This paper presents a synthetic analysis method for multi sourced g eo logical data from geographic information system (GIS). In the previous practices of mineral resources prediction, a usually adopted methodol...This paper presents a synthetic analysis method for multi sourced g eo logical data from geographic information system (GIS). In the previous practices of mineral resources prediction, a usually adopted methodology has been sta tistical analysis of cells delimitated based on thoughts of random sampling. Tha t might lead to insufficient utilization of local spatial information, for a cel l is treated as a point without internal structure. We now take “cell clusters ”, i. e. , spatial associations of cells, as basic units of statistics, thus th e spatial configuration information of geological variables is easier to be dete cted and utilized, and the accuracy and reliability of prediction are improved. We build a linear multi discriminating model for the clusters via genetic algor ithm. Both the right judgment rates and the in class vs. between class distan ce ratios are considered to form the evolutional adaptive values of the populati on. An application of the method in gold mineral resources prediction in east Xi njiang, China is presented.展开更多
A genetic neural net work m odel about design of Mg content in the alloy , based on tested databetw een Mg and tensile intensity or elongation in Zn 27 % Al alloy , has been established . Theresult has sho w n th...A genetic neural net work m odel about design of Mg content in the alloy , based on tested databetw een Mg and tensile intensity or elongation in Zn 27 % Al alloy , has been established . Theresult has sho w n that the genetic neural netw ork is a better an d m ore applied method for m a terials design than the regress analysis .展开更多
文摘This paper presents a synthetic analysis method for multi sourced g eo logical data from geographic information system (GIS). In the previous practices of mineral resources prediction, a usually adopted methodology has been sta tistical analysis of cells delimitated based on thoughts of random sampling. Tha t might lead to insufficient utilization of local spatial information, for a cel l is treated as a point without internal structure. We now take “cell clusters ”, i. e. , spatial associations of cells, as basic units of statistics, thus th e spatial configuration information of geological variables is easier to be dete cted and utilized, and the accuracy and reliability of prediction are improved. We build a linear multi discriminating model for the clusters via genetic algor ithm. Both the right judgment rates and the in class vs. between class distan ce ratios are considered to form the evolutional adaptive values of the populati on. An application of the method in gold mineral resources prediction in east Xi njiang, China is presented.
文摘A genetic neural net work m odel about design of Mg content in the alloy , based on tested databetw een Mg and tensile intensity or elongation in Zn 27 % Al alloy , has been established . Theresult has sho w n that the genetic neural netw ork is a better an d m ore applied method for m a terials design than the regress analysis .
