首页|Study Findings from Arizona State University Broaden Understanding of Machine Le arning (Random forests for detecting weak signals and extracting physical inform ation: A case study of magnetic navigation)
Study Findings from Arizona State University Broaden Understanding of Machine Le arning (Random forests for detecting weak signals and extracting physical inform ation: A case study of magnetic navigation)
扫码查看
点击上方二维码区域，可以放大扫码查看
原文链接
NETL
NSTL
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on artificial intelligence is now available. According to news reporting originating from Tempe, Arizona, by NewsRx correspondents, research stated, "It has been recently demonstrated th at two machine-learning architectures, reservoir computing and time-delayed feed -forward neural networks, can be exploited for detecting the Earth's anomaly mag netic field immersed in overwhelming complex signals for magnetic navigation in a GPS-denied environment." Funders for this research include Air Force Office of Scientific Research. Our news correspondents obtained a quote from the research from Arizona State Un iversity: "The accuracy of the detected anomaly field corresponds to a positioni ng accuracy in the range of 10-40 m. To increase the accuracy and reduce the unc ertainty of weak signal detection as well as to directly obtain the position inf ormation, we exploit the machine-learning model of random forests that combines the output of multiple decision trees to give optimal values of the physical qua ntities of interest. In particular, from time-series data gathered from the cock pit of a flying airplane during various maneuvering stages, where strong backgro und complex signals are caused by other elements of the Earth's magnetic field a nd the fields produced by the electronic systems in the cockpit, we demonstrate that the random-forest algorithm performs remarkably well in detecting the weak anomaly field and in filtering the position of the aircraft." According to the news reporters, the research concluded: "With the aid of the co nventional inertial navigation system, the positioning error can be reduced to l ess than 10 m. We also find that, contrary to the conventional wisdom, the class ic Tolles-Lawson model for calibrating and removing the magnetic field generated by the body of the aircraft is not necessary and may even be detrimental for th e success of the random-forest method."
Arizona State UniversityTempeArizonaUnited StatesNorth and Central AmericaCyborgsEmerging TechnologiesMach ine Learning
NETL
NSTL
