Leveraging Artificial Intelligence and Fleet Sensor Data towards a Higher Resolution Road Weather Model.

Road weather conditions such as ice, snow, or heavy rain can have a significant impact on driver safety. In this paper, we present an approach to continuously monitor the road conditions in real time by equipping a fleet of vehicles with sensors. Based on the observed conditions, a physical road weather model is used to forecast the conditions for the following hours. This can be used to deliver timely warnings to drivers about potentially dangerous road conditions. To optimally process the large data volumes, we show how artificial intelligence is used to (1) calibrate the sensor measurements and (2) to retrieve relevant weather information from camera images. The output of the road weather model is compared to forecasts at road weather station locations to validate the approach.

A Learn-to-Rank Approach for Predicting Road Cycling Race Outcomes.

Professional road cycling is a very competitive sport, and many factors influence the outcome of the race. These factors can be internal (e.g., psychological preparedness, physiological profile of the rider, and the preparedness or fitness of the rider) or external (e.g., the weather or strategy of the team) to the rider, or even completely unpredictable (e.g., crashes or mechanical failure). This variety makes perfectly predicting the outcome of a certain race an impossible task and the sport even more interesting. Nonetheless, before each race, journalists, ex-pro cyclists, websites and cycling fans try to predict the possible top 3, 5, or 10 riders. In this article, we use easily accessible data on road cycling from the past 20 years and the Machine Learning technique Learn-to-Rank (LtR) to predict the top 10 contenders for 1-day road cycling races. We accomplish this by mapping a relevancy weight to the finishing place in the first 10 positions. We assess the performance of this approach on 2018, 2019, and 2021 editions of six spring classic 1-day races. In the end, we compare the output of the framework with a mass fan prediction on the Normalized Discounted Cumulative Gain (NDCG) metric and the number of correct top 10 guesses. We found that our model, on average, has slightly higher performance on both metrics than the mass fan prediction. We also analyze which variables of our model have the most influence on the prediction of each race. This approach can give interesting insights to fans before a race but can also be helpful to sports coaches to predict how a rider might perform compared to other riders outside of the team.

ATARI: A Graph Convolutional Neural Network Approach for Performance Prediction in Next-Generation WLANs.

IEEE 802.11 (Wi-Fi) is one of the technologies that provides high performance with a high density of connected devices to support emerging demanding services, such as virtual and augmented reality. However, in highly dense deployments, Wi-Fi performance is severely affected by interference. This problem is even worse in new standards, such as 802.11n/ac, where new features such as Channel Bonding (CB) are introduced to increase network capacity but at the cost of using wider spectrum channels. Finding the best channel assignment in dense deployments under dynamic environments with CB is challenging, given its combinatorial nature. Therefore, the use of analytical or system models to predict Wi-Fi performance after potential changes (e.g., dynamic channel selection with CB, and the deployment of new devices) are not suitable, due to either low accuracy or high computational cost. This paper presents a novel, data-driven approach to speed up this process, using a Graph Neural Network (GNN) model that exploits the information carried in the deployment's topology and the intricate wireless interactions to predict Wi-Fi performance with high accuracy. The evaluation results show that preserving the graph structure in the learning process obtains a 64% increase versus a naive approach, and around 55% compared to other Machine Learning (ML) approaches when using all training features.

Structured Cognitive-Motor Dual Task Training Compared to Single Mobility Training in Persons with Multiple Sclerosis, a Multicenter RCT.

The aim was to compare the effectiveness of dual-task training (DTT) compared to single mobility training (SMT) on dual-task walking, mobility and cognition, in persons with Multiple Sclerosis (pwMS). Forty pwMS were randomly assigned to the DTT or SMT groups. The DTT-group performed dual-task exercises using an interactive tablet-based application, while the SMT-group received conventional walking and balance exercises. Both interventions were supervised and identical in weeks (8) and sessions (20). Nine cognitive-motor dual-task conditions were assessed at baseline, after intervention and at 4-weeks follow-up (FU). The dual-task cost (DTC), percentage change of dual-task performance compared to single-task performance, was the primary outcome. Mobility and cognition were secondarily assessed. Mixed model analyses were done with group, time and the interaction between group and time as fixed factors and participants as random factors. Significant time by group interactions were found for the digit-span walk and subtraction walk dual-task conditions, with a reduction in DTC (gait speed) for the DTT maintained at FU. Further, absolute dual-task gait speed during walking over obstacles only improved after the DTT. Significant improvements were found for both groups in various motor and cognitive measures. However, the DTT led to better dual-task walking compared to the SMT.

Responsiveness and meaningful improvement of mobility measures following MS rehabilitation.

OBJECTIVE: To determine responsiveness of functional mobility measures, and provide reference values for clinically meaningful improvements, according to disability level, in persons with multiple sclerosis (pwMS) in response to physical rehabilitation. METHODS: Thirteen mobility measures (clinician- and patient-reported) were assessed before and after rehabilitation in 191 pwMS from 17 international centers (European and United States). Combined anchor- and distribution-based methods were used. A global rating of change scale, from patients' and therapists' perspective, served as external criteria when determining the area under the receiver operating characteristic curve (AUC), the minimally important change (MIC), and the smallest real change (SRC). Patients were stratified into 2 subgroups based on disability level (Expanded Disability Status Scale score ≤4 [n = 72], >4 [n = 119]). RESULTS: The Multiple Sclerosis Walking Scale-12, physical subscale of the Multiple Sclerosis Impact Scale-29 (especially for the mildly disabled pwMS), Rivermead Mobility Index, and 5-repetition sit-to-stand test (especially for the moderately to severely disabled pwMS) were the most sensitive measures in detecting improvements in mobility. Findings were determined once the AUC (95% confidence interval) was above 0.5, MIC was greater than SRC, and results were comparable from the patient and therapist perspective. CONCLUSIONS: Responsiveness, clinically meaningful improvement, and real changes of frequently used mobility measures were calculated, showing great heterogeneity, and were dependent on disability level in pwMS.