为更精确地预测航班过站时间,将全国机场按照规模差异及不同地理位置所导致的客流量差异和天气差异对航班过站时间造成的不同影响进行分类,基于各类机场航班数据,构建混合轻量级梯度提升机算法(LightGBM)模型对航班过站时间分类预测。...为更精确地预测航班过站时间,将全国机场按照规模差异及不同地理位置所导致的客流量差异和天气差异对航班过站时间造成的不同影响进行分类,基于各类机场航班数据,构建混合轻量级梯度提升机算法(LightGBM)模型对航班过站时间分类预测。引入自适应鲁棒损失函数(adaptive robust loss function,ARLF)改进LightGBM模型损失函数,降低航班数据中存在离群值的影响;通过改进的麻雀搜索算法对改进后的LightGBM模型进行参数寻优,形成混合LightGBM模型。采用全国2019年全年航班数据进行验证,实验结果验证了方法的可行性。展开更多
当前基于深度学习的地表覆盖分类方法依赖于大规模且标注精准的训练样本。但受限于成本和技术因素,训练样本不可避免地混入噪声标签,导致分类精度降低。因此,本文提出了融合协同学习和抗噪损失的含噪地表覆盖分类方法。该方法以协同学...当前基于深度学习的地表覆盖分类方法依赖于大规模且标注精准的训练样本。但受限于成本和技术因素,训练样本不可避免地混入噪声标签,导致分类精度降低。因此,本文提出了融合协同学习和抗噪损失的含噪地表覆盖分类方法。该方法以协同学习机制为主体架构,首先利用参数非共享的双支卷积网络分别提取影像初分类特征;然后,基于双支网络的影像分类概率建模干净数据和噪声数据,构建基于信息熵的噪声可信度评价指标;最后,以可信度评价指标代替人工设定权重的方式,提出基于噪声可信度的自适应主动被动损失函数,引导协同学习网络关注噪声样本。试验表明,该方法在公开数据集GID(模拟噪声)和众源数据OSM(实际噪声)上的平均交并比(mean intersection over union,mIOU)分别提升3.85%~23.3%和5.89%~6.73%,说明该方法具有更好的抗噪性能。展开更多
For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pa...For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pairs through offline training to estimate the channel state information.Also,it utilizes pilots to offer more helpful information about the communication channel.The proposedCNN-CSE performance is compared with previously published results for Bidirectional/long short-term memory(BiLSTM/LSTM)NNs-based CSEs.The CNN-CSE achieves outstanding performance using sufficient pilots only and loses its functionality at limited pilots compared with BiLSTM and LSTM-based estimators.Using three different loss function-based classification layers and the Adam optimization algorithm,a comparative study was conducted to assess the performance of the presented DNNs-based CSEs.The BiLSTM-CSE outperforms LSTM,CNN,conventional least squares(LS),and minimum mean square error(MMSE)CSEs.In addition,the computational and learning time complexities for DNN-CSEs are provided.These estimators are promising for 5G and future communication systems because they can analyze large amounts of data,discover statistical dependencies,learn correlations between features,and generalize the gotten knowledge.展开更多
摘要为更精确地预测航班过站时间,将全国机场按照规模差异及不同地理位置所导致的客流量差异和天气差异对航班过站时间造成的不同影响进行分类,基于各类机场航班数据,构建混合轻量级梯度提升机算法(LightGBM)模型对航班过站时间分类预测。引入自适应鲁棒损失函数(adaptive robust loss function,ARLF)改进LightGBM模型损失函数,降低航班数据中存在离群值的影响;通过改进的麻雀搜索算法对改进后的LightGBM模型进行参数寻优,形成混合LightGBM模型。采用全国2019年全年航班数据进行验证,实验结果验证了方法的可行性。
摘要当前基于深度学习的地表覆盖分类方法依赖于大规模且标注精准的训练样本。但受限于成本和技术因素,训练样本不可避免地混入噪声标签,导致分类精度降低。因此,本文提出了融合协同学习和抗噪损失的含噪地表覆盖分类方法。该方法以协同学习机制为主体架构,首先利用参数非共享的双支卷积网络分别提取影像初分类特征;然后,基于双支网络的影像分类概率建模干净数据和噪声数据,构建基于信息熵的噪声可信度评价指标;最后,以可信度评价指标代替人工设定权重的方式,提出基于噪声可信度的自适应主动被动损失函数,引导协同学习网络关注噪声样本。试验表明,该方法在公开数据集GID(模拟噪声)和众源数据OSM(实际噪声)上的平均交并比(mean intersection over union,mIOU)分别提升3.85%~23.3%和5.89%~6.73%,说明该方法具有更好的抗噪性能。
基金funded by Taif University Researchers Supporting Project No.(TURSP-2020/214),Taif University,Taif,Saudi Arabia。
摘要For a 5G wireless communication system,a convolutional deep neural network(CNN)is employed to synthesize a robust channel state estimator(CSE).The proposed CSE extracts channel information from transmit-and-receive pairs through offline training to estimate the channel state information.Also,it utilizes pilots to offer more helpful information about the communication channel.The proposedCNN-CSE performance is compared with previously published results for Bidirectional/long short-term memory(BiLSTM/LSTM)NNs-based CSEs.The CNN-CSE achieves outstanding performance using sufficient pilots only and loses its functionality at limited pilots compared with BiLSTM and LSTM-based estimators.Using three different loss function-based classification layers and the Adam optimization algorithm,a comparative study was conducted to assess the performance of the presented DNNs-based CSEs.The BiLSTM-CSE outperforms LSTM,CNN,conventional least squares(LS),and minimum mean square error(MMSE)CSEs.In addition,the computational and learning time complexities for DNN-CSEs are provided.These estimators are promising for 5G and future communication systems because they can analyze large amounts of data,discover statistical dependencies,learn correlations between features,and generalize the gotten knowledge.
摘要为了抑制采样点中粗差对数字高程模型(digital elevation model,DEM)建模的影响,以较高精度的多面函数(multi-quadric,MQ)为基函数,由改进Huber损失函数和权重惩罚项组成目标函数,发展了MQ抗差插值算法(MQ-H)。通过优化MQ-H目标函数,采样点权重计算最终转换为方程组求解。以数学曲面为研究对象,将MQ-H计算结果与传统MQ及最小绝对偏差MQ(MQ-L)进行比较,结果表明:当采样误差服从正态分布时,MQ-H计算精度与传统MQ相当,而远高于MQ-L;当采样误差服从拉普拉斯分布时,MQ-H计算精度略高于MQ-L及传统MQ;当采样点被粗差污染时,MQ-H计算精度远高于传统MQ及MQ-L。在实例分析中,以无人遥测飞艇立体像对获取的地面离散高程点为基础数据,基于MQ-H构建测区DEM,并将计算结果与传统插值算法,如反距离加权(inverse distance weighting,IDW)、普通克里金(ordinary Kriging,OK)和专业DEM插值软件ANUDEM(Australian National University DEM)进行比较,结果表明,传统插值方法在不同程度上受采样点中异常值或偶然误差影响,而MQ-H受异常值影响较小,且能准确捕捉到地形细节信息。