Search

Despite years of research, the mechanisms governing the onset, relapse, symptomatology, and treatment of schizophrenia (SZ) remain elusive. The lack of appropriate analytic tools to deal with the heterogeneity and complexity of SZ may be one of the reasons behind this situation. Deep learning, a subfield of artificial intelligence (AI) inspired by the nervous system, has recently provided an accessible way of modeling and analyzing complex, high-dimensional, nonlinear systems. The unprecedented accuracy of deep learning algorithms in classification and prediction tasks has revolutionized a wide range of scientific fields and is rapidly permeating SZ research. Deep learning has the potential of becoming a valuable aid for clinicians in the prediction, diagnosis, and treatment of SZ, especially in combination with principles from Bayesian statistics. Furthermore, deep learning could become a powerful tool for uncovering the mechanisms underlying SZ thanks to a growing number of techniques designed for improving model interpretability and causal reasoning. The purpose of this article is to introduce SZ researchers to the field of deep learning and review its latest applications in SZ research. In general, existing studies have yielded impressive results in classification and outcome prediction tasks. However, methodological concerns related to the assessment of model performance in several studies, the widespread use of small training datasets, and the little clinical value of some models suggest that some of these results should be taken with caution.

In the new era of very large telescopes, where data are crucial to expand scientific knowledge, we have witnessed many deep learning applications for the automatic classification of light curves. Recurrent neural networks (RNNs) are one of the models used for these applications, and the Long Short-Term Memory (LSTM) unit stands out for being an excellent choice for the representation of long time series. In general, RNNs assume observations at discrete times, which may not suit the irregular sampling of light curves. A traditional technique to address irregular sequences consists of adding the sampling time to the network’s input, but this is not guaranteed to capture sampling irregularities during training. Alternatively, the Phased LSTM (PLSTM) unit has been created to address this problem by updating its state using the sampling times explicitly. In this work, we study the effectiveness of the LSTM- and PLSTM-based architectures for the classification of astronomical light curves. We use seven catalogues containing periodic and non-periodic astronomical objects. Our findings show that LSTM outperformed PLSTM on six of seven data sets. However, the combination of both units enhances the results in all data sets.

In this article, we present a new approach to the detection of Loss-Of-Excitation (LOE), a typical failure of synchronous generators. Unlike most of the algorithms proposed in the literature, which only use the information available at the point of connection, we also take advantage of prior knowledge of the generator model. To track the field voltage and the other state variables, we have chosen the Constrained Unscented Kalman Filter (CUKF) as the core estimation technique, with phasor measurements as the input for this filtering algorithm. Detection of LOE is then performed by using the Faulty Modes Detection and Diagnosis (FMDD) algorithm, which combines the normal operation and a LOE-based model to decide in real-time whether an LOE has occurred or not. Results of simulations using a small two-area power system and the IEEE 39-bus system show that LOE detection times can be significantly reduced as compared to conventional and state-of-the-art approaches. Moreover, we observe that the new fault detection signal used to trip the generator can avoid short-term voltage stability problems. Fil: Marchi, Pablo Gabriel. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Parque Centenario. Centro de Simulación Computacional para Aplicaciones Tecnológicas; Argentina Fil: Gill Estevez, Pablo Daniel. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Parque Centenario. Centro de Simulación Computacional para Aplicaciones Tecnológicas; Argentina Fil: Messina, Francisco Javier. Mc Gill University; Canadá Fil: Galarza, Cecilia Gabriela. Consejo Nacional de Investigaciones Científicas y Técnicas. Oficina de Coordinación Administrativa Parque Centenario. Centro de Simulación Computacional para Aplicaciones Tecnológicas; Argentina

Location of non-stationary forced oscillation (FO) sources can be a challenging task, especially in cases under resonance condition with natural system modes, where the magnitudes of the oscillations could be greater in places far from the source. Therefore, it is of interest to construct a global time-frequency (TF) representation (TFR) of the system, which can capture the oscillatory components present in the system. In this paper we develop a systematic methodology for frequency identification and component filtering of non-stationary power system forced oscillations (FO) based on multi-channel TFR. The frequencies of the oscillatory components are identified on the TF plane by applying a modified ridge estimation algorithm. Then, filtering of the components is carried out on the TF plane applying the anti-transform functions over the individual TFRs around the identified ridges. This step constitutes an initial stage for the application of the Dissipating Energy Flow (DEF) method used to locate FO sources. Besides, we compare three TF approaches: short-time Fourier transform (STFT), STFT-based synchrosqueezing transform (FSST) and second order FSST (FSST2). Simulated signals and signals from real operation are used to show that the proposed method provides a systematic framework for identification and filtering of power systems non-stationary forced oscillations., Submitted to IEEE Transactions on Power Systems

Mine operations in the future will require automatic rock characterization at many different stages, since it can be used to supervise and optimize various processes in the laboratory as well as at the mine locations for planning and exploitation. Different methods for classifying rocks based on image analysis have been proposed in the past. In this paper, we report the use of hyperspectral sensors in the classification of rock lithology. The lithology provides information about the chemical composition of the rock, and its physical properties. According to our literature review, this is the first time hyperspectral sensors have been employed in rock type classification. Additionally, it is the first time the use of three different technologies in rock type classification has been reported: hyperspectral sensors, laser range and a color camera. We use two hyperspectral sensors, one has sensibility within the visible and near-infrared range of 400–1000 nm, and the second has sensibility within the short-wavelength infrared range of 900–2500 nm. The range and high definition color images are used to perform accurate segmentation of the rock samples. Images are tessellated into sub-images in which various features from the three sensor types are extracted. In a first stage, the sub-images are classified by using a support-vector machine (SVM) classifier with the extracted features as inputs. In a second stage, the rock segmentation is used to perform a voting process among all the sub-images of each rock and improve the classification. The method was tested using a database with 13 lithologies from a copper mine in Chile. The results show that lithological classification performance obtained by using hyperspectral images greatly exceeds the performance of the color and range images. The achieved classification performance was 98.62% using sub-image classification and 99.95% using a voting process among sub-images. The number of features was also reduced by using the CMIM (Conditional Mutual Information Maximization) feature selection method, achieving a performance of over 99% with using only 3% of the total number of features.

The fast construction times of projects based on variable generation technologies (VGTs) such as photovoltaic and wind generation, together with growing difficulties for building new transmission lines due to socio-environmental requirements, have opened new challenges in the development of sustainable power systems. Due to the complexity of the Transmission Network Expansion Planning (TNEP) problem, current models are usually oversimplified and do not always meet the requirements needed for the practical application. Examples of these simplifications are the use of reduced network equivalents, limiting the planning horizon to one or a few years and limiting the expansion options to adding new lines in given corridors. To meet the new challenges and achieve a time-effective increase of the transmission capacity for the integration of VGTs, improved models and algorithms capable of taking into account a higher degree of detail in the TNEP problem are needed. In this article, a novel meta-heuristic multi-year TNEP model based on Ant Colony Optimization (ACO) is presented. One of the main characteristics of the model is that it enables us to consider simultaneously further expansion options such as line reconductoring, voltage uprating, and adding series compensation to lines. We tested the proposed ACO model with the Garver’s 6-bus test system and a modified version of the IEEE 118-bus test system, assuming a significant incorporation of VGTs. The results obtained for a 15-year planning task show (i) an excellent performance of the model in terms of quality of the obtained solution and computational times, compared to the traditional MILP approach, and (ii) including line uprating options within the multi-year TNEP brings significant benefits such as reducing the total investment and congestion costs of the system as well as the number of lines to be built.

We present a real-time stamp classifier of astronomical events for the ALeRCE (Automatic Learning for the Rapid Classification of Events) broker. The classifier is based on a convolutional neural network, trained on alerts ingested from the Zwicky Transient Facility (ZTF). Using only the \textit{science, reference} and \textit{difference} images of the first detection as inputs, along with the metadata of the alert as features, the classifier is able to correctly classify alerts from active galactic nuclei, supernovae (SNe), variable stars, asteroids and bogus classes, with high accuracy ($\sim$94\%) in a balanced test set. In order to find and analyze SN candidates selected by our classifier from the ZTF alert stream, we designed and deployed a visualization tool called SN Hunter, where relevant information about each possible SN is displayed for the experts to choose among candidates to report to the Transient Name Server database. From June 26th 2019 to February 28th 2021, we have reported 6846 SN candidates to date (11.8 candidates per day on average), of which 971 have been confirmed spectroscopically. Our ability to report objects using only a single detection means that 70\% of the reported SNe occurred within one day after the first detection. ALeRCE has only reported candidates not otherwise detected or selected by other groups, therefore adding new early transients to the bulk of objects available for early follow-up. Our work represents an important milestone toward rapid alert classifications with the next generation of large etendue telescopes, such as the Vera C. Rubin Observatory., Submitted to AAS on Jun 30th. Comments welcome

We present the first version of the ALeRCE (Automatic Learning for the Rapid Classification of Events) broker light curve classifier. ALeRCE is currently processing the Zwicky Transient Facility (ZTF) alert stream, in preparation for the Vera C. Rubin Observatory. The ALeRCE light curve classifier uses variability features computed from the ZTF alert stream, and colors obtained from AllWISE and ZTF photometry. We apply a Balanced Random Forest algorithm with a two-level scheme, where the top level classifies each source as periodic, stochastic, or transient, and the bottom level further resolves each of these hierarchical classes, amongst 15 total classes. This classifier corresponds to the first attempt to classify multiple classes of stochastic variables (including core- and host-dominated active galactic nuclei, blazars, young stellar objects, and cataclysmic variables) in addition to different classes of periodic and transient sources, using real data. We created a labeled set using various public catalogs (such as the Catalina Surveys and {\em Gaia} DR2 variable stars catalogs, and the Million Quasars catalog), and we classify all objects with $\geq6$ $g$-band or $\geq6$ $r$-band detections in ZTF (868,371 sources as of 2020/06/09), providing updated classifications for sources with new alerts every day. For the top level we obtain macro-averaged precision and recall scores of 0.96 and 0.99, respectively, and for the bottom level we obtain macro-averaged precision and recall scores of 0.57 and 0.76, respectively. Updated classifications from the light curve classifier can be found at the \href{http://alerce.online}{ALeRCE Explorer website}., 39 pages, 24 figures, 5 tables, 4 apendices. Accepted for publication in the Astronomical Journal (AJ)

The training dynamics of hidden layers in deep learning are poorly understood in theory. Recently, the Information Plane (IP) was proposed to analyze them, which is based on the information-theoretic concept of mutual information (MI). The Information Bottleneck (IB) theory predicts that layers maximize relevant information and compress irrelevant information. Due to the limitations in MI estimation from samples, there is an ongoing debate about the properties of the IP for the supervised learning case. In this work, we derive a theoretical convergence for the IP of autoencoders. The theory predicts that ideal autoencoders with a large bottleneck layer size do not compress input information, whereas a small size causes compression only in the encoder layers. For the experiments, we use a Gram-matrix based MI estimator recently proposed in the literature. We propose a new rule to adjust its parameters that compensates scale and dimensionality effects. Using our proposed rule, we obtain experimental IPs closer to the theory. Our theoretical IP for autoencoders could be used as a benchmark to validate new methods to estimate MI in neural networks. In this way, experimental limitations could be recognized and corrected, helping with the ongoing debate on the supervised learning case., 8 pages, 9 figures. In proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN 2020)

The brain electrical activity presents several short events during sleep that can be observed as distinctive micro-structures in the electroencephalogram (EEG), such as sleep spindles and K-complexes. These events have been associated with biological processes and neurological disorders, making them a research topic in sleep medicine. However, manual detection limits their study because it is time-consuming and affected by significant inter-expert variability, motivating automatic approaches. We propose a deep learning approach based on convolutional and recurrent neural networks for sleep EEG event detection called Recurrent Event Detector (RED). RED uses one of two input representations: a) the time-domain EEG signal, or b) a complex spectrogram of the signal obtained with the Continuous Wavelet Transform (CWT). Unlike previous approaches, a fixed time window is avoided and temporal context is integrated to better emulate the visual criteria of experts. When evaluated on the MASS dataset, our detectors outperform the state of the art in both sleep spindle and K-complex detection with a mean F1-score of at least 80.9% and 82.6%, respectively. Although the CWT-domain model obtained a similar performance than its time-domain counterpart, the former allows in principle a more interpretable input representation due to the use of a spectrogram. The proposed approach is event-agnostic and can be used directly to detect other types of sleep events., Comment: 8 pages, 5 figures. In proceedings of the 2020 International Joint Conference on Neural Networks (IJCNN 2020)

In this work, we propose several enhancements to a geometric transformation based model for anomaly detection in images (GeoTranform). The model assumes that the anomaly class is unknown and that only inlier samples are available for training. We introduce new filter based transformations useful for detecting anomalies in astronomical images, that highlight artifact properties to make them more easily distinguishable from real objects. In addition, we propose a transformation selection strategy that allows us to find indistinguishable pairs of transformations. This results in an improvement of the area under the Receiver Operating Characteristic curve (AUROC) and accuracy performance, as well as in a dimensionality reduction. The models were tested on astronomical images from the High Cadence Transient Survey (HiTS) and Zwicky Transient Facility (ZTF) datasets. The best models obtained an average AUROC of 99.20% for HiTS and 91.39% for ZTF. The improvement over the original GeoTransform algorithm and baseline methods such as One-Class Support Vector Machine, and deep learning based methods is significant both statistically and in practice., Comment: 8 pages, 6 figures, 4 tables. Accepted for publication in proceedings of the IEEE World Congress on Computational Intelligence (IEEE WCCI), Glasgow, UK, 19-24 July, 2020

Clustering is a fundamental task in unsupervised learning that depends heavily on the data representation that is used. Deep generative models have appeared as a promising tool to learn informative low-dimensional data representations. We propose Matching Priors and Conditionals for Clustering (MPCC), a GAN-based model with an encoder to infer latent variables and cluster categories from data, and a flexible decoder to generate samples from a conditional latent space. With MPCC we demonstrate that a deep generative model can be competitive/superior against discriminative methods in clustering tasks surpassing the state of the art over a diverse set of benchmark datasets. Our experiments show that adding a learnable prior and augmenting the number of encoder updates improve the quality of the generated samples, obtaining an inception score of \(9.49 \pm 0.15\) and improving the Frechet inception distance over the state of the art by a \(46.9\%\) in CIFAR10.

Non-stationary forced oscillations (FOs) have been observed in power system operations. However, most detection methods assume that the frequency of FOs is stationary. In this paper, we present a methodology for the analysis of non-stationary FOs. Firstly, Fourier synchrosqueezing transform (FSST) is used to provide a concentrated time-frequency representation of the signals that allows identification and retrieval of non-stationary signal components. To continue, the Dissipating Energy Flow (DEF) method is applied to the extracted components to locate the source of forced oscillations. The methodology is tested using simulated as well as real PMU data. The results show that the proposed FSST-based signal decomposition provides a systematic framework for the application of DEF Method to non-stationary FOs., Comment: Submitted to IEEE Transactions on Power System

The determination of hardness and approximate mineral composition of rocks and classifying these lithologies aids in controlling various processes in the plant, such as reducing the grinding process, which accounts for about 50% of its energy consumption. In this paper, a new method for rock lithological classification is presented, based on color as well as 3D laser based features. The method uses color and laser range images, acquired from rocks on a conveyor belt, to compute Gabor and LBP (Local Binary Pattern) features. Various Gabor and LBP features are tested, including rotation invariant features. The images are tessellated into sub-images in which the features are computed. The classification is performed in two stages. In the first stage, the sub-images are classified by using a support-vector machine (SVM) classifier. In the second stage, the classification is improved by a voting process among all the sub-images of each rock. The method was tested on a database with five different rock lithologies taken from a copper mine which has been used in previous studies, allowing comparison with our new results. The results show that the classification performance was improved significantly by adding the 3D laser texture features, and using a combination of rotation invariant Gabor and LBP features, achieving a classification accuracy of 99.24% on the database. Using the CMIM (Conditional Mutual Information Maximization) feature selection method showed that only 10% of the total extracted features are required to achieve the maximum correct classification rate and that using the 3D laser features, (for the first time in our rock classification method to the best of our knowledge) is important for maintaining high classification performance.

This article focused on the estimation of the state of charge (SoC) of a Li-con Cell by carrying out a series of experimental tests at various operating temperatures and SoC. The cell was characterized by electrochemical impedance spectroscopy (EIS) tests, from which the impedance frequency spectrum for different SoC and temperatures was obtained. Indeed, the cell model consisted of a modified Randles circuit type that included a constant phase element so-called Warburg impedance. Each circuit parameter was obtained from the EIS tests. The obtained were been used to develop two numerical models for each parameter, i.e., one based on numerical correlations and the other based on the artificial neural network (ANN) method. A genetic algorithm was used to solve and optimize the numerical models. The accuracy of the models was examined and the results showed that the ANN-based model was more accurate than the correlations-based model. The root mean square relative error (RMSRE) of the parameters Rs, R1, C1 and W for the ANN-based model were: 4.63%, 13.65%, 10.96% and 4.4%, respectively, compared to 7.09%, 27.45%, 34.36% and 7.07% for the correlations-based model, respectively. The SoC was estimated using the extended Kalman filter based on a Randles model, with an estimation RMSRE of about 1.19%.

We introduce the Automatic Learning for the Rapid Classification of Events (ALeRCE) broker, an astronomical alert broker designed to provide a rapid and self--consistent classification of large etendue telescope alert streams, such as that provided by the Zwicky Transient Facility (ZTF) and, in the future, the Vera C. Rubin Observatory Legacy Survey of Space and Time (LSST). ALeRCE is a Chilean--led broker run by an interdisciplinary team of astronomers and engineers, working to become intermediaries between survey and follow--up facilities. ALeRCE uses a pipeline which includes the real--time ingestion, aggregation, cross--matching, machine learning (ML) classification, and visualization of the ZTF alert stream. We use two classifiers: a stamp--based classifier, designed for rapid classification, and a light--curve--based classifier, which uses the multi--band flux evolution to achieve a more refined classification. We describe in detail our pipeline, data products, tools and services, which are made public for the community (see \url{https://alerce.science}). Since we began operating our real--time ML classification of the ZTF alert stream in early 2019, we have grown a large community of active users around the globe. We describe our results to date, including the real--time processing of $9.7\times10^7$ alerts, the stamp classification of $1.9\times10^7$ objects, the light curve classification of $8.5\times10^5$ objects, the report of 3088 supernova candidates, and different experiments using LSST-like alert streams. Finally, we discuss the challenges ahead to go from a single-stream of alerts such as ZTF to a multi--stream ecosystem dominated by LSST., Comment: Submitted to AAS on Jun 29th. Preview for LSST PCW 2020. Comments welcome

Trademarks are recognizable images and/or words used to distinguish various products or services. They become associated with the reputation, innovation, quality, and warranty of the products. Countries around the world have offices for industrial/intellectual property (IP) registration. A new trademark image in application for registration should be distinct from all the registered trademarks. Due to the volume of trademark registration applications and the size of the databases containing existing trademarks, it is impossible for humans to make all the comparisons visually. Therefore, technological tools are essential for this task. In this work we use a pre-trained, publicly available Convolutional Neural Network (CNN) VGG19 that was trained on the ImageNet database. We adapted the VGG19 for the trademark image retrieval (TIR) task by fine tuning the network using two different databases. The VGG19v was trained with a database organized with trademark images using visual similarities, and the VGG19c was trained using trademarks organized by using conceptual similarities. The database for the VGG19v was built using trademarks downloaded from the WEB, and organized by visual similarity according to experts from the IP office. The database for the VGG19c was built using trademark images from the United States Patent and Trademarks Office and organized according to the Vienna conceptual protocol. The TIR was assessed using the normalized average rank for a test set from the METU database that has 922,926 trademark images. We computed the normalized average ranks for VGG19v, VGG19c, and for a combination of both networks. Our method achieved significantly better results on the METU database than those published previously.

Current Transmission Network Expansion Planning (TNEP) models are usually strongly simplified in order to achieve optimal solutions within reasonable execution times and computational resources. Examples of these simplifications are the use of reduced network equivalents and the consideration of only a few years within the planning horizon. Due to these simplifications, current TNEP models do not always meet the requirements needed for practical applications. This is particularly true in case of power systems with increased use of renewable energies in which case the levels of variability and uncertainty require a better representation of the system. To meet these new challenges and achieve a time-effective increase of the transmission capacity for the integration of renewable energies, models that consider more accurate representations of power systems are needed. These models must also be able to handle realistic-size power systems in order to serve as supporting tool for real planning processes. In this article, a novel heuristic model based on Ant Colony Optimization for the multi-year TNEP is presented. The characteristics of ACO algorithms make the proposed model especially suitable for considering several expansion options, larger planning horizons, and several load-generation profiles. For validating the model, 25 years plans were calculated in the Garver's 6-bus system and in the IEEE 118-bus system. In both cases, several independent simulations were executed and the results were compared with the ones obtained using a traditional MILP approach. The results showed that all runs found the optimal solution within reasonable computation times, which enables us to validate our model.

The exponential growth of the data collected by telescopes have turned astronomy into a data-drive science. The detection of astronomical transient events, short-lived and bright phenomena such as the Supernovae, is currently a main science driver of many astronomical surveys. There is an opportunity for the application of machine learning methods for the automatic detection of astronomical transients.In this paper we focus on the unsupervised learning case to perform an exploratory analysis on a dataset of 1,250,000 astronomical transient candidates from the High Cadence Transient Survey. Our contributions can be summarized in 1) The application of Deep Variational Embedding for latent space clustering of a large database of transient candidates obtaining a clustering accuracy of 95.33% and 2) The proposal of an auto-regularization term as a novel approach to solve the common problem of over-regularization in variational autoencoders, we show that using this term not only improves the convergence of the algorithm but also increases the clustering accuracy and reconstruction quality.

We propose a new sequential classification model for astronomical objects based on a recurrent convolutional neural network (RCNN) which uses sequences of images as inputs. This approach avoids the computation of light curves or difference images. This is the first time that sequences of images are used directly for the classification of variable objects in astronomy. The second contribution of this work is the image simulation process. We generate synthetic image sequences that take into account the instrumental and observing conditions, obtaining a realistic, set of movies for each astronomical object. The simulated dataset is used to train our RCNN classifier. This approach allows us to generate datasets to train and test our RCNN model for different astronomical surveys and telescopes. We aim at building a simulated dataset whose distribution is close enough to the real dataset, so that a fine tuning could match the distributions between real and simulated dataset. To test the RCNN classifier trained with the synthetic dataset, we used real-world data from the High cadence Transient Survey (HiTS) obtaining an average recall of 85%, improved to 94% after performing fine tuning with 10 real samples per class. We compare the results of our model with those of a light curve random forest classifier. The proposed RCNN with fine tuning has a similar performance on the HiTS dataset compared to the light curve classifier, trained on an augmented training set with 10 real samples per class. The RCNN approach presents several advantages in an alert stream classification scenario, such as a reduction of the data pre-processing, faster online evaluation and easier performance improvement using a few real data samples. These results encourage us to use this method for alert brokers systems that will process alert streams generated by new telescopes such as the Large Synoptic Survey Telescope., Comment: 20 pages, 20 figures (corrected compilation errors). This is an Accepted Manuscript version of an article accepted for publication in Publications of the Astronomical Society of the Pacific. Nether the Astronomical Society of the Pacific nor IOP Publishing Ltd is responsible for any errors or omissions in this version of the manuscript or any version derived from it

In this paper, we propose an enhanced CNN model for detecting supernovae (SNe). This is done by applying a new method for obtaining rotational invariance that exploits cyclic symmetry. In addition, we use a visualization approach, the layer-wise relevance propagation (LRP) method, which allows finding the relevant pixels in each image that contribute to discriminate between SN candidates and artifacts. We introduce a measure to assess quantitatively the effect of the rotational invariant methods on the LRP relevance heatmaps. This allows comparing the proposed method, CAP, with the original Deep-HiTS model. The results show that the enhanced method presents an augmented capacity for achieving rotational invariance with respect to the original model. An ensemble of CAP models obtained the best results so far on the HiTS dataset, reaching an average accuracy of 99.53%. The improvement over Deep-HiTS is significant both statistically and in practice., Comment: 8 pages, 5 figures. Accepted for publication in proceedings of the IEEE World Congress on Computational Intelligence (IEEE WCCI), Rio de Janeiro, Brazil, 8-13 July, 2018

We report on the serendipitous observations of Solar System objects imaged during the High cadence Transient Survey (HiTS) 2014 observation campaign. Data from this high cadence, wide field survey was originally analyzed for finding variable static sources using Machine Learning to select the most-likely candidates. In this work we search for moving transients consistent with Solar System objects and derive their orbital parameters. We use a simple, custom detection algorithm to link trajectories and assume Keplerian motion to derive the asteroid's orbital parameters. We use known asteroids from the Minor Planet Center (MPC) database to assess the detection efficiency of the survey and our search algorithm. Trajectories have an average of nine detections spread over 2 days, and our fit yields typical errors of $\sigma_a\sim 0.07 ~{\rm AU}$, $\sigma_{\rm e} \sim 0.07 $ and $\sigma_i\sim 0.^{\circ}5~ {\rm deg}$ in semi-major axis, eccentricity, and inclination respectively for known asteroids in our sample. We extract 7,700 orbits from our trajectories, identifying 19 near Earth objects, 6,687 asteroids, 14 Centaurs, and 15 trans-Neptunian objects. This highlights the complementarity of supernova wide field surveys for Solar System research and the significance of machine learning to clean data of false detections. It is a good example of the data--driven science that LSST will deliver., Comment: 9 pages, 7 figures

Lithium-battery energy storage systems (LiBESS) are increasingly being used on electric mobility and stationary applications. Despite its increasing use and improvements of the technology there are still challenges associated with cost reduction, increasing lifetime and capacity, and higher safety. A correct battery thermal management system (BTMS) design is critical to achieve these goals. In this paper, a general framework for obtaining optimal BTMS designs is proposed. Due to the trade-off between the BTMS's design goals and the complex modeling of thermal response inside the battery pack, this paper proposes to solve this problem using a novel Multi-Objective Particle Swarm Optimization (MOPSO) approach. A theoretical case of a module with 6 cells and a real case of a pack used in a Solar Race Car are presented. The results show the capabilities of the proposal methodology, in which improved designs for battery packs are obtained.

The Large Synoptic Survey Telescope (LSST) will produce an unprecedented amount of light curves using six optical bands. Robust and efficient methods that can aggregate data from multidimensional sparsely-sampled time series are needed. In this paper we present a new method for light curve period estimation based on the quadratic mutual information (QMI). The proposed method does not assume a particular model for the light curve nor its underlying probability density and it is robust to non-Gaussian noise and outliers. By combining the QMI from several bands the true period can be estimated even when no single-band QMI yields the period. Period recovery performance as a function of average magnitude and sample size is measured using 30,000 synthetic multi-band light curves of RR Lyrae and Cepheid variables generated by the LSST Operations and Catalog simulators. The results show that aggregating information from several bands is highly beneficial in LSST sparsely-sampled time series, obtaining an absolute increase in period recovery rate up to 50%. We also show that the QMI is more robust to noise and light curve length (sample size) than the multiband generalizations of the Lomb Scargle and Analysis of Variance periodograms, recovering the true period in 10-30% more cases than its competitors. A python package containing efficient Cython implementations of the QMI and other methods is provided., Accepted for publication ApJ Supplement Series: Special Issue on Solar/Stellar Astronomy Big Data

Segment Growing Neural Gas (Segment-GNG) has been recently proposed as a new spatiotemporal quantization method for time series. Unlike traditional quantization algorithms that are prototype-based, Segment-GNG uses segments as basic units of quantization. In this paper we extend the Segment-GNG model in order to deal with time series prediction. First Segment-GNG makes a quantization of the trajectories in the state-space representation of the time series. Then a local prediction model is associated with each segment, which allows us to make predictions. The proposed model is tested with the Mackey-Glass and Lorenz chaotic time series in one-step ahead prediction tasks. The results obtained are competitive with the best results published in the literature.

Context: In the last six years, the VVV survey mapped 562 sq. deg. across the bulge and southern disk of the Galaxy. However, a detailed study of these regions, which includes $\sim 36$ globular clusters (GCs) and thousands of open clusters is by no means an easy challenge. High differential reddening and severe crowding along the line of sight makes highly hamper to reliably distinguish stars belonging to different populations and/or systems. Aims: The aim of this study is to separate stars that likely belong to the Galactic GC NGC 6544 from its surrounding field by means of proper motion (PM) techniques. Methods: This work was based upon a new astrometric reduction method optimized for images of the VVV survey. Results: Photometry over the six years baseline of the survey allowed us to obtain a mean precision of $\sim0.51$ mas/yr, in each PM coordinate, for stars with Ks < 15 mag. In the area studied here, cluster stars separate very well from field stars, down to the main sequence turnoff and below, allowing us to derive for the first time the absolute PM of NGC 6544. Isochrone fitting on the clean and differential reddening corrected cluster color magnitude diagram yields an age of $\sim$ 11-13 Gyr, and metallicity [Fe/H] = -1.5 dex, in agreement with previous studies restricted to the cluster core. We were able to derive the cluster orbit assuming an axisymmetric model of the Galaxy and conclude that NGC 6544 is likely a halo GC. We have not detected tidal tail signatures associated to the cluster, but a remarkable elongation in the galactic center direction has been found. The precision achieved in the PM determination also allows us to separate bulge stars from foreground disk stars, enabling the kinematical selection of bona fide bulge stars across the whole survey area. Our results show that VVV data is perfectly suitable for this kind of analysis., 13 pages, 12 figures, accepted in A&A

We introduce Deep-HiTS, a rotation invariant convolutional neural network (CNN) model for classifying images of transients candidates into artifacts or real sources for the High cadence Transient Survey (HiTS). CNNs have the advantage of learning the features automatically from the data while achieving high performance. We compare our CNN model against a feature engineering approach using random forests (RF). We show that our CNN significantly outperforms the RF model reducing the error by almost half. Furthermore, for a fixed number of approximately 2,000 allowed false transient candidates per night we are able to reduce the miss-classified real transients by approximately 1/5. To the best of our knowledge, this is the first time CNNs have been used to detect astronomical transient events. Our approach will be very useful when processing images from next generation instruments such as the Large Synoptic Survey Telescope (LSST). We have made all our code and data available to the community for the sake of allowing further developments and comparisons at https://github.com/guille-c/Deep-HiTS.

Optimization and validation of a capillary zone electrophoresis (CZE) method for the determination of inner and external inorganic sulfate from doxorubicin-loaded liposomes as a measurement of encapsulation efficiency are presented. Sulfate was determined using a fused silica capillary (50 cm x 75 μm ID) and background electrolyte (BGE) composed of 5 mM chromate with 1 mM of TTAB at pH 10.5 with indirect UV detection at 254 nm. The separations were achieved at temperature of 25 ºC, 5 kV of reverse applied voltage using a pressure of 0.5 psi for 5s of sample introduction. Sulfate quantitation from the outside of liposomes was obtained by simple dilution of the liposome sample but an extraction with a non-ionic surfactant and a mixture of methanol-chloroform-water were necessary to breakdown the liposomes for the quantitation of the total sulfate (inside and outside) with acceptable recovery percentages (96.3% to 102.6%). Parameters of validation were evaluated according to ICH guidelines such as specificity, linearity, LOD, LOQ, accuracy, precision and robustness. The proposed CE method resulted to be suitable for the inner and external sulfate analysis of doxorubicin-loaded liposomes for routine quality and stability control studies. Fil: Flor, Sabrina Andrea. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina. Universidad de Buenos Aires. Facultad de Farmacia y Bioquímica. Departamento de Química Analítica y Fisicoquímica; Argentina Fil: Estevez, Pablo Nicolás. Universidad de Buenos Aires. Facultad de Farmacia y Bioquímica. Departamento de Química Analítica y Fisicoquímica; Argentina Fil: Tripodi, Valeria Paula. Universidad de Buenos Aires. Facultad de Farmacia y Bioquímica. Departamento de Tecnología Farmacéutica; Argentina. Universidad de Buenos Aires. Facultad de Farmacia y Bioquímica. Departamento de Química Analítica y Fisicoquímica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina Fil: Legaspi, María Julia. Laboratorios Raffo S. A.; Argentina Fil: Mammarela, Carlos. Laboratorios Raffo S. A.; Argentina Fil: Lucangioli, Silvia Edith. Universidad de Buenos Aires. Facultad de Farmacia y Bioquímica. Departamento de Tecnología Farmacéutica; Argentina. Consejo Nacional de Investigaciones Científicas y Técnicas; Argentina

In this work, we present a review of the state of the art of information-theoretic feature selection methods. The concepts of feature relevance, redundance, and complementarity (synergy) are clearly defined, as well as Markov blanket. The problem of optimal feature selection is defined. A unifying theoretical framework is described, which can retrofit successful heuristic criteria, indicating the approximations made by each method. A number of open problems in the field are presented.

We present the first results of the High cadence Transient Survey (HiTS), a survey whose objective is to detect and follow up optical transients with characteristic timescales from hours to days, especially the earliest hours of supernova (SN) explosions. HiTS uses the Dark Energy Camera (DECam) and a custom made pipeline for image subtraction, candidate filtering and candidate visualization, which runs in real-time to be able to react rapidly to the new transients. We discuss the survey design, the technical challenges associated with the real-time analysis of these large volumes of data and our first results. In our 2013, 2014 and 2015 campaigns we have detected more than 120 young SN candidates, but we did not find a clear signature from the short-lived SN shock breakouts (SBOs) originating after the core collapse of red supergiant stars, which was the initial science aim of this survey. Using the empirical distribution of limiting-magnitudes from our observational campaigns we measured the expected recovery fraction of randomly injected SN light curves which included SBO optical peaks produced with models from Tominaga et al. (2011) and Nakar & Sari (2010). From this analysis we cannot rule out the models from Tominaga et al. (2011) under any reasonable distributions of progenitor masses, but we can marginally rule out the brighter and longer-lived SBO models from Nakar & Sari (2010) under our best-guess distribution of progenitor masses. Finally, we highlight the implications of this work for future massive datasets produced by astronomical observatories such as LSST., 30 pages, 14 figures, accepted for publication in ApJ

Sleep spindles (SSs) are characteristic electroencephalographic (EEG) waveforms of sleep stages N2 and N3. One of the main problems associated with SS detection is the high number of false positives. In this paper we propose a new periodogram based on correntropy to detect SSs and enhance their characterization. Correntropy is a generalized correlation, under the information theoretic learning framework. A non-negative matrix factorization decomposition of correntropy allows us to obtain a new periodogram, which shows an improved resolution capability compared to the conventional power spectrum density. Preliminary results show that the proposed method obtained a sensitivity rate of 0.868 with a false positive rate of 0.121.

During the last couple of years Astronomy, as many other fields, has been facing the problem of automatic processing of massive data. This has been primarily driven by large survey instruments, which scan large areas of the sky aiming to catalog everything they find. The High Cadence Transient Survey (HiTS) is one of these surveys that searches for phenomena of limited duration (such as supernovae) called transients. The HiTS pipeline produces transient candidates by subtracting science images from a template. In this paper we present a convolutional neural network (ConvNet) approach to classify sources found in the difference images as real transients or artifacts. We compare our results against a random forest classification model that has been created by the HiTS team during the last two years through feature engineering. Our ConvNet model obtains features automatically and obtains a 99.32% accuracy as compared to the previous 98.89% accuracy from the random forest model. This approach will be very useful when processing data from next generation instruments such as the Large Synoptic Survey Telescope (LSST).

Many processes in nature display quasi-periodic behavior, including variable stars in distant galaxies and oscillations in brains. In this work we model quasi-periodic lightcurves using neuropercolation, which describes complex spatio-temporal oscillations arising from random cellular automata near criticality. We show that neuropercolation is able to model lightcurves from various stars of the gamma-Doradus type with high accuracy even in the presence of missing data points and unevenly distributed time series. We provide physical interpretation of the obtained results.

The recent surge of huge astronomical telescopes opens new possibilities for astrophysical studies, with corresponding challenges regarding massive data analysis. Taking advantage of these new technologies, the High Cadence Transient Survey (HiTS) has developed a pipeline to detect transient astronomical phenomena, such as supernovae, by analyzing pairs of stamps of objects extracted directly from the telescope images in an online fashion. We introduce a new complementary method for detecting faint, low signal-to-noise ratio supernovae by discriminating the evolution of luminosities of pixels through filtering sequences of images. Our method uses the Correntropy Filter (CF), which is a nonlinear extension of the classic Kalman Filter. CF uses an information-theoretic cost function called Cross-Correntropy that allows the discarding of artifacts and outliers, which are abundant in astronomical measurements. The proposed method was tested on the HiTS surveys and the results show that it is able to rediscover most supernovae in the high cadence epochs. In addition, it has found 30 new supernova candidates too faint to be discriminated in a pair of stamps. The analysis of longer sequences of images allows us to reduce the number of false positives, but at the expense of a late detection.