Big Data Analytics for Time-Critical Mobility Forecasting ab 128.49 € als pdf eBook: From Raw Data to Trajectory-Oriented Mobility Analytics in the Aviation and Maritime Domains. Aus dem Bereich: eBooks, Sachthemen & Ratgeber, Computer & Internet,
Big Data Analytics for Time-Critical Mobility Forecasting ab 138.99 € als gebundene Ausgabe: From Raw Data to Trajectory-Oriented Mobility Analytics in the Aviation and Maritime Domains. 1st ed. 2020. Aus dem Bereich: Bücher, English, International, Gebundene Ausgaben,
Big Data Analytics for Time-Critical Mobility Forecasting ab 138.99 EURO From Raw Data to Trajectory-Oriented Mobility Analytics in the Aviation and Maritime Domains. 1st ed. 2020
Big Data Analytics for Time-Critical Mobility Forecasting ab 128.49 EURO From Raw Data to Trajectory-Oriented Mobility Analytics in the Aviation and Maritime Domains
The structure, evolution and behavior of atmospheric boundary layer (ABL) is largely regulated by topography, land-surface characteristics, atmospheric radiation and synoptic conditions. Therefore, the mesoscale models like Weather Research Forecasting (WRF) are better suited for ABL studies. This book emphasizes upon the ABL characteristics over north Indian region during two contrasting synoptic situations of summer and winter. First chapter is introductory in nature. A brief description about the WRF modeling system is given in the second chapter. Third chapter describes about the study of regional scale boundary layer characteristics over north India. In chapter four, consequences of sensitivity experiments with different land-surface and boundary layer parameterization schemes are presented. To investigate the influence of finer resolution on the boundary layer characteristics, two-way nesting technique is implemented in the study described in fifth chapter by keeping the parent domain intact and the child domains configured with 5 km resolution over the three cities Delhi, Ahmedabad and Jodhpur.
In this research study, the Ribble Estuary and Fylde Coast model was refined to more accurately predict bathing water quality and use parameters which give a better representation of the existing physical and bio-chemical processes. Empirical formulation linking the mortality (decay) rate of bacterial water quality indicators to environmental conditions such as solar irradiation, turbidity, temperature and salinity was added to the numerical code. The linked boundary between the 1-D and 2-D domains of the numerical model was improved by removing large overlapped linked region. An existing numerical code was rewritten to take advantage of the parallel computing capability of the Graphics Processing Unit (GPU). This was tested on the Ribble Estuary and the Thames Estuary model. This research study improved the ability to predict bathing water quality accurately by introducing more realistic representation of environmental conditions and using parallel computing. This improved the ability to carry real time forecasting of bathing water quality and hence prevent failure to meet the requirements of the EU Bathing Water Directive.
The phenomenon of uncertainty is encountered in many domains and should be faced. Even if the sources of this phenomenon are numerous, it is essentially due to our incapacity to predict precisely the future behaviour of a part or the whole of a given system. Many mathematical techniques have been developed in the few last decades, which help in mastering the uncertainty, and therefore in reducing our ignorance of how systems really behave. In the Supply Chain Management domain, the main source of randomness is the future demand. This later is generally modelled using probability distribution functions, which are developed via different forecasting techniques. The influence of this demand variability on the performance of the Supply Chain is very important: for example, in 2007 the global inventory shortage rate in the retail industry were around 8.3%. On the other hand, in 2003 the global Unsaleable products cost around 1% in the grocery industry. These two types of costs, which are mainly caused by the uncertainty of the future demand, represent important lost for the whole Supply Chain actors.
The impact of fisheries is of great importance on biological, economic, social and political levels. There is still a high uncertainty about the relationships between climate, fish and management decisions. This dissertation provides methodological contributions to several of the data analysis activities necessary to reduce this uncertainty. Firstly, this dissertation deals with finding a trade-off between the performance and the number of zooplankton taxa to classify. The contribution in this domain is a wrapper method where the expert can evaluate the training set in terms of this trade-off between both. Secondly, a methodological pipeline of machine learning state-of-the-art methods is proposed to provide robust forecasting with scarce data. The proposed methodology allows building a probabilistic model where three levels of anchovy recruitment can be predicted based on a small set of factors. Finally, the new machine learning paradigm of multi-dimensional classifiers is applied to simultaneous forecasting of multi-species recruitment. The study proposes a set of pre-processing methods and metrics. The proposed methods are tested on both synthetic and real domains.
Nowadays batches of data are continuously transmitted from a rich variety of sources including websites, mobile devices and other data sources, henceforth referred to as evolving datasets. Discovering associations and their dynamics hidden in such large evolving datasets has been recognized as critical for domains ranging from market products analysis, stock trend monitoring, targeted advertising to weather forecasting.