基于类别信息熵加权的MKNN算法

针对MKNN算法对类属性数据处理简单的问题,引入信息熵作为处理类属性数据的相似性度量,进而引入类别信息熵的概念。对同一类型的类属性数据根据其类别信息熵权重的大小,把数据集的记录进行分类进而得到测试结果。实验结果验证了该算法的有效性。

SNR and RSSI Based an Optimized Machine Learning Based Indoor Localization Approach:Multistory Round Building Scenario over LoRa Network

In situations when the precise position of a machine is unknown,localization becomes crucial.This research focuses on improving the position prediction accuracy over long-range(LoRa)network using an optimized machine learning-based technique.In order to increase the prediction accuracy of the reference point position on the data collected using the fingerprinting method over LoRa technology,this study proposed an optimized machine learning(ML)based algorithm.Received signal strength indicator(RSSI)data from the sensors at different positions was first gathered via an experiment through the LoRa network in a multistory round layout building.The noise factor is also taken into account,and the signal-to-noise ratio(SNR)value is recorded for every RSSI measurement.This study concludes the examination of reference point accuracy with the modified KNN method(MKNN).MKNN was created to more precisely anticipate the position of the reference point.The findings showed that MKNN outperformed other algorithms in terms of accuracy and complexity.

基于改进KNN算法的潜山复杂岩性测井识别方法

兴隆台中生界砾岩油气藏是辽河坳陷近年发现的大型整装构造-岩性油藏,探明程度低,勘探潜力大。油藏受岩相与构造的共同控制,储层非均质性极强,岩性类型复杂多样,导致测井识别难度较大,严重制约了该区的勘探进程。为此,依据岩心观察、岩屑录井及薄片鉴定结果,按照储层分类评价需求及测井可识别原则,重新将研究区岩性划分为碎屑岩和火山岩两大类,具体包括花岗质砾岩、混合砾岩、砂岩、泥岩、玄武岩、凝灰岩等6种岩石类型。通过分析不同类型岩石的测井响应特征,建立岩性交会图版,确定敏感测井参数。在此基础上,针对测井数据特点,对K最邻近值(KNN)算法进行改进,提出了基于测井属性加权的剪切邻近(MKNN)机器学习算法,并用于岩性预测。结果表明:相比传统的K最邻近值(KNN)算法,MKNN算法效率更高,解决了KNN算法受岩性样本类型不均衡及测井参数重叠的影响,岩性识别准确率由82.3%提高至88.7%,有效地解决了勘探老区岩性精细评价问题。该研究对提高复杂岩性油藏的测井评价精度具有一定的借鉴意义。