Mladen Milosevic

Smartphones for smart wheelchairs

Individuals with limited ambulatory skills are at high risk for all physical inactivity-related diseases, such as coronary disease and diabetes. Increased physical activity can significantly lower risks of these diseases. However, quantifying recommendations for increased physical activity remain challenging for individuals who use wheelchairs for mobility. In this paper we introduce a smart wheelchair that utilizes a smartphone with its built-in sensors to capture and record physical activity of manual wheelchair users in both unstructured and structured environments. We develop algorithms for data acquisition and processing on the smartphone and implement them in an Android application called mWheelness. The application is successfully tested in laboratory and free-living experiments using several modern smartphones.

Quantifying Timed-Up-and-Go test: A smartphone implementation

Timed-Up-and-Go (TUG) is a simple, easy to administer, and frequently used test for assessing balance and mobility in elderly and people with Parkinsons disease. An instrumented version of the test (iTUG) has been recently introduced to better quantify subjects movements during the test. The subject is typically instrumented by a dedicated device designed to capture signals from inertial sensors that are later analyzed by healthcare professionals. In this paper we introduce a smartphone application called sTUG that completely automates the iTUG test so it can be performed at home. sTUG captures the subjects movements utilizing smartphones built-in accelerometer and gyroscope sensors, determines the beginning and the end of the test and quantifies its individual phases, and optionally uploads test descriptors into a medical database. We describe the parameters used to quantify the iTUG test and algorithms to extract the parameters from signals captured by the smartphone sensors.

A mobile system for assessment of physiological response to posture transitions

Posture changes initiate a dynamic physiological response that can be used as an indicator of the overall health status. We introduce an inconspicuous mobile wellness monitoring system (imWell) that continuously assesses the dynamic physiological response to posture transitions during activities of daily living. imWell utilizes a Zephyr BioHarness 3 physiological monitor that continually reports heart activity and physical activity via Bluetooth to a personal device (e.g. smartphone). The personal device processes the reported activity data in real-time to recognize posture transitions from the accelerometer data and to characterize dynamic heart response to posture changes. It annotates, logs, and uploads the heart activity data to our mHealth server. In this paper we present algorithms for detection of posture transitions and heart activity characterization during a sit-to-stand transition. The proposed system was tested on seven healthy subjects performing a predefined protocol. The total average and standard deviation for sit-to-stand transition time is 2.7±0.69 s, resulting in the change of heart rate of 27.36±9.30 bpm (from 63.3±9.02 bpm to 90.66±10.09 bpm).

mHealth @ UAH: computing infrastructure for mobile health and wellness monitoring

New health care systems that integrate wearable sensors, personal devices, and servers promise to fundamentally change the way health care services are delivered and used.

An environment for automated power measurements on mobile computing platforms

Mobile computing devices such as smartphones, tablet computers, and e-readers have become the dominant personal computing platforms. Energy efficiency is a prime design requirement for mobile device manufacturers and smart application developers alike. Runtime power measurements on mobile platforms provide insights that can eventually lead to more energy-efficient operation. In this paper we describe mPowerProfile - an environment for automated power measurements of programs running on a mobile development platform. We discuss mPowerProfiles main functions and its utilization in several example studies based on the Pandaboard and Raspberry Pi platforms.

Preliminary analysis of physiological changes of nursing students during training

Long-term exposure to stress has been associated with chronic diseases, depression, and immune disorders. The precise detection and assessment of stress depends on personalized physiological monitoring and assessment of influence of personal and workplace factors We monitored nursing students during training on a high fidelity simulator in the Real-time Physiological Monitoring Lab at the University of Alabama in Huntsville. In this paper we present the preliminary results of this pilot study. A total of 14 participants were recorded: 12 female and 2 male subjects, 23-46 years old with an average age of 32.8 years. We analyzed heart rate, Heart Rate Variability (HRV), respiration, and physical activity. The results indicate significant strain on subjects during simulation: heart rate increased 16.7%, from 82.8 to 96.6 bpm (p<;0.001), falling to a slightly increased level after the training session (84.9 bpm); Root Mean Square of Successive RR Differences (RMSSD) decreased from 38.9 ms to 37.7 ms; the breathing rate increased during the simulation from 16.9 to 17.7 breaths/min. Distractions also significantly influenced physiological parameters: the first telephone call increased heart rate on average 9 bpm (p<;0.001), while the second call increased heart rate 8.6 bpm (p<;0.001). The simulated patient-related events created even more prominent response; the average heart rate increased 17.4 bpm (p<;0.001) at the onset of “patient in crisis” event. Real-time wearable monitoring may provide assessment of occupational stress.

A real-time control of multiple Avatars using Wii remotes and Avatar system

Virtual reality training and rehabilitation systems require an unobtrusive and inexpensive monitoring of users with minimum latency. Inertial sensors have inherent drift that limits absolute positioning of sensors, while infrared sensors require special setup and expensive deployment. We developed Avatar system as hybrid infrared and inertial solution for low cost deployment. In this paper we propose a synchronized extension of the Avatar system for multiple users. The system allows monitoring of multiple users using time division multiplexing of infrared diodes on users body and two Wii© Remotes as optical sensors for absolute positioning. A network of inertial nodes on each user is controlled by a master node that serves as a gateway for communication with a capture device, synchronizes and drives infrared LEDs. The capture device communicates through Bluetooth with master nodes (iControl) and Wii remotes. We present system architecture, principles of operation, and performance analysis of the implemented system.

Real-time monitoring of occupational stress of nurses

Prolonged exposure to stress has been associated with chronic diseases, depression, and immune disorders. Stress perception is highly subjective. Assessment of occupational stress requires personalized physiological monitoring and timely collection of individual characterization of sources of stress. We implemented a wearable system for monitoring of occupational stress of nurses — UAHealth. Personal monitors are implemented on iPhone smartphones with Ant+ wireless interface. Interbeat intervals are collected from a chest belt, and step count and cadence from foot pod sensor. All data are processed in real-time on the phone to assess stress index. A 30-minute personalized maximum over predefined threshold initiates a questionnaire to collect assessment of sources of stress. In this paper we present system organization and preliminary results.

Research methodology for real-time stress assessment of nurses.

This article presents a research methodology for analysis of stress effects and allostatic load of nurses during daily activities. Stress-related health issues are critical in healthcare workers, in particular nurses. Typical causes of stress include inadequate staffing of nurses for the number and acuity of patients, dealing with difficult patients and families, and lack of autonomy in care delivery decisions. This is all compounded by lack of recovery time while on shift, variable shifts with limited recovery time between days worked, and fatigue from dealing with difficult patients, families, and healthcare workers. Under unresolved stress, the heart rate and other vital parameters may fail to return to the baseline. This study examined the physiological responses of nurses during care on a high-fidelity patient simulation to develop a research methodology and identify physiological parameters suitable for real-time assessment of allostatic load during work. Our results demonstrated that heart rate and heart rate variability can be reliably measured using wearable sensors to assess allostatic load. During this study and our previous related work, we acquired valuable experience regarding selection and deployment of commercially available sensors, system integration, recruitment of subjects, and general research methodology. The research methodology developed and presented in this article can be applied to a number of other applications and experimental protocols.