首页|Reports from Beijing Jiaotong University Provide New Insights intoMachine Learn ing (Enhancing PH-otdr Classification PerformanceThrough Event Augmentation)
Reports from Beijing Jiaotong University Provide New Insights intoMachine Learn ing (Enhancing PH-otdr Classification PerformanceThrough Event Augmentation)
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 DailyNews Daily News – Fresh data on Machine Learning are pre sented in a new report. According to newsoriginating from Beijing, People’s Rep ublic of China, by NewsRx correspondents, research stated, “As oneof the resear ch focuses in the past decades, phase sensitive optical domain reflectometer (Ph i-OTDR) hascome to the tipping point of its wide application. With the expansio n of its application, how to classifyand identify Phi-OTDR events more effectiv ely and efficiently in practical applications has become a keyand urgent issue. ”Funders for this research include Fundamental Research Funds for the Central Uni versities, NationalKey Research & Development Program of China.Our news journalists obtained a quote from the research from Beijing Jiaotong Un iversity, “Overthe past several years, the incorporation of machine learning me thodologies has garnered considerableattention in this area. Nevertheless, the performance of those machine learning models heavily relies onthe quantity and quality of the collected data. That is, the challenge of collecting rare event s ignals in thesensing applications strongly limits the ability of the model to c lassify accurately. To overcome the aboveweakness and further boost the capabil ity of & Fcy;-OTDR, we propose an event augmentation methodto enh ance the diversity and generalization of raw data. Experimental results show tha t the proposedmethod improves the event classification accuracy of our & Fcy;-OTDR from 76.4% to 91.0%.”
BeijingPeople’s Republic of ChinaAsi aCyborgsEmergingTechnologiesMachine LearningBeijing Jiaotong University
NETL
NSTL
