Limits...
Auto detection and segmentation of physical activities during a Timed-Up-and-Go (TUG) task in healthy older adults using multiple inertial sensors.

Nguyen HP, Ayachi F, Lavigne-Pelletier C, Blamoutier M, Rahimi F, Boissy P, Jog M, Duval C - J Neuroeng Rehabil (2015)

Bottom Line: Segmentation time stamps were compared to results from two examiners visually segmenting the activities of the TUG.We were able to detect these activities in a TUG with 100% sensitivity and specificity (n = 192) during the 10 meter TUG.When applying the segmentation algorithms to the 10 meter TUG, we were able to parse 100% of the transition points (n = 224) between different segments that were as reliable and less variable than visual segmentation performed by two independent examiners.

View Article: PubMed Central - PubMed

Affiliation: Département de Kinanthropologie, Université du Québec à Montréal, C.P. 8888, succursale Centre-Ville, Montréal, H3C 3P8, Québec, Canada. hpnguyen@utexas.edu.

ABSTRACT

Background: Recently, much attention has been given to the use of inertial sensors for remote monitoring of individuals with limited mobility. However, the focus has been mostly on the detection of symptoms, not specific activities. The objective of the present study was to develop an automated recognition and segmentation algorithm based on inertial sensor data to identify common gross motor patterns during activity of daily living.

Method: A modified Time-Up-And-Go (TUG) task was used since it is comprised of four common daily living activities; Standing, Walking, Turning, and Sitting, all performed in a continuous fashion resulting in six different segments during the task. Sixteen healthy older adults performed two trials of a 5 and 10 meter TUG task. They were outfitted with 17 inertial motion sensors covering each body segment. Data from the 10 meter TUG were used to identify pertinent sensors on the trunk, head, hip, knee, and thigh that provided suitable data for detecting and segmenting activities associated with the TUG. Raw data from sensors were detrended to remove sensor drift, normalized, and band pass filtered with optimal frequencies to reveal kinematic peaks that corresponded to different activities. Segmentation was accomplished by identifying the time stamps of the first minimum or maximum to the right and the left of these peaks. Segmentation time stamps were compared to results from two examiners visually segmenting the activities of the TUG.

Results: We were able to detect these activities in a TUG with 100% sensitivity and specificity (n = 192) during the 10 meter TUG. The rate of success was subsequently confirmed in the 5 meter TUG (n = 192) without altering the parameters of the algorithm. When applying the segmentation algorithms to the 10 meter TUG, we were able to parse 100% of the transition points (n = 224) between different segments that were as reliable and less variable than visual segmentation performed by two independent examiners.

Conclusions: The present study lays the foundation for the development of a comprehensive algorithm to detect and segment naturalistic activities using inertial sensors, in hope of evaluating automatically motor performance within the detected tasks.

No MeSH data available.


Related in: MedlinePlus

Flow chart of the detection algorithm use to identify the scripted activities during a TUG. These sensors were normalized and detrended for uniformity across all participants. The high cut frequencies of the band pass filter were determined by optimizing the difference between the transition time using the inertial sensors and by visual inspection. TMax or TMin denotes the large peaks that correspond to different activities while tmin or tmax represents the first minimum or maximum to the left or right of TMax or TMin.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
getmorefigures.php?uid=PMC4403848&req=5

Fig3: Flow chart of the detection algorithm use to identify the scripted activities during a TUG. These sensors were normalized and detrended for uniformity across all participants. The high cut frequencies of the band pass filter were determined by optimizing the difference between the transition time using the inertial sensors and by visual inspection. TMax or TMin denotes the large peaks that correspond to different activities while tmin or tmax represents the first minimum or maximum to the left or right of TMax or TMin.

Mentions: The sensors selected for activity detection were based on how they corresponded to the biomechanics of movement during the performance of these activities. Standing which denotes when participants stand up from the chair was detected using the acceleration of the trunk (az, Trunk). Sitting which denotes when participants sit down on the chair was also detected using the same sensor data. Sensors on the trunk or chest have been used to identify Standing and Sitting during physical activities [4]. However, in this study, the time derivative of the acceleration of the thigh was also used to differentiate between Standing and Sitting. During Standing, and during Sitting, . The angular velocity (ωy, Trunk) of the trunk was used to detect Turning. The angular velocity of the head (ωy, Head) was also used to verify that Turning has occurred and the direction of Turning. Walking was detected by using a 500-millisecond window to detect the oscillation in the angular velocity (ωx, Hip) of the hip. Walking was also detected during Turning; however priority was given to classify this as Turning. The detections of Standing, Turning, Sitting, and Walking are shown in Figure 2. The activities were detected by finding the maximal or minimal peaks of the selected sensors that corresponded to different activities. The square signals were generated by setting the threshold at 30% of peak amplitude to provide visual indication that an event was detected. The algorithm and sensors used to detect the activities during a TUG are shown in Figure 3.Figure 2


Auto detection and segmentation of physical activities during a Timed-Up-and-Go (TUG) task in healthy older adults using multiple inertial sensors.

Nguyen HP, Ayachi F, Lavigne-Pelletier C, Blamoutier M, Rahimi F, Boissy P, Jog M, Duval C - J Neuroeng Rehabil (2015)

Flow chart of the detection algorithm use to identify the scripted activities during a TUG. These sensors were normalized and detrended for uniformity across all participants. The high cut frequencies of the band pass filter were determined by optimizing the difference between the transition time using the inertial sensors and by visual inspection. TMax or TMin denotes the large peaks that correspond to different activities while tmin or tmax represents the first minimum or maximum to the left or right of TMax or TMin.
© Copyright Policy - open-access
Related In: Results  -  Collection

License 1 - License 2
Show All Figures
getmorefigures.php?uid=PMC4403848&req=5

Fig3: Flow chart of the detection algorithm use to identify the scripted activities during a TUG. These sensors were normalized and detrended for uniformity across all participants. The high cut frequencies of the band pass filter were determined by optimizing the difference between the transition time using the inertial sensors and by visual inspection. TMax or TMin denotes the large peaks that correspond to different activities while tmin or tmax represents the first minimum or maximum to the left or right of TMax or TMin.
Mentions: The sensors selected for activity detection were based on how they corresponded to the biomechanics of movement during the performance of these activities. Standing which denotes when participants stand up from the chair was detected using the acceleration of the trunk (az, Trunk). Sitting which denotes when participants sit down on the chair was also detected using the same sensor data. Sensors on the trunk or chest have been used to identify Standing and Sitting during physical activities [4]. However, in this study, the time derivative of the acceleration of the thigh was also used to differentiate between Standing and Sitting. During Standing, and during Sitting, . The angular velocity (ωy, Trunk) of the trunk was used to detect Turning. The angular velocity of the head (ωy, Head) was also used to verify that Turning has occurred and the direction of Turning. Walking was detected by using a 500-millisecond window to detect the oscillation in the angular velocity (ωx, Hip) of the hip. Walking was also detected during Turning; however priority was given to classify this as Turning. The detections of Standing, Turning, Sitting, and Walking are shown in Figure 2. The activities were detected by finding the maximal or minimal peaks of the selected sensors that corresponded to different activities. The square signals were generated by setting the threshold at 30% of peak amplitude to provide visual indication that an event was detected. The algorithm and sensors used to detect the activities during a TUG are shown in Figure 3.Figure 2

Bottom Line: Segmentation time stamps were compared to results from two examiners visually segmenting the activities of the TUG.We were able to detect these activities in a TUG with 100% sensitivity and specificity (n = 192) during the 10 meter TUG.When applying the segmentation algorithms to the 10 meter TUG, we were able to parse 100% of the transition points (n = 224) between different segments that were as reliable and less variable than visual segmentation performed by two independent examiners.

View Article: PubMed Central - PubMed

Affiliation: Département de Kinanthropologie, Université du Québec à Montréal, C.P. 8888, succursale Centre-Ville, Montréal, H3C 3P8, Québec, Canada. hpnguyen@utexas.edu.

ABSTRACT

Background: Recently, much attention has been given to the use of inertial sensors for remote monitoring of individuals with limited mobility. However, the focus has been mostly on the detection of symptoms, not specific activities. The objective of the present study was to develop an automated recognition and segmentation algorithm based on inertial sensor data to identify common gross motor patterns during activity of daily living.

Method: A modified Time-Up-And-Go (TUG) task was used since it is comprised of four common daily living activities; Standing, Walking, Turning, and Sitting, all performed in a continuous fashion resulting in six different segments during the task. Sixteen healthy older adults performed two trials of a 5 and 10 meter TUG task. They were outfitted with 17 inertial motion sensors covering each body segment. Data from the 10 meter TUG were used to identify pertinent sensors on the trunk, head, hip, knee, and thigh that provided suitable data for detecting and segmenting activities associated with the TUG. Raw data from sensors were detrended to remove sensor drift, normalized, and band pass filtered with optimal frequencies to reveal kinematic peaks that corresponded to different activities. Segmentation was accomplished by identifying the time stamps of the first minimum or maximum to the right and the left of these peaks. Segmentation time stamps were compared to results from two examiners visually segmenting the activities of the TUG.

Results: We were able to detect these activities in a TUG with 100% sensitivity and specificity (n = 192) during the 10 meter TUG. The rate of success was subsequently confirmed in the 5 meter TUG (n = 192) without altering the parameters of the algorithm. When applying the segmentation algorithms to the 10 meter TUG, we were able to parse 100% of the transition points (n = 224) between different segments that were as reliable and less variable than visual segmentation performed by two independent examiners.

Conclusions: The present study lays the foundation for the development of a comprehensive algorithm to detect and segment naturalistic activities using inertial sensors, in hope of evaluating automatically motor performance within the detected tasks.

No MeSH data available.


Related in: MedlinePlus