1,720,959 research outputs found
Exploring a deep learning based spatio-temporal forecasting model: testing for scalability and other features
No full textIn recent years, there has been a rapid increase in demand for forecasting services in the fields of solar power gathering and city pollution control, among many other spatio-temporal variable use cases. It is important that we anticipate this demand by developing new models and architectures capable of accurately predicting these variables. But our efforts must not be limited towards achieving greater accuracy alone. Other non-functional characteristics such as flexibility, robustness and scalability are also required. In this thesis, a novel architecture based on deep learning technologies will be explored. The main aim being to test the scaling capabilities of such a model, as well as implementing features that would allow a successful deployment of the model in a real-world like scenario
Employment rates by sex, age and educational attainment level (%)
No full text<p><a href="https://ec.europa.eu/eurostat/data/database?p_p_id=NavTreeportletprod_WAR_NavTreeportletprod_INSTANCE_nPqeVbPXRmWQ&p_p_lifecycle=0&p_p_state=pop_up&p_p_mode=view&p_p_col_id=column-2&p_p_col_pos=1&p_p_col_count=2&_NavTreeportletprod_WAR_NavTreeportletprod_INSTANCE_nPqeVbPXRmWQ_nodeInfoService=true&nodeId=86380">Link to basic metadata.</a></p>
<p><a href="https://ec.europa.eu/eurostat/cache/metadata/en/lfsq_esms.htm">Link to extended description.</a></p>
Técnicas de aprendizaje profundo en dispositivos de bajo consumo aplicadas a la seguridad vial
No full textTrabajo fin de Máster defendido en el Instituto de Física de Cantabria, el 16 de septiembre de 2019 -Curso 2018-2019 - Máster Interuniversitario en Ciencia de Datos / Master in Data Science (UIMP-UC-CSIC)[EN] In this work we explore several applications of deep learning to the field of road safety, with a focus on the efficiency and modularity of the supporting hardware setup. The problem of distance measurement to the vehicle in front while driving is tackled, being camera recordings the only input for the inference step.[ES] En este trabajo exploramos diversas aplicaciones del aprendizaje profundo al campo de la seguridad vial, poniendo el foco en la eficiencia y la modularidad de la configuración hardware que las sustenta. El problema de la medición de la distancia al vehículo situado en frente durante la conducción es abordado, utilizando sólo grabaciones con una cámara como entrada para la inferencia.Peer reviewe
Air pollution datasets
No full textProcessed air pollution datasets originally obtained from the open data portal of the Madrid City Hall. The pollutants include:
Fine particulate matter: PM2.5
Coarse particulate matter: PM10
Ozone: O3
Nitrogen monoxide: NO
Nitrogen dioxide: NO2
Nitrogen oxides: NOx
Sulfur dioxide: SO2
Carbon monoxide: CO
Toluene: TOL
Benzene: BEN
Ethylbenzene: EBE
The period covered goes from the 1st of January 2010 to the 30th of April 2022. Each pollutant is recorded by a variable number of sensors, between 6 and 24 of them (additional information here). They cover Madrid city and surroundings (see this map). Additional information about the pollutants can be found here.
The specific datasets in HDF5 format are:
01h_flat_raw.h5: Hourly raw data, one table per pollutant. The first column is the timestamp, which are in time-since-epoch. 108049 rows and between 7 and 25 columns.
01h_35x30_norm_linear_J0.0.h5: Hourly mesh-grid data, normalized and linearly interpolated. Single table of shape: (108049, 35, 30, 11).
01h_35x30_norm_nearest_J0.0.h5: Hourly mesh-grid data, normalized and nearest-neighbors interpolated. Single table of shape: (108049, 35, 30, 11).
01h_35x30_raw_linear_J0.0.h5: Hourly mesh-grid data, linearly interpolated. Single table of shape: (108049, 35, 30, 11).
01h_35x30_raw_nearest_J0.0.h5: Hourly mesh-grid data, nearest-neighbors interpolated. Single table of shape: (108049, 35, 30, 11).
01h_35x30_stand_linear_J0.0.h5: Hourly mesh-grid data, standardized and linearly interpolated. Single table of shape: (108049, 35, 30, 11).
01h_35x30_stand_nearest_J0.0.h5: Hourly mesh-grid data, standardized and nearest-neighbors interpolated. Single table of shape: (108049, 35, 30, 11).
This datasets are prepared to work with the framework published at https://github.com/iipr/air-qualit
Mobility demand mesh-grid datasets
No full text15m_flat_bike_count.h5: Table that contains the number of bike rides that started on every bike station in Chicago, per time interval. Time resolution is 15min, covering 2013-2020 (280512 timestamps).
15m_flat_bike_norm_abs.h5: Same as 15m_flat_bike_count.h5, but normalized using the maximum number of rides recorded in that period, i.e.: 84. The normalization is calculated as x' = (x - min(X)) / (max(X) - min(X)).
15m_flat_taxi_count.h5: Table that contains the number of taxi trip counts that started on every taxi zone in Chicago, per time interval. Time resolution is 15min, covering 2013-2020 (280512 timestamps).
15m_flat_taxi_norm_abs.h5: Same as 15m_flat_taxi_count.h5, but normalized using the maximum number of trips recorded in that period, i.e.: 418. The normalization is calculated as x' = (x - min(X)) / (max(X) - min(X)).
15m_map_90_60_bike_norm_abs.h5: Mobility mesh-grid for bikes, calculated from 15m_flat_bike_norm_abs.h5 counting the total number of rides per element of the grid and time interval. The final shape of the dataset is 280512 x 90 x 60.
15m_map_90_60_taxi_norm_abs.h5: Mobility mesh-grid for taxis, calculated from 15m_flat_taxi_norm_abs.h5 using linear interpolation. The final shape of the dataset is 280512 x 90 x 60.
station-locations-bike.csv: Geolocations of the bicycle racks of Chicago.
zone-centroids-taxi.csv: Geolocations of the centroids of the taxi zones of Chicago.
grid-locations-bike.csv: Locations of the elements of a 90x60 grid overlaying Chicago that contain bicycle racks.
holidays.csv: Holidays in Chicago for the period 2013-2020
Going 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
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
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
