Real-time combustion state identification via image processing: A dynamic data-driven approach

2016 ◽  
Author(s):  
Michael Hauser ◽  
Yue Li ◽  
Jihang Li ◽  
Asok Ray
Keyword(s):  
Image Processing ◽  
Real Time ◽  
Data Driven ◽  
Dynamic Data ◽  
State Identification ◽  
Data Driven Approach

A Data-Driven Approach for Resource Gathering in Real-Time Strategy Games

2012 ◽  
pp. 304-315 ◽  
Author(s):  
Dion Christensen ◽  
Henrik Ossipoff Hansen ◽  
Jorge Pablo Cordero Hernandez ◽  
Lasse Juul-Jensen ◽  
Kasper Kastaniegaard ◽  
...  
Keyword(s):  
Real Time ◽  
Data Driven ◽  
Strategy Games ◽  
Data Driven Approach

scholarly journals A Data-Driven Approach for Daily Real-Time Estimates and Forecasts of Near-Surface Soil Moisture

2017 ◽  
Vol 18 (3) ◽  
pp. 837-843 ◽  
Author(s):  
Randal D. Koster ◽  
Rolf H. Reichle ◽  
Sarith P. P. Mahanama
Keyword(s):  
United States ◽  
Soil Moisture ◽  
Real Time ◽  
Surface Soil ◽  
Data Driven ◽  
Surface Soil Moisture ◽  
Near Surface ◽  
Time Estimates ◽  
Data Driven Approach ◽  
Global Surface

Abstract NASA’s Soil Moisture Active Passive (SMAP) mission provides global surface soil moisture retrievals with a revisit time of 2–3 days and a latency of 24 h. Here, to enhance the utility of the SMAP data, an approach is presented for improving real-time soil moisture estimates (nowcasts) and for forecasting soil moisture several days into the future. The approach, which involves using an estimate of loss processes (evaporation and drainage) and precipitation to evolve the most recent SMAP retrieval forward in time, is evaluated against subsequent SMAP retrievals themselves. The nowcast accuracy over the continental United States is shown to be markedly higher than that achieved with the simple yet common persistence approach. The accuracy of soil moisture forecasts, which rely on precipitation forecasts rather than on precipitation measurements, is reduced relative to nowcast accuracy but is still significantly higher than that obtained through persistence.

A Data-Driven Approach using Machine Learning to Enable Real-Time Flight Path Planning

2020 ◽  
Author(s):  
Jung-Hyun Kim ◽  
Simon I. Briceno ◽  
Cedric Y. Justin ◽  
Dimitri Mavris
Keyword(s):  
Machine Learning ◽  
Path Planning ◽  
Real Time ◽  
Flight Path ◽  
Data Driven ◽  
Data Driven Approach

scholarly journals Real-Time Supply Chain Simulation: A Big Data-Driven Approach

2019 ◽  
Author(s):  
Antonio A.C. Vieira ◽  
Luis M.S. Dias ◽  
Maribel Y. Santos ◽  
Guilherme A.B. Pereira ◽  
Jose A. Oliveira
Keyword(s):  
Big Data ◽  
Supply Chain ◽  
Real Time ◽  
Data Driven ◽  
Data Driven Approach ◽  
Supply Chain Simulation

scholarly journals A data-driven approach for real-time full body pose reconstruction from a depth camera

2011 ◽  
Author(s):  
Andreas Baak ◽  
Meinard Muller ◽  
Gaurav Bharaj ◽  
Hans-Peter Seidel ◽  
Christian Theobalt
Keyword(s):  
Real Time ◽  
Data Driven ◽  
Depth Camera ◽  
Data Driven Approach ◽  
Full Body

scholarly journals Big Data-Driven Based Real-Time Traffic Flow State Identification and Prediction

2015 ◽  
Vol 2015 ◽  
pp. 1-11 ◽  
Author(s):  
Hua-pu Lu ◽  
Zhi-yuan Sun ◽  
Wen-cong Qu
Keyword(s):  
Big Data ◽  
Real Time ◽  
Traffic Flow ◽  
Optimization Model ◽  
Bilevel Optimization ◽  
Data Driven ◽  
Stage Model ◽  
Flow State ◽  
Real Time Traffic ◽  
State Identification

With the rapid development of urban informatization, the era of big data is coming. To satisfy the demand of traffic congestion early warning, this paper studies the method of real-time traffic flow state identification and prediction based on big data-driven theory. Traffic big data holds several characteristics, such as temporal correlation, spatial correlation, historical correlation, and multistate. Traffic flow state quantification, the basis of traffic flow state identification, is achieved by a SAGA-FCM (simulated annealing genetic algorithm based fuzzyc-means) based traffic clustering model. Considering simple calculation and predictive accuracy, a bilevel optimization model for regional traffic flow correlation analysis is established to predict traffic flow parameters based on temporal-spatial-historical correlation. A two-stage model for correction coefficients optimization is put forward to simplify the bilevel optimization model. The first stage model is built to calculate the number of temporal-spatial-historical correlation variables. The second stage model is present to calculate basic model formulation of regional traffic flow correlation. A case study based on a real-world road network in Beijing, China, is implemented to test the efficiency and applicability of the proposed modeling and computing methods.

Sign in / Sign up

Export Citation Format

Share Document