Uniform Manifold Approximation Research Articles

Generation of chemical library of near-IR dyes for photovoltaics applications

The dyes with light absorption ability in extended spectrum have huge potential in various photovoltaics applications. Absorption maxima (Lambda max) is predicted using machine learning (ML). Multiple machine learning models are used. Random Forest is best model among the tried ML models. A library of new dyes is created using python-based tool. Absorption maxima of newly generated dyes is predicted using best ML model (Random Forest). The generated library of dyes is visualized using Uniform Manifold Approximation and Projection (UMAP) plot. 30 dyes with absorption in extended spectrum are selected. Synthetic accessibility assessment is done to check ease of synthesis of selected dyes and to further narrow down the number of potential candidates. Structural behavior of selected dyes is studied using hierarchical cluster analysis. This study offers a theoretical framework for developing potential dyes that could exhibit light absorption in near-IR region of solar spectrum.

Enhanced synthetic generation of channel state information for millimeter‐wave networks in 5G communication systems

AbstractIn 5G communication systems, millimeter‐wave networks are pivotal, relying heavily on Channel State Information (CSI) for effective user‐to‐base station (BS) transmission. However, the acquisition of genuine CSI data remains a hurdle, often due to the expenses associated with simulations or physical experiments. This paper introduces an innovative method for generating artificial CSI data from real datasets, aiming to closely replicate authentic CSI samples. The procedure begins with an initial clustering analysis, followed using Principal Component Analysis and Uniform Manifold Approximation and Projection to reduce dimensionality. Then, the data distributions are transformed into multivariate normal distributions using Probability Integral Transformations (PIT). For data synthesis, Multilayer Perceptron based regression models are utilized, followed by inverse PIT transformations to return the data to its original space. Our method is compared against KDE‐based algorithms, demonstrating superior fidelity in reproducing real CSI samples. Additionally, we stress the importance of capturing CSI correlations among different BSs to refine data synthesis. This research propels forward data synthesis techniques, offering potential solutions for mitigating interference challenges in dense MMW networks and advancing 5G communication systems.

Identification of Beef Odors under Different Storage Day and Processing Temperature Conditions Using an Odor Sensing System.

This study used an odor sensing system with a 16-channel electrochemical sensor array to measure beef odors, aiming to distinguish odors under different storage days and processing temperatures for quality monitoring. Six storage days ranged from purchase (D0) to eight days (D8), with three temperature conditions: no heat (RT), boiling (100 °C), and frying (180 °C). Gas chromatography-mass spectrometry (GC-MS) analysis showed that odorants in the beef varied under different conditions. Compounds like acetoin and 1-hexanol changed significantly with the storage days, while pyrazines and furans were more detectable at higher temperatures. The odor sensing system data were visualized using principal component analysis (PCA) and uniform manifold approximation and projection (UMAP). PCA and unsupervised UMAP clustered beef odors by storage days but struggled with the processing temperatures. Supervised UMAP accurately clustered different temperatures and dates. Machine learning analysis using six classifiers, including support vector machine, achieved 57% accuracy for PCA-reduced data, while unsupervised UMAP reached 49.1% accuracy. Supervised UMAP significantly enhanced the classification accuracy, achieving over 99.5% with the dimensionality reduced to three or above. Results suggest that the odor sensing system can sufficiently enhance non-destructive beef quality and safety monitoring. This research advances electronic nose applications and explores data downscaling techniques, providing valuable insights for future studies.

Dimensionality reduction distills complex evolutionary relationships in seasonal influenza and SARS-CoV-2.

Public health researchers and practitioners commonly infer phylogenies from viral genome sequences to understand transmission dynamics and identify clusters of genetically-related samples. However, viruses that reassort or recombine violate phylogenetic assumptions and require more sophisticated methods. Even when phylogenies are appropriate, they can be unnecessary or difficult to interpret without specialty knowledge. For example, pairwise distances between sequences can be enough to identify clusters of related samples or assign new samples to existing phylogenetic clusters. In this work, we tested whether dimensionality reduction methods could capture known genetic groups within two human pathogenic viruses that cause substantial human morbidity and mortality and frequently reassort or recombine, respectively: seasonal influenza A/H3N2 and SARS-CoV-2. We applied principal component analysis (PCA), multidimensional scaling (MDS), t-distributed stochastic neighbor embedding (t-SNE), and uniform manifold approximation and projection (UMAP) to sequences with well-defined phylogenetic clades and either reassortment (H3N2) or recombination (SARS-CoV-2). For each low-dimensional embedding of sequences, we calculated the correlation between pairwise genetic and Euclidean distances in the embedding and applied a hierarchical clustering method to identify clusters in the embedding. We measured the accuracy of clusters compared to previously defined phylogenetic clades, reassortment clusters, or recombinant lineages. We found that MDS embeddings accurately represented pairwise genetic distances including the intermediate placement of recombinant SARS-CoV-2 lineages between parental lineages. Clusters from t-SNE embeddings accurately recapitulated known phylogenetic clades, H3N2 reassortment groups, and SARS-CoV-2 recombinant lineages. We show that simple statistical methods without a biological model can accurately represent known genetic relationships for relevant human pathogenic viruses. Our open source implementation of these methods for analysis of viral genome sequences can be easily applied when phylogenetic methods are either unnecessary or inappropriate.

Non-Intrusive Load Monitoring Based on Dimensionality Reduction and Adapted Spatial Clustering

Non-invasive load monitoring (NILM) deduces changes in energy consumption patterns and operational statuses of electrical equipment from power signals in the feed line. With the emergence of fine-grained power load distribution, the importance of utilizing this technology for implementing demand-side energy management in smart grid development has become increasingly prominent. To address the issue of low load identification accuracy stemming from complex and diverse load types, this paper introduces a NILM method based on uniform manifold approximation and projection (UMAP) reduction and enhanced density-based spatial clustering of applications with noise (DBSCAN). Firstly, this paper combines the characteristics of user load under transient and steady-state conditions and selects data with significant differences to construct a load-characteristic database. Additionally, UMAP is employed to reduce the dimensionality of high-dimensional load features and rebuild a load feature database. Subsequently, DBSCAN is utilized to categorize typical user loads, followed by a correlation analysis with the load-characteristic database to determine the types or classes of loads that involve switching actions. Finally, this paper simulates and analyzes the proposed method using the electricity consumption data of industrial users from the CER–Electricity–Data dataset. It identifies the electricity load data commonly utilized by users in a specific area of Zhejiang Province in China. The experimental results indicate that the accuracy of the proposed non-invasive load identification method reaches 95%. Compared to the wavelet transform, decision tree, and backpropagation network methods, the improvement is approximately 5%.

Digital Epidemiology of Prescription Drug References on X (Formerly Twitter): Neural Network Topic Modeling and Sentiment Analysis.

Data from the social media platform X (formerly Twitter) can provide insights into the types of language that are used when discussing drug use. In past research using latent Dirichlet allocation (LDA), we found that tweets containing "street names" of prescription drugs were difficult to classify due to the similarity to other colloquialisms and lack of clarity over how the terms were used. Conversely, "brand name" references were more amenable to machine-driven categorization. This study sought to use next-generation techniques (beyond LDA) from natural language processing to reprocess X data and automatically cluster groups of tweets into topics to differentiate between street- and brand-name data sets. We also aimed to analyze the differences in emotional valence between the 2 data sets to study the relationship between engagement on social media and sentiment. We used the Twitter application programming interface to collect tweets that contained the street and brand name of a prescription drug within the tweet. Using BERTopic in combination with Uniform Manifold Approximation and Projection and k-means, we generated topics for the street-name corpus (n=170,618) and brand-name corpus (n=245,145). Valence Aware Dictionary and Sentiment Reasoner (VADER) scores were used to classify whether tweets within the topics had positive, negative, or neutral sentiments. Two different logistic regression classifiers were used to predict the sentiment label within each corpus. The first model used a tweet's engagement metrics and topic ID to predict the label, while the second model used those features in addition to the top 5000 tweets with the largest term-frequency-inverse document frequency score. Using BERTopic, we identified 40 topics for the street-name data set and 5 topics for the brand-name data set, which we generalized into 8 and 5 topics of discussion, respectively. Four of the general themes of discussion in the brand-name corpus referenced drug use, while 2 themes of discussion in the street-name corpus referenced drug use. From the VADER scores, we found that both corpora were inclined toward positive sentiment. Adding the vectorized tweet text increased the accuracy of our models by around 40% compared with the models that did not incorporate the tweet text in both corpora. BERTopic was able to classify tweets well. As with LDA, the discussion using brand names was more similar between tweets than the discussion using street names. VADER scores could only be logically applied to the brand-name corpus because of the high prevalence of non-drug-related topics in the street-name data. Brand-name tweets either discussed drugs positively or negatively, with few posts having a neutral emotionality. From our machine learning models, engagement alone was not enough to predict the sentiment label; the added context from the tweets was needed to understand the emotionality of a tweet.

Assessing spirlin Alburnoides bipunctatus (Bloch, 1782) as an early indicator of climate change and anthropogenic stressors using ecological modeling and machine learning

Combining single-species ecological modeling with advanced machine learning to investigate the long-term population dynamics of the rheophilic fish spirlin offers a powerful approach to understanding environmental changes and climate shifts in aquatic ecosystems. A new ESHIPPOClim model was developed by integrating climate change assessment into the ESHIPPO model. The model identifies spirlin as a potential early indicator of environmental changes, highlighting the interactive effects of climate change and anthropogenic stressors on fish populations and freshwater ecosystems. The ESHIPPOClim model reveals that 28.57 % of the spirlin's data indicates high resilience and ecological responsiveness, with 34.92 % showing medium-high adaptability, suggesting its substantial ability to withstand environmental stressors. With 36.51 % of the data in medium level and no data in the low category, spirlin may serve as a sentinel species, providing early warnings of environmental stressors before they severely impact other species or ecosystems. The results of uniform manifold approximation and projection (UMAP) and a decision tree show that pollution has the highest impact on the population dynamics of spirlin, followed by annual water temperature, overexploitation, and invasive species. Despite the obtained key drivers, higher abundance, dominance, and frequency values were detected in habitats with higher HIPPO stressors and climate change effects. Integrating state-of-the-art machine learning models has enhanced the predictive power of the ESHIPPOClim model, achieving approximately 90 % accuracy in identifying spirlin as an early indicator of climate change and anthropogenic stressors. The ESHIPPOClim model offers a holistic approach with broad practical applications using a simplified three-point scale, adaptable to various fish species, communities, and regions. The ecological modeling supported with advanced machine learning could serve as a foundation for rapid and cost-effective management of aquatic ecosystems, revealing the adaptability potential of fish species, which is crucial in rapidly changing environments.

Machine learning-based reproducible prediction of type 2 diabetes subtypes

Aims/hypothesisClustering-based subclassification of type 2 diabetes, which reflects pathophysiology and genetic predisposition, is a promising approach for providing personalised and effective therapeutic strategies. Ahlqvist’s classification is currently the most vigorously validated method because of its superior ability to predict diabetes complications but it does not have strong consistency over time and requires HOMA2 indices, which are not routinely available in clinical practice and standard cohort studies. We developed a machine learning (ML) model to classify individuals with type 2 diabetes into Ahlqvist’s subtypes consistently over time.MethodsCohort 1 dataset comprised 619 Japanese individuals with type 2 diabetes who were divided into training and test sets for ML models in a 7:3 ratio. Cohort 2 dataset, comprising 597 individuals with type 2 diabetes, was used for external validation. Participants were pre-labelled (T2Dkmeans) by unsupervised k-means clustering based on Ahlqvist’s variables (age at diagnosis, BMI, HbA1c, HOMA2-B and HOMA2-IR) to four subtypes: severe insulin-deficient diabetes (SIDD), severe insulin-resistant diabetes (SIRD), mild obesity-related diabetes (MOD) and mild age-related diabetes (MARD). We adopted 15 variables for a multiclass classification random forest (RF) algorithm to predict type 2 diabetes subtypes (T2DRF15). The proximity matrix computed by RF was visualised using a uniform manifold approximation and projection. Finally, we used a putative subset with missing insulin-related variables to test the predictive performance of the validation cohort, consistency of subtypes over time and prediction ability of diabetes complications.ResultsT2DRF15 demonstrated a 94% accuracy for predicting T2Dkmeans type 2 diabetes subtypes (AUCs ≥0.99 and F1 score [an indicator calculated by harmonic mean from precision and recall] ≥0.9) and retained the predictive performance in the external validation cohort (86.3%). T2DRF15 showed an accuracy of 82.9% for detecting T2Dkmeans, also in a putative subset with missing insulin-related variables, when used with an imputation algorithm. In Kaplan–Meier analysis, the diabetes clusters of T2DRF15 demonstrated distinct accumulation risks of diabetic retinopathy in SIDD and that of chronic kidney disease in SIRD during a median observation period of 11.6 (4.5–18.3) years, similarly to the subtypes using T2Dkmeans. The predictive accuracy was improved after excluding individuals with low predictive probability, who were categorised as an ‘undecidable’ cluster. T2DRF15, after excluding undecidable individuals, showed higher consistency (100% for SIDD, 68.6% for SIRD, 94.4% for MOD and 97.9% for MARD) than T2Dkmeans.Conclusions/interpretationThe new ML model for predicting Ahlqvist’s subtypes of type 2 diabetes has great potential for application in clinical practice and cohort studies because it can classify individuals with missing HOMA2 indices and predict glycaemic control, diabetic complications and treatment outcomes with long-term consistency by using readily available variables. Future studies are needed to assess whether our approach is applicable to research and/or clinical practice in multiethnic populations.Graphical

Using machine learning techniques for exploration and classification of laboratory data

Abstract Objectives The study aims to acquaint readers with six widely used machine learning (ML) techniques (Principal Component Analysis (PCA), Uniform Manifold Approximation and Projection (UMAP), k-means, hierarchical clustering and the decision tree models (rpart and random forest)) that might be useful for the analysis of laboratory data. Methods Utilizing a recently validated data set from lung cancer diagnostics, we investigate how ML can support the search for a suitable tumor marker panel for the differentiation of small cell (SCLC) and non-small cell lung cancer (NSCLC). Results The ML techniques used here effectively helped to gain a quick overview of the data structures and provide initial answers to the clinical questions. Dimensionality reduction techniques such as PCA and UMAP offered insightful visualization and impression of the data structure, suggesting the existence of two tumor groups with a large overlap of largely inconspicuous values. This impression was confirmed by a cluster analysis with the k-means algorithm, indicative of unsupervised learning. For supervised learning, decision tree models like rpart or random forest demonstrated their utility in differential diagnosis of the two tumor types. The rpart model, which constructs binary decision trees based on the recursive partitioning algorithm, suggests a tree involving four serum tumor markers (STMs), which were confirmed by the random forest approach. Both highlighted pro-gastrin-releasing peptide (ProGRP), neuron specific enolase (NSE), cytokeratin-19 fragment (CYFRA 21-1) and cancer antigen (CA) 72-4 as key tumor markers, aligning with the outcomes of the initial statistical analysis. Cross-validation of the two proposals showed a higher area under the receiver operating characteristic (AUROC) curve of 0.95 with a 95 % confidence interval (CI) of 0.92–0.97 for the random forest model compared to an AUROC curve of 0.88 (95 % CI: 0.83–0.93). Conclusions ML can provide a useful overview of inherent medical data structures and distinguish significant from less pertinent features. While by no means replacing human medical and statistical expertise, ML can significantly accelerate the evaluation of medical data, supporting a more informed diagnostic dialogue between physicians and statisticians.

Single-cell transcriptomic analysis reveals a decrease in the frequency of macrophage-RGS1high subsets in patients with osteoarticular tuberculosis

BackgroundCell subsets differentially modulate host immune responses to Mycobacterium tuberculosis (MTB) infection. However, the nature and functions of these subsets against osteoarticular tuberculosis (OTB) are unclear. Here, we aimed to understand the phenotypes and functions of immune cell subsets in patients with OTB using single-cell RNA sequencing (scRNA-Seq).MethodsPathological and healthy adjacent tissues were isolated from patients with OTB and subjected to scRNA-Seq. Unsupervised clustering of cells was performed based on gene expression profiles, and uniform manifold approximation and projection was used for clustering visualization.ResultsThirteen cell subsets were identified in OTB tissues. scRNA-seq datasets of patients and healthy controls (HCs) showed that infection changed the frequency of immune cell subsets in OTB tissues. Myeloid cell examination revealed nine subsets. The frequency of macrophage-RGS1high subsets decreased in OTB tissues; this increased MTB susceptibility in an SLC7A11/ferroptosis-dependent manner. Immunohistochemistry assays and flow cytometry for patients with OTB and osteoarticular bacterial infection (OBI) and HCs verified that the frequency of macrophage-RGS1high subset decreased in OTB tissues and blood samples, thereby distinguishing patients with OTB from HCs and patients with OBI.ConclusionThe macrophage-RGS1high subset levels were decreased in patients with OTB, and would be up-regulated after effective treatment. Therefore, the clinical significance of this study is to discover that macrophage-RGS1high subset may serve as a potential biomarker for OTB diagnosis and treatment efficacy monitoring.

Benchmarking clustering, alignment, and integration methods for spatial transcriptomics

BackgroundSpatial transcriptomics (ST) is advancing our understanding of complex tissues and organisms. However, building a robust clustering algorithm to define spatially coherent regions in a single tissue slice and aligning or integrating multiple tissue slices originating from diverse sources for essential downstream analyses remains challenging. Numerous clustering, alignment, and integration methods have been specifically designed for ST data by leveraging its spatial information. The absence of comprehensive benchmark studies complicates the selection of methods and future method development.ResultsIn this study, we systematically benchmark a variety of state-of-the-art algorithms with a wide range of real and simulated datasets of varying sizes, technologies, species, and complexity. We analyze the strengths and weaknesses of each method using diverse quantitative and qualitative metrics and analyses, including eight metrics for spatial clustering accuracy and contiguity, uniform manifold approximation and projection visualization, layer-wise and spot-to-spot alignment accuracy, and 3D reconstruction, which are designed to assess method performance as well as data quality. The code used for evaluation is available on our GitHub. Additionally, we provide online notebook tutorials and documentation to facilitate the reproduction of all benchmarking results and to support the study of new methods and new datasets.ConclusionsOur analyses lead to comprehensive recommendations that cover multiple aspects, helping users to select optimal tools for their specific needs and guide future method development.

Crop Water Status Analysis from Complex Agricultural Data Using UMAP-Based Local Biplot

To optimize growth and management, precision agriculture relies on a deep understanding of agricultural dynamics, particularly crop water status analysis. Leveraging unmanned aerial vehicles, we can efficiently acquire high-resolution spatiotemporal samples by utilizing remote sensors. However, non-linear relationships among data features, localized within specific subgroups, frequently emerge in agricultural data. Interpreting these complex patterns requires sophisticated analysis due to the presence of noise, high variability, and non-stationarity behavior in the collected samples. Here, we introduce Local Biplot, a methodological framework tailored for discerning meaningful data patterns in non-stationary contexts for precision agriculture. Local Biplot relies on the well-known uniform manifold approximation and projection method, such as UMAP, and local affine transformations to codify non-stationary and non-linear data patterns while maintaining interpretability. This lets us find important clusters for transformation and projection within a single global axis pair. Hence, our framework encompasses variable and observational contributions within individual clusters. At the same time, we provide a relevance analysis strategy to help explain why those clusters exist, facilitating the understanding of data dynamics while favoring interpretability. We demonstrated our method’s capabilities through experiments on both synthetic and real-world datasets, covering scenarios involving grass and rice crops. Moreover, we use random forest and linear regression models to predict water status variables from our Local Biplot-based feature ranking and clusters. Our findings revealed enhanced clustering and prediction capability while emphasizing the importance of input features in precision agriculture. As a result, Local Biplot is a useful tool to visualize, analyze, and compare the intricate underlying patterns and internal structures of complex agricultural datasets.

Detection of defects in composite insulators based on laser‐induced plasma combined with machine learning

AbstractDue to Prolonged operation and external environmental factors, composite insulators may develop various defects, which can potentially lead to serious accidents in power systems. Detecting and analyzing these defects is critically important. In this study, we combine machine learning with laser‐induced breakdown spectroscopy (LIBS) to identify defects in composite insulators and obtain spectral data from both defective and nondefective samples. The Uniform Manifold Approximation and Projection algorithm was employed to reduce the dimensionality of the data, thereby enhancing detection accuracy and efficiency. Decision tree, random forest (RF), K‐nearest neighbor, and support vector machine algorithms were used to classify the dimensionality‐reduced data. The results indicate that the RF algorithm achieved the best classification performance, with accuracies of 100% and 95.46% for the training and test sets, respectively. Furthermore, the precision, recall, and F1 scores, which reflect model performance, also showed superior results with the RF algorithm. These findings suggest that the combination of LIBS technology and machine learning can rapidly and accurately detect and analyze defects in composite insulators, offering new insights and methods for defect detection in composite insulators.

Comparative Analysis of Manifold Learning-Based Dimension Reduction Methods: A Mathematical Perspective

Manifold learning-based approaches have emerged as prominent techniques for dimensionality reduction. Among these methods, t-Distributed Stochastic Neighbor Embedding (t-SNE) and Uniform Manifold Approximation and Projection (UMAP) stand out as two of the most widely used and effective approaches. While both methods share similar underlying procedures, empirical observations indicate two distinctive properties: global data structure preservation and computational efficiency. However, the underlying mathematical principles behind these distinctions remain elusive. To address this gap, this study presents a comparative analysis of the subprocesses involved in these methods, aiming to elucidate the mathematical mechanisms underlying the observed distinctions. By meticulously examining the equation formulations, the mathematical mechanisms contributing to global data structure preservation and computational efficiency are elucidated. To validate the theoretical analysis, data are collected through a laboratory experiment, and an open-source dataset is utilized for validation across different datasets. The consistent alignment of results obtained from both balanced and unbalanced datasets robustly confirms the study’s findings. The insights gained from this study provide a deeper understanding of the mathematical underpinnings of t-SNE and UMAP, enabling more informed and effective use of these dimensionality reduction techniques in various applications, such as anomaly detection, natural language processing, and bioinformatics.

Hunting for Polluted White Dwarfs and Other Treasures with Gaia XP Spectra and Unsupervised Machine Learning

White dwarfs (WDs) polluted by exoplanetary material provide the unprecedented opportunity to directly observe the interiors of exoplanets. However, spectroscopic surveys are often limited by brightness constraints, and WDs tend to be very faint, making detections of large populations of polluted WDs difficult. In this paper, we aim to increase considerably the number of WDs with multiple metals in their atmospheres. Using 96,134 WDs with Gaia DR3 BP/RP (XP) spectra, we constructed a 2D map using an unsupervised machine-learning technique called Uniform Manifold Approximation and Projection (UMAP) to organize the WDs into identifiable spectral regions. The polluted WDs are among the distinct spectral groups identified in our map. We have shown that this selection method could potentially increase the number of known WDs with five or more metal species in their atmospheres by an order of magnitude. Such systems are essential for characterizing exoplanet diversity and geology.

Spectroscopic Phenological Characterization of Mangrove Communities

Spaceborne spectroscopic imaging offers the potential to improve our understanding of biodiversity and ecosystem services, particularly for challenging and rich environments like mangroves. Understanding the signals present in large volumes of high-dimensional spectroscopic observations of vegetation communities requires the characterization of seasonal phenology and response to environmental conditions. This analysis leverages both spectroscopic and phenological information to characterize vegetation communities in the Sundarban riverine mangrove forest of the Ganges–Brahmaputra delta. Parallel analyses of surface reflectance spectra from NASA’s EMIT imaging spectrometer and MODIS vegetation abundance time series (2000–2022) reveal the spectroscopic and phenological diversity of the Sundarban mangrove communities. A comparison of spectral and temporal feature spaces rendered with low-order principal components and 3D embeddings from Uniform Manifold Approximation and Projection (UMAP) reveals similar structures with multiple spectral and temporal endmembers and multiple internal amplitude continua for both EMIT reflectance and MODIS Enhanced Vegetation Index (EVI) phenology. The spectral and temporal feature spaces of the Sundarban represent independent observations sharing a common structure that is driven by the physical processes controlling tree canopy spectral properties and their temporal evolution. Spectral and phenological endmembers reside at the peripheries of the mangrove forest with multiple outward gradients in amplitude of reflectance and phenology within the forest. Longitudinal gradients of both phenology and reflectance amplitude coincide with LiDAR-derived gradients in tree canopy height and sub-canopy ground elevation, suggesting the influence of surface hydrology and sediment deposition. RGB composite maps of both linear (PC) and nonlinear (UMAP) 3D feature spaces reveal a strong contrast between the phenological and spectroscopic diversity of the eastern Sundarban and the less diverse western Sundarban.

Enhanced classification of pyrite generations based on mineral chemistry using uniform manifold approximation and projection (UMAP)

Trace element signatures are tracked to unravel the genetic history of ore deposits in several mineral systems. This is particularly true for pyrite, a ubiquitous component of many ore-forming systems, including orogenic gold deposits. Here, we critically compare the efficacy of utilizing Uniform Manifold Approximation and Projection (UMAP) versus Principal Component Analysis (PCA) as dimensionality reduction tools applied to a 31 element dataset collected using Laser Ablation Inductively Coupled Mass Spectrometry of pyrite grains from the Kibali gold district (Democratic Republic of Congo). Because of the non-linearity inherent to mineral chemistry and because of its superior preservation of local (distances within clusters) and global (separation between clusters) data relationships, the UMAP approach outperforms dimensionality reduction by PCA. We further present a workflow in which UMAP dimensionality reduction is followed by k-means clustering to guide the classification of pyrite generations in the Kibali case study. Validating this approach with trace elements and UMAP + k-means on a seed-by-seed petrography basis shows that the workflow significantly enhances the original pyrite classification, previously based on texture. This study thus emphasizes the utility of employing advanced statistical analysis methods to capture the intricate nature of pyrite formation. These findings will shape best practices for handling large multi-element datasets in pyrite mineral chemistry studies and are extrapolatable to other mineral systems in which trace element signatures are used to infer the conditions of ore deposit genesis.

Deep learning-based electricity theft prediction in non-smart grid environments

In developing countries, smart grids are nonexistent, and electricity theft significantly hampers power supply. This research introduces a lightweight deep-learning model using monthly customer readings as input data. By employing careful direct and indirect feature engineering techniques, including Principal Component Analysis (PCA), t-distributed Stochastic Neighbor Embedding (t-SNE), UMAP (Uniform Manifold Approximation and Projection), and resampling methods such as Random-Under-Sampler (RUS), Synthetic Minority Over-sampling Technique (SMOTE), and Random-Over-Sampler (ROS), an effective solution is proposed. Previous studies indicate that models achieve high precision, recall, and F1 score for the non-theft (0) class, but perform poorly, even achieving 0 %, for the theft (1) class. Through parameter tuning and employing Random-Over-Sampler (ROS), significant improvements in accuracy, precision (89 %), recall (94 %), and F1 score (91 %) for the theft (1) class are achieved. The results demonstrate that the proposed model outperforms existing methods, showcasing its efficacy in detecting electricity theft in non-smart grid environments.

Enhancing the rationale of convolutional neural networks for glitch classification in gravitational wave detectors: a visual explanation

In the pursuit of detecting gravitational waves, ground-based interferometers (e.g. LIGO, Virgo, and KAGRA) face a significant challenge: achieving the extremely high sensitivity required to detect fluctuations at distances significantly smaller than the diameter of an atomic nucleus. Cutting-edge materials and innovative engineering techniques have been employed to enhance the stability and precision of the interferometer apparatus over the years. These efforts are crucial for reducing the noise that masks the subtle gravitational wave signals. Various sources of interference, such as seismic activity, thermal fluctuations, and other environmental factors, contribute to the total noise spectra characteristic of the detector. Therefore, addressing these sources is essential to enhance the interferometer apparatus’s stability and precision. Recent research has emphasised the importance of classifying non-stationary and non-Gaussian glitches, employing sophisticated algorithms and machine learning methods to distinguish genuine gravitational wave signals from instrumental artefacts. The time-frequency-amplitude representation of these transient disturbances exhibits a wide range of new shapes, variability, and features, reflecting the evolution of interferometer technology. In this study, we developed a convolutional neural network model to classify glitches using spectrogram images from the Gravity Spy O1 dataset. We employed score-class activation mapping and the uniform manifold approximation and projection algorithm to visualise and understand the classification decisions made by our model. We assessed the model’s validity and investigated the causes of misclassification from these results.

Compressed representation of brain genetic transcription.

The architecture of the brain is too complex to be intuitively surveyable without the use of compressed representations that project its variation into a compact, navigable space. The task is especially challenging with high-dimensional data, such as gene expression, where the joint complexity of anatomical and transcriptional patterns demands maximum compression. The established practice is to use standard principal component analysis (PCA), whose computational felicity is offset by limited expressivity, especially at great compression ratios. Employing whole-brain, voxel-wise Allen Brain Atlas transcription data, here we systematically compare compressed representations based on the most widely supported linear and non-linear methods-PCA, kernel PCA, non-negative matrix factorisation (NMF), t-stochastic neighbour embedding (t-SNE), uniform manifold approximation and projection (UMAP), and deep auto-encoding-quantifying reconstruction fidelity, anatomical coherence, and predictive utility across signalling, microstructural, and metabolic targets, drawn from large-scale open-source MRI and PET data. We show that deep auto-encoders yield superior representations across all metrics of performance and target domains, supporting their use as the reference standard for representing transcription patterns in the human brain.