首页|Findings from Mississippi State University Broaden Understanding of Machine Lear ning (Machine Learning Methods and Visual Observations to Categorize Behavior of Grazing Cattle Using Accelerometer Signals)
Findings from Mississippi State University Broaden Understanding of Machine Lear ning (Machine Learning Methods and Visual Observations to Categorize Behavior of Grazing Cattle Using Accelerometer Signals)
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 – Researchers detail new data in artific ial intelligence. According to news originating from Starkville, Mississippi, by NewsRx correspondents, research stated, “Accelerometers worn by animals produce distinct behavioral signatures, which can be classified accurately using machin e learning methods such as random forest decision trees.” Funders for this research include Thinking Like A Mountain To Improve Animal Pro duction Systems Ecology, Energy Budgets, And Mechanistic Models; Usda National I nstitute of Food And Agriculture. The news reporters obtained a quote from the research from Mississippi State Uni versity: “The objective of this study was to identify accelerometer signal separ ation among parsimonious behaviors. We achieved this objective by (1) describing functional differences in accelerometer signals among discrete behaviors, (2) i dentifying the optimal window size for signal pre-processing, and (3) demonstrat ing the number of observations required to achieve the desired level of model ac curacy,. Crossbred steers (Bos taurus indicus; n = 10) were fitted with GPS coll ars containing a video camera and tri-axial accelerometers (read-rate = 40 Hz). Distinct behaviors from accelerometer signals, particularly for grazing, were ap parent because of the head-down posture.”
Mississippi State UniversityStarkvilleMississippiUnited StatesNorth and Central AmericaCyborgsEmerging Techn ologiesMachine Learning
NETL
NSTL
