Aiming to hide the real money gains and to avoid taxes, fictive prices are sometimes recorded in the real estate transactions. This paper is concerned with artificial neural networks based screening ...of real estate transactions aiming to categorize them into "clear" and "fictitious" classes. The problem is treated as an outlier detection task. Both unsupervised and supervised approaches to outlier detection are studied here. The soft minimal hypersphere support vector machine (SVM) based novelty detector is employed to solve the task without the supervision. In the supervised case, the effectiveness of SVM, multilayer perceptron (MLP), and a committee based classification of the real estate transactions are studied. To give the user a deeper insight into the decisions provided by the models, the real estate transactions are not only categorized into "clear" and "fictitious" classes, but also mapped onto the self organizing map (SOM), where the regions of "clear", "doubtful" and "fictitious" transactions are identified. We demonstrate that the stability of the regions evolved in the SOM during training is rather high. The experimental investigations performed on two real data sets have shown that the categorization accuracy obtained from the supervised approaches is considerably higher than that obtained from the unsupervised one. The obtained accuracy is high enough for the technique to be used in practice. PUBLICATION ABSTRACT
Amounts of historical data collected increase and business intelligence applicability with automatic forecasting of time series are in high demand. While no single time series modeling method is ...universal to all types of dynamics, forecasting using an ensemble of several methods is often seen as a compromise. Instead of fixing ensemble diversity and size, we propose to predict these aspects adaptively using meta-learning. Meta-learning here considers two separate random forest regression models, built on 390 time-series features, to rank 22 univariate forecasting methods and recommend ensemble size. The forecasting ensemble is consequently formed from methods ranked as the best, and forecasts are pooled using either simple or weighted average (with a weight corresponding to reciprocal rank). The proposed approach was tested on 12561 micro-economic time-series (expanded to 38633 for various forecasting horizons) of M4 competition where meta-learning outperformed Theta and Comb benchmarks by relative forecasting errors for all data types and horizons. Best overall results were achieved by weighted pooling with a symmetric mean absolute percentage error of 9.21% versus 11.05% obtained using the Theta method.
The recent detection of TeV neutrino emission from the nearby active galaxy NGC 1068 by IceCube suggests that AGN could make a sizable contribution to the total high-energy cosmic neutrino flux. The ...absence of TeV gamma rays from NGC 1068, indicates neutrino production originates in the innermost region of the AGN. Disk-corona models predict a correlation between neutrinos and keV X-rays in Seyfert galaxies, a subclass of AGN to which NGC 1068 belongs. Using 10 years of IceCube through-going track events, we report results from searches for neutrino signals from 27 additional sources in the Northern Sky by studying both the generic single power-law spectral assumption and spectra predicted by the disk-corona model. Our results show excesses of neutrinos associated with two sources, NGC 4151 and CGCG 420-015, at 2.7\(\sigma\) significance, and at the same time constrain the collective neutrino emission from our source list.
Hypothesis tests based on unbinned log-likelihood (LLH) functions are a common technique used in multi-messenger astronomy, including IceCube's neutrino point-source searches. We present the general ...Python-based tool "SkyLLH", which provides a modular framework for implementing and executing log-likelihood functions to perform data analyses with multi-messenger astronomy data. Specific SkyLLH framework features for a new and improved time-integrated IceCube point-source analysis are highlighted, including the support for kernel density estimation (KDE) based probability density functions. In addition, the support for a variety of point-source analysis types, such as stacked and time-variable searches, will be presented.
The IceCube Neutrino Observatory is a one-cubic-kilometer-sized neutrino telescope deployed deep in the Antarctic ice at the South Pole. One of IceCube's major goals is finding the origins of ...astrophysical high-energy neutrinos. In 2022, IceCube identified the strongest point-like neutrino source so far, the active galaxy NGC 1068. Analyzing 9 years of muon-neutrino data from the Northern Sky recorded between 2011 and 2020, the emission from NGC 1068 is significant at 4.2\(\,\sigma\). We present a planned extension to this search with additional years of data. One of these years includes data from 2010 when IceCube was only partially constructed. We discuss the improvement in sensitivity and discovery potential for neutrino point sources across the Northern sky. We show that by building on the established analysis techniques, previous observations could be improved, not only for NGC 1068 but for all possible sources in the Northern sky.
The IceCube Neutrino Observatory, deployed inside the deep glacial ice at the South Pole, is the largest neutrino telescope in the world. While eight years have passed since IceCube discovered a ...diffuse flux of high-energy astrophysical neutrinos, the sources of the vast majority of these neutrinos remain unknown. Here, we present a new search for neutrino point sources that improves the accuracy of the statistical analysis, especially in the low energy regime. We replaced the usual Gaussian approximations of IceCube's point spread function with precise numerical representations, obtained from simulations, and combined them with new machine learning-based estimates of event energies and angular errors. Depending on the source properties, the new analysis provides improved source localization, flux characterization and thereby discovery potential (by up to 30%) over previous works. The analysis will be applied to IceCube data that has been recorded with the full 86-string detector configuration from 2011 to 2020 and includes improved detector calibration.
Darbe analizuojamas statybinių medžiagų konkurencingumas, nustatyti statybinių medžiagų konkurencingumą įtakojantys veiksniai ir pateikti pasiūlymai rinkos gerinimui. Pasitvirtino hipotezė, kad ...statybinių medžiagų paklausą ir kainas įtakoja klientų poreikiai ir jų finansinės galimybės, tačiau pasaulinės krizės įtaka yra labai ženkli,. Atlikta darbuotojų ir pirkėjų apklausa padėjo nustatyti, kokios statybinės medžiagos dažniausiai yra perkamos, kaip klientai ir darbuotojai vertina įmonę ir jos konkurentus, kokiomis paslaugomis ir nuolaidomis dažniausiai naudojasi, kaip vertina prekių kokybę. Apibendrinus tyrimo rezultatus, pateiktos teorinės ir praktinės išvados bei rekomendacijos.
In this work is analyzed ability of building materials, identifying subjects who influence it and provided proposals for improvement of market. There were approved hypothesis that the demand and prices of building materials are under of influence of customer’s requirements, their financial situation, but the global crisis influence is very visible. Accomplished inquiry of employees and buyers helped to establish, what building materials are saleable, how clients and employers estimate company and her competitors, which services and discounts usually use and how estimate the quality of goods. Theoretical and practical conclusions and recommendations proposed by summarized results of research.
Šiame darbe nagrinėsime teorines ir praktines problemas, kurios atsiranda, kai neturtinė žala padaroma draudiminio įvykio metu ir turėtų būti pilnai ar iš dalies atlyginama draudimo įmonės. Ši tema ...aktuali tuo, kad plečiantis draudimo įmonių veiklai, atsirandant vis daugiau privalomojo draudimo rūšių, dėl to, iš kitos pusės visuomenei intensyviai vykdant ekonominę veiklą, atsitinka vis daugiau draudiminių įvykių, kuriuose nuostuolius padengti turi draudimo įmonės, savaime suprantama, kad tai kelia nemažai problemų, nes visos draudimo sritys yra pakankamai naujos ir yra nedaug praktikos susijusios su tokių išmokų priteisimu, be to, pats neturtinės žalos įvertinimas ir jos priteisimas Lietuvos teismų sistemoje nėra nusistovėjęs ir sistemiškai aiškiai suformuluotas. Atsiranda daug neturtinės žalos įvertinimo sunkumų, nes tokia žala sunkiai pamatuojama, nes neturtinė žala, tai tokie praradimai, kurie negali būti įvertinti pinigais, galime kalbėti tik apie galimą kompensaciją. Be to, dauguma draudimo įmonių linkę vertinti savo draudimo paslaugas kaip turto draudimą ir neturtinę žalą atlygina labai nenoriai, neatlygina visai arba atlygina nepakankamai, skiriasi civilinio draudimo sąlygos įvairiose veiklos srityse. Taigi, iš vienos pusės plečiant Lietuvoje neturtinės žalos atlyginimo atvejų sąrašą ir didinant priteistinos neturtinės žalos dydžius, savaime suprantama, kad visuomenėje iškyla poreikis apsidrausti nuo galimų nuostuolių, taip pat ir nuo nuostolių atlyginimo padarius žalą... toliau žr. visą tekstą
Long ago people recognized non-pecuniary damage, as wel as pecuniary losses, which are stemming from physical injuries, death or emotional trauma. All these kinds of damages are hard to estimate and determine though. Despite the fact that some lawyers argue for abolition of compansation for non-pecuniary damage, this sort of damage still seem to be significant dealing with defence of a plaintiff under this rubric in defferent European countries. By the means of legal practice of non-pecuniary nature the person could claim damages for physical and emotional suffering, nervousness, grief, anxiety and ambarrasment. However, non-pecuniary damage should not be identified with pecuniary losses. At this point, the apprehension of non-pecuniary damage is supposed to be linked to the compensation instead of fine. In order to clarify this statement, the most important is that the compensation of non-pecuniary damage, first of all, serves as damage rewarding or as a kind of civil remedy and protection. Although, some voises said that pain and suffering awardas are hard to estimate due to the fact that the damage valuation of these kinds of losses sometimes we just can not figure out properly. Nowadays, under legal regulation, courts determine and estimate the value on non-pecuniary damage bearing in mind all significant circumstanses. Consequently, courts could change the value on non-pecuniary damage in two ways: lower or higher the compensation for these losses. Moreover, courts... to full text