16985 research outputs found
Sort by
Partizipation als Wegbereiter und -begleiter adaptiver (digitaler) Transformation des Gesundheitswesens
No full textShuntless current measurement in sector-shaped power grid cables: A simulation and machine learning approach
No full text
Feasibility of behavior change techniques to promote physical activity of people with acute stroke during hospitalization – a pilot randomized controlled trial
No full textObjective
The primary objective was to determine the feasibility of using behavior change techniques in people with acute stroke during hospitalisation. Furthermore, preliminary effects of these interventions on the physical activity and mobility of the participants were evaluated as a second objective.
Design
Non-blinded, parallel-group pilot randomized controlled trial.
Setting
The trial was conducted on a stroke unit of a university hospital in Germany.
Participants
A random sample of 24 participants was selected. Included were acute people with stroke (<48 hours after incident), with NIHSS 0-5, who were able to ambulate independently.
Interventions
Participants of the intervention group received three behavior change techniques alongside standard physiotherapy during their hospital stay: education, goal setting, and monitoring. In the control group, participants received standard physiotherapy.
Main Outcome Measure(s)
Feasibility was assessed based on previously established feasibility criteria. Physical activity levels were measured using accelerometry, while mobility was evaluated with the De Morton Mobility Index.
Results
24 participants were recruited in total (participation rate: 77.4%), 12 of them received the intervention. There were no drop-outs and no loss to follow-up (drop-out rate 0%; retention rate: 100%). The recruitment rate, retention, acceptability, and safety of the intervention have been assessed as feasible. The target adherence of 80% potential wear time of an accelerometer could not be confirmed. No adverse events were reported. A trend for higher physical activity of the intervention group was observed, however, the results are not statistically significant.
Conclusions
Despite a small number of participants, the feasibility and safety of the use of behavior change techniques with acute people with stroke, as well as indications of a potential effect, were established. Therefore, after implementing adjustments regarding the recruitment and inclusion of participants, the recommendation can be made to conduct a definite trial
Automating assist identification in football (soccer): a machine learning approach using event and tracking data
No full textAssists—the number of last passes before a goal—have been a predominant metric to evaluate offensive players contribution in association football. This poses two major limitations: first, assist definitions differ across data collection vendors, and second, the focus on passes leading to goals creates a strong dependency on the player taking the shot. We introduce the term potential assists comprising all actions, that prepare a teammate’s shot regardless of conversion. Additionally, we use expert-knowledge to derive an objective definition for potential assists and show that it can be detected with a substantial inter-rater reliability. Using this definition, we utilize video footage to label 500 assists manually and train multiple supervised machine learning models to classify potential assists based on 29 features derived from positional and event data. We apply our automated detection approach on 105 DFB-Pokal matches and demonstrate a scalable method to enhance automatic event detection and improve the comparability of assist statistics for application in player assessment and scouting
Assessing the need for COD fractionation in modelling impacts of source separation on wastewater treatment plants
No full textWastewater management challenges can be addressed through source separation strategies, such as urine or grey water separation. To quantify advantages and avoid operational issues, an understanding of the impact of source separation on municipal wastewater treatment plant (WWTP) operation and effluent discharge is necessary. This can be achieved using activated sludge models. A key question is whether detailed chemical oxygen demand (COD) fractionation of domestic wastewater sub-streams is needed or if a load-based approach suffices for simulations. Determining COD fractions of wastewater sub-streams is effort-intensive and uncertain, with unclear effects on simulation improvement. Therefore, a simulation study was conducted, in which urine, grey water, black water, and brown water were subsequently separated from the inflow of a WWTP model. Two distinct fractionation scenarios were investigated: (i) purely load-related separation and (ii) load-related separation with individual COD fractionation. The results indicate that most trends in all source separation scenarios are comparable between both fractionation scenarios for most parameters. Only the COD effluent concentrations for grey water separation showed opposing trends. Differentiated fractionation impacts precipitant consumption in grey and brown water scenarios. Thus, a purely load-related approach suffices to identify the main benefits or operational challenges of source separation on WWTPs
