Search

Dimensionality reduction and clustering are often used as preliminary steps for many complex machine learning tasks. The presence of noise and outliers can deteriorate the performance of such preprocessing and therefore impair the subsequent analysis tremendously. In manifold learning, several studies indicate solutions for removing background noise or noise close to the structure when the density is substantially higher than that exhibited by the noise. However, in many applications, including astronomical datasets, the density varies alongside manifolds that are buried in a noisy background. We propose a novel method to extract manifolds in the presence of noise based on the idea of Ant colony optimization. In contrast to the existing random walk solutions, our technique captures points that are locally aligned with major directions of the manifold. Moreover, we empirically show that the biologically inspired formulation of ant pheromone reinforces this behavior enabling it to recover multiple manifolds embedded in extremely noisy data clouds. The algorithm performance in comparison to state-of-the-art approaches for noise reduction in manifold detection and clustering is demonstrated, on several synthetic and real datasets, including an N-body simulation of a cosmological volume., Accepted for publication by IEEE Transactions on Knowledge and Data Engineering

Recent developments in communication technologies, such as 5G, together with innovative computing paradigms, such as edge computing, provide further possibilities for the implementation of real-time networked control systems. However, privacy and cyber-security concerns arise when sharing private data between sensors, agents and a third-party computing facility. In this paper, a secure version of the distributed formation control is presented, analyzed and simulated, where gradient-based formation control law is implemented in the edge, with sensor and actuator information being secured by fully homomorphic encryption method based on learning with error (FHE-LWE) combined with a proposed mixed uniform-logarithmic quantizer (MULQ). The novel quantizer is shown to be suitable for realizing secure control systems with FHE-LWE where the critical real-time information can be quantized into a prescribed bounded space of plaintext while satisfying a sector bound condition whose lower and upper-bound can be made sufficiently close to an identity. An absolute stability analysis is presented, that shows the asymptotic stability of the closed-loop secure control system.

The distribution of galaxies and clusters of galaxies on the mega-parsec scale of the Universe follows an intricate pattern now famously known as the Large-Scale Structure or the Cosmic Web. To study the environments of this network, several techniques have been developed that are able to describe its properties and the properties of groups of galaxies as a function of their environment. In this work, we analyse the previously introduced framework: 1-Dimensional Recovery, Extraction, and Analysis of Manifolds (1-dream) on N-body cosmological simulation data of the Cosmic Web. The 1-DREAM toolbox consists of five Machine Learning methods, whose aim is the extraction and modelling of one-dimensional structures in astronomical big data settings. We show that 1-DREAM can be used to extract structures of different density ranges within the Cosmic Web and to create probabilistic models of them. For demonstration, we construct a probabilistic model of an extracted filament and move through the structure to measure properties such as local density and velocity. We also compare our toolbox with a collection of methodologies which trace the Cosmic Web. We show that 1-DREAM is able to split the network into its various environments with results comparable to the state-of-the-art methodologies. A detailed comparison is then made with the public code disperse, in which we find that 1-DREAM is robust against changes in sample size making it suitable for analysing sparse observational data, and finding faint and diffuse manifolds in low-density regions.

The presence of manifolds is a common assumption in many applications, including astronomy and computer vision. For instance, in astronomy, low-dimensional stellar structures, such as streams, shells, and globular clusters, can be found in the neighborhood of big galaxies such as the Milky Way. Since these structures are often buried in very large data sets, an algorithm, which can not only recover the manifold but also remove the background noise (or outliers), is highly desirable. While other works try to recover manifolds either by pushing all points toward manifolds or by downsampling from dense regions, aiming to solve one of the problems, they generally fail to suppress the noise on manifolds and remove background noise simultaneously. Inspired by the collective behavior of biological ants in food-seeking process, we propose a new algorithm that employs several random walkers equipped with a local alignment measure to detect and denoise manifolds. During the walking process, the agents release pheromone on data points, which reinforces future movements. Over time the pheromone concentrates on the manifolds, while it fades in the background noise due to an evaporation procedure. We use the Markov chain (MC) framework to provide a theoretical analysis of the convergence of the algorithm and its performance. Moreover, an empirical analysis, based on synthetic and real-world data sets, is provided to demonstrate its applicability in different areas, such as improving the performance of t-distributed stochastic neighbor embedding (t-SNE) and spectral clustering using the underlying MC formulas, recovering astronomical low-dimensional structures, and improving the performance of the fast Parzen window density estimator.

Compact stellar systems such as Ultra-compact dwarfs (UCDs) and Globular Clusters (GCs) around galaxies are known to be the tracers of the merger events that have been forming these galaxies. Therefore, identifying such systems allows to study galaxies mass assembly, formation and evolution. However, in the lack of spectroscopic information detecting UCDs/GCs using imaging data is very uncertain. Here, we aim to train a machine learning model to separate these objects from the foreground stars and background galaxies using the multi-wavelength imaging data of the Fornax galaxy cluster in 6 filters, namely u, g, r, i, J and Ks. The classes of objects are highly imbalanced which is problematic for many automatic classification techniques. Hence, we employ Synthetic Minority Over-sampling to handle the imbalance of the training data. Then, we compare two classifiers, namely Localized Generalized Matrix Learning Vector Quantization (LGMLVQ) and Random Forest (RF). Both methods are able to identify UCDs/GCs with a precision and a recall of >93% and provide relevances that reflect the importance of each feature dimension for the classification. Both methods detect angular sizes as important markers for this classification problem. While it is astronomical expectation that color indices of u−i and i−Ks are the most important colors, our analysis shows that colors such as g−r are more informative, potentially because of higher signal-to-noise ratio. Besides the excellent performance the LGMLVQ method allows further interpretability by providing the feature importance for each individual class, class-wise representative samples and the possibility for non-linear visualization of the data as demonstrated in this contribution. We conclude that employing machine learning techniques to identify UCDs/GCs can lead to promising results. Especially transparent methods allow further investigation and analysis of importance of the measurements for the detection problem and provide tools for non-linear visualization of the data.

Topological data analysis tools enjoy increasing popularity in a wide range of applications, such as Computer graphics, Image analysis, Machine learning, and Astronomy for extracting information. However, due to computational complexity, processing large numbers of samples of higher dimensionality quickly becomes infeasible. This contribution is twofold: We present an efficient novel sub-sampling strategy inspired by Coulomb's law to decrease the number of data points in d-dimensional point clouds while preserving its homology. The method is not only capable of reducing the memory and computation time needed for the construction of different types of simplicial complexes but also preserves the size of the voids in d-dimensions, which is crucial e.g. for astronomical applications. Furthermore, we propose a technique to construct a probabilistic description of the border of significant cycles and cavities inside the point cloud. We demonstrate and empirically compare the strategy in several synthetic scenarios and an astronomical particle simulation of a dwarf galaxy for the detection of superbubbles (supernova signatures). (c) 2021 The Authors. Published by Elsevier B.V. This is an open access article under the CC BY license (http:// creativecommons.org/licenses/by/4.0/).

Less is known about the relationship between conduct disorder (CD), callous–unemotional (CU) traits, and positive and negative parenting in youth compared to early childhood. We combined traditional univariate analyses with a novel machine learning classifier (Angle-based Generalized Matrix Learning Vector Quantization) to classify youth (N = 756; 9–18 years) into typically developing (TD) or CD groups with or without elevated CU traits (CD/HCU, CD/LCU, respectively) using youth- and parent-reports of parenting behavior. At the group level, both CD/HCU and CD/LCU were associated with high negative and low positive parenting relative to TD. However, only positive parenting differed between the CD/HCU and CD/LCU groups. In classification analyses, performance was best when distinguishing CD/HCU from TD groups and poorest when distinguishing CD/HCU from CD/LCU groups. Positive and negative parenting were both relevant when distinguishing CD/HCU from TD, negative parenting was most relevant when distinguishing between CD/LCU and TD, and positive parenting was most relevant when distinguishing CD/HCU from CD/LCU groups. These findings suggest that while positive parenting distinguishes between CD/HCU and CD/LCU, negative parenting is associated with both CD subtypes. These results highlight the importance of considering multiple parenting behaviors in CD with varying levels of CU traits in late childhood/adolescence.

Increasing number of sectors which affect human lives, are using Machine Learning (ML) tools. Hence the need for understanding their working mechanism and evaluating their fairness in decision-making, are becoming paramount, ushering in the era of Explainable AI (XAI). In this contribution we introduced a few intrinsically interpretable models which are also capable of dealing with missing values, in addition to extracting knowledge from the dataset and about the problem. These models are also capable of visualisation of the classifier and decision boundaries: they are the angle based variants of Learning Vector Quantization. We have demonstrated the algorithms on a synthetic dataset and a real-world one (heart disease dataset from the UCI repository). The newly developed classifiers helped in investigating the complexities of the UCI dataset as a multiclass problem. The performance of the developed classifiers were comparable to those reported in literature for this dataset, with additional value of interpretability, when the dataset was treated as a binary class problem., Comment: Accepted for proceedings of the International Joint Conference on Neural Networks (IJCNN) 2020

Background: Measurement of steroid metabolite excretion in urine by gas chromatography-mass spectrometry (GC-MS) provides a comprehensive profile of an individual’s adrenal and gonadal steroid production. It has long been acknowledged as a useful tool for diagnosis of inborn disorders of steroidogenesis leading to congenital adrenal hyperplasia and disorders of sex development. Ratios of steroid metabolites can be employed as surrogates for enzymatic activities of distinct steroidogenic enzymes and can also be applied to single random urine samples, making this a more feasible approach for use with paediatric patients. However, widespread use in the acute setting for diagnosis of these disorders is hampered by the considerable expertise required for interpretation. Here we developed a novel steroid metabolomics approach for the detection and differential diagnosis of inborn steroidogenic disorders, combining mass spectrometry-based steroid profiling with machine learning-based data analysis, suitable for automation and interpretation without specialist expertise. Methods: We performed multi-steroid profiling by GC-MS, quantifying 34 steroid metabolites, in urine samples from 829 healthy controls and 178 untreated patients with inborn steroidogenic disorders. This cohort included patients with inborn deficiencies in the following enzymes: CYP21A2 (n=26), CYP11B1 (n=12), CYP17A1 (n=30), POR (n=37), HSD3B2 (n=22), and SRD5A2 (n=51). We assessed the diagnostic performance of conventional biochemical assessment employing 15 steroid precursor-to-product ratios, each historically established as indicative of a distinct steroidogenesis disorder. We compared this to the performance of our novel steroid metabolomics approach, which involved analysis of the GC-MS multi-steroid profiles by a custom-designed approach, Angle Learning Vector Quantization (ALVQ), which classifies samples by comparing similarity of their steroid metabolome to representative steroid metabolome prototypes for each enzyme deficiency. Results: The conventional biochemical steroid ratio approach demonstrated acceptable sensitivity and specificity. However, the automated steroid metabolomics approach (ALVQ) performed significantly superior to this, particularly with regards to specificity. For differentiating patients from healthy controls, sensitivity and specificity of ALVQ were 97% and 98%, respectively. For differentiation of each pathogenic enzymatic defect, ALVQ performed superiorly, with sensitivity and specificity ranging between 95 and 100%. Conclusion: We present a novel steroid metabolomics approach, able to automatically detect and differentiate six different inborn disorders of steroidogenesis, with improved performance when compared to reference standard metabolite ratios. Steroid metabolomics can expedite and standardise interpretation of complex urinary steroid metabolome data, making this technique more accessible to clinicians, and has excellent potential for implementation in routine clinical practice.

Background Urinary steroid metabolite profiling is an accurate reflection of adrenal and gonadal steroid output and metabolism in peripheral target cells of steroid action. Measurement of steroid metabolite excretion by gas chromatography-massspectrometry (GC–MS) is considered reference standard for biochemical diagnosis of steroidogenic disorders. However, performance of GC–MS analysis and interpretation of the resulting data requires significant expertise and age- and sex-specific reference ranges. Here we developed novel computational approaches for rapid interpretation of GC–MS data for diagnosis of inborn steroidogenic disorders Methods We analysed the urinary steroid metabolome by GC–MS in 829 healthy controls(302 neonates and infants, 167 children and 360 adults) and 118 untreated patients with genetically confirmed inborn disorders (21-hydroxylase deficiency,17-hydroxylase deficiency, POR deficiency, 11b-hydroxylase deficiency, 3b-HSD2 deficiency, 17b-HSD3 deficiency, 5a-reductase type 2 deficiency, cytochrome b5 deficiency). We calculated age-related normative values for established metabolite ratios representing distinct enzymatic functions. We developed a novel interpretable machine learning technique, Angle Learning Vector Quantisation (ALVQ), which looks at all possible metabolite ratios, computationally reduces these to the most relevant for discrimination, and differentiates disease states by comparison to a representative prototype. The method runs independent of sex and age information, units of measurement and method of urine collection. Results Conventional biochemical ratios had 100% sensitivity but only very poor specificity. By contrast, ALVQ predicted 'affected urine' vs 'healthy urine' with 100% sensitivity and 97% specificity. For our three most prevalent conditions(PORD, SRD5A2 and CYP21A2), the specific condition was identified correctly in 96% of cases. Conclusion We developed a novel Steroid Metabolomics approach to automatically diagnose inborn steroidogenic disorders with very high sensitivity and specificity, superior to current methods, and with high potential for implementation in routine clinical care.

Neighbor-preserving embedding of relational data in low-dimensional Euclidean spaces is studied. Contrary to variants of stochastic neighbor embedding that minimize divergence measures between estimated neighborhood probability distributions, the proposed approach fits configurations in the output space by maximizing correlation with potentially asymmetric or missing relationships in the input space. In addition to the linear Pearson correlation measure, the use of soft formulations of Spearman and Kendall rank correlation is investigated for optimizing embeddings like 2D point cloud configurations. We illustrate how this scale-invariant correlation-based framework of multidimensional scaling (cbMDS) helps going beyond distance-preserving scaling approaches and how the embedding results are characteristically different from recent neighborhood embedding techniques. (C) 2014 Elsevier B.V. All rights reserved.

International audience