ST-MVL: Filling Missing Values in Geo-Sensory Time Series Data

By Xiuwen Yi, Yu Zheng, Junbo Zhang, Tianrui Li. 2016

214 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Jiaming Song
2. Yang Song
3. Stefano Ermon
4. Ling Yang
5. Ming-Hsuan Yang
6. Junbo Zhang
7. Haitao Yuan
8. Y. Tashiro

Citations in the corpus

• A survey on data fusion in internet of things: Towards secure and privacy-preserving fusion (2019, background): “4 IoT Data Fusion Requirements Data fusion can be efficiently applied to reconstruct and fill missing values or data [2, 46, 47], to conduct prediction [48, 49], to identify the causality of specific events and give a conclusion about causal connections [50, 51], and to detect anomalies [52], etc.”
• BRITS: Bidirectional Recurrent Imputation for Time Series (2018, methodology): “For example, in the air quality data [32], each feature represents one measurement in a monitoring station.”
• A Survey of Traffic Prediction: from Spatio-Temporal Data to Intelligent Transportation (2021, methodology): “For example, Lee et al. [57] design a factorial hidden Markov model to recover missing values, while Yi [58] combine many empirical statistic models (e.g., inverse distance weighting and simple exponential smoothing,) with user-based and item-based collaborative filtering to collectively fill…”
• SAITS: Self-Attention-based Imputation for Time Series (2022, background): “…failure of collection sensors, communication error, and unexpected malfunction, missing values are common to see in time series from the real-world environment, for example, patient health measurement [1], air-quality monitoring [2], telecommunication networking [3], and educational systems [4].”
• Diffusion Models: A Comprehensive Survey of Methods and Applications (2022, background): “Nevertheless, time series usually contain missing values for multiple reasons, caused by mechanical or artificial errors [213, 229, 269].”
• Predicting Citywide Crowd Flows Using Deep Spatio-Temporal Residual Networks (2017, background): “A branch of research also partitions a city into grids, and then studies the traffic flow in each region of the city, such as predicting urban air quality [47,48], detecting anomalous traffic patterns [49], inferring missing air quality [50], forecasting of spatio-temporal data [3].”
• CSDI: Conditional Score-based Diffusion Models for Probabilistic Time Series Imputation (2021, background): “The second one is the air quality dataset [2].”