Search results for " Classification"
showing 10 items of 1043 documents
Gravitational-wave parameter inference using Deep Learning
2021
We explore machine learning methods to detect gravitational waves (GW) from binary black hole (BBH) mergers using deep learning (DL) algorithms. The DL networks are trained with gravitational waveforms obtained from BBH mergers with component masses randomly sampled in the range from 5 to 100 solar masses and luminosity distances from 100 Mpc to, at least, 2000 Mpc. The GW signal waveforms are injected in public data from the O2 run of the Advanced LIGO and Advanced Virgo detectors, in time windows that do not coincide with those of known detected signals, and the data from each detector in the Advanced LIGO and Advanced Virgo network is combined into a unique RGB image. We show that a clas…
Using active learning to adapt remote sensing image classifiers
2011
The validity of training samples collected in field campaigns is crucial for the success of land use classification models. However, such samples often suffer from a sample selection bias and do not represent the variability of spectra that can be encountered in the entire image. Therefore, to maximize classification performance, one must perform adaptation of the first model to the new data distribution. In this paper, we propose to perform adaptation by sampling new training examples in unknown areas of the image. Our goal is to select these pixels in an intelligent fashion that minimizes their number and maximizes their information content. Two strategies based on uncertainty and cluster…
A Layered Architecture for Sentiment Classification of Products Reviews in Italian Language
2017
The paper illustrates a system for the automatic classification of the sentiment orientation expressed into reviews written in Italian language. A proper stratification of linguistic resources is adopted in order to solve the lacking of an opinion lexicon specifically suited for the Italian language. Experiments show that the proposed system can be applied to a wide range of domains.
Classification of Sequences with Deep Artificial Neural Networks: Representation and Architectural Issues
2021
DNA sequences are the basic data type that is processed to perform a generic study of biological data analysis. One key component of the biological analysis is represented by sequence classification, a methodology that is widely used to analyze sequential data of different nature. However, its application to DNA sequences requires a proper representation of such sequences, which is still an open research problem. Machine Learning (ML) methodologies have given a fundamental contribution to the solution of the problem. Among them, recently, also Deep Neural Network (DNN) models have shown strongly encouraging results. In this chapter, we deal with specific classification problems related to t…
Simultaneous detection of the seven main tomato-infecting RNA viruses by two multiplex reverse transcription polymerase chain reactions
2012
Cucumber mosaic virus, Tomato spotted wilt virus, Tomato mosaic virus, Tomato chlorosis virus, Pepino mosaic virus, Torrado tomato virus and Tomato infectious chlorosis virus cause serious damage and significant economic losses in tomato crops worldwide. The early detection of these pathogens is essential for preventing the viruses from spreading and improving their control. In this study, a procedure based on two multiplex RT-PCRs was developed for the sensitive and reliable detection of these seven viruses. Serial dilutions of positive controls were analysed by this methodology, and the results were compared with those obtained by ELISA and singleplex versions of RT-PCR. The multiplex and…
HepatomiRNoma: The proposal of a new network of targets for diagnosis, prognosis and therapy in hepatocellular carcinoma
2015
Abstract: The diagnosis and treatment of hepatocellular carcinoma (HCC) underwent a huge advancement in the last years. Recently, microRNAs (miRNAs) have been also studied to provide a new tool for early diagnosis of high risk patients, for prognostic classification to identify those patients who benefit cancer treatment and for predictive definition to select the right targeted drug. In this review we revised all the available data obtained to explore the role of miRNAs in HCC. This analysis led to identification of miRNAs which could gain a diagnostic, prognostic or predictive role. The results of studies on miRNAs involved in HCC are initial and far from providing scientific evidences to…
Activity typologies as a design model for the ubiquitous detection of daily routines
2018
Emerging technologies open up new visions and business potential for systems design and development in the areas of wellbeing and health. New technologies enable the detection of human performance and early changes in physical and cognitive functioning, making it possible to monitor an older person’s wellbeing. This kind of technology or service sets significant requirements for design, as design concepts must be able to capture the complexity of people’s daily lives in terms of activities and environments. Technology itself is “blind” unless designers can adapt it to human life. There is thus a distinct need for comprehensive design and development models that generate adequate human requi…
USING WRB TO MAP THE SOIL SYSTEMS OF ITALY
2012
Aim of this work was to test the 2010 version of the WRB soil classification for compilating a map of the soil systems of Italy at 1:500,000 scale. The source of data was the national geodatabase storing information on 1,414 Soil Typological Units (STUs). Though, basically, we followed WRB criteria to prioritize soil qualifiers, however, it was necessary to work out an original methodology in the map legend representation to reproduce the high variability inside each delineation meanwhile avoiding any loss of information. Each map unit may represent a combination of three codominant STUs at the most. Dominant STUs were assessed summing up the occurrence of STUs in the Land Components (LCs) …
Towards a quality assessment of freshwater ecosystems through the morphological analysis of phytoplankton.
2012
Among the organisms living at low Reynolds numbers, those belonging to the ecological group of phytoplankton offer an amazing morphological diversity and all the scientists involved in phytoplankton research have commonly observed that they may express a quite high variability, both intra- and inter-specific, in their size and morphology. These features have been traditionally used just for taxonomic classification. However, the ecological value of morphological descriptors in phytoplankton is increasingly used to investigate their abilities in resource (light and nutrients) uptake as a result of natural selection and competition. At the same time, the analysis of suitable morphology and si…