Driving while distracted or losing alertness significantly increases the risk of traffic accident. The emerging Internet of Things (IoT) systems for smart driving hold the promise of significantly reducing road accidents. In particular, detecting unsafe hand motions and warning the driver using smart sensors can improve the driver’s alertness and skill. However, due to the impact of the vehicle’s movement and the significant variation across different driving environments, detecting the position of the driver’s hand is challenging. This article presents SafeWatch—a system based on smartwatches and smartphones that detects the driver’s unsafe behaviors in a real-time manner. SafeWatch infers driver’s hand position based on several important features, such as the posture of the driver’s forearm and the vibration on the smartwatch. SafeWatch employs a novel adaptive training algorithm that keeps updating the training data set at run-time based on inferred hand positions in certain driving conditions. The evaluation with 75 real driving trips from six subjects shows that SafeWatch has a high accuracy over 97.0% for both recall and precision in detection of the unsafe hand positions when the condition lasts for more than 6.0 s , as well as over 97.1% recall and over 91.0% precision in detection of the unsafe hand movements when it lasts for more than 2.5 s . The relative position of the hand to the steering wheel also reveals some detailed driving habits, like the type of steering method.

By learning from the existing family mealtime activities, family members can be motivated to make the positive changes towards better relationships, which are important for the physical and mental health of children. Moreover, the details of family mealtime activities provide rich information for study in sociology and culture. This paper presents FamilyLog - a practical system to log family mealtime activities using smartphones and smartwatches. FamilyLog automatically detects and logs details of activities during the mealtime, including occurrence and duration of meal, conversations, participants, TV viewing, etc., in an unobtrusive manner. Based on the sensor data collected from real families, we carefully design robust yet lightweight signal features from a set of complex activities during the meal, including clattering sound, arm gestures of eating, human voice, TV sound, etc. Moreover, FamilyLog opportunistically fuses data from built-in sensors of multiple mobile devices available in a family with a CRFs-based classifier. To evaluate the real-world performance of FamilyLog, we perform extensive experiments that consist of 77 days of sensor data from 37 subjects in 8 families with children. FamilyLog can detect those events with high accuracy across different families and home environments.

Recently a class of new in-vehicle technologies based on off-the-shelf mobile devices have been developed to improve driver safety and driving experience. For instance, smartwatches are utilized to monitor driving performance and detect possible secondary tasks of drivers such as texting, operating the in-vehicle infotainment, or eating. However, a key challenge for these systems is to track the real-time attitude of mobile devices in a driving vehicle. This demo presents a novel system called Real-time Attitude and Motion Tracking (RAMT) that can enable a mobile device to accurately learn the coordinate system of the moving vehicle, and hence track the attitude and the motion of the device in real time.

Research has shown that family mealtime plays a critical role in establishing good relationships among family members and maintaining their physical and mental health. In particular, regularly eating dinner as a family significantly reduces prevalence of obesity. However, American families with children spend only 1 hour on family meals while three hours watching TV on an average work day. Fine-grained activity-logging is proven effective for increasing self-awareness and motivating people to modify their life styles for improved wellness. This paper presents FamilyLog - a practical system to log family mealtime activities using smartphones and smartwatches. FamilyLog automatically detects and logs details of activities during the mealtime, including occurrence and duration of meal, conversations, participants, TV viewing etc., in an unobtrusive manner. Based on the sensor data collected from real families, we carefully design robust yet lightweight signal features from a set of complex activities during the meal, including clattering sound, arm gestures of eating, human voice, TV sound, etc. Moreover, FamilyLog opportunistically fuses data from built-in sensors of multiple mobile devices available in a family through an HMM-based classifier. To evaluate the real-world performance of FamilyLog, we perform extensive experiments that consist of 77 days of sensor data from 37 subjects in 8 families with children. Our results show that FamilyLog can detect those events with high accuracy across different families and home environments.

Tracking heart rate for fitness using wrist-type wearables is challenging, because of the significant noise caused by intensive wrist movements. In this paper, we present FitBeat - a lightweight system that enables accurate heart rate tracking on wrist-type wearables during intensive exercises. Unlike existing approaches that rely on computation- intensive signal processing, FitBeat integrates and augments standard filter and spectral analysis tool, which achieves comparable accuracy while significantly reducing computational overhead. FitBeat integrates contact sensing, motion sensing and simple spectral analysis algorithms to suppress various error sources. We implement FitBeat on a COTS smartwatch, and evaluate the performance of FitBeat for typical workouts of different intensities, including walking, running and riding. Experimental results involving 10 subjects show that the average error of FitBeat is around 4 beats per minute, which improves heart rate accuracy of the default heart rate tracker of Moto 360 by 10x.

Mobility model plays a crucial part in wireless network simulation or mathematical analysis, especially for human mobility because real mobility network constructed by human is hard to trace, measure or apply to different scenarios. For delay-tolerant networks, mobility model also affects the frequency and duration of opportunities for data transfer between nodes, which is a key factor of network performance, so whether we can choose a model according to realistic scenes is important for the accuracy and practicability of simulation. In this paper, we propose a new mobility model of students' daily activities based on the analysis and conclusion of students' habits and customs in campus environments, which is able to produce inter-contact time, contact time distribution and other contact information. We validate the movement model by using the ONE simulator comparing with other movement models and tracing data from real-world measurement experiments. Results show that SAME is consistent with actual student behavior characteristics.