Search results for "Time series"
showing 10 items of 247 documents
Indoor free space optics link under the weak turbulence regime: Measurements and model validation
2015
In this study, the authors present the measurements performed on a free space optics (FSO) communications link using an indoor atmospheric chamber. In particular, the authors have generated several different optical turbulence conditions, demonstrating how even the weak turbulence regime can strongly affect the FSO link performance. The authors have carried out an in-depth analysis of the data collected during the measurements, and calculated the turbulence strength (i.e. scintillation index and Rytov variance) and the important performance metrics (i.e. the Q-factor and bit error rate) to evaluate the FSO link quality. Moreover, the authors have tested, for the first time, an appositely de…
THE IMPACT OF ELECTION RESULTS ON THE MEMBER NUMBERS OF THE LARGE PARTIES IN BAVARIA AND GERMANY
2005
In this paper, we investigate the relations between the numbers of members of various parties and their results in the elections in Bavaria and in Germany. Deriving from the finding that there is a strong time-delayed correlation between these data-sets for the two largest parties in Bavaria, we show in a simulation based on the Sznajd model that such a correlation leads to very stable majorities, just as in Bavaria.
Use of neurofuzzy networks to improve wastewater flow-rate forecasting
2009
A neurofuzzy wastewater flow-rate forecasting model (NFWFFM) has been developed and tested with actual data measured at the input of two wastewater treatment facilities which treat the wastewater corresponding to 150,000 and 1,250,000p.e., respectively. Good agreements between forecasted and actual flow-rates were obtained. The artificial intelligence algorithm uses only two input variables (day of the week and average daily flow-rate of day before) and one output variable (predicted average daily flow-rate). Using three months data for training the network, a long-term forecast (one month) is made with average errors below 10%. Results were compared with those obtained by applying the Cens…
Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine
2022
Thanks to the emergence of cloud-computing platforms and the ability of machine learning methods to solve prediction problems efficiently, this work presents a workflow to automate spatiotemporal mapping of essential vegetation traits from Sentinel-3 (S3) imagery. The traits included leaf chlorophyll content (LCC), leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fractional vegetation cover (FVC), being fundamental for assessing photosynthetic activity on Earth. The workflow involved Gaussian process regression (GPR) algorithms trained on top-of-atmosphere (TOA) radiance simulations generated by the coupled canopy radiative transfer model (RTM) SC…
An Improved Forecasting Model from Satellite Imagery Based on Optimum Wavelet Bases and Adam Optimized LSTM Methods
2021
This paper proposes a new hybrid approach I-WT-LSTM (i.e., Improved Wavelet Long Short-Term Memory (LSTM) Model) for forecasting non-stationary time series (TS) from satellite imagery. The proposed approach consists of two steps: The first step aims at decomposing TS using Multi-Resolution Analysis wavelet (MRA-WT) into inter-and intra-annual components using 18 different mother wavelets (MW). Then, the energy to Shannon entropy ratio criterion is calculated to select the best MW. The second step is based on the LSTM model using Adam optimizer to predict the future. The proposed approach is tested using TS derived from Moderate Resolution Imaging Spectroradiometer (MODIS) images from 2001 t…
Time series clustering with different distance measures to tell Web bots and humans apart
2022
The paper deals with the problem of differentiating Web sessions of bots and human users by observing some characteristics of their traffic at the Web server input. We propose an approach to cluster bots’ and humans’ sessions represented as time series. First, sessions are expressed as sequences of HTTP requests coming to the server at specific timestamps; then, they are pre-preprocessed to form time series of limited length. Time series are clustered and the clustering performance is evaluated in terms of the ability to partition bots and humans into separate clusters. The proposed approach is applied to real server log data and validated with the use of different time series distance meas…
Spatial Coherence of Tropical Rainfall at the Regional Scale
2007
AbstractThis study examines the spatial coherence characteristics of daily station observations of rainfall in five tropical regions during the principal rainfall season(s): the Brazilian Nordeste, Senegal, Kenya, northwestern India, and northern Queensland. The rainfall networks include between 9 and 81 stations, and 29–70 seasons of observations. Seasonal-mean rainfall totals are decomposed in terms of daily rainfall frequency (i.e., the number of wet days) and mean intensity (i.e., the mean rainfall amount on wet days).Despite the diverse spatiotemporal sampling, orography, and land cover between regions, three general results emerge. 1) Interannual anomalies of rainfall frequency are us…
Analysis and modeling of wind directions time series
2013
This work aims at studying some aspects of wind directions in Italy and supplying appropriate models. A comparison is presented between independent mixture and Hidden Markov models, which seem to be appropriate as far as the series we studied.
All-day activity of Dolichovespula saxonica (Hymenoptera, Vespidae) colonies in Central Finland
2022
In social vespid wasps, colony activity varies at many temporal scales. We studied the peak season activity (number of individuals entering the nest per min) of colonies of the social vespine wasp Dolichovespula saxonica in its native range in boreal Finland. Six colonies were monitored non-stop for a full day, starting before sunrise and ending after sunset. Shorter monitoring was carried out before and/or after the full-day monitoring. All colonies were active before sunrise and after sunset, and the overall activity was positively linked with colony size. Activity showed irregular minute-to-minute cycles in all colonies. The broader within-day dynamics were idiosyncratic among the coloni…
A Support Vector Machine Signal Estimation Framework
2018
Support vector machine (SVM) were originally conceived as efficient methods for pattern recognition and classification, and the SVR was subsequently proposed as the SVM implementation for regression and function approximation. Nowadays, the SVR and other kernel‐based regression methods have become a mature and recognized tool in digital signal processing (DSP). This chapter starts to pave the way to treat all the problems within the field of kernel machines, and presents the fundamentals for a simple, framework for tackling estimation problems in DSP using support vector machine SVM. It outlines the particular models and approximations defined within the framework. The chapter concludes wit…