antennas in plasma; corona; learning (artificial intelligence); noise; partial discharges; pattern classification; physics computing; plasma diagnostics; plasma simulation; principal component analysis; PCA-KNN partial discharge classification model accuracy; block training method; computer program; corona; electromagnetic wave; internal discharge; k-nearest neighbor model; log-periodic antenna; noise signal peak; noise signals; odd-event data training method; partial discharge pattern classification; principal component analysis; shielding room; signal period kurtosis; signal period skewness; spectrum analyzer; surface discharge; training data number effect; training method effect; Accuracy; Discharges (electric); Noise; Partial discharges; Testing; Training; Training data; electromagnetic wave; k-nearest neighbors; partial discharge pattern; principal component analysis; statistical classification;
机译:回顾密歇根州Fort Leonard Wood的初次入职培训放电,以确保放电分类类型的准确性:2003财政年度。
机译:较短相位解析的局部放电持续时间对PD分类精度的影响
机译:通过新的数据预处理方法提高局部放电的模式识别精度
机译:变压器铁心建模对局部放电电流脉冲仿真精度的影响
机译:广义局部学分模型的计算机自适应测验能力估计方法的准确性
机译:人工神经网络与Taguchi方法稳健分类模型提高乳腺癌分类准确性
机译:图3:培训和测试分类跨越时期的培训和测试分类准确性:(a)在CiFar-10数据集上培训和测试ARESB-10,ARESB-18和ARESB-34型号的前1个精度; (b)在CIFAR-100数据集上训练和测试ARESB-10,ARESB-18和ARESB-34型号的顶级精度。