Deep Compressed Sensing based Data Imputation for Urban Environmental Monitoring
Deep Compressed Sensing based Data Imputation for Urban Environmental Monitoring
复制标题
DOI：
10.1145/3599236
复制
发表时间：
2023-10
影响因子：
4.1
通讯作者：
Qingyi Chang;Dan Tao;Jiangtao Wang;Ruipeng Gao
中科院分区：
文献类型：
--
作者：
Qingyi Chang;Dan Tao;Jiangtao Wang;Ruipeng Gao
数据输入在众测中非常普遍，特别是对于物联网（IoT）设备。一方面，从传感器收集的数据不可避免地会受到不可预测性的影响或损坏。另一方面，延长传感器网络的活动时间已成为环境监测的迫切需要。利用神经网络设计数据输入算法可以充分利用模型中存储的先验信息。本文提出了一种在物联网数据集上提取用于训练神经网络的子集的预处理算法，包括时间窗确定、传感器聚合、传感器排除和数据帧形状选择。此外，我们还提出了一种基于生成模型的深度压缩感知数据输入算法。它探索了新的表示矩阵，可以在高缺失率的情况下输入数据。最后，我们分别在EPFL SensorScope数据集上对我们的子集提取算法和数据输入算法进行了测试，结果表明，在极端数据丢失的情况下，这两种算法都有效地提高了准确率和鲁棒性。
Data imputation is prevalent in crowdsensing, especially for Internet of Things (IoT) devices. On the one hand, data collected from sensors will inevitably be affected or damaged by unpredictability. On the other hand, extending the active time of sensor networks has urgently aspired environmental monitoring. Using neural networks to design a data imputation algorithm can take advantage of the prior information stored in the models. This paper proposes a preprocessing algorithm to extract a subset for training a neural network on an IoT dataset, including time window determination, sensor aggregation, sensor exclusion and data frame shape selection. Moreover, we propose a data imputation algorithm using deep compressed sensing with generative models. It explores novel representation matrices and can impute data in the case of a high missing ratio situation. Finally, we test our subset extraction algorithm and data imputation algorithm on the EPFL SensorScope dataset, respectively, and they effectively improve the accuracy and robustness even with extreme data loss.