scholarly journals Multivariate Time Series Analysis of Temperatures in the Archaeological Museum of L’Almoina (Valencia, Spain)

Sensors ◽  
2021 ◽  
Vol 21 (13) ◽  
pp. 4377
Author(s):  
Sandra Ramírez ◽  
Manuel Zarzo ◽  
Fernando-Juan García-Diego
Keyword(s):  
Time Series ◽  
Time Series Analysis ◽  
Multivariate Time Series ◽  
Principal Component ◽  
Thermal Conditions ◽  
Archaeological Site ◽  
Series Analysis ◽  
Long Term Monitoring ◽  
Term Monitoring

An earlier study carried out in 2010 at the archaeological site of L’Almoina (Valencia, Spain) found marked daily fluctuations of temperature, especially in summer. Such pronounced gradient is due to the design of the museum, which includes a skylight as a ceiling, covering part of the remains in the museum. In this study, it was found that the thermal conditions are not homogeneous and vary at different points of the museum and along the year. According to the European Standard EN10829, it is necessary to define a plan for long-term monitoring, elaboration and study of the microclimatic data, in order to preserve the artifacts. With the aforementioned goal of extending the study and offering a tool to monitor the microclimate, a new statistical methodology is proposed. For this propose, during one year (October 2019–October 2020), a set of 27 data-loggers was installed, aimed at recording the temperature inside the museum. By applying principal component analysis and k-means, three different microclimates were established. In order to characterize the differences among the three zones, two statistical techniques were put forward. Firstly, Sparse Partial Least Squares Discriminant Analysis (sPLS-DA) was applied to a set of 671 variables extracted from the time series. The second approach consisted of using a random forest algorithm, based on the same functions and variables employed by the first methodology. Both approaches allowed the identification of the main variables that best explain the differences between zones. According to the results, it is possible to establish a representative subset of sensors recommended for the long-term monitoring of temperatures at the museum. The statistical approach proposed here is very effective for discriminant time series analysis and for explaining the differences in microclimate when a net of sensors is installed in historical buildings or museums.

Exploring long-term urban cycles with multivariate time-series analysis

2021 ◽  
pp. 239980832110581
Author(s):  
Luca Salvati
Keyword(s):  
Time Series ◽  
Life Cycle ◽  
Time Series Analysis ◽  
Population Growth ◽  
Multivariate Time Series ◽  
Metropolitan Region ◽  
Series Analysis ◽  
Multivariate Time Series Analysis ◽  
Non Linear

European cities underwent long-term socioeconomic transformations resulting in a shift from centralized demographic growth typical of late industrialization to a more recent (and spatially uncoordinated) de-concentration of population and economic activities. While abandoning traditional compact models and moving toward settlement dispersion, population growth in urban areas was assumed to follow a “life cycle” constituted of four developmental stages (urbanization, suburbanization, counter-urbanization, and re-urbanization). We studied anomalies in the City Life Cycle (CLC) of a large metropolitan region (Athens, Greece) with the aim at achieving a less mechanistic interpretation of long-term population growth in complex social contexts. Using population data that cover more than 170 years (1848–2020) and multivariate time-series analysis, a non-linear growth history was delineated, with sequential accelerations and decelerations characteristic of the first CLC stage (urbanization). Considering the classical division in three radio-centric districts (core, ring, and agglomeration), different development stages coexisted since World War II. Heterogeneous suburbanization processes mixed up with late urbanization and weaker impulses of counter-urbanization and re-urbanization. The empirical results of time-series analysis confirm the non-linear expansion of Athens, shedding further light on long-term mechanisms of metropolitan development and informing management policies of urban growth.

scholarly journals Long-Term Data Traffic Forecasting for Network Dimensioning in LTE with Short Time Series

Electronics ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 1151
Author(s):  
Carolina Gijón ◽  
Matías Toril ◽  
Salvador Luna-Ramírez ◽  
María Luisa Marí-Altozano ◽  
José María Ruiz-Avilés
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Time Series Analysis ◽  
Data Traffic ◽  
Medium Term ◽  
Short Term ◽  
Traffic Forecasting ◽  
Series Analysis ◽  
Radio Planning

Network dimensioning is a critical task in current mobile networks, as any failure in this process leads to degraded user experience or unnecessary upgrades of network resources. For this purpose, radio planning tools often predict monthly busy-hour data traffic to detect capacity bottlenecks in advance. Supervised Learning (SL) arises as a promising solution to improve predictions obtained with legacy approaches. Previous works have shown that deep learning outperforms classical time series analysis when predicting data traffic in cellular networks in the short term (seconds/minutes) and medium term (hours/days) from long historical data series. However, long-term forecasting (several months horizon) performed in radio planning tools relies on short and noisy time series, thus requiring a separate analysis. In this work, we present the first study comparing SL and time series analysis approaches to predict monthly busy-hour data traffic on a cell basis in a live LTE network. To this end, an extensive dataset is collected, comprising data traffic per cell for a whole country during 30 months. The considered methods include Random Forest, different Neural Networks, Support Vector Regression, Seasonal Auto Regressive Integrated Moving Average and Additive Holt–Winters. Results show that SL models outperform time series approaches, while reducing data storage capacity requirements. More importantly, unlike in short-term and medium-term traffic forecasting, non-deep SL approaches are competitive with deep learning while being more computationally efficient.

Sign in / Sign up

Export Citation Format

Share Document