Using Mobile Phones for Activity Recognition in Parkinson’s Patients

Sensory Motor Performance Program, Rehabilitation Institute of Chicago Chicago, IL, USA
Frontiers in Neurology 11/2012; 3:158. DOI: 10.3389/fneur.2012.00158
Source: PubMed


Mobile phones with built-in accelerometers promise a convenient, objective way to quantify everyday movements and classify those movements into activities. Using accelerometer data we estimate the following activities of 18 healthy subjects and eight patients with Parkinson's disease: walking, standing, sitting, holding, or not wearing the phone. We use standard machine learning classifiers (support vector machines, regularized logistic regression) to automatically select, weigh, and combine a large set of standard features for time series analysis. Using cross validation across all samples we are able to correctly identify 96.1% of the activities of healthy subjects and 92.2% of the activities of Parkinson's patients. However, when applying the classification parameters derived from the set of healthy subjects to Parkinson's patients, the percent correct lowers to 60.3%, due to different characteristics of movement. For a fairer comparison across populations we also applied subject-wise cross validation, identifying healthy subject activities with 86.0% accuracy and 75.1% accuracy for patients. We discuss the key differences between these populations, and why algorithms designed for and trained with healthy subject data are not reliable for activity recognition in populations with motor disabilities.

Download full-text


Available from: Mark B Shapiro, Oct 09, 2015
21 Reads
  • Source
    • "Second, the HMM module within our framework effectively integrates together the activity and floor inference. Previous studies either recognized human activity from inertial motion unit sensors [5], [7], or inferred the floors from barometric sensors [12], [13]. To our best knowledge, the activity and floor recognition have not been considered at the same time. "
    [Show abstract] [Hide abstract]
    ABSTRACT: Smartphone based indoor localization caught mas-sive interest of the localization community in recent years. Combining pedestrian dead reckoning obtained using the phone's inertial sensors with the GraphSLAM (Simultaneous Localization and Mapping) algorithm is one of the most effective approaches to reconstruct the entire pedestrian trajectory given a set of visited landmarks during movement. A key to GraphSLAM-based localization is the detection of reliable landmarks, which are typically identified using visual cues or via NFC tags or QR codes. Alternatively, human activity can be classified to detect organic landmarks such as visits to stairs and elevators while in movement. We provide a novel human activity classification framework that is invariant to the pose of the smartphone. Pose invariant features allow robust observation no matter how a user puts the phone in the pocket. In addition, activity classification obtained by an SVM (Support Vector Machine) is used in a Bayesian framework with an HMM (Hidden Markov Model) that improves the activity inference based on temporal smoothness. Furthermore, the HMM jointly infers activity and floor information, thus providing multi-floor indoor localization. Our experiments show that the proposed framework detects landmarks accurately and enables multi-floor indoor localization from the pocket using GraphSLAM.
    International Conference on Pattern Recognition; 08/2014
  • Source
    • "Activity recognition is simply continuous monitoring of physical activity in a free living environment for prolonged periods. HAR provides new opportunities for context aware applications in various areas including healthcare [1] [2], assisted living, sports coaching, security, virtual reality and wearable computing. For example, in area of ubiquitous healthcare applications, the ability to recognize everyday activities could enable such systems to monitor and learn any changes in daily behavior of an elderly which might be the indication of developing mental or physical medical conditions. "
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a smartphone based portable activity recognition system to record and recognize daily activity patterns of users. This system can assist patients and any individual to better understand their unhealthy behavior, however, making them to change that behavior by improving their daily level of physical activity.
    2014 International Symposium on Consumer Electronics (ICSE); 06/2014
  • Source
    • "Patients with Parkinson's disease wore three body-fixed inertial sensors which were used to accurately identify activities including walking, sitting, standing, lying, sit to stand, and stand to sit transitions (Salarian et al., 2007). It has also been shown that a mobile phone placed in a pocket can be used to recognize activities in people with Parkinson's disease (Albert et al., 2012b). Each of these systems can quantify physical activity, but they require participants to wear sensors in a fixed location, and generally wearing more sensors leads to more accurate tracking (Bao and Intille, 2004). "
    [Show abstract] [Hide abstract]
    ABSTRACT: For rehabilitation and diagnoses, an understanding of patient activities and movements is important. Modern smartphones have built in accelerometers which promise to enable quantifying minute-by-minute what patients do (e.g. walk or sit). Such a capability could inform recommendations of physical activities and improve medical diagnostics. However, a major problem is that during everyday life, we carry our phone in different ways, e.g. on our belt, in our pocket, in our hand, or in a bag. The recorded accelerations are not only affected by our activities but also by the phone's location. Here we develop a method to solve this kind of problem, based on the intuition that activities change rarely, and phone locations change even less often. A Hidden Markov Model (HMM) tracks changes across both activities and locations, enabled by a static Support Vector Machine (SVM) classifier that probabilistically identifies activity-location pairs. We find that this approach improves tracking accuracy on healthy subjects as compared to a static classifier alone. The obtained method can be readily applied to patient populations. Our research enables the use of phones as activity tracking devices, without the need of previous approaches to instruct subjects to always carry the phone in the same location.
    Journal of Neuroscience Methods 09/2013; 231. DOI:10.1016/j.jneumeth.2013.09.015 · 2.05 Impact Factor
Show more