Data Missing Problem In Smart Surveillance Environment

The number of surveillance cameras distributed over Smart Cities and the streaming workload generated by them have been increased. Although Fog computing has been used to reduce latency and jitter time, the gateways IoT may fail to collect information, producing missing or invalid data, affecting the quality of service. Therefore, this paper presents an analysis of gap filling algorithms to data missing problem in a smart surveillance environment. Performance Evaluation study has shown that it is possible to maximize the accuracy of data imputation using Singular Spectrum Analysis (SSA). SSA is characterized by time series field by performing a non-parametric spectral estimation with spatial-temporal correlations. Statistical outcomes have confirmed the requirement of accurate data imputation techniques to the Smart City environment, specifically in the surveillance scenario. In addition, the performance evaluation technique has allowed emphasizing the contribution of imputation data approaches. These approaches can estimate values that were not correctly monitored, increasing the accuracy in the estimation of the Streaming video, and thus improving the quality of service.