@article{starliper_mohammadzadeh_songkakul_hernandez_bozkurt_lobaton_2019, title={Activity-Aware Wearable System for Power-Efficient Prediction of Physiological Responses}, volume={19}, ISSN={["1424-8220"]}, url={https://doi.org/10.3390/s19030441}, DOI={10.3390/s19030441}, abstractNote={Wearable health monitoring has emerged as a promising solution to the growing need for remote health assessment and growing demand for personalized preventative care and wellness management. Vital signs can be monitored and alerts can be made when anomalies are detected, potentially improving patient outcomes. One major challenge for the use of wearable health devices is their energy efficiency and battery-lifetime, which motivates the recent efforts towards the development of self-powered wearable devices. This article proposes a method for context aware dynamic sensor selection for power optimized physiological prediction using multi-modal wearable data streams. We first cluster the data by physical activity using the accelerometer data, and then fit a group lasso model to each activity cluster. We find the optimal reduced set of groups of sensor features, in turn reducing power usage by duty cycling these and optimizing prediction accuracy. We show that using activity state-based contextual information increases accuracy while decreasing power usage. We also show that the reduced feature set can be used in other regression models increasing accuracy and decreasing energy burden. We demonstrate the potential reduction in power usage using a custom-designed multi-modal wearable system prototype.}, number={3}, journal={SENSORS}, author={Starliper, Nathan and Mohammadzadeh, Farrokh and Songkakul, Tanner and Hernandez, Michelle and Bozkurt, Alper and Lobaton, Edgar}, year={2019}, month={Feb} }
 @inproceedings{lokare_samadi_zhong_gonzalez_mohammadzadeh_lobaton_2017, title={Energy-efficient activity recognition via multiple time-scale analysis}, url={http://dx.doi.org/10.1109/ssci.2017.8285176}, DOI={10.1109/ssci.2017.8285176}, abstractNote={In this work, we propose a novel power-efficient strategy for supervised human activity recognition using a multiple time-scale approach, which takes into account various window sizes. We assess the proposed methodology on our new multimodal dataset for activities of daily life (ADL), which combines the use of physiological and inertial sensors from multiple wearable devices. We aim to develop techniques that can run efficiently in wearable devices for real-time activity recognition. Our analysis shows that the proposed approach Sequential Maximum-Likelihood (SML) achieves high F1 score across all activities while providing lower power consumption than the standard Maximum-Likelihood (ML) approach.}, booktitle={2017 IEEE Symposium Series on Computational Intelligence (SSCI)}, publisher={IEEE}, author={Lokare, N. and Samadi, S. and Zhong, Boxuan and Gonzalez, L. and Mohammadzadeh, F. and Lobaton, E.}, year={2017}, pages={1466–1472} }
 @article{mohammadzadeh_liu_bond_nam_2015, title={Feasibility of a Wearable, Sensor-based Motion Tracking System}, volume={3}, ISSN={2351-9789}, url={http://dx.doi.org/10.1016/j.promfg.2015.07.128}, DOI={10.1016/j.promfg.2015.07.128}, abstractNote={The objective of this study was to develop and evaluate the feasibility of a wearable, sensor-based motion tracking system that provides an economical and quantitative means of recording upper limb motion for physical rehabilitation. The tracking system is comprised of a wirelessly connected network of inertial measurement units (IMUs), each containing a gyroscope and an accelerometer. Two IMUs were rigidly attached to each subject's forearm and upper arm. A trajectorizing algorithm was developed to estimate the three dimensional upper limb motion based on the measurements of the IMUs. A major advantage of the algorithm is that it allows the IMUs to be attached with arbitrary orientation to each limb and no manual anthropomorphic measurements need to be performed. By recording specific, known motions, the sensors can be calibrated with respect to their orientation in space and with respect to their orientation relative to their respective body segments. During the experiment, healthy subjects performed elbow flexion-extension motions that were recorded using the IMUs. To validate the system including the accuracy of recorded data and the correctness of the trajectorizing algorithm, an optical motion capture system was also used to record the same motions. Results showed that the proposed motion tracking system measured the elbow joint angles of the flexion-extension motions with high consistency with the measurements obtained from the optical motion capture system. Statistical analysis showed that joint angles between two systems are highly correlated. The error of elbow joint angles measured by our system yielded small root mean square error (RMSE) and small median absolute deviation (MAD). These results suggest that an IMU-based (more specifically, a gyroscope-based) motion tracking system can be realistically used to accurately track a patient's motion without the need of numerous sensors or an overly complicated set-up.}, journal={Procedia Manufacturing}, publisher={Elsevier BV}, author={Mohammadzadeh, Farrokh F. and Liu, Shijing and Bond, Kyle A. and Nam, Chang S.}, year={2015}, pages={192–199} }