Estimation of Mechanical Power Output Employing Deep Learning on Inertial Measurement Data in Roller Ski Skating.

The ability to optimize power generation in sports is imperative, both for understanding and balancing training load correctly, and for optimizing competition performance. In this paper, we aim to estimate mechanical power output by employing a time-sequential information-based deep Long Short-Term Memory (LSTM) neural network from multiple inertial measurement units (IMUs). Thirteen athletes conducted roller ski skating trials on a treadmill with varying incline and speed. The acceleration and gyroscope data collected with the IMUs were run through statistical feature processing, before being used by the deep learning model to estimate power output. The model was thereafter used for prediction of power from test data using two approaches. First, a user-dependent case was explored, reaching a power estimation within 3.5% error. Second, a user-independent case was developed, reaching an error of 11.6% for the power estimation. Finally, the LSTM model was compared to two other machine learning models and was found to be superior. In conclusion, the user-dependent model allows for precise estimation of roller skiing power output after training the model on data from each athlete. The user-independent model provides less accurate estimation; however, the accuracy may be sufficient for providing valuable information for recreational skiers.

Towards Human Motion Tracking Enhanced by Semi-Continuous Ultrasonic Time-of-Flight Measurements.

Human motion analysis is a valuable tool for assessing disease progression in persons with conditions such as multiple sclerosis or Parkinson's disease. Human motion tracking is also used extensively for sporting technique and performance analysis as well as for work life ergonomics evaluations. Wearable inertial sensors (e.g., accelerometers, gyroscopes and/or magnetometers) are frequently employed because they are easy to mount and can be used in real life, out-of-the-lab-settings, as opposed to video-based lab setups. These distributed sensors cannot, however, measure relative distances between sensors, and are also cumbersome when it comes to calibration and drift compensation. In this study, we tested an ultrasonic time-of-flight sensor for measuring relative limb-to-limb distance, and we developed a combined inertial sensor and ultrasonic time-of-flight wearable measurement system. The aim was to investigate if ultrasonic time-of-flight sensors can supplement inertial sensor-based motion tracking by providing relative distances between inertial sensor modules. We found that the ultrasonic time-of-flight measurements reflected expected walking motion patterns. The stride length estimates derived from ultrasonic time-of-flight measurements corresponded well with estimates from validated inertial sensors, indicating that the inclusion of ultrasonic time-of-flight measurements could be a feasible approach for improving inertial sensor-only systems. Our prototype was able to measure both inertial and time-of-flight measurements simultaneously and continuously, but more work is necessary to merge the complementary approaches to provide more accurate and more detailed human motion tracking.

A User Study: Keyboard and Applications to Simplify Smartphone Adoption for Seniors.

The aim of the user study was to evaluate how the developed assistive physical keyboard, the Ezi-PAD, and integrated senior friendly applications, can encourage non-smartphone seniors to start using the smartphone and enable senior smartphone users to continue using a smartphone in spite of increasing motoric or visual impairment. A number of seniors with different experience and impairment, aged 64 to 86, were equipped with a smartphone and an Ezi-PAD assembly. After basic training, their use of the smartphone was monitored for up to 2 months. Five out of nine participants used the system for 2 months, and found the Ezi-PAD easy to use. The senior friendly applications gave extra utilitarian value to the phone.

Portable qEEG and HD-tCS Device for Point-of-Injury Traumatic Brain Injury Diagnostics.

Mild Traumatic Brain Injury (mTBI) can cause prolonged or permanent injuries if left undetected and ignored. It is therefore of great interest to lower the threshold for diagnosis of individuals with mTBI injury. We report on the development of a prototype of a portable quantified EEG (qEEG) system intended for in-the-field mTBI diagnostics. The 32-electrode system is fully battery driven, is interfaced with a control unit being part of a telemedicine care system. Electrode montage is a central problem effectively challenging measurements outside clinical environments. The system concept is unique in the sense that it will allow an automated montage process employing a flexible, disposable, one-size-fits-all electrode cap. All electrodes are individually configurable so that they can be used for both wet and dry qEEG electrodes. All electrodes can also be individually configured to allow Trans-Cranial Current Stimulation (tCS) sessions in DC, AC or other current supply modalities. The system has been functionality tested in end-to-end configurations where all control and measurement signals are forwarded between the head device on one side and the user interface and telemedicine system on the other. Tests confirm that the device can acquire and forward EEG data from 32 channels in parallel at target sensitivities up to 1 kHZ sampling frequencies. Additional device clinical evaluation is planned.

ESUMS: a mobile system for continuous home monitoring of rehabilitation patients.

The pressure on the healthcare services is building up for several reasons. The ageing population trend, the increase in life-style related disease prevalence, as well as the increased treatment capabilities with associated general expectation all add pressure. The use of ambient healthcare technologies can alleviate the situation by enabling time and cost-efficient monitoring and follow-up of patients discharged from hospital care. We report on an ambulatory system developed for monitoring of physical rehabilitation patients. The system consists of a wearable multisensor monitoring device; a mobile phone with client application aggregating the data collected; a service-oriented-architecture based server solution; and a PC application facilitating patient follow-up by their health professional carers. The system has been tested and verified for accuracy in controlled environment trials on healthy volunteers, and also been usability tested by 5 congestive heart failure patients and their nurses. This investigation indicated that patients were able to use the system, and that nurses got an improved basis for patient follow-up.

Protective jacket enabling decision support for workers in cold climate.

The cold and harsh climate in the High North represents a threat to safety and work performance. The aim of this study was to show that sensors integrated in clothing can provide information that can improve decision support for workers in cold climate without disturbing the user. Here, a wireless demonstrator consisting of a working jacket with integrated temperature, humidity and activity sensors has been developed. Preliminary results indicate that the demonstrator can provide easy accessible information about the thermal conditions at the site of the worker and local cooling effects of extremities. The demonstrator has the ability to distinguish between activity and rest, and enables implementation of more sophisticated sensor fusion algorithms to assess work load and pre-defined activities. This information can be used in an enhanced safety perspective as an improved tool to advice outdoor work control for workers in cold climate.

Hand-arm vibration exposure monitoring with wearable sensor module.

Vibration exposure is a serious risk within work physiology for several work groups. Combined with cold artic climate, the risk for permanent harm is even higher. Equipment that can monitor the vibration exposure and warn the user when at risk will provide a safer work environment for these work groups. This study evaluates whether data from a wearable wireless multi-parameter sensor module can be used to estimate vibration exposure and exposure time. This work has been focused on the characterization of the response from the accelerometer in the sensor module and the optimal location of the module in the hand-arm configuration.

Wearable wireless multi-parameter sensor module for physiological monitoring.

Advances in low power technology have given new possibilities for continuous physiological monitoring in several domains such as health care with disease prevention and quality of care services and workers in harsh environment. A miniaturized, multifunctional sensor module that transmits sensor data wirelessly using Bluetooth Smart technology has been developed. The wireless communication link is influenced by factors like antenna orientation, reflections, interference and noise. Test results for signal strength measurements for the wireless transmission in various setups are given and discussed.