Luka Celić

WBAN for Physical Activity Monitoring in Health Care and Wellness

Physical activity is an important factor of an individual’s health, and often a part of rehabilitation for patients suffering from post-trauma or some chronic diseases. The objective of this paper is to present the use of Wireless Body Area Network (WBAN) for measuring mobility and physical activity during assisted exercising as well as the algorithms for quantification of measurement results. Wireless sensor network is composed of sensor nods located on examinees’ body. With the help of networked sensors, it is possible to detect other physiological parameters of examinees at the same time, such as heart rate, breathing rate, temperature and body posture. Monitoring of physical activity has been realized with a three-axis accelerometer, while the data acquired from sensor node is sent to the central wearable node. Algorithms for the classification of mobility (different type of physical activity) during standard daily activities and for differentiation of exercises during workout has been developed and validated on a number of volunteers. In this paper we report on the second, used for assisted exercising. The algorithm is based on the first-neighbour method in n-dimensional space of signal features. Algorithm shows good features for physically different exercises. Our experience also indicates that the monitoring of physical activity and vital parameters at the same time is adequate for application in the rehabilitation of diabetic patients.

Integration of Measurement Devices Supporting Diabetic Patients into a Remote Care System

Patient care and management can be significantly improved by introduction of remote home care and monitoring. Patients with diabetes are obliged to collect and monitor data such as blood glucose level, insulin doses applied, weight, daily exercise and activity and/or blood pressure. This paper describes complete system for remote home care and monitoring of patients, the Personalized Intelligent Mobile Health System (PIMHS) for Diabetic Patients.

Virtual Reality System for Assisted Exercising Using WBAN

This paper presents a virtual reality system for assisted exercise using Wireless Body Area Network (WBAN). Sensor nodes with integrated accelerometer, gyroscope and magnetometer are used for orientation-driven visualization of human body motion. A virtual scene is created using Unity 3D game-engine. The scene involves virtual trainer for providing the visual guidance during exercise, and user’s avatar for real-time tracking of the user’s motion. The user is given direct feedback while exercising in form of textual and audio messages. Qualitative and quantitative assessment of the performance of each exercise is retrieved through the network. The application is deployed for use on mobile devices (e.g. smartphones, tablets) and PCs.

System for Assisted Exercising and Qualitative Exercise Assessment

In recently studies, as one of simpler and better solution for measuring human mobility and physical activity, Wireless Body Area Networks (WBAN) have been introduced. In order to acquire those information and due to the desire of future growth in mentioned filed, WBAN consisting of inertial and magnetic sensors was developed at our Department. The WBAN together with developed desktop application forms a unique system for assisted exercising and exercise evaluation. In exercising evaluation of patients or sportsmen, a new approach in qualitative assessment is used. New approach introduces “Exercise Signature” as a reference signal for evaluation of exercising. The main concept is that every exercise has some characteristic data which are calculated by the developed algorithm and then saved in exercise database. The mentioned application is not only used for calculating characteristic exercise data, but it also has a role in visualization of the virtual trainer which leads the person who is exercising through his personalized training. In this work, we present detailed description of the whole assisted strength exercising system and elaborate its possible applications. Endurance exercising protocols will be described elsewhere.

Quality of Human Activities Measurement from Accelerometer Data of a Smartphone

In the past few years, usage of smartphones increased significantly because of their computational power, large screens, memory capacity, large number of embedded sensors and other features. The aim of this study is to explore, test and compare the quality of measuring human activities through acquisition of raw data from smartphone built-in accelerometer. In a series of experiments, acceleration measurements from different smartphones were compared to the accelerometer data from a custom made sensor node. The selected activities that were measured are: walking, walking up stairs, walking down stairs, brisk walking, running and sitting (as a state of inactivity). Signal processing was made in Matlab. After calculation and comparison of the magnitude of linear acceleration, Fast Fourier Transform (FFT) was calculated for each activity on 256 samples of the signal. Then the energy of each activity was calculated and compared. Results show that the recorded acceleration values and their variations of amplitude of linear acceleration for sitting is negligible, while the amplitudes for other activities (walking, walking up stairs, down stairs and running) are more significant. Also, the amplitudes of the running activity measured with the sensor node are considerably larger than amplitudes of all other activities (walking, walking up stairs and walking down stairs). However, signals measured with smartphone introduced an error into calculation of linear acceleration because at least one of accelerometer axis from smartphone accelerometers was saturated for activities of greater intensity (brisk walking and running). Measurements using the accelerometer of the sensor node have shown larger differences between amplitudes of linear acceleration and differences between energy for each activity and the results of recordings can be used for measurements and not for monitoring applications only.

Quantitative and Qualitative Assessment of Assisted Strength Exercising

Human motion detection and tracking systems, which are not video camera based, are becoming more and more popular in rehabilitation, sportsmen tracking or elderly monitoring. The most commonly used motion sensors in these systems are accelerometers and gyroscopes, which are used along with other sensors as a part of wearable wireless body area network (WBAN). In this work we present an algorithm for closed-loop assisted exercising based on Finite State Machine (FSM). The algorithm can be used either for rehabilitation purposes or physical exercise training. As inputs, the algorithm uses real time signals acquired from an accelerometer and a gyroscope of a sensor node in a WBAN. For testing purposes, signals were recorded from 13 healthy subjects during three different strength training exercises (lateral raise, inner-bicep curl, and seated shoulder press) while the sensor node was attached on the wrist of a subject’s dominant arm. Qualitative and quantitative assessment of the accelerometer and gyroscope signals was made. Results of tests confirm that assisted exercising using on-line feedback enable more precise movement control closer to prescribed pattern in time and intensity. The proposed FSM based algorithm is suitable for implementation on embedded systems. One of the potential applications of the proposed algorithm is in e-health systems such as HeartWays system providing advanced solutions for supporting cardiac patients in rehabilitation.

Supporting Diabetic Patients with a Remote Patient Monitoring Systems

In order to achieve better self-control of their diabetes and to decrease long-term risks of complications, diabetic patients monitor several different parameters on a day-to-day basis. These parameters, such as blood glucose level, insulin intake, weight, diet, exercise and physical activity, blood pressure, can be easily acquired using IT technologies without oppressing the patient with handwritten diaries. At the same time, healthcare professionals are provided with the data on time and can intervene without delay, if necessary. The system collects data on blood glucose level using special device for communication between glucose meter and either a smartphone or a PC. A person’s weight is acquired using a modified body scale which, while weighing, at the same time scans patient’s feet and stores images for further processing and comparison with the images from pressure measurement platform. Patients enter their own diet and therapy using a smartphone app. Information on exercise and physical activity is provided using WBAN (Wireless Body Area Network) system with complementing software, both developed at our University. The system supports patients while performing previously determined exercise plan without the immediate presence of trainer, and also acquires data on regular daily activity (walking, running, sitting,…). The parts of the system providing some of the parameters are either developed in our previous studies or commercial, and they are integrated into our e-system. After collecting, the data is stored in a database for further use by diabetic patients themselves or by their healthcare providers.

Human Identification by Simultaneous Recording of Acceleration and ECG Data

This paper presents a method of human identification based on ensemble empirical mode decomposition (EEMD) of an one-lead electrocardiogram (ECG) signal and by box approximation geometry of reconstructed attractors in latent space of a signal measured by an accelerometer located on the waist. Preprocessing of the ECG signal eliminates effects of noise and heart rate variability. The ECG signal is decomposed into a number of intrinsic mode functions (IMFs) and significant heartbeat signal features are extracted using Welch spectral analysis. Human gait is considered a dynamical system and the features are the eigenvalues of the reconstructed attractor in the odd principal dimensions obtained using the Singular Spectrum Analysis methodology. The K-nearest neighbours (K-NN) method is applied as the classifier tool.

Real-Time Evaluation of Repetitive Physical Exercise Using Orientation Estimation from Inertial and Magnetic Sensors

Human motion tracking has an important role in a wide variety of applications, including physical exercise. Exercise tracking systems based on the combined use of inertial and magnetic sensors (also called IMU systems) have witnessed a fast increase in popularity in recent years due to their high accuracy and portability. Nonetheless, a complete solution that would guide a user in correctly performing a movement and provide a real-time evaluation of the performed movement is still not available. This paper presents an IMU based system for human motion tracking and its application in real-time evaluation of repetitive physical exercise. The user is provided with a visual demonstration of the correct exercise execution and his own movements. An algorithm is used to compare the movements, thus enabling quantitative and qualitative exercise assessment. However, only simple exercises (that include one limb motion) have been tested with this system, and evaluation of more complex movements shall be explored in the future.

Simultaneous Measurement of Trunk Orientation and Centre of Pressure for Postural Stability Evaluation

Human balance control system allows people to independently perform acts of daily living and to avoid falls that can cause injuries and hospitalization. Aging or various pathologies may cause disorders in the balance system and result in wide variety of problems and generally decreased quality of life. Researchers and health professionals therefore strive to develop effective methods and instruments for prompt diagnosis and rehabilitation of balance disorders. A common approach used to detect balance problems in scientific studies and clinical applications is to analyze various parameters of postural stability gathered during quiet stance. This paper presents an experimental setting for postural stability evaluation composed of two independent systems. A commercial force platform (Ecowalk) and a sensor node with multiple inertial and magnetic sensors are combined to simultaneously measure trunk orientation and center-of-pressure (COP) during quiet stance. A preliminary study with 8 healthy subjects was conducted in order to test the system functionality. Trunk orientation and COP were measured in four different conditions for every subject as they tried to maintain steady upright position. The area of trunk sway trajectory and COP variability were calculated from orientation and force platform measurements. The goal of this study was to explore whether use of the created experimental setting can provide a measure of two different biomechanical properties related to the balance control system during quiet stance trials. The initial results are promising as they have shown consistency in both variables during trials in different conditions, but further measurements with more subjects are needed for stronger conclusions.