首页|New Machine Learning Study Findings Have Been Reported by Investigators at China University of Mining and Technology Beijing (Classifying Iron Ore With Water or Dust Adhesion Combining Differential Feature and Random Forest Using Hyperspect ral ...)
New Machine Learning Study Findings Have Been Reported by Investigators at China University of Mining and Technology Beijing (Classifying Iron Ore With Water or Dust Adhesion Combining Differential Feature and Random Forest Using Hyperspect ral ...)
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-Investigators discuss new findings in Machine Learning. According to news reporting originating from Beijing, People's Republic of China, by NewsRx correspondents, research stated, "Hyperspectral im aging (HSI), a promising technique integrating imaging and spectroscopy, can hel p sort iron ores with different total iron (TFe) contents. However, the adhesion of dust (caused by crushing) or water can affect the sorting process." Financial supporters for this research include National Natural Science Foundati on of China (NSFC), Fundamental Research Funds for the Central Universities. Our news editors obtained a quote from the research from the China University of Mining and Technology Beijing, "Currently, the mechanisms underlying this influ ence and methods to conveniently mitigate it remain unclear, hindering the pract ical application of HSI-based sorting. This study aimed to investigate this issu e. For the experimental materials, 300 ore samples (particle size: 20-40 mm) wit h different TFe contents were prepared. Subsequently, three sample conditions we re prepared (‘No dust, no water', ‘With dust, no water' and ‘No dust, with water ') through washing and drying measures, and their hyperspectral images were acqu ired (953-2517 nm). Finally, the TFe content of each ore sample was measured. Af ter preprocessing, the effects of water and dust on the spectra and sorting proc ess were initially analyzed. Subsequently, a new spectral differential feature c onsidering dust and water (DFDW) was proposed to mitigate this influence. Then, using the spectral and calculated proportion features as input, different grades of iron ore were classified into four classes using a machine learning classifi er. For validation, models using several different input features and machine le arning classifiers were tested for classification accuracy (the ratio of correct ly predicted instances to the total number of predictions). On ‘No dust, no wate r', ‘With dust, no water' and ‘No dust, with water' data, the model DFDW-random forest (RF) achieved accuracies of 87.7 %, 85.0 %, and 85.3 %, respectively, which was optimal."
BeijingPeople's Republic of ChinaAsiaCyborgsEmerging TechnologiesMachine LearningChina University of Mining and Technology Beijing
NETL
NSTL
