Suchergebnisse

An earthquake is a tremor felt on the surface of the earth created by the movement of the major pieces of its outer shell. Till now, many attempts have been made to forecast earthquakes, which saw some success, but these attempted models are specific to a region. In this paper, an earthquake occurrence and location prediction model is proposed. After reviewing the literature, long short-term memory (LSTM) is found to be a good option for building the model because of its memory-keeping ability. Using the Keras tuner, the best model was selected from candidate models, which are composed of combinations of various LSTM architectures and dense layers. This selected model used seismic indicators from the earthquake catalog of Bangladesh as features to predict earthquakes of the following month. Attention mechanism was added to the LSTM architecture to improve the model's earthquake occurrence prediction accuracy, which was 74.67%. Additionally, a regression model was built using LSTM and dense layers to predict the earthquake epicenter as a distance from a predefined location, which provided a root mean square error of 1.25. ; Validerad;2021;Nivå 2;2021-04-19 (alebob); Finansiär: Informationand Communication Technology division of the Governmentof the People's Republic of Bangladesh

State-space models are a popular choice in modelling voting intentions and election results by using poll data. The presented multivariate state-space model attempts to go beyond random-walk or Kalman-filter approaches (with comparable performance to simple weighted survey averages) to the problem by introducing a long-short term event memory effect. This effect serves as reasonable explanation to the observation that the voter's share partially tends to reverse to the party's long-term trend after larger short term movements. Any event influencing the voter's share of a party is presumed to have a convex shaped effect decomposable into a short term effect due to e.g. media spreading and a smaller long term effect remaining despite overlay effects of new events and forgetting. This effect is modelled by a mixture of a random walk and two contrasting autoregressive processes. By also taking advantage of the widely observed effect that government parties tend to fall in voter's share, whereas the opposite effect is observed for opposition parties, mid- and long-term predictions of election outcomes can be considerably be improved. The Stan-model is fitted and evaluated on poll data from seven pollsters for the German national elections ("Bundestagswahl") from 1994 to 2017, where low double digits (out-of-sample) improvements in prediction performance can be seen between 3- and 18-months prior elections. By taking into account the pollsters house effects, their poll errors and even more importantly their correlations in poll errors, an appropriate and realistic estimation error can be propagated.

The fourth volume in the prestigious Advances in Long-Term Care Series continues to address the challenges of long-term care with innovation and practical insight. Highlighting the dynamic nature of long-term care, the authors share their practical insight and explore issues linked to the cost and process of delivering care to an increasing number of clients. Topics include transitions between acute and long-term care, geriatric day hospitals, subacute care, and more. Contributors from a range of gerontologic disciplines use new research as bases to develop care solutions under the mandates of

Political, economic, and social policies of the Communist Party of Spain.