Abstract-Research has found that relatively few people engage in regular exercise or other physical activities. Despite the availability of numerous mobile applications and specialized devices for self-tracking, people mostly lack the motivation for performing physical activities. In this article we present SmartFit, a mobile application that uses step count for promoting the physical activities in adults. This article points out that while considering walk, activity duration is not sufficient for determining users activeness state.Step count is another factor that should be taken into account. For this we propose an approach for converting the steps into duration for which activity has been performed. This duration is then used in Smartfit for categorizing user into different activeness levels. Gamification techniques have been incorporated in SmartFit as they are found to serve the purpose of motivating and encouraging the user. Gamification is used for awarding/deducting points to user in order to keep them engaged for longer period. Furthermore feedback is also provided to users depending upon their goal and achieved progress. The objective is to facilitate and motivate the user and then keep them engaged in carrying out the recommended level of physical activities.

No abstract

To investigate whether a deep learning model can detect Covid-19 from disruptions in the human body's physiological (heart rate) and rest-activity rhythms (rhythmic dysregulation) caused by the SARS-CoV-2 virus. Methods: We propose CovidRhythm, a novel Gated Recurrent Unit (GRU) Network with Multi-Head Self-Attention (MHSA) that combines sensor and rhythmic features extracted from heart rate and activity (steps) data gathered passively using consumer-grade smart wearable to predict Covid-19. A total of 39 features were extracted (standard deviation, mean, min/max/avg length of sedentary and active bouts) from wearable sensor data. Biobehavioral rhythms were modeled using nine parameters (mesor, amplitude, acrophase, and intra-daily variability). These features were then input to CovidRhythm for predicting Covid-19 in the incubation phase (one day before biological symptoms manifest). Results: A combination of sensor and biobehavioral rhythm features achieved the highest AUC-ROC of 0.79 [Sensitivity = 0.69, Specificity=0.89, F 0.1 = 0.76], outperforming prior approaches in discriminating Covid-positive patients from healthy controls using 24 hours of historical wearable physiological. Rhythmic features were the most predictive of Covid-19 infection when utilized either alone or in conjunction with sensor features. Sensor features predicted healthy subjects best. Circadian rest-activity rhythms that combine 24h activity and sleep information were the most disrupted. Conclusions: CovidRhythm demonstrates that biobehavioral rhythms derived from consumer-grade wearable data can facilitate timely Covid-19 detection. To the best of our knowledge, our work is the first to detect Covid-19 using deep learning and biobehavioral rhythms features derived from consumer-grade wearable data.

No abstract

Goal: To investigate whether a deep learning model can detect Covid-19 from disruptions in the human body's physiological (heart rate) and rest-activity rhythms (rhythmic dysregulation) caused by the SARS-CoV-2 virus. Methods: We propose CovidRhythm, a novel Gated Recurrent Unit (GRU) Network with Multi-Head Self-Attention (MHSA) that combines sensor and rhythmic features extracted from heart rate and activity (steps) data gathered passively using consumer-grade smart wearable to predict Covid-19. A total of 39 features were extracted (standard deviation, mean, min/max/avg length of sedentary and active bouts) from wearable sensor data. Biobehavioral rhythms were modeled using nine parameters (mesor, amplitude, acrophase, and intra-daily variability). These features were then input to CovidRhythm for predicting Covid-19 in the incubation phase (one day before biological symptoms manifest). Results: A combination of sensor and biobehavioral rhythm features achieved the highest AUC-ROC of 0.79 [Sensitivity = 0.69, Specificity=0.89, F 0.1 = 0.76], outperforming prior approaches in discriminating Covid-positive patients from healthy controls using 24 hours of historical wearable physiological. Rhythmic features were the most predictive of Covid-19 infection when utilized either alone or in conjunction with sensor features. Sensor features predicted healthy subjects best. Circadian rest-activity rhythms that combine 24h activity and sleep information were the most disrupted. Conclusions: CovidRhythm demonstrates that biobehavioral rhythms derived from consumer-grade wearable data can facilitate timely Covid-19 detection. To the best of our knowledge, our work is the first to detect Covid-19 using deep learning and biobehavioral rhythms features derived from consumer-grade wearable data.