each method. A comparison of classification accuracies reveals that the LTSA method yields superior classification results compared to other manifold learning approaches. The study demonstrates the advantages of manifold learning methods in processing hyperspectral image data, providing an experimental reference for subsequent research on hyperspectral image dimensionality reduction using manifold learning methods. [ABSTRACT FROM AUTHOR]

Real-time play recognition and classification algorithms are crucial for automating video production and live broadcasts of sporting events. However, current methods relying on human pose estimation and deep neural networks introduce high latency on commodity hardware, limiting their usability in low-cost real-time applications. We present PlayNet, a novel approach to real-time handball play classification. Our method is based on Kalman embeddings, a new low-dimensional representation for game states that enables efficient operation on commodity hardware and customized camera layouts. Firstly, we leverage Kalman filtering to detect and track the main agents in the playing field, allowing us to represent them in a single normalized coordinate space. Secondly, we utilize a neural network trained in nonlinear dimensionality reduction through fuzzy topological data structure analysis. As a result, PlayNet achieves real-time play classification with under 55 ms of latency on commodity hardware, making it a promising addition to automated live broadcasting and game analysis pipelines. [ABSTRACT FROM AUTHOR]

Insightful visualization of multidimensional scalar fields, in particular parameter spaces, is key to many computational science and engineering disciplines. We propose a principal component-based approach to visualize such fields that accurately reflects their sensitivity to their input parameters. The method performs dimensionality reduction on the space formed by all possible partial functions (i.e., those defined by fixing one or more input parameters to specific values), which are projected to low-dimensional parameterized manifolds such as 3D curves, surfaces, and ensembles thereof. Our mapping provides a direct geometrical and visual interpretation in terms of Sobol's celebrated method for variance-based sensitivity analysis. We furthermore contribute a practical realization of the proposed method by means of tensor decomposition, which enables accurate yet interactive integration and multilinear principal component analysis of high-dimensional models. [ABSTRACT FROM AUTHOR]

Since its emergence in late 2019, SARS-CoV-2 has diversified into a large number of lineages and caused multiple waves of infection globally. Novel lineages have the potential to spread rapidly and internationally if they have higher intrinsic transmissibility and/or can evade host immune responses, as has been seen with the Alpha, Delta, and Omicron variants of concern. They can also cause increased mortality and morbidity if they have increased virulence, as was seen for Alpha and Delta. Phylogenetic methods provide the "gold standard" for representing the global diversity of SARS-CoV-2 and to identify newly emerging lineages. However, these methods are computationally expensive, struggle when datasets get too large, and require manual curation to designate new lineages. These challenges provide a motivation to develop complementary methods that can incorporate all of the genetic data available without down-sampling to extract meaningful information rapidly and with minimal curation. In this paper, we demonstrate the utility of using algorithmic approaches based on word-statistics to represent whole sequences, bringing speed, scalability, and interpretability to the construction of genetic topologies. While not serving as a substitute for current phylogenetic analyses, the proposed methods can be used as a complementary, and fully automatable, approach to identify and confirm new emerging variants. [ABSTRACT FROM AUTHOR]

Raman spectroscopy is a popular tool for characterizing complex biological materials and their geological remains. Ordination methods, such as principal component analysis (PCA), use spectral variance to create a compositional space, the ChemoSpace, grouping samples based on spectroscopic manifestations reflecting different biological properties or geological processes. PCA allows to reduce the dimensionality of complex spectroscopic data and facilitates the extraction of informative features into formats suitable for downstream statistical analyses, thus representing a first step in the development of diagnostic biosignatures from complex modern and fossil tissues. For such samples, however, there is presently no systematic and accessible survey of the impact of sample, instrument, and spectral processing on the occupation of the ChemoSpace. Here, the influence of sample count, unwanted signals and different signal‐to‐noise ratios, spectrometer decalibration, baseline subtraction, and spectral normalization on ChemoSpace grouping is investigated and exemplified using synthetic spectra. Increase in sample size improves the dissociation of groups in the ChemoSpace, and our sample yields a representative and mostly stable pattern in occupation with less than 10 samples per group. The impact of systemic interference of different amplitude and frequency, periodical or random features that can be introduced by instrument or sample, on compositional biological signatures is reduced by PCA and allows to extract biological information even when spectra of differing signal‐to‐noise ratios are compared. Routine offsets ( ±$$ \pm $$1 cm−1) in spectrometer calibration contribute in our sample to less than 0.1% of the total spectral variance captured in the ChemoSpace and do not obscure biological information. Standard adaptive baselining, together with normalization, increases spectral comparability and facilitates the extraction of informative features. The ChemoSpace approach to biosignatures represents a powerful tool for exploring, denoising, and integrating molecular information from modern and ancient organismal samples. [ABSTRACT FROM AUTHOR]

This study investigates the roles of mucosal-associated invariant T (MAIT) cells and Vα7.2+/CD161− T cells in skin diseases, focusing on atopic dermatitis. MAIT cells, crucial for bridging innate and adaptive immunity, were analyzed alongside Vα7.2+/CD161− T cells in peripheral blood samples from 14 atopic dermatitis patients and 10 healthy controls. Flow cytometry and machine learning algorithms were employed for a comprehensive analysis. The results indicate a significant decrease in MAIT cells and CD69 subsets in atopic dermatitis, coupled with elevated CD38 and polyfunctional MAIT cells producing TNFα and Granzyme B (TNFα+/GzB+). Vα7.2+/CD161− T cells in atopic dermatitis exhibited a decrease in CD8 and IFNγ-producing subsets but an increase in CD38 activated and IL-22-producing subsets. These results highlight the distinctive features of MAIT cells and Vα7.2+/CD161− T cells and their different roles in the pathogenesis of atopic dermatitis and provide insights into their potential roles in immune-mediated skin diseases. [ABSTRACT FROM AUTHOR]

Background: Identifying active lesions in magnetic resonance imaging (MRI) is crucial for the diagnosis and treatment planning of multiple sclerosis (MS). Active lesions on MRI are identified following the administration of Gadolinium-based contrast agents (GBCAs). However, recent studies have reported that repeated administration of GBCA results in the accumulation of Gd in tissues. In addition, GBCA administration increases health care costs. Thus, reducing or eliminating GBCA administration for active lesion detection is important for improved patient safety and reduced healthcare costs. Current state-of-the-art methods for identifying active lesions in brain MRI without GBCA administration utilize data-intensive deep learning methods. Objective: To implement nonlinear dimensionality reduction (NLDR) methods, locally linear embedding (LLE) and isometric feature mapping (Isomap), which are less data-intensive, for automatically identifying active lesions on brain MRI in MS patients, without the administration of contrast agents. Materials and Methods: Fluid-attenuated inversion recovery (FLAIR), T2-weighted, proton density-weighted, and pre- and post-contrast T1-weighted images were included in the multiparametric MRI dataset used in this study. Subtracted pre- and post-contrast T1-weighted images were labeled by experts as active lesions (ground truth). Unsupervised methods, LLE and Isomap, were used to reconstruct multiparametric brain MR images into a single embedded image. Active lesions were identified on the embedded images and compared with ground truth lesions. The performance of NLDR methods was evaluated by calculating the Dice similarity (DS) index between the observed and identified active lesions in embedded images. Results: LLE and Isomap, were applied to 40 MS patients, achieving median DS scores of 0.74 ± 0.1 and 0.78 ± 0.09, respectively, outperforming current state-of-the-art methods. Conclusions: NLDR methods, Isomap and LLE, are viable options for the identification of active MS lesions on non-contrast images, and potentially could be used as a clinical decision tool. [ABSTRACT FROM AUTHOR]

The most valuable information of Hyperspectral Image (HSI) should be processed properly. Using dimensionality reduction techniques in two distinct approaches, we created a structure for HSI to collect physiological and diagnostic information. The tissue Oxygen Saturation Level (StO2) was extracted using the HSI approach as a physiological characteristic for stress detection. Our research findings suggest that this unique characteristic may not be affected by humidity or temperature in the environment. Comparing the standard StO2 reference and pressure concentrations, the social stress assessments showed a substantial variance and considerable practical differentiation. The proposed system has already been evaluated on tumor images from rats with head and neck cancers using a spectrum from 450 to 900 nm wavelength. The Fourier transformation was developed to improve precision, and normalize the brightness and mean spectrum components. The analysis of results showed that in a difficult situation where awareness could be inexpensive due to feature possibilities for rapid classification tasks and significant in measuring the structure of HSI analysis for cancer detection throughout the surgical resection of wildlife. Our proposed model improves performance measures such as reliability at 89.62% and accuracy at 95.26% when compared with existing systems. [ABSTRACT FROM AUTHOR]

Recently, digital images are widely used in several applications through advanced wearable devices and networks. Despite several benefits of digital images, such as easy distribution, storage, and reproduction, it is difficult to prevent the issue of identity theft, privacy leakage, and ownership conflicts. To solve the above issues, dimensionality reduction-based robust watermarking for color images, supported with suitable encryption, is presented in this article. In this method, principal component analysis (PCA)-based dimensionality reduction is applied to the color carrier image to produce three principal components. The third component with minimum energy is then concealed with a mark image using non-sub-sampled shearlet transform (NSST)-singular value decomposition (SVD)-based watermarking to resolve the ownership issues, if any. In addition, encryption of marked image is done to provide better security and authenticity. The final encrypted image is then stored in a cloud environment for better accessibility. Finally, an experimental and comparative evaluation of the proposed framework justifies its versatility, robustness, and imperceptibility with the best improvement of 47.49 %. [ABSTRACT FROM AUTHOR]

We present a new classifier that uses a generalized Heronian mean (GHM) operator, and fuzzy robust principal component analysis (FRPCA) algorithms. The similarity classifier was earlier studied with other aggregation operators, including: the ordered weighted averaging (OWA), generalized mean, arithmetic mean among others. Parameters in the GHM operator makes the new classifier suitable for handling a variety of modeling problems involving parameter settings. Motivated by the nature of the GHM operator, we examine which FRPCA algorithm is suitable for use to achieve optimal performance of the new classifier. The effects of dimensionality reduction and fuzziness variable on classification accuracy are examined. The performance of the new classifier is tested on three real-world datasets: fertility, horse-colic, and Haberman's survival. Compared with previously studied similarity classifiers, the new method achieved improved classification accuracy for the tested datasets. In fertility dataset, the new classifier achieved improvements in accuracy of 1 4. 6 0 % , 1 9. 7 3 % , and 2 3. 0 0 % compared with the OWA, generalized mean, and arithmetic mean based classifiers respectively. The new classifier is simpler to implement since it does not require any weight generation criteria as the case is for the OWA based classifier. [ABSTRACT FROM AUTHOR]

The metric learning area studies methodologies to find the most appropriate distance function for a given dataset. It was shown that dimensionality reduction algorithms are closely related to metric learning because, in addition to obtaining a more compact representation of the data, such methods also implicitly derive a distance function that best represents similarity between a pair of objects in the collection. Principal Component Analysis is a traditional linear dimensionality reduction algorithm that is still widely used by researchers. However, its procedure faithfully represents outliers in the generated space, which can be an undesirable characteristic in pattern recognition applications. With this is mind, it was proposed the replacement of the traditional punctual approach by a contextual one based on the data samples neighborhoods. This approach implements a mapping from the usual feature space to a parametric feature space, where the difference between two samples is defined by the vector whose scalar coordinates are given by the statistical divergence between two probability distributions. It was demonstrated for some divergences that the new approach outperforms several existing dimensionality reduction algorithms in a wide range of datasets. Although, it is important to investigate the framework divergence sensitivity. Experiments using Total Variation, Renyi, Sharma-Mittal and Tsallis divergences are exhibited in this paper and the results evidence the method robustness. [ABSTRACT FROM AUTHOR]

In recent years, the dimensionality reduction has become more important as the number of dimensions of data used in various tasks such as regression and classification has increased. As popular nonlinear dimensionality reduction methods, t-distributed stochastic neighbor embedding (t-SNE) and uniform manifold approximation and projection (UMAP) have been proposed. However, the former outputs only one low-dimensional space determined by the t-distribution and the latter is difficult to control the distribution of distance between each pair of samples in low-dimensional space. To tackle these issues, we propose novel t-SNE and UMAP extended by q-Gaussian distribution, called q-Gaussian-distributed stochastic neighbor embedding (q-SNE) and q-Gaussian-distributed uniform manifold approximation and projection (q-UMAP). The q-Gaussian distribution is a probability distribution derived by maximizing the tsallis entropy by escort distribution with mean and variance, and a generalized version of Gaussian distribution with a hyperparameter q. Since the shape of the q-Gaussian distribution can be tuned smoothly by the hyperparameter q, q-SNE and q-UMAP can in- tuitively derive different embedding spaces. To show the quality of the proposed method, we compared the visualization of the low-dimensional embedding space and the classification accuracy by k-NN in the low-dimensional space. Empirical results on MNIST, COIL-20, OliverttiFaces and FashionMNIST demonstrate that the q-SNE and q-UMAP can derive better embedding spaces than t-SNE and UMAP. [ABSTRACT FROM AUTHOR]

In today's internet-driven world, a multitude of attacks occurs daily, propelled by a vast user base. The effective detection of these numerous attacks is a growing area of research, primarily accomplished through intrusion detection systems (IDS). IDS are vital for monitoring network traffic to identify malicious activities, such as Denial of Service, Probe, Remote-to-Local, and User-to-Root attacks. Our research focused on evaluating different auto-encoders for enhancing network intrusion detection. The proposed method sparse deep denoising auto-encoder approach produces the dimensionality reduction used to predict and classify attacks in datasets. With the most records among the datasets by training the auto-encoder on normal network data, this utilized reconstruction error as an indicator of anomalies. We tested our approach using standard datasets like KDDCup99, NSL-KDD, UNSW-NB15, and NMITIDS. Remarkably, our sparse deep denoising auto-encoder achieved an accuracy of over 96% based solely on reconstruction error. The primary aim of this work is to improve intrusion detection by achieving higher detection accuracy compared to existing methods. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) play a crucial role in diverse applications, encompassing environmental monitoring, healthcare, and industrial automation. However, these networks are susceptible to various security threats, underscoring the need for robust attack detection systems. In this paper, we propose a Stochastic Machine Learning-Based Attack Detection System for WSNs that leverages the synergy of Hidden Markov Models (HMMs) and Gaussian Mixture Models (GMMs). The proposed system employs Principal Component Analysis for dimensionality reduction in the WSN dataset, thereby retaining essential routing features while mitigating the number of variables. Additionally, iterative machine learning Expectation-Maximization is employed to train the HMMs and GMMs, empowering the system to accurately detect and classify malicious activities and erroneous routing data. To evaluate the system’s efficacy, a series of experiments were conducted, entailing variations in the parameters of both HMMs and GMMs. Notably, the findings underscore that the configuration comprising 3 HMMs and 4 GMMs surpasses other combinations, achieving an exceptional accuracy level of 94.55%. Furthermore, a comprehensive comparison is drawn between the proposed system and common machine learning classifiers. This analysis unequivocally highlights the system’s superiority in terms of accuracy and overall performance. Notable is the system’s exceptional performance in cross-validation, consistently achieving accuracies within the range of 0.96 to 0.98. The proposed Stochastic Machine Learning-Based Attack Detection System introduces a highly promising approach to fortify the security of WSNs. The amalgamation of rigorous experimentation, comparative analysis, and impressive results underscores its potential as an effective security enhancement tool. [ABSTRACT FROM AUTHOR]

Amidst the surge in high-dimensional data, filter feature selection techniques have emerged as preferred tools for selecting relevant features, owing to their advantages such as enhanced generalization, faster training times, dimensionality reduction, and improved model performance. However, traditional feature selection methods often exhibit instability, resulting in the selection of varying feature subsets and subsequently different classification accuracies. Addressing this challenge, we propose a novel approach termed Multi-Univariate Hybrid Feature Selection (MUNIFES) to bolster the discriminative power between features and target classes in text classification tasks. MUNIFES integrates the local feature relevance of filter methods, a facet that has been overlooked in prior literature, through a multi-iterative process to select optimal feature subsets from each univariate feature selection method. Leveraging an ensemble of discriminative strength metrics including Chi-Square (Chi2), Analysis of Variance (ANOVA), and Infogain methods, MUNIFES achieves superior performance in selecting optimal feature subsets. Evaluation conducted on the 20newsgroup dataset and its variant (17newsgroup) with 10 classifiers, including ensemble, classification, optimization algorithms, and Artificial Neural Network (ANN), demonstrates the efficacy of MUNIFES compared to state-of-the-art feature selection methods, showcasing improved accuracy in classification tasks. [ABSTRACT FROM AUTHOR]

Protein–protein interactions are crucial for the entry of viruses into the cell. Understanding the mechanism of interactions is essential in studying human-virus association, developing new biologics and drug candidates, as well as viral infections and antiviral responses. Experimental methods to analyze human-virus protein–protein interactions based on protein sequence data are time-consuming and labor-intensive, so machine learning models are being developed to predict interactions and determine large-scale interactomes between species. The present work highlights the importance of sequence features in classifying interacting and non-interacting proteins from the protein sequence data. Higher dimensional amino acid sequence features such as Amino Acid Composition (AAC), Dipeptide Composition (DPC), Grouped Amino Acid Composition (GAAC), Pseudo-Amino Acid Composition (PAAC) etc., are extracted. Following feature extraction, three datasets were created: Dataset 1 contains all of the extracted features. While Datasets 2 and 3 contain the most relevant features obtained through dimensionality reduction. To analyze the importance of high-dimensional features and their participation in protein–protein interactions, a random forest classifier is trained on three datasets. With dimensionality reduction, the model exhibited exceptional accuracy, indicating that dimensionality reduction fails to capture the complexity of interactions and the underlying relationships between human and viral proteins. As a result of retaining high-dimensional features, it is possible to capture all the characteristics of protein–protein interactions that resemble host–pathogen associations, leading to the development of biologically meaningful models. Our proposed approach is a more realistic and comprehensive classification model, leading to deeper insights and better applications in virology and drug development. [ABSTRACT FROM AUTHOR]

The generalized solutions of the dimensionality reduction problem in diffusion–reaction systems have been found for the first time by rigorously decoupling probability functions. Numerically exact results are obtained by straightforwardly applying the generalized solution to three models: protein‐DNA binding model (3D‐1D reduction), surface‐mediated diffusion (3D‐2D reduction), and line‐mediated diffusion cases (2D‐1D reduction). The results are confirmed by Monte Carlo simulations. [ABSTRACT FROM AUTHOR]

At present, it is critical to accurately monitor wheat crops to help decision-making processes in precision agriculture. This research aims to retrieve various wheat crop traits from hyperspectral data using machine learning regression algorithms (MLRAs) and dimensionality reduction (DR) techniques. This experiment was conducted in an agricultural field in Arborea, Oristano-Sardinia, Italy, with different factors such as cultivars, N-treatments, and soil ploughing conditions. Hyperspectral data were acquired on the ground using a full-range Spectral Evolution spectrometer (350–2500 nm). Four DR techniques, including (i) variable influence on projection (VIP), (ii) principal component analysis (PCA), (iii) vegetation indices (VIs), and (iv) spectroscopic feature (SF) calculation, were undertaken to reduce the dimension of the hyperspectral data while maintaining the information content. We used five MLRA models, including (i) partial least squares regression (PLSR), (ii) random forest (RF), (iii) support vector regression (SVR), (iv) Gaussian process regression (GPR), and (v) neural network (NN), to retrieve wheat traits at either leaf and canopy levels. The studied traits were leaf area index (LAI), leaf and canopy water content (LWC and CWC), leaf and canopy chlorophyll content (LCC and CCC), and leaf and canopy nitrogen content (LNC and CNC). MLRA models were able to accurately retrieve wheat traits at the canopy level with PLSR and NN indicating the highest modelling performance. On the contrary, MLRA models indicated less accurate retrievals of the leaf-level traits. DR techniques were found to notably improve the retrieval accuracy of crop traits. Furthermore, the generated models were re-calibrated using soil spectra and then transferred to an airborne dataset collected using a CASI-SASI hyperspectral sensor, allowing the estimation of wheat traits across the entire field. The predicted crop trait maps illustrated consistent patterns while also preserving the real-field characteristics well. Lastly, a statistical paired t-test was undertaken to conduct a proof of concept of wheat phenotyping analysis considering the different agricultural variables across the study site. N-treatment caused significant differences in wheat crop traits in many instances, whereas the observed differences were less pronounced between the cultivars. No particular impact of soil ploughing conditions on wheat crop characteristics was found. Using such combinations of MLRA and DR techniques based on hyperspectral data can help to effectively monitor crop traits throughout the cropping seasons and can also be readily applied to other agricultural settings to help both precision farming applications and the implementation of high-throughput phenotyping solutions. [ABSTRACT FROM AUTHOR]

The surfaces produced by the machining process are sensitive to the type of machining process and the conditions under which it is performed. Thus, surface texture identification is crucial in quality assurance, as it acts as a feedback to the machining process. Machined surface identification using image processing and machine learning (ML)-based techniques is gaining much importance due to industrial automation. This investigation addresses the development of ML models using gray-level co-occurrence matrices (GLCM) features to classify the machined (turned, ground and shaped) surfaces. The influence of distance-based dimensionality reduction techniques (DRT) viz., Fisher's criterion, Separation index and Bhattacharya distance on the performance of the ML-based image classifiers is explored. The GLCM features extracted from the machined surface images are used as inputs to ML classifiers. A threshold criterion function (TCF) is used to select the sensitive features in the DRT. Among all the classifiers, the (Random Forest) RAF model could produce a better classification accuracy as high as 95.3%. Also, analysis results show that the proposed dimensionality reduction methodology with TCF effectively identifies the most sensitive features. A maximum dimensionality reduction of 62% is achieved. The proposed methodology showed a 7.2% improvement in classification accuracy over the techniques reported in the previous study. Thus, developed ML models successfully classify the machined surface images with a minimum time and computational burden on the computer. [ABSTRACT FROM AUTHOR]

The 2-D compact variational mode decomposition (2-D-C-VMD) has potential research significance in data mining of hyperspectral images (HSIs). The paper proposes a method of concatenation of features. First, the 2-D-C-VMD technique is used to decompose the HSIs to obtain smooth and clear boundary sub-band images when the 2-D-C-VMD takes the most preferred a priori parameter K ×. Second, the optimal low-frequency component features of the image and the optimal high-frequency component constructed features are concatenated first and last, and the structure of the concatenation is constructed into a new fused data. Finally, in order to avoid the redundancy of the fused data band information from affecting the classification result, combine a recently developed simple and practical superpixelwise principal component analysis (SuperPCA) dimensionality reduction method to effectively reduce the dimensionality of the fused data. By comparing the analysis with relying only on the optimal low-frequency image feature information and with the direct linear superposition fusion that has been employed, it is verified that the concatenation of features approach proposed in this paper can obtain better recognition results. [ABSTRACT FROM AUTHOR]

Autoencoders (AEs) are a type of unsupervised neural networks, which can be used to solve various tasks, e.g., dimensionality reduction, image compression, and image denoising. An AE has two goals: (i) compress the original input to a low-dimensional space at the bottleneck of the network topology using an encoder, (ii) reconstruct the input from the representation at the bottleneck using a decoder. Both encoder and decoder are optimized jointly by minimizing a distortion-based loss which implicitly forces the model to keep only the information in input data required to reconstruct them and to reduce redundancies. In this paper, we propose a scheme to explicitly penalize feature redundancies in the bottleneck representation. To this end, we propose an additional loss term, based on the pairwise covariances of the network units, which complements the data reconstruction loss forcing the encoder to learn a more diverse and richer representation of the input. We tested our approach across different tasks, namely dimensionality reduction, image compression, and image denoising. Experimental results show that the proposed loss leads consistently to superior performance compared to using the standard AE loss. • We propose a scheme to avoid redundant features in the bottleneck representation of autoencoders. • We explicitly penalize the pair-wise correlations between the features and learn a diverse compressed embedding. • The proposed penalty acts as an unsupervised regularizer and can be integrated into any autoencoder model. [ABSTRACT FROM AUTHOR]

The definitive diagnosis and classification of individual cancers are crucial for patient care and cancer research. To achieve a robust diagnosis of central nervous system (CNS) tumors, a genotype‐phenotype integrated diagnostic approach was introduced in recent versions of the World Health Organization classification, followed by the incorporation of a genome‐wide DNA methylome‐based classification. Microarray‐based platforms are widely used to obtain DNA methylome data, and the German Cancer Research Center (Deutsches Krebsforschungszentrum [DKFZ]) has a webtool for a DNA methylation‐based classifier (DKFZ classifier). Integration of DNA methylome will further enhance the precision of CNS tumor classification, especially in diagnostically challenging cases. However, in the clinical application of DNA methylome‐based classification, challenges related to data interpretation persist, in addition to technical caveats, regulations, and limited accessibility. Dimensionality reduction (DMR) can complement integrated diagnosis by visualizing a profile and comparing it with other known samples. Therefore, DNA methylome‐based classification is a highly useful research tool for auxiliary analysis in challenging diagnostic and rare disease cases, and for establishing novel tumor concepts. Decoding the DNA methylome, especially by DMR in addition to DKFZ classifier, emphasizes the capability of grasping the fundamental biological principles that provide new perspectives on CNS tumors. [ABSTRACT FROM AUTHOR]

This paper presents a methodology that is designed for rapid exploratory analysis of the outputs from ensembles of climate models, especially when these outputs consist of maps. The approach formalizes and extends the technique of "intermodel empirical orthogonal function" analysis, combining multivariate analysis of variance techniques with singular value decompositions (SVDs) of structured components of the ensemble data matrix. The SVDs yield spatial patterns associated with these components, which we call ensemble principal patterns (EPPs). A unique hierarchical partitioning of variation is obtained for balanced ensembles in which all combinations of factors, such as GCM and RCM pairs in a regional ensemble, appear with equal frequency: suggestions are also proposed to handle unbalanced ensembles without imputing missing values or discarding runs. Applications include the selection of ensemble members to propagate uncertainty into subsequent analyses, and the diagnosis of modes of variation associated with specific model variants or parameter perturbations. The approach is illustrated using outputs from the EuroCORDEX regional ensemble over the United Kingdom. [ABSTRACT FROM AUTHOR]

The photoacoustic effect is an attractive tool for diagnosis in several biomedical applications. Analyzing photoacoustic signals, however, is challenging to provide qualitative results in an automated way. In this work, we introduce a dynamic modeling scheme of photoacoustic sensor data to classify blood samples according to their physiological status. Thirty-five whole human blood samples were studied with a state-space model estimated by a subspace method. Furthermore, the samples are classified using the model parameters and the linear discriminant analysis algorithm. The classification performance is compared with time- and frequency-domain features and an autoregressive-moving-average model. As a result, the proposed analysis can predict five blood classes: healthy women and men, microcytic and macrocytic anemia, and leukemia. Our findings indicate that the proposed method outperforms conventional signal processing techniques to analyze photoacoustic data for medical diagnosis. Hence, the method is a promising tool in point-of-care devices to detect hematological diseases in clinical scenarios. [ABSTRACT FROM AUTHOR]

We present a machine learning workflow to discover signatures in acoustic measurements that can be utilized to create a low-dimensional model to accurately predict the location of keyhole pores formed during additive manufacturing processes. Acoustic measurements were sampled at 100 kHz during single-layer laser powder bed fusion (LPBF) experiments, and spatio-temporal registration of pore locations was obtained from post-build radiography. Power spectral density (PSD) estimates of the acoustic data were then decomposed using non-negative matrix factorization with custom k -means clustering (NMF k ) to learn the underlying spectral patterns associated with pore formation. NMF k returned a library of basis signals and matching coefficients to blindly construct a feature space based on the PSD estimates in an optimized fashion. Moreover, the NMF k decomposition led to the development of computationally inexpensive machine learning models which are capable of quickly and accurately identifying pore formation with classification accuracy of supervised and unsupervised label learning greater than 95% and 90%, respectively. The intrinsic data compression of NMFk, the relatively light computational cost of the machine learning workflow, and the high classification accuracy makes the proposed workflow an attractive candidate for edge computing toward in-situ keyhole pore prediction in LPBF. [ABSTRACT FROM AUTHOR]

In the past decade, deep learning methods have proven to be highly effective in the classification of hyperspectral images (HSI), consistently outperforming traditional approaches. However, the large number of spectral bands in HSI data can lead to interference during the learning process. To address this issue, dimensionality reduction techniques can be employed to minimize data redundancy and improve HSI classification performance. Hence, we have developed an efficient lightweight learning framework consisting of two main components. Firstly, we utilized band selection and principal component analysis to reduce the dimensionality of HSI data, thereby reducing redundancy while retaining essential features. Subsequently, the pre-processed data was input into a modified VGG-based learning network for HSI classification. This method incorporates an improved dynamic activation function for the multi-layer perceptron to enhance non-linearity, and reduces the number of nodes in the fully connected layers of the original VGG architecture to improve speed while maintaining accuracy. This modified network structure, referred to as lightweight-VGG (LVGG), was specifically designed for HSI classification. Comprehensive experiments conducted on three publicly available HSI datasets consistently demonstrated that the LVGG method exhibited similar or better performance compared to other typical methods in the field of HSI classification. Our approach not only addresses the challenge of interference in deep learning methods for HSI classification, but also offers a lightweight and efficient solution for achieving high classification accuracy. [ABSTRACT FROM AUTHOR]

Single-cell multi-omics technology has catalyzed a transformative shift in contemporary cell biology, illuminating the nuanced relationship between genotype and phenotype. This paradigm shift hinges on the understanding that while genomic structures remain uniform across cells within an organism, the expression patterns dictate physiological traits. Leveraging high throughput sequencing, single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool, enabling comprehensive transcriptomic analysis at unprecedented resolution. This paper navigates through a landscape of dimensionality reduction techniques essential for distilling meaningful insights from the scRNA-seq datasets. Notably, while foundational, Principal Component Analysis may fall short of capturing the intricacies of diverse cell types. In response, nonlinear techniques have garnered traction, offering a more nuanced portrayal of cellular relationships. Among these, Pairwise Controlled Manifold Approximation Projection (PaCMAP) stands out for its capacity to preserve local and global structures. We present an augmented iteration, Compactness Preservation Pairwise Controlled Manifold Approximation Projection (CP-PaCMAP), a novel advancement for scRNA-seq data visualization. Employing benchmark datasets from critical human organs, we demonstrate the superior efficacy of CP-PaCMAP in preserving compactness, offering a pivotal breakthrough for enhanced classification and clustering in scRNA-seq analysis. A comprehensive suite of metrics, including Trustworthiness, Continuity, Mathew Correlation Coefficient, and Mantel test, collectively validate the fidelity and utility of proposed and existing techniques. These metrics provide a multi-dimensional evaluation, elucidating the performance of CP-PaCMAP compared to other dimensionality reduction techniques. [ABSTRACT FROM AUTHOR]

Feature Selection (FS) is an essential research topic in the area of machine learning. FS, which is the process of identifying the relevant features and removing the irrelevant and redundant ones, is meant to deal with high dimensionality problems to select the best performing feature subset. In the literature, many feature selection techniques approach the task as a research problem, where each state in the search space is a possible feature subset. In this paper, we introduce a new feature selection method based on reinforcement learning. First, decision tree branches are used to traverse the search space. Second, a transition similarity measure is proposed so as to ensure exploit-explore trade-off. Finally, the informative features are the most involved ones in constructing the best branches. The performance of the proposed approaches is evaluated on nine standard benchmark datasets. The results using the AUC score show the effectiveness of the proposed system. [ABSTRACT FROM AUTHOR]

Tetrahedral homonuclear tetrameric species are neutral or ionic tetrahedra of chemical elements, true molecular tetrahedra in strict geometrical sense. The aim of this work was to find all true elemental tetrahedra experimentally determined as stable and capable of being transferred from one medium/condition to another, to rationalize their structures and properties, and seek their technological significance. A database of elemental tetrahedra was built based on reliable literature, and a dataset of molecular descriptors was generated. Correlation analysis, hierarchical cluster analysis, principal component analysis, and some regression analysis were carried out. Twelve chemical elements from Groups 13-15 have tetrahedral species: anions E4 8-(Al, Ga, In, Tl), anions E4 4-(Si, Ge, Sn, Pb), neutral molecules E4 (P, As, Sb), and cations E4 + (P, As, Sb, Bi). These species appear in 39 forms, such as gas phase, solid Zintl phases, thin films, Zintl phase ammoniates, and cage compounds, among others. Zintl phases and forms of P4 and As4 are important for synthesis of new materials, chemical reactions, and other applications. Data compression has shown that the true tetrahedral species are a three-dimensional phenomenon, and that true tetrahedra can be distinguished from fictive tetrahedra. Grouping of the tetrahedra according to their periodic groups, charges, frequency, and diversity class values, tetrahedral size, and metallic character, were observed. Empirical rules for species size and principal components were established for true tetrahedra. Most descriptors are parabolic functions of the class variable. True tetrahedral species partly remain a puzzle and should be further investigated. [ABSTRACT FROM AUTHOR]

Inspired by the impressive successes of compress sensing-based machine learning algorithms, data augmentation-based efficient Gibbs samplers for Bayesian high-dimensional classification models are developed by compressing the design matrix to a much lower dimension. Ardent care is exercised in the choice of the projection mechanism, and an adaptive voting rule is employed to reduce sensitivity to the random projection matrix. Focusing on the high-dimensional Probit regression model, we note that the naive implementation of the data augmentation-based Gibbs sampler is not robust to the presence of co-linearity in the design matrix - a setup ubiquitous in n < p problems. We demonstrate that a simple fix based on joint updates of parameters in the latent space circumnavigates this issue. With a computationally efficient MCMC scheme in place, we introduce an ensemble classifier by creating R (~ 25-50) projected copies of the design matrix, and subsequently running R classification models with the R projected design matrix in parallel. We combine the output from the R replications via an adaptive voting scheme. Our scheme is inherently parallelizable and capable of taking advantage of modern computing environments often equipped with multiple cores. The empirical success of our methodology is illustrated in elaborate simulations and gene expression data applications. We also extend our methodology to a high-dimensional logistic regression model and carry out numerical studies to showcase its efficacy. [ABSTRACT FROM AUTHOR]

Cholera is a leading cause of mortality in Nigeria. The two most significant predictors of cholera are a lack of access to clean water and poor sanitary conditions. Other factors such as natural disasters, illiteracy, and internal conflicts that drive people to seek sanctuary in refugee camps may contribute to the spread of cholera in Nigeria. The aim of this research is to develop a cholera outbreak risk prediction (CORP) model using machine learning tools and data science. In this study, we developed a CORP model using design science perspectives and machine learning to detect cholera outbreaks in Nigeria. Nonnegative matrix factorization (NMF) was used for dimensionality reduction, and synthetic minority oversampling technique (SMOTE) was used for data balancing. Outliers were detected using density-based spatial clustering of applications with noise (DBSCAN) were removed improving the overall performance of the model, and the extreme-gradient boost algorithm was used for prediction. The findings revealed that the CORP model outcomes resulted in the best accuracy of 99.62%, Matthews's correlation coefficient of 0.976, and area under the curve of 99.2%, which were improved compared with the previous findings. The developed model can be helpful to healthcare providers in predicting possible cholera outbreaks. [ABSTRACT FROM AUTHOR]

Software-Defined Networking (SDN) is a strategy that leads the network via software by separating its control plane from the underlying forwarding plane. In support of a global digital network, multi-domain SDN architecture emerges as a viable solution. However, the complex and ever-evolving nature of network threats in a multi-domain environment presents a significant security challenge for controllers in detecting abnormalities. Moreover, multi-domain anomaly detection poses a daunting problem due to the need to process vast amounts of data from diverse domains. Deep learning models have gained popularity for extracting high-level feature representations from massive datasets. In this work, a novel deep neural network architecture, supervised learning based LD-BiHGA (Low Dimensional Bi-channel Hybrid GAN Attention) system is designed to learn class-specific features for accurate anomaly detection. Two asymmetric GANs are employed for learning the normal and abnormal network flows separately. Then, to extract more relevant features, a bi-channel attention mechanism is added. This is the first study to introduce an innovative hybrid architecture that merges bi-channel hybrid GANs with attention models for the purpose of anomaly detection in a multi-domain SDN environment that effectively handles real-time unbalanced data. The suggested architecture demonstrates its effectiveness on three benchmark datasets, achieving an average accuracy improvement of 7.225% on balanced datasets and 3.335% on imbalanced datasets compared to previous intrusion detection system (IDS) architectures in the literature. [ABSTRACT FROM AUTHOR]

Dimensionality reduction is a key technique for processing high-dimensional data, and linear discriminant analysis and its variant algorithms are effective supervised algorithms. However, most discriminant analysis algorithms have the following disadvantages: a) Cannot select more discriminative features; b) Ignore the interference of noise and redundant features in the original space; c) The computational complexity of updating the adjacency graph is high. In order to overcome these shortcomings, this paper proposed a fast adaptive local ratio sum discriminant analysis algorithm based on subspace learning. First, a model that unified the ratio sum criterion and subspace learning was proposed to explore the potential structure of the data in the subspace, select features with more discriminative information, and avoid being affected by noise in the original space; secondly, an anchor-based Strategies to construct an adjacency graph to represent the local structure of the data to accelerate the learning of the adjacency graph; finally,introducing Shannon entropy to avoid trivial solutions. Finally, the effectiveness of the algorithm is verified by comparison experiments on multiple data sets. [ABSTRACT FROM AUTHOR]

We present a novel technique for pruning called activation-based pruning to effectively prune fully connected feedforward neural networks for multi-object classification. Our technique is based on the number of times each neuron is activated during model training. We compare the performance of activation-based pruning with a popular pruning method: magnitude-based pruning. Further analysis demonstrated that activation-based pruning can be considered a dimensionality reduction technique, as it leads to a sparse low-rank matrix approximation for each hidden layer of the neural network. We also demonstrate that the rank-reduced neural network generated using activation-based pruning has better accuracy than a rank-reduced network using principal component analysis. We provide empirical results to show that, after each successive pruning, the amount of reduction in the magnitude of singular values of each matrix representing the hidden layers of the network is equivalent to introducing the sum of singular values of the hidden layers as a regularization parameter to the objective function. [ABSTRACT FROM AUTHOR]

Multi-omic analyses are necessary to understand the complex biological processes taking place at the tissue and cell level, but also to make reliable predictions about, for example, disease outcome. Several linear methods exist that create a joint embedding using paired information per sample, but recently there has been a rise in the popularity of neural architectures that embed paired -omics into the same non-linear manifold. This work describes a head-to-head comparison of linear and non-linear joint embedding methods using both bulk and single-cell multi-modal datasets. We found that non-linear methods have a clear advantage with respect to linear ones for missing modality imputation. Performance comparisons in the downstream tasks of survival analysis for bulk tumor data and cell type classification for single-cell data lead to the following insights: First, concatenating the principal components of each modality is a competitive baseline and hard to beat if all modalities are available at test time. However, if we only have one modality available at test time, training a predictive model on the joint space of that modality can lead to performance improvements with respect to just using the unimodal principal components. Second, -omic profiles imputed by neural joint embedding methods are realistic enough to be used by a classifier trained on real data with limited performance drops. Taken together, our comparisons give hints to which joint embedding to use for which downstream task. Overall, product-of-experts performed well in most tasks and was reasonably fast, while early integration (concatenation) of modalities did quite poorly. [ABSTRACT FROM AUTHOR]

Electrochemical multisensor systems were proven to be a very perspective research direction in modern analytical chemistry. The multisensor approach assumes an employment of cross‐sensitive chemical sensors in combination with multivariate data processing methods. Dimensionality reduction of the data obtained from multisensor systems is a very important step and it is mostly based on the traditional tools of chemometrics, such as Principal Component Analysis (PCA). In case of chemically complex samples, the response of multisensor systems may have a complex nonlinear nature and the use of linear modelling methods does not seem optimal. However, the potential of nonlinear dimensionality reduction methods in the processing of multisensor data has not yet been systematically studied. In this report we aim to fill this gap and assess the performance of various nonlinear dimensionality reduction tools: Isomap, Self‐Organizing Kohonen Maps, and Autoencoder. These methods were explored using three datasets from potentiometric multisensor systems obtained in various real applications. It was shown that nonlinear dimensionality reduction methods give the possibility to obtain additional and more detailed information about the analyzed objects/processes compared to PCA. However, calculation time for nonlinear dimensionality reduction methods essentially exceeds that for PCA, and it can be a limiting factor for application of such algorithms. [ABSTRACT FROM AUTHOR]