1,721,054 research outputs found
Recursive feature elimination with random forest for PTR-MS analysis of agroindustrial products
No full text
Applications of generalized radial basis functions in speaker normalization and identification
No full textThe paper describes two applications of radial basis function networks to automatic speech recognition. We used local basis networks of elliptical kernels of different functional form, with recursive allocation of units and on-line optimization of parameters (GRAN model). In the first application, the neural network is used as a front end of a continuous speech speaker-dependent recognition system to normalize the input data from new speakers. With a limited amount of new acoustic data, the recognition error of phone units from the Italian speech corpus APASCI is decreased with an adaptability ratio of 25%. The same model has also been applied in a speaker identification task on a database collected at IRST consisting of isolated digits. An identification error rate of 17% has been obtained on the whole database (50 speakers)
Geographical information systems and bootstrap aggregation (bagging) of tree-based classifiers for lyme disease risk prediction in Trentino, Italian Alps
No full textThe risk of exposure to Lyme disease in the province of Trento, Italian Alps, was predicted through the analysis of the distribution of Ixodes ricinus (L.) nymphs infected with Borrelia burgdorferi s.l. with a model based on bootstrap aggregation (bagging) of tree-based classifiers within a geographical information system (GIS). Data on I. ricinus density assessed by dragging the vegetation in 438 sites during 1996 were cross-correlated with the digital cartography of a GIS, which included the variables altitude, exposure and slope, substratum, vegetation type and roe deer density. Ticks were more abundant at altitudes below 1,300 m a.s.l., in the presence of limestone and vegetation cover with thermophile deciduous forests and high densities of roe deer. A bootstrap aggregation procedure (bagging) was used to produce a model for the prediction of tick occurrence, the accuracy of which was tested on actual tick counts assessed by a further dragging campaign carried out during 1997 to determine infection prevalence and resulted in average 77%. Other tests of the model were made on additional and independent data sets. The prevalence of infection with Borrelia burgdorferi s.l, determined by polymerase chain reaction on 2,208 nymphs collected by random dragging in 245 transects selected within eight areas where the model predicted the occurrence of I. ricinus during 1997, was 17.5% and was positively correlated to tick abundance and roe deer density. These findings were used to relate the output of the bagged model (probability of tick occurrence) to the density of infected nymphs through a stepwise model selection procedure and thus to produce a GIS digital map of the probability distribution of infected nymphs in the Province of Trento at high resolution scale (50 by 50-m cell resolution). The application of the bagging procedure increased the accuracy of the prediction made by a single classification tree, a well-known classification method for the analysis of epidemiological dat
Development and application of new predictive models to identify sensory drivers of typicality
No full textGoing Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Efficient feature selection for PTR-MS fingerprinting of agroindustrial products
No full textWe recently introduced the Random Forest - Recursive Feature Elimination (RF-RFE) algorithm for feature selection. In this paper we apply it to the identification of relevant features in the spectra (fingerprints) produced by Proton Transfer Reaction - Mass Spectrometry (PTR-MS) analysis of four agro-industrial products (two datasets with cultivars of Berries and other two with typical cheeses, all from North Italy). The method is compared with the more traditional Support Vector Machine - Recursive Feature Elimination (SVM-RFE), extended to allow multiclass problems. Using replicated experiments we estimate unbiased generalization errors for both methods. We analyze the stability of the two methods and find that RF-RFE is more stable than SVM-RFE in selecting small subsets of features. Our results also show that RF-RFE outperforms SVM-RFE on the task of finding small subsets of features with high discrimination levels on PTR-MS dataset
ISAMUD: an integrated software environment for analysis and management of GPS telemetry data
Full text linkGPS technology has certainly represented a revolution for telemetry. Geographic locations (XY coordinates) of collared animals can be obtained from satellites (via VHF/GSM download or directly via ARGOS system), along with other data, such as activity, outside temperature and precision of the localisation. However, the potentially huge data sets collected by GPS collars may represent a challenge, both in terms of data management and spatial analysis. 25 roe deer (16 females and 9 males) have been captured and marked with GSM-GPS collars (Vectronic GPS-Pro 1D) from January 2005 to date in Eastern Italian Alps (Trentino Province, Monte Bondone area). Data are sent by the collars via GSM net, processed and downloaded as e-mail messages and finally converted to dbf files. We developed an integrated software environment to automatically store, associate geographic variables to and spatially analyse the data. ISAMUD (Information System for Analysis and Management of Ungulates Data) is mostly based on Open Source, Windows (Microsoft ®) and Linux operating softwares. The Geo-database PostgreSQL (http://www.postgresql.org/) and its spatial geographic extension PostGIS (http://postgis.refractions.net) are the core of the information system. Thanks to the latter, some geographic functions can be applied directly in the database, without invoking an external GIS, e.g. some categorical geographic variables (landuse, hunting districts...) can be associated to the localisations. Other more complex geographic features can be uploaded by the Open Source GIS GRASS (Geographic Resources Analysis Support System, http://grass.itc.it/), now available also in Windows version, via the interface Quantum GIS (QGIS) (www.qgis.org). Statistical and geostatistical analyses, including Home Range calculations, are carried out in R (http://www.r-project.org/), thanks to the numerous available packages, Adehabitat among all (http://cran.r-project.org/src/contrib/Descriptions/adehabitat.html), or to ad hoc developed functions. Results are then stored in the main geodatabase, to be available for further analyses. The database can be accessed by either PostgreSQL graphic interface, including PGADMIN III (http://www.pgadmin.org/) and ACCESS (www.microsoft.com/access/). The user-friendly data input/output format has been developed within the latter. The flexibility of the system allows the development of other modules and the applicability to different data sets from different species
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
