Limits...
Improving activity recognition using a wearable barometric pressure sensor in mobility-impaired stroke patients.

Massé F, Gonzenbach RR, Arami A, Paraschiv-Ionescu A, Luft AR, Aminian K - J Neuroeng Rehabil (2015)

Bottom Line: The first stage processed the events to infer activities and the second stage improved activity recognition by applying behavioral constraints.The proposed classifier essentially benefits from a better recognition of standing activity (70.3 % versus 61.5 % [FIS-IMU] and 42.5 % [EPOCH]) with 98.2 % CCR for body elevation estimation.The monitoring and recognition of daily activities in mobility-impaired stoke patients can be significantly improved using a trunk-fixed sensor that integrates BP, inertial sensors, and an event-based activity classifier.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Movement Analysis and Measurement, Ecole Polytechnique Fédérale de Lausanne, Station 11, 1015, Lausanne, Switzerland. fabien.masse@epfl.ch.

ABSTRACT

Background: Stroke survivors often suffer from mobility deficits. Current clinical evaluation methods, including questionnaires and motor function tests, cannot provide an objective measure of the patients' mobility in daily life. Physical activity performance in daily-life can be assessed using unobtrusive monitoring, for example with a single sensor module fixed on the trunk. Existing approaches based on inertial sensors have limited performance, particularly in detecting transitions between different activities and postures, due to the inherent inter-patient variability of kinematic patterns. To overcome these limitations, one possibility is to use additional information from a barometric pressure (BP) sensor.

Methods: Our study aims at integrating BP and inertial sensor data into an activity classifier in order to improve the activity (sitting, standing, walking, lying) recognition and the corresponding body elevation (during climbing stairs or when taking an elevator). Taking into account the trunk elevation changes during postural transitions (sit-to-stand, stand-to-sit), we devised an event-driven activity classifier based on fuzzy-logic. Data were acquired from 12 stroke patients with impaired mobility, using a trunk-worn inertial and BP sensor. Events, including walking and lying periods and potential postural transitions, were first extracted. These events were then fed into a double-stage hierarchical Fuzzy Inference System (H-FIS). The first stage processed the events to infer activities and the second stage improved activity recognition by applying behavioral constraints. Finally, the body elevation was estimated using a pattern-enhancing algorithm applied on BP. The patients were videotaped for reference. The performance of the algorithm was estimated using the Correct Classification Rate (CCR) and F-score. The BP-based classification approach was benchmarked against a previously-published fuzzy-logic classifier (FIS-IMU) and a conventional epoch-based classifier (EPOCH).

Results: The algorithm performance for posture/activity detection, in terms of CCR was 90.4 %, with 3.3 % and 5.6 % improvements against FIS-IMU and EPOCH, respectively. The proposed classifier essentially benefits from a better recognition of standing activity (70.3 % versus 61.5 % [FIS-IMU] and 42.5 % [EPOCH]) with 98.2 % CCR for body elevation estimation.

Conclusion: The monitoring and recognition of daily activities in mobility-impaired stoke patients can be significantly improved using a trunk-fixed sensor that integrates BP, inertial sensors, and an event-based activity classifier.

No MeSH data available.


Related in: MedlinePlus

Block diagram of the activity recognition algorithm. Following the acquisition of the IMU and barometric pressure signals from the wearable device, the acquired signals are then preprocessed to extract key events (postural transitions, steps, lying periods). Then these events are combined into a hierarchical FIS to output the basic activities. The output of FIS II, i.e. the detected activities were fed into the decision tree for body elevation estimation and fed back into the FIS I for the detection of next activities
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4549072&req=5

Fig1: Block diagram of the activity recognition algorithm. Following the acquisition of the IMU and barometric pressure signals from the wearable device, the acquired signals are then preprocessed to extract key events (postural transitions, steps, lying periods). Then these events are combined into a hierarchical FIS to output the basic activities. The output of FIS II, i.e. the detected activities were fed into the decision tree for body elevation estimation and fed back into the FIS I for the detection of next activities

Mentions: Unlike epoch-based classifiers, the proposed event-driven activity classifier relied on preprocessed events such as the start/end of walking and lying periods and STS postural transitions. After detection, these events were processed through a two-stage H-FIS to classify the basic daily-life posture/activities: lying, sitting, standing, and walking. While the first stage (FIS I - Event FIS) was in charge of translating the detected events into activities, the second stage (FIS II - Behavior FIS) was designed to apply linguistic behavioral constraints for improving the recognition of activities as inferred by the first stage. The standing and walking activities were further categorized by a decision tree according to the estimated elevation level: flat level standing, elevator down (standing with a downward elevation change), elevator up (standing with an upward elevation change), flat level walking, walking downstairs, and walking upstairs. A schematic of the algorithm is illustrated in Fig. 1.Fig. 1


Improving activity recognition using a wearable barometric pressure sensor in mobility-impaired stroke patients.

Massé F, Gonzenbach RR, Arami A, Paraschiv-Ionescu A, Luft AR, Aminian K - J Neuroeng Rehabil (2015)

Block diagram of the activity recognition algorithm. Following the acquisition of the IMU and barometric pressure signals from the wearable device, the acquired signals are then preprocessed to extract key events (postural transitions, steps, lying periods). Then these events are combined into a hierarchical FIS to output the basic activities. The output of FIS II, i.e. the detected activities were fed into the decision tree for body elevation estimation and fed back into the FIS I for the detection of next activities
© Copyright Policy - OpenAccess
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4549072&req=5

Fig1: Block diagram of the activity recognition algorithm. Following the acquisition of the IMU and barometric pressure signals from the wearable device, the acquired signals are then preprocessed to extract key events (postural transitions, steps, lying periods). Then these events are combined into a hierarchical FIS to output the basic activities. The output of FIS II, i.e. the detected activities were fed into the decision tree for body elevation estimation and fed back into the FIS I for the detection of next activities
Mentions: Unlike epoch-based classifiers, the proposed event-driven activity classifier relied on preprocessed events such as the start/end of walking and lying periods and STS postural transitions. After detection, these events were processed through a two-stage H-FIS to classify the basic daily-life posture/activities: lying, sitting, standing, and walking. While the first stage (FIS I - Event FIS) was in charge of translating the detected events into activities, the second stage (FIS II - Behavior FIS) was designed to apply linguistic behavioral constraints for improving the recognition of activities as inferred by the first stage. The standing and walking activities were further categorized by a decision tree according to the estimated elevation level: flat level standing, elevator down (standing with a downward elevation change), elevator up (standing with an upward elevation change), flat level walking, walking downstairs, and walking upstairs. A schematic of the algorithm is illustrated in Fig. 1.Fig. 1

Bottom Line: The first stage processed the events to infer activities and the second stage improved activity recognition by applying behavioral constraints.The proposed classifier essentially benefits from a better recognition of standing activity (70.3 % versus 61.5 % [FIS-IMU] and 42.5 % [EPOCH]) with 98.2 % CCR for body elevation estimation.The monitoring and recognition of daily activities in mobility-impaired stoke patients can be significantly improved using a trunk-fixed sensor that integrates BP, inertial sensors, and an event-based activity classifier.

View Article: PubMed Central - PubMed

Affiliation: Laboratory of Movement Analysis and Measurement, Ecole Polytechnique Fédérale de Lausanne, Station 11, 1015, Lausanne, Switzerland. fabien.masse@epfl.ch.

ABSTRACT

Background: Stroke survivors often suffer from mobility deficits. Current clinical evaluation methods, including questionnaires and motor function tests, cannot provide an objective measure of the patients' mobility in daily life. Physical activity performance in daily-life can be assessed using unobtrusive monitoring, for example with a single sensor module fixed on the trunk. Existing approaches based on inertial sensors have limited performance, particularly in detecting transitions between different activities and postures, due to the inherent inter-patient variability of kinematic patterns. To overcome these limitations, one possibility is to use additional information from a barometric pressure (BP) sensor.

Methods: Our study aims at integrating BP and inertial sensor data into an activity classifier in order to improve the activity (sitting, standing, walking, lying) recognition and the corresponding body elevation (during climbing stairs or when taking an elevator). Taking into account the trunk elevation changes during postural transitions (sit-to-stand, stand-to-sit), we devised an event-driven activity classifier based on fuzzy-logic. Data were acquired from 12 stroke patients with impaired mobility, using a trunk-worn inertial and BP sensor. Events, including walking and lying periods and potential postural transitions, were first extracted. These events were then fed into a double-stage hierarchical Fuzzy Inference System (H-FIS). The first stage processed the events to infer activities and the second stage improved activity recognition by applying behavioral constraints. Finally, the body elevation was estimated using a pattern-enhancing algorithm applied on BP. The patients were videotaped for reference. The performance of the algorithm was estimated using the Correct Classification Rate (CCR) and F-score. The BP-based classification approach was benchmarked against a previously-published fuzzy-logic classifier (FIS-IMU) and a conventional epoch-based classifier (EPOCH).

Results: The algorithm performance for posture/activity detection, in terms of CCR was 90.4 %, with 3.3 % and 5.6 % improvements against FIS-IMU and EPOCH, respectively. The proposed classifier essentially benefits from a better recognition of standing activity (70.3 % versus 61.5 % [FIS-IMU] and 42.5 % [EPOCH]) with 98.2 % CCR for body elevation estimation.

Conclusion: The monitoring and recognition of daily activities in mobility-impaired stoke patients can be significantly improved using a trunk-fixed sensor that integrates BP, inertial sensors, and an event-based activity classifier.

No MeSH data available.


Related in: MedlinePlus