Search results: Found 5

Listing 1 - 5 of 5
Sort by
Attention, predictions and expectations and their violation: attentional control in the human brain

Authors: --- ---
Book Series: Frontiers Research Topics ISSN: 16648714 ISBN: 9782889193677 Year: Pages: 211 DOI: 10.3389/978-2-88919-367-7 Language: English
Publisher: Frontiers Media SA
Subject: Neurology --- Science (General)
Added to DOAB on : 2015-11-19 16:29:12
License:

Loading...
Export citation

Choose an application

Abstract

In the burdened scenes of everyday life, our brains must select from among many competing inputs for perceptual synthesis - so that only the most relevant receive full attention and irrelevant (distracting) information is suppressed. At the same time, we must remain responsive to salient events outside our current focus of attention - and balancing these two processing modes is a fundamental task our brain constantly needs to solve. Both the physical saliency of a stimulus, as well as top-down predictions about imminent sensations crucially influence attentional selection and consequently the response to unexpected events. Research over recent decades has identified two separate brain networks involved in predictive top-down control and reorientation to unattended events (or oddball stimuli): the dorsal and ventral fronto-parietal attention systems of the human brain. Moreover, specific electrophysiological brain responses are known to characterize attentional orienting as well as the processing of deviant stimuli. However, many key questions are outstanding. What are the exact functional differences between these cortical attention systems? How are they lateralised in the two hemispheres? How do top-down and bottom-up signals interact to enable flexible attentional control? How does structural damage to one system affect the functionality of the other in brain damaged patients? Are there sensory-specific and supra-modal attentional systems in the brain? In addition to these questions, it is now accepted that brain responses are not only affected by the saliency of external stimuli, but also by our expectations about sensory inputs. How these two influences are balanced, and how predictions are formed in cortical networks, or generated on the basis of experience-dependent learning, are intriguing issues. In this Research Topic, we aim to collect innovative contributions that shed further light on the (cortical) mechanisms of attentional control in the human brain. In particular, we would like to encourage submissions that investigate the behavioural correlates, functional anatomy or electrophysiological markers of attentional selection and reorientation. Special emphasis will be given to studies investigating the context-sensitivity of these attentional processes in relation to prior expectations, trial history, contextual cues or physical saliency. We would like to encourage submissions employing different research methods (psychophysical recordings, neuroimaging techniques such as fMRI, MEG, EEG or ECoG, as well as neurostimulation methods such as TMS or tDCS) in healthy volunteers or neurological patients. Computational models and animal studies are also welcome. Finally, we also welcome submission of meta-analyses and reviews articles that provide new insights into, or conclusions about recent work in the field.

Time Predictions: Understanding and Avoiding Unrealism in Project Planning and Everyday Life

Authors: ---
Book Series: Simula SpringerBriefs on Computing ISBN: 9783319749525 9783319749532 Year: Volume: 5 Pages: 110 DOI: https://doi.org/10.1007/978-3-319-74953-2 Language: English
Publisher: Springer Grant: Simula Research Laboratory
Subject: Statistics
Added to DOAB on : 2018-07-20 18:40:07
License:

Loading...
Export citation

Choose an application

Abstract

Predicting the time needed to complete a project, task or daily activity can be difficult and people frequently underestimate how long an activity will take. This book sheds light on why and when this happens, what we should do to avoid it and how to give more realistic time predictions. It describes methods for predicting time usage in situations with high uncertainty, explains why two plus two is usually more than four in time prediction contexts, reports on research on time prediction biases, and summarizes the evidence in support of different time prediction methods and principles. Based on a comprehensive review of the research, it is the first book summarizing what we know about judgment-based time predictions.Large parts of the book are directed toward people wishing to achieve better time predictions in their professional life, such as project managers, graphic designers, architects, engineers, film producers, consultants, software developers, or anyone else in need of realistic time usage predictions. It is also of benefit to those with a general interest in judgment and decision-making or those who want to improve their ability to predict and plan ahead in daily life.

Flood Forecasting Using Machine Learning Methods

Authors: --- ---
ISBN: 9783038975489 Year: Pages: 376 DOI: 10.3390/books978-3-03897-549-6 Language: eng
Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Subject: Technology (General) --- General and Civil Engineering --- Environmental Engineering
Added to DOAB on : 2019-03-08 11:42:05
License:

Loading...
Export citation

Choose an application

Abstract

This book is a printed edition of the Special Issue Flood Forecasting Using Machine Learning Methods that was published in Water

Keywords

data scarce basins --- runoff series --- data forward prediction --- ensemble empirical mode decomposition (EEMD) --- stopping criteria --- method of tracking energy differences (MTED) --- deep learning --- convolutional neural networks --- superpixel --- urban water bodies --- high-resolution remote-sensing images --- monthly streamflow forecasting --- artificial neural network --- ensemble technique --- phase space reconstruction --- empirical wavelet transform --- hybrid neural network --- flood forecasting --- self-organizing map --- bat algorithm --- particle swarm optimization --- flood routing --- Muskingum model --- machine learning methods --- St. Venant equations --- rating curve method --- nonlinear Muskingum model --- hydrograph predictions --- flood routing --- Muskingum model --- hydrologic models --- improved bat algorithm --- Wilson flood --- Karahan flood --- flood susceptibility modeling --- ANFIS --- cultural algorithm --- bees algorithm --- invasive weed optimization --- Haraz watershed --- ANN-based models --- flood inundation map --- self-organizing map (SOM) --- recurrent nonlinear autoregressive with exogenous inputs (RNARX) --- ensemble technique --- artificial neural networks --- uncertainty --- streamflow predictions --- sensitivity --- flood forecasting --- extreme learning machine (ELM) --- backtracking search optimization algorithm (BSA) --- the upper Yangtze River --- deep learning --- LSTM network --- water level forecast --- the Three Gorges Dam --- Dongting Lake --- Muskingum model --- wolf pack algorithm --- parameters --- optimization --- flood routing --- flash-flood --- precipitation-runoff --- forecasting --- lag analysis --- random forest --- machine learning --- flood prediction --- flood forecasting --- hydrologic model --- rainfall–runoff, hybrid & --- ensemble machine learning --- artificial neural network --- support vector machine --- natural hazards & --- disasters --- adaptive neuro-fuzzy inference system (ANFIS) --- decision tree --- survey --- classification and regression trees (CART), data science --- big data --- artificial intelligence --- soft computing --- extreme event management --- time series prediction --- LSTM --- rainfall-runoff --- flood events --- flood forecasting --- data assimilation --- particle filter algorithm --- micro-model --- Lower Yellow River --- ANN --- hydrometeorology --- flood forecasting --- real-time --- postprocessing --- machine learning --- early flood warning systems --- hydroinformatics --- database --- flood forecast --- Google Maps

Machine Learning Techniques Applied to Geoscience Information System and Remote Sensing

Authors: ---
ISBN: 9783039212156 / 9783039212163 Year: Pages: 438 DOI: 10.3390/books978-3-03921-216-3 Language: eng
Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Subject: Technology (General) --- General and Civil Engineering --- Mechanical Engineering
Added to DOAB on : 2019-12-09 11:49:15
License:

Loading...
Export citation

Choose an application

Abstract

As computer and space technologies have been developed, geoscience information systems (GIS) and remote sensing (RS) technologies, which deal with the geospatial information, have been rapidly maturing. Moreover, over the last few decades, machine learning techniques including artificial neural network (ANN), deep learning, decision tree, and support vector machine (SVM) have been successfully applied to geospatial science and engineering research fields. The machine learning techniques have been widely applied to GIS and RS research fields and have recently produced valuable results in the areas of geoscience, environment, natural hazards, and natural resources. This book is a collection representing novel contributions detailing machine learning techniques as applied to geoscience information systems and remote sensing.

Keywords

landslide --- bagging ensemble --- Logistic Model Trees --- GIS --- Vietnam --- colorization --- random forest regression --- grayscale aerial image --- change detection --- gully erosion --- environmental variables --- data mining techniques --- SCAI --- GIS --- mapping --- single-class data descriptors --- materia medica resource --- Panax notoginseng --- one-class classifiers --- geoherb --- change detection --- convolutional network --- deep learning --- panchromatic --- remote sensing --- remote sensing image segmentation --- convolutional neural networks --- Gaofen-2 --- hybrid structure convolutional neural networks --- winter wheat spatial distribution --- classification-based learning --- real-time precise point positioning --- convergence time --- ionospheric delay constraints --- precise weighting --- landslide --- weights of evidence --- logistic regression --- random forest --- hybrid model --- traffic CO --- traffic CO prediction --- neural networks --- GIS --- land use/land cover (LULC) --- unmanned aerial vehicle --- texture --- gray-level co-occurrence matrix --- machine learning --- crop --- landslide susceptibility --- random forest --- boosted regression tree --- information gain --- landslide susceptibility map --- ALS point cloud --- multi-scale --- classification --- large scene --- coarse particle --- particulate matter 10 (PM10) --- landsat image --- machine learning --- support vector machine --- high-resolution --- optical remote sensing --- object detection --- deep learning --- transfer learning --- land subsidence --- Bayes net --- naïve Bayes --- logistic --- multilayer perceptron --- logit boost --- change detection --- convolutional network --- deep learning --- panchromatic --- remote sensing --- leaf area index (LAI) --- machine learning --- Sentinel-2 --- sensitivity analysis --- training sample size --- spectral bands --- spatial sparse recovery --- constrained spatial smoothing --- spatial spline regression --- alternating direction method of multipliers --- landslide prediction --- machine learning --- neural networks --- model switching --- spatial predictive models --- predictive accuracy --- model assessment --- variable selection --- feature selection --- model validation --- spatial predictions --- reproducible research --- Qaidam Basin --- remote sensing --- TRMM --- artificial neural network --- n/a

Climate Variability and Climate Change Impacts on Land Surface, Hydrological Processes and Water Management

Authors: --- ---
ISBN: 9783039215072 / 9783039215089 Year: Pages: 460 DOI: 10.3390/books978-3-03921-508-9 Language: eng
Publisher: MDPI - Multidisciplinary Digital Publishing Institute
Subject: Science (General) --- Environmental Sciences
Added to DOAB on : 2019-12-09 11:49:15
License:

Loading...
Export citation

Choose an application

Abstract

During the last several decades, Earth´s climate has undergone significant changes due to anthropogenic global warming, and feedbacks to the water cycle. Therefore, persistent efforts are required to improve our understanding of hydrological processes and to engage in efficient water management strategies that explicitly consider changing environmental conditions. The twenty-four contributions in this book have broadly addressed topics across four major research areas: (1) Climate and land-use change impacts on hydrological processes, (2) hydrological trends and causality analysis faced in hydrology, (3) hydrological model simulations and predictions, and (4) reviews on water prices and climate extremes. The broad spectrum of international contributions to the Special Issue indicates that climate change impacts on water resources analysis attracts global attention. We hope that the collection of articles presented here can provide scientists, policymakers and stakeholders alike with insights that support sustainable decision-making in the face of climate change and increasingly scarce environmental resources.

Keywords

hydrological drought --- Three Gorges Dam --- GRACE --- compound extremes --- climate change --- multivariate distribution --- quantile regression --- indicator --- PUB --- rainfall-runoff experiments --- distributed hydrological model --- Hydro-Informatic Modelling System (HIMS) --- freshwater availability --- runoff --- simulated rainfall --- plot scale --- litter layer --- topsoil --- karst --- Yellow River Delta --- estuarine wetlands --- spatiotemporal change analysis --- remote sensing --- intra-annual climate change --- variation in percentage of flood-season precipitation --- natural streamflow variation --- contribution and sensitivity analysis --- Yellow River --- highland agricultural field area --- diffuse pollutant discharge --- multiple regression model --- climate change --- jackknife validation --- water security --- water pricing --- sustainable water management --- trends and patterns --- economics --- precipitation --- air temperature --- river discharge --- Mann-Kendall test --- Selenga river basin --- Lake Baikal basin --- Mongolia --- snowfall to precipitation ratio --- WRF model --- arid region --- Xinjiang --- water resources management --- climate change --- LULCC --- Budyko equation --- streamflow --- drought --- climate variability --- land surface change --- runoff --- Budyko framework --- elasticity coefficient --- Weihe River Basin --- flood --- streamflow --- CMIP5 --- climate change --- HEC-RAS --- trend analysis --- precipitation --- temperature --- eco-region --- Ethiopia --- Three Gorges Project --- dam --- runoff changes --- flood control --- Yangtze River --- benefits --- evapotranspiration --- Pan evaporation --- TFPW-MK --- Haihe River Basin --- hydrological simulation --- quantitative analysis --- SWAT model --- land use/cover change --- climate change --- scenario simulation --- Climate variability --- Large-scale climate indices --- Reservoir inflow forecasting --- Ensemble empirical mode decomposition --- Time series model --- Artificial intelligence model --- grid-based --- HRU-based --- SHM --- SWAT --- large scale basin --- climate change --- human activities --- power operations --- cascade joint operation chart --- inter-basin water transfer project --- climate change --- MATOPIBA agricultural frontier --- water security --- hydroclimatic analysis --- water conflicts --- average annual runoff --- runoff map --- hydrological model --- GIS --- DPR Korea --- streamflow reduction --- climate change --- coal mining --- SWCM --- coal mining concentrated watershed --- the Loess Plateau --- hydrology --- land cover --- land use and climate change --- water resources management --- macro scale modeling --- climate variability --- climate change --- land use change --- hydrological processes --- trends --- water management --- model --- predictions

Listing 1 - 5 of 5
Sort by
Narrow your search
-->