Improving the Prediction of Passenger Numbers in Public Transit Networks by Combining Short-term Forecasts with Real-time Occupancy Data

Passengers of public transportation nowadays expect reliable and accurate travel information. The need for occupancy information is becoming more prevalent in intelligent public transport systems as people started avoiding overcrowded vehicles during the COVID-19 pandemic. Furthermore, public transportation companies require accurate occupancy forecasts to improve service quality. We present a novel approach to improve the prediction of passenger numbers that enhances a day-ahead prediction with real-time data. We first train a baseline predictor on historical automatic passenger counting data. Next, we train a realtime model on the deviations between baseline prediction and observed values, thus capturing events not addressed by the baseline. For the forecast, we attempt to detect emerging patterns in real time and adjust the baseline prediction with deviations from the patterns. Our experiments with data from Germany show that the proposed model improves the forecast of the baseline model and is only outperformed by artificial neural networks in some instances. If the training sets only cover a limited period of up to four months, our approach outperforms competing methods. For larger training sets, there are mixed results in the sense that for some test cases, certain types of neural networks yield slightly better results, but our method still performs well with less training effort, is explainable along the whole prediction process and can be applied to existing prediction methods. Author

Home respiratory specimen collection in children with cystic fibrosis

Introduction: Collection of respiratory cultures for airway microbiology surveillance is an essential component of routine clinical care of individuals with CF. The COVID-19 global pandemic has necessitated an increase in the use of telehealth services to deliver care, but one limitation of telehealth is the inability to collect respiratory specimens. Therefore, we initiated a protocol for at-home collection of expectorated sputum (ES) and oropharyngeal (OP) swabs from children with CF followed at the Children's Hospital Colorado CF Center. Methods: Home respiratory specimen collection is offered by providers around the time of telehealth encounters. Respiratory specimen collection kits for either ES or OP swabs are mailed to participating families with instructions for specimen collection and return. The specimens are returned either by overnight mail or dropped off at a local Children's Colorado clinical laboratory for processing and culture according to a standard CF protocol. Data recorded include parental interest in receiving a kit, the number of kits sent and returned, and microbiology culture results. We plan to compare culture results from the home respiratory specimen to the most recent respiratory specimen collected in clinic for each patient to track concordance of the culture in the home environment, and to establish whether new pathogens were identified. We are also tracking the rate of Pseudomonas aeruginosa identification on home respiratory specimens to assess frequency with which the at-home specimen culture results impact clinical care decisions. Results: Home respiratory specimen collection kits have been sent to the families of 46 participating children with CF (patient age range 2-20 years), including 27 OP swab kits and 19 ES collection kits. Home respiratory specimen collection has only been declined by 4 families to whom it was offered (patient age range 2-11 years). To date, 13 specimens, including 11 OP swabs and 2 ES samples, have been returned for processing and culture. No growth or growth of upper respiratory flora alone was detected from 3 of the specimens, which was consistent with the most recent culture results from an in-clinic visit in each of these cases. One or more CF pathogens grew from 10 of the specimens. Of these, 5 grew the same CF pathogens that had previously grown from the patients' most recent in-clinic culture. CF pathogens were identified for 5 patients which had not been detected on the most recent in-clinic specimen. For 2 of these patients, the home collection specimen demonstrated growth of P. aeruginosa and resulted in initiation of eradication treatment with inhaled tobramycin. Conclusions: Home collection of respiratory specimens for bacterial culture is feasible in children with CF. Thus far, most specimens demonstrated growth of one or more CF pathogens, and most home cultures had results that were similar to recent in-clinic specimens, suggesting acceptable sample collection technique and sample integrity in the home setting. Anti-pseudomonal therapy was initiated for two children based on growth of P. aeruginosa from the home respiratory specimen.