Towards an End-to-End Framework of CCTV-Based Urban Traffic Volume Detection and Prediction.

Near real-time urban traffic analysis and prediction are paramount for effective intelligent transport systems. Whilst there is a plethora of research on advanced approaches to study traffic recently, only one-third of them has focused on urban arterials. A ready-to-use framework to support decision making in local traffic bureaus using largely available IoT sensors, especially CCTV, is yet to be developed. This study presents an end-to-end urban traffic volume detection and prediction framework using CCTV image series. The framework incorporates a novel Faster R-CNN to generate vehicle counts and quantify traffic conditions. Then it investigates the performance of a statistical-based model (SARIMAX), a machine learning (random forest; RF) and a deep learning (LSTM) model to predict traffic volume 30 min in the future. Tests at six locations with varying traffic conditions under different lengths of past time series are used to train the prediction models. RF and LSTM provided the most accurate predictions, with RF being faster than LSTM. The developed framework has been successfully applied to fill data gaps under adverse weather conditions when data are missing. It can be potentially implemented in near real time at any CCTV location and integrated into an online visualization platform.

Chlorination effects on DNA based characterization of water microbiomes and implications for the interpretation of data from disinfected systems.

Quantitative PCR (qPCR) and next generation sequencing (NGS) are nucleic acid based microbiology techniques that provide new insights into drinking water quality, but considerable uncertainty remains around their correct interpretation. We noticed the presence of bacterial DNA from various putative pathogens, including from faecal indicator bacteria (FIB), in disinfected water, when culturable FIB were absent. To understand these observations better we studied the effect of chlorination on conventional and DNA based microbial water quality assessments. Surface water chlorination reduced plate counts for various FIB by up to >6 log units, intact cell counts by flow cytometry by 3.3 log units, and 16S rRNA gene copies by qPCR by 1.5 and 1.6 log units for total bacteria and total coliforms, respectively. Nanopore sequencing of 16S rRNA amplicons with the portable MinION device revealed the DNA from several families containing putative pathogens appeared to be more resistant than that of other bacteria to degradation by chlorine disinfection. For instance, 16S rRNA genes assigned to the Enterobacteriaceae family, members of which are mostly the target of coliform tests, increased in relative abundance from 0.001 ± 0.0002% to 0.0036 ± 0.003% after chlorine treatment. Hence, metagenomic drinking water data needs to be interpreted with caution. Plate counts and flow cytometry in combination with DNA based analysis provide more robust insight than NGS or qPCR alone.