Sturm: Sparse Tubal-Regularized Multilinear Regression for fMRI

Sparse wavelet regression with multiple predictive curves

We use sparse regression methods (SRMs) to build accurate and explainable models that predict the stellar mass of central and satellite galaxies as a function of properties of their host dark matter haloes. SRMs are machine learning algorithms that provide a framework for modelling the governing equations of a system from data. In contrast with other machine learning algorithms, the solutions of SRM methods are simple and depend on a relatively small set of adjustable parameters. We collect data from 35 459 galaxies from the EAGLE simulation using 19 redshift slices between z = 0 and z = 4 to parametrize the mass evolution of the host haloes. Using an appropriate formulation of input parameters, our methodology can model satellite and central haloes using a single predictive model that achieves the same accuracy as when predicted separately. This allows us to remove the somewhat arbitrary distinction between those two galaxy types and model them based only on their halo growth history. Our models can accurately reproduce the total galaxy stellar mass function and the stellar mass-dependent galaxy correlation functions (ξ(r)) of EAGLE. We show that our SRM model predictions of ξ(r) is competitive with those from subhalo abundance matching and might be comparable to results from extremely randomized trees. We suggest SRM as an encouraging approach for populating the haloes of dark matter only simulations with galaxies and for generating mock catalogues that can be used to explore galaxy evolution or analyse forthcoming large-scale structure surveys.

Sparse regression methods such as l1-regularized linear regression, or Lasso [18], are commonly used for analysis of high-dimensional, small-sample datasets, due to their good generalization and feature-selection properties. However, predictive accuracy of sparse regression can be further improved by incorporating more realistic data-modeling assumptions (e.g., nonlinearity) and by fully exploiting all available data, as suggested by the transductive approach [6], which makes instance-specific predictions based on both labeled (training) data and unlabeled (test) data, instead of learning a single fixed model from training data. Based on these ideas, we develop a novel method, called Transductive HSIC Lasso, that incorporates transduction into a nonlinear sparse regression approach known as HSIC Lasso [19]. Unlike the existing transductive Lasso algorithm of [1], our approach does not rely on imputation, i.e., on estimation of unknown labels using a predictor built on training data; the latter may sometimes result in poor overall performance due to unreliable label estimates. Instead, our method exploits the structure of the HSIC Lasso, which maximizes the relevance between the selected features and the label, while minimizing the redundancy between the selected features; transduction is achieved by including unlabeled samples into the redundancy computation. Our experiments demonstrate advantages of the proposed method over the state-of-the-art approaches, both on simulated and real-life data, such as prediction of phenotypic traits from genomic data, and prediction of subject’s pain level from his/her functional MRI data.

Sparse linear regression for reconstructing muscle activity from human cortical fMRI

Crop growth and yield monitoring are essential for food security and agricultural economic return prediction. Remote sensing is an efficient technique for measuring growing season crop canopies and providing information on the spatial variability of crop yields. In this study, ten vegetation indices (VIs) derived from time series PlanetScope and Sentinel-2 images were used to investigate the potential to estimate corn grain yield with different regression methods. A field-scale spatial crop yield prediction model was developed and used to produce yield maps depicting spatial variability in the field. Results from this study clearly showed that high-resolution PlanetScope satellite data could be used to detect the corn yield variability at field level, which could explain 15% more variability than Sentinel-2A data at the same spatial resolution of 10 m. Comparison of the model performance and variable importance measure between models illustrated satisfactory results for assessing corn productivity with VIs. The green chlorophyll vegetation index (GCVI) values consistently produced the highest correlations with corn yield, accounting for 72% of the observed spatial variation in corn yield. More reliable quantitative yield estimation could be made using a multi-linear stepwise regression (MSR) method with multiple VIs. Good agreement between observed and predicted yield was achieved with the coefficient of determination value being 0.81 at 86 days after seeding. The results would help farmers and decision-makers generate predicted yield maps, identify crop yield variability, and make further crop management practices timely.

In this work we will apply sparse linear regression methods to forecast wind farm energy production using numerical weather prediction (NWP) features over several pressure levels, a problem where pattern dimension can become very large. We shall place sparse regression in the context of proximal optimization, which we shall briefly review, and we shall show how sparse methods outperform other models while at the same time shedding light on the most relevant NWP features and on their predictive structure.

The purpose of this study was to develop a spike-related functional magnetic resonance (MR) imaging method to detect epileptic brain activity. Correlations between simultaneous spike-related functional MR imaging and electroencephalographic (EEG) recordings were performed in 10 patients with focal epilepsy. Postprocessing techniques were implemented to eliminate contamination of the EEG recording from ballistocardiography and the echo-planar MR imaging sequence. A diagnostic EEG recording was achieved during functional MR imaging. Spike location correlated with the site of blood oxygen level-dependent signal increase. Spike-related functional MR imaging is a promising technique for detecting focal epileptic brain activity.

Abstract. Six collocated spectrophotometers based in Arosa/Davos, Switzerland, have been measuring ozone profiles continuously since 1956 for the oldest Dobson instrument and since 2005 for the Brewer instruments. The datasets of these two ground-based triads (three Dobsons and three Brewers) allow for continuous intercomparisons and derivation of long-term trend estimates. Mainly, two periods in the post-2000 Dobson D051 dataset show anomalies when compared to the Brewer triad time series: in 2011–2013, an offset has been attributed to technical interventions during the renewal of the spectrophotometer acquisition system, and in 2018, an offset with respect to the Brewer triad has been detected following an instrumental change on the spectrophotometer wedge. In this study, the worldwide longest Umkehr dataset (1956–2020) is carefully homogenized using collocated and simultaneous Dobson and Brewer measurements. A recently published report (Garane et al., 2022) described results of an independent homogenization of the same dataset performed by comparison to the Modern-Era Retrospective analysis for Research and Applications version 2 (MERRA-2) Global Modeling Initiative (M2GMI) model simulations. In this paper, the two versions of homogenized Dobson D051 records are intercompared to analyze residual differences found during the correction periods. The Aura Microwave Limb Sounder (MLS) station overpass record (2005–2020) is used as an independent reference for the comparisons. The two homogenized data records show common correction periods, except for the 2017–2018 period, and the corrections are similar in magnitude. In addition, the post-2000 ozone profile trends are estimated from the two homogenized Dobson D051 time series by dynamical linear modeling (DLM), and results are compared with the DLM trends derived from the collocated Brewer Umkehr time series. By first investigating the long-term Dobson ozone record for trends using the well-established multilinear regression (MLR) method, we find that the trends obtained by both MLR and DLM techniques are similar within their uncertainty ranges in the upper and middle stratosphere but that the trend's significances differ in the lower stratosphere. Post-2000 DLM trend estimates show a positive trend of 0.2 to 0.5 % yr−1 above 35 km, significant for Dobson D051 but lower and therefore nonsignificantly different from zero at the 95 % level of confidence for Brewer B040. As shown for the Dobson D051 data record, the trend only seems to become significantly positive in 2004. Moreover, a persistent negative trend is estimated in the middle stratosphere between 25 and 30 km. In the lower stratosphere, the trend is negative at 20 km, with different levels of significance depending on the period and on the dataset.

A simple, low cost instrument that measures impedance and phase angle was used along with a parallel-plate capacitance system to estimate the moisture content (MC) of six types of wheat. Moisture content of grain is important and is measured at various stages of their processing and storage. A sample of about 150 g of wheat was placed separately between a set of parallel plate electrodes and the impedance and phase angle of the system were measured at frequencies 1 and 5 MHz. A semi-empirical equation was developed using the measured impedance and phase angle values, and the computed capacitance, and the MC values obtained by standard air-oven method. Multi Linear Regression (MLR) method was used for the empirical equation development using statistical software. In the present work, a low-cost impedance analyzer designed and assembled in our laboratory was used to measure the impedance and phase angles. MC values of wheat samples in the moisture range of 9% to 25%, not used in the calibration, were predicted by the equations and compared with their standard air-oven values. For over 97% of the samples tested from the six varieties of wheat, the predicted MC values were within 1% of the air-oven values. This method, being nondestructive and rapid, will have considerable application in the drying and storage processes of wheat and similar field crops.

A simple, low cost instrument called the CI meter, that measures impedance and phase angle was used along with a parallel-plate capacitance system to estimate the moisture content (MC) of six types of wheat. MC measurement of grain is important at various stages of their purchase, processing and storage. Samples of about 150 g of wheat at different MC levels were placed separately between a set of parallel plate electrodes, and the impedance and phase angle of the system were measured at 1 and 5 MHz. The MC values of all these samples were obtained by the standard air-oven method A semi- empirical equation was developed using the measured impedance and phase angle values and the computed capacitance, and the oven MC values obtained. Multi Linear Regression (MLR) method was used for the development of the empirical equation. In the present work, a low-cost impedance analyzer designed by Kandala, and assembled in the National Peanut Laboratory was used to measure the impedance and phase angles. MC values of wheat samples in the moisture range of 9% to 25%, not used in the calibration, were predicted by the equation develop, and compared with the standard air-oven values. For over 97% of the samples tested from the six varieties of wheat, the predicted MC values were within 1% of the air-oven values. This method, being nondestructive and rapid, will have considerable application in the buying, processing, drying and storage processes of wheat and similar field crops.

Kernel functions embed into the autoencoder to identify the sparse models of nonlinear dynamics

Introduction. Magnetic Resonance Imaging (MRI) has modified the practice of radiology. MRI is base on safe interaction between radiowaves at a particular frequency and hydrogen nuclei in the body. Metabolic encephalophaties are by definition those disorder of the central nervous system that are not due primarily to structural abnormalities. Aim. Here we present the 1H MRI and functional MRI (fMRI) method applied to diagnosis of disorders of the central nervous system. Material and methods. Analysis of literature and self-research. Results.We have discussed the major MRI applications in the characteristic of the central nervous system. The relationship beteen the motion of flowing blood and the representation of the blood on images is complex. This work is an introduction to the basic ideas and techniques of fMRI. Therefore, both, 1H MRI and functional MRI, methods are ued in neuroscience. Conclusion. Nonivasive MRI and functional MRI are daily diagnostics methods in neurology.

Boron-dipyrromethene (BODIPY) compounds have unique photophysical properties and have been applied in fluorescence imaging, sensing, optoelectronics, and beyond. In order to design effective BODIPY compounds, it is crucial to acquire a comprehensive understanding of the relationships between the structures of BODIPY and the corresponding photoproperties. Fifteen molecular descriptors were identified to be strongly correlated with the maximum absorption wavelength. The developed ML/QSPR model exhibited good predictive performance, with coefficients of determination (R2) of 0.945 for the training set and 0.734 for the test set, demonstrating robustness and reliability. A posterior analysis of some of the selected descriptors in the model provided insights into the structural features that influence BODIPY compound properties; meanwhile, it also emphasizes the importance of molecular branching, size, and specific functional groups. This work shows that applied combined cheminformatics and machine learning approach is robust to screen the BODIPY compounds and design novel structures with enhanced performance. In the present study, all the BODIPY models studied were fully optimized, and the corresponding absorption spectrum was obtained at DFT/TDDFT//B3LYP/6-311G(d,p) level. All the above calculations were executed by the Gaussian 16 program. Based upon the theoretical computational results, the machine learning-based quantitative structure-property relationship (ML/QSPR) model was employed for predicting the maximum absorption wavelength (λ) of BODIPY compounds by combining hand-crafted molecular descriptors (MD) and explainable machine learning (EML) techniques using Scikit-learn python library. A dataset of 131 BODIPY compounds with their experimental photophysical properties was used to generate a diverse set of molecular descriptors capturing information about the size, shape, connectivity, and other structural features of these compounds using Chemaxon and Alvadesc software. A genetic algorithm (GA) variable selection together with the multi-linear regression (MLR) method were applied to develop the best predictive model using the Genetic Selection python library.

Backgroundβ-glucuronidase enzyme is mostly found in plants and animals. It plays a vital role in detoxification of reactive metabolites that are interrelated to several illnesses and the growth of colon cancer. It speeds up the breaking down of β-glucuronosyl-O-bonds. Lack of β-glucuronidase enzyme leads to Sly syndrome in humans, and overexpression of this enzyme leads to many diseases. Therefore, it becomes necessary to mediate the effect of this enzyme.ResultTheoretical investigation via QSAR modeling on 30 indole derivatives was performed to build a model which could be used to predict the activity of the indole derivatives. QSAR was carried out using multi-linear regression (MLR) method utilizing genetic function approximation (GFA) to develop the QSAR models. A very high predictive QSAR model was reported based on its statistical fitness with good internal and external validation parameters: R2trng = 0.954942, Qcv2 = 0.925462, R2test = 0.855393, and LOF = 0.042924. Molecular docking on the 30 indole derivatives was also performed to screen and identify the lead compound that would be used as template for designing new indole compounds. The docking investigation reveals that ligand 10 binds very tight in the binding pocket of β-glucuronidase enzyme with binding energy of − 9.5 kcal/mol. The ligand (10) was chosen as a template for designing new β-glucuronidase inhibitors. The four design compounds were found to be better than the template and the standard drug (D-saccharic acid 1, 4-lactone) with binding energies of − 9.6, − 9.7, − 9.8, and − 9.9 kcal/mol.ConclusionA very high predictive QSAR model with good internal and external validation parameters: R2trng = 0.954942, Qcv2 = 0.925462, R2test = 0.855393, and LOF = 0.042924, was built and reported in this study. Molecular docking investigation reveals that the most potent compound among all the data set was compound 10 with binding energy of − 9.5 kcal/mole. It bound to the binding pocket of β-glucuronidase enzyme via hydrophobic, electrostatic, and hydrogen bond, and it was retained as template for designing new indole compounds. The design compound with serial number ID 4 was identified to have the highest binding energy of − 9.9 kcal/mole among the designed compounds. It bound to the binding site of the β-glucuronidase enzyme via halogen, hydrophobic, electrostatic, and hydrogen bond. The design compounds were discovered to be better than the template used in the design and the standard drug.

Quantitative structure–activity relationship analysis of perfluoroiso-propyldinitrobenzene derivatives known as photosystem II electron transfer inhibitors