1. Creating better models of data work through big exercises of imagination2020, radijska ali televizijska oddaja Najdeno v: ključnih besedah Povzetek najdenega: ...predictive economies, data, social tech, machine learning, autonomy, data worker, trade union, solidarity,... Ključne besede: predictive economies, data, social tech, machine learning, autonomy, data worker, trade union, solidarity, labour extraction, data labour rights Objavljeno: 08.12.2020; Ogledov: 1417; Prenosov: 9 Polno besedilo (0,00 KB) 
2. Explicit Feature Construction and Manipulation for Covering Rule Learning AlgorithmsJohannes Fuernkranz, Nada Lavrač, Dragan Gamberger, 2010, samostojni znanstveni sestavek ali poglavje v monografski publikaciji Opis: Features are the main rule building blocks for rule learning algorithms. They can be simple tests for attribute values or complex logical terms representing available domain knowledge. In contrast to common practice in classification rule learning, we argue that separation of the feature construction and rule construction processes has theoretical and practical justification. Explicit usage of features enables a unifying framework of both propositional and relational rule learning and we present and analyze procedures for feature construction in both types of domains. It is demonstrated that the presented procedure for constructing a set of simple features has the property that the resulting set enables construction of complete and consistent rules whenever it is possible, and that the set does not include obviously irrelevant features. Additionally, the concept of feature relevancy is important for the effectiveness of rule learning. It this work, we illustrate the concept in the coverage space and
prove that the relative relevancy has the qualitypreserving property in respect to the resulting rules. Moreover, we show that the transformation from the attribute to the feature space enables a novel, theoretically justified way of handling unknown attribute values. The same approach
enables that estimated imprecision of continuous attributes can be taken into account, resulting in construction of robust features in respect to this imprecision. Najdeno v: ključnih besedah Povzetek najdenega: ... Machine learning, Feature construction, Rule learning, Unknown attribute... Ključne besede: Machine learning, Feature construction, Rule learning, Unknown attribute values Objavljeno: 14.07.2017; Ogledov: 3328; Prenosov: 0 Polno besedilo (365,76 KB) 
3. 
4. Mass composition of ultrahigh energy cosmic rays at the Pierre Auger ObservatoryGašper Kukec Mezek, 2019, doktorska disertacija Opis: Cosmic rays with energies above 10^18 eV, usually referred to as ultrahigh energy cosmic rays (UHECR), have been a mystery from the moment they have been discovered. Although we have now more information on their extragalactic origin, their direct sources still remain hidden due to deviations caused by galactic magnetic fields. Another mystery, apart from their production sites, is their nature. Their mass composition, still uncertain at these energies, would give us a better understanding on their production, acceleration, propagation and capacity to produce extensive air showers in the Earth's atmosphere. Mass composition studies of UHECR try to determine their nature from the difference in development of their extensive air showers.
In this work, observational parameters from the hybrid detection system of the Pierre Auger Observatory are used in a multivariate analysis to obtain the mass composition of UHECR. The multivariate analysis (MVA) approach combines a number of mass composition sensitive variables and tries to improve the separation between different UHECR particle masses. Simulated distributions of different primary particles are fitted to measured observable distributions in order to determine individual elemental fractions of the composition. When including observables from the surface detector, we find a discrepancy in the estimated mass composition between a mixed simulation sample and the Pierre Auger data. Our analysis results from the Pierre Auger data are to a great degree independent on hadronic interaction models. Although they differ at higher primary masses, the different models are more consistent, when combining fractions of oxygen and iron. Compared to previously published results, the systematic uncertainty from hadronic interaction models is roughly four times smaller. Our analysis reports a predominantly heavy composition of UHECR, with more than a 50% fraction of oxygen and iron at low energies. The composition is then becoming heavier with increasing energy, with a fraction of oxygen and iron above 80% at the highest energies. Najdeno v: ključnih besedah Povzetek najdenega: ...air showers, mass composition, Pierre Auger Observatory, machine learning, multivariate analysis... Ključne besede: astroparticle physics, ultrahigh energy cosmic rays, extensive air showers, mass composition, Pierre Auger Observatory, machine learning, multivariate analysis Objavljeno: 03.04.2019; Ogledov: 3283; Prenosov: 147 Polno besedilo (17,53 MB) 
5. Machine learning models for government to predict COVID19 outbreakPoonam Chaudhary, Saibal K. Pal, Rajan Gupta, Gaurav Pandey, 2020, izvirni znanstveni članek Opis: The COVID19 pandemic has become a major threat to the whole world. Analysis of this disease requires major attention by the government in all countries to take necessary steps in reducing the effect of this global pandemic. In this study, outbreak of this disease has been analysed and trained for Indian region till 10th May, 2020, and testing has been done for the number of cases for the next three weeks. Machine learning models such as SEIR model and Regression model have been used for predictions based on the data collected from the official portal of the Government of India in the time period of 30th January, 2020, to 10th May, 2020. The performance of the models was evaluated using RMSLE and achieved 1.52 for SEIR model and 1.75 for the regression model. The RMSLE error rate between SEIR model and Regression model was found to be 2.01. Also, the value of R0, which is the spread of the disease, was calculated to be 2.84. Expected cases are predicted around 175K200K in the threeweek time period of test data, which is very close to the actual numbers. This study will help the government and doctors in preparing their plans for the future. Najdeno v: ključnih besedah Ključne besede: COVID19, India, spread exposed infected recovered model, regression model, machine learning, predictions, forecasting Objavljeno: 01.04.2021; Ogledov: 1046; Prenosov: 61 Polno besedilo (0,00 KB) Gradivo ima več datotek! Več...

6. Comparative analysis of epidemiological models for COVID19 pandemic predictionsSaibal K. Pal, Rajan Gupta, Gaurav Pandey, 2021, izvirni znanstveni članek Opis: Epidemiological modeling is an important problem around the world. This research presents COVID19 analysis to understand which model works better for different regions. A comparative analysis of three growth curve fitting models (Gompertz, Logistic, and Exponential), two mathematical models (SEIR and IDEA), two forecasting models (Holt’s exponential and ARIMA), and four machine/deep learning models (Neural Network, LSTM Networks, GANs, and Random Forest) using three evaluation criteria on ten prominent regions around the world from North America, South America, Europe, and Asia has been presented. The minimum and median values for RMSE were 1.8 and 5372.9; the values for the mean absolute percentage error were 0.005
and 6.63; and the values for AIC were 87.07 and 613.3, respectively, from a total of 125 experiments across 10 regions. The growth curve fitting models worked well where flattening of the cases has started. Based on region’s growth curve, a relevant model from the list can be used for predicting the number of infected cases for COVID19. Some other models used in forecasting the number of cases have been added in the future work section, which can help researchers to forecast the number of cases in different regions of the world. Najdeno v: ključnih besedah Povzetek najdenega: ...models (Holt’s exponential and ARIMA), and four machine/deep learning models (Neural Network, LSTM Networks, GANs,... Ključne besede: epidemic modeling, machine learning, neural networks, pandemic forecasting, timeseries forecasting Objavljeno: 15.07.2021; Ogledov: 1088; Prenosov: 17 Polno besedilo (3,16 MB) Gradivo ima več datotek! Več...

7. Application of machine learning techniques for cosmic ray event classification and implementation of a realtime ultrahigh energy photon search with the surface detector of the Pierre Auger ObservatoryLukas Zehrer, 2021, doktorska disertacija Opis: Despite their discovery already more than a century ago, Cosmic Rays (CRs) still did not divulge all their properties yet. Theories about the origin of ultrahigh energy (UHE, > 10^18 eV) CRs predict accompanying primary photons. The existence of UHE photons can be investigated with the world’s largest groundbased experiment for detection of CRinduced extensive air showers (EAS), the Pierre Auger Observatory, which offers an unprecedented exposure to rare UHE cosmic particles.
The discovery of photons in the UHE regime would open a new observational window to the Universe, improve our understanding of the origin of CRs, and potentially uncloak new physics beyond the standard model.
The novelty of the presented work is the development of a "realtime" photon candidate event stream to a global network of observatories, the Astrophysical Multimessenger Observatory Network (AMON). The stream classifies CR events observed by the Auger surface detector (SD) array as regards their probability to be photon nominees, by feeding to advanced machine learning (ML) methods observational air shower parameters of individual CR events combined in a multivariate analysis (MVA).
The described straightforward classification procedure further increases the Pierre Auger Observatory’s endeavour to contribute to the global effort of multimessenger (MM) studies of the highest energy astrophysical phenomena, by supplying AMON partner observatories the possibility to followup detected UHE events, live or in their archival data. Najdeno v: ključnih besedah Ključne besede: astroparticle physics, ultrahigh energy cosmic rays, ultrahigh energy photons, extensive air showers, Pierre Auger Observatory, multimessenger, AMON, machine learning, multivariate analysis, dissertations Objavljeno: 27.10.2021; Ogledov: 1165; Prenosov: 55 Polno besedilo (0,00 KB) Gradivo ima več datotek! Več...

8. Finding (or not) dark matter in gammaray images of the Galactic center with computer visionSascha Caron, Gabrijela Zaharijas, Gudlaugur Johannesson, Christopher Eckner, Luc Hendriks, Roberto Ruiz de Austri, 2021, objavljeni povzetek znanstvenega prispevka na konferenci Najdeno v: ključnih besedah Povzetek najdenega: ... machine learning, gamma rays... Ključne besede: machine learning, gamma rays Objavljeno: 17.02.2022; Ogledov: 527; Prenosov: 2 Polno besedilo (8,16 MB) Gradivo ima več datotek! Več...

9. Complex networkbased cough signal analysis for digital auscultation: a machine learning approachSwapna Mohanachandran Nair Sindhu, 2022, izvirni znanstveni članek Opis: The paper proposes a novel approach to bring out the potential of complex networks based on graph theory to unwrap the hidden characteristics of cough signals, croup (BC), and pertussis (PS). The spectral and complex network analyses of 48 cough sounds are utilized for understanding the airflow through the infected respiratory tract. Among the different phases of the cough sound timedomain signals of BC and PS – expulsive (X), intermediate (I), and voiced (V)  the phase ‘I’ is noisy in BC due to improper glottal functioning. The spectral analyses reveal highfrequency components in both cough signals with an additional highintense lowfrequency spread in BC. The complex network features created by the correlation mapping approach, like number of edges (E), graph density (G), transitivity (), degree centrality (D), average path length (L), and number of components () distinguishes BC and PS. The higher values of E, G, and for BC indicate its musical nature through the strong correlation between the signal segments and the presence of highintense lowfrequency components in BC, unlike that in PS. The values of D, L, and discriminate BC and PS in terms of the strength of the correlation between the nodes within them. The linear discriminant analysis (LDA) and quadratic support vector machine (QSVM) classifies BC and PS, with greater accuracy of 94.11% for LDA. The proposed work opens up the potentiality of employing complex networks for cough sound analysis, which is vital in the current scenario of COVID19. Najdeno v: ključnih besedah Ključne besede: Complex network analysis, Auscultation, Croup cough, Pertussis
Spectral analysis, Machine learning techniques Objavljeno: 30.06.2022; Ogledov: 248; Prenosov: 0 Polno besedilo (1,71 MB) 
10. Fractal and timeseries analyses based rhonchi and bronchial auscultation: A machine learning approachSWAPNA MOHANACHANDRAN NAIR SINDHU SWAPNA,, 2022, izvirni znanstveni članek Opis: Objectives: The present work reports the study of 34 rhonchi (RB) and
Bronchial Breath (BB) signals employing machine learning techniques, timefrequency, fractal, and nonlinear timeseries analyses. Methods: The timefrequency analyses and the complexity in the dynamics of airflow in BB
and RB are studied using both Power Spectral Density (PSD) features and
nonlinear measures. For accurate prediction of these signals, PSD and nonlinear measures are fed as input attributes to various machine learning
models. Findings: The spectral analyses reveal fewer, lowintensity frequency
components along with its overtones in the intermittent and rapidly damping
RB signal. The complexity in the dynamics of airflow in BB and RB is investigated
through the fractal dimension, Hurst exponent, phase portrait, maximal
Lyapunov exponent, and sample entropy values. The greater value of entropy
for the RB signal provides an insight into the internal morphology of the airways
containing mucous and other obstructions. The Principal Component Analysis
(PCA) employs PSD features, and Linear Discriminant Analysis (LDA) along
with Pattern Recognition Neural Network (PRNN) uses nonlinear measures
for predicting BB and RB. Signal classification based on phase portrait
features evaluates the multidimensional aspects of signal intensities, whereas
that based on PSD features considers mere signal intensities. The principal
components in PCA cover about 86.5% of the overall variance of the data class,
successfully distinguishing BB and RB signals. LDA and PRNN that use nonlinear timeseries parameters identify and predict RB and BB signals with 100%
accuracy, sensitivity, specificity, and precision. Novelty: The study divulges the
potential of nonlinear measures and PSD features in classifying these signals
enabling its application to be extended for lowcost, noninvasive COVID19
detection and realtime health monitoring. Najdeno v: ključnih besedah Ključne besede: lung signal, fractal analysis, sample entropy, nonlinear timeseries, machine learning techniques Objavljeno: 30.06.2022; Ogledov: 233; Prenosov: 0 Polno besedilo (1,50 MB) 