Measuring gait pattern in elderly individuals by using a plantar pressure measurement device

Nakajima, Kanako; Anzai, Emi; Iwakami, Yumi; Ino, Shuichi; Yamashita, K.; Ohta, Yoshihiro

doi:10.3233/thc-140856

“…They were connected to a 12-bit resolution data acquisition unit with a wireless data transmission sampling rate capacity of 100 Hz, allowing real-time recording during normal ambulatory activities. Insoles with a similar configuration have proven to be valid for the evaluation of posture and gait in previous studies (Saito et al, 2011;Nakajima et al, 2014;Anzai et al, 2020). Multiple pairs of the insole in different sizes were available.…”

Section: -Sensor Plantar Pressure Measurement Insolementioning

confidence: 99%

“…Nine daily life activities are considered. The smart-insole prototype used in the present study is equipped with the 7-sensor plantar pressure measurement insole, described elsewhere ( Saito et al, 2011 ; Nakajima et al, 2014 ). The data analysis is conducted using machine learning methods.…”

Section: Introductionmentioning

confidence: 99%

Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study

Ren

¹

,

Aubert-Kato

²

,

Anzai

³

et al. 2020

PeerJ

Self Cite

View full text Add to dashboard Cite

Background Wearable activity trackers are regarded as a new opportunity to deliver health promotion interventions. Indeed, while the prediction of active behaviors is currently primarily relying on the processing of accelerometer sensor data, the emergence of smart clothes with multi-sensing capacities is offering new possibilities. Algorithms able to process data from a variety of smart devices and classify daily life activities could therefore be of particular importance to achieve a more accurate evaluation of physical behaviors. This study aims to (1) develop an activity recognition algorithm based on the processing of plantar pressure information provided by a smart-shoe prototype and (2) to determine the optimal hardware and software configurations. Method Seventeen subjects wore a pair of smart-shoe prototypes composed of plantar pressure measurement insoles, and they performed the following nine activities: sitting, standing, walking on a flat surface, walking upstairs, walking downstairs, walking up a slope, running, cycling, and completing office work. The insole featured seven pressure sensors. For each activity, at least four minutes of plantar pressure data were collected. The plantar pressure data were cut in overlapping windows of different lengths and 167 features were extracted for each window. Data were split into training and test samples using a subject-wise assignment method. A random forest model was trained to recognize activity. The resulting activity recognition algorithms were evaluated on the test sample. A multi hold-out procedure allowed repeating the operation with 5 different assignments. The analytic conditions were modulated to test (1) different window lengths (1–60 seconds), (2) some selected sensor configurations and (3) different numbers of data features. Results A window length of 20 s was found to be optimum and therefore used for the rest of the analysis. Using all the sensors and all 167 features, the smart shoes predicted the activities with an average success of 89%. “Running” demonstrated the highest sensitivity (100%). “Walking up a slope” was linked with the lowest performance (63%), with the majority of the false negatives being “walking on a flat surface” and “walking upstairs.” Some 2- and 3-sensor configurations were linked with an average success rate of 87%. Reducing the number of features down to 20 does not alter significantly the performance of the algorithm. Conclusion High-performance human behavior recognition using plantar pressure data only is possible. In the future, smart-shoe devices could contribute to the evaluation of daily physical activities. Minimalist configurations integrating only a small number of sensors and computing a reduced number of selected features could maintain a satisfying performance. Future experiments must include a more heterogeneous population.

show abstract

“…They were connected to a 12-bit resolution data acquisition unit with a wireless data transmission sampling rate capacity of 100 Hz, allowing real-time recording during normal ambulatory activities. Insoles with a similar configuration have proven to be valid for the evaluation of posture and gait in previous studies (Saito et al, 2011;Nakajima et al, 2014;Anzai et al 2020). Multiple pairs of the insole in different sizes were available.…”

Section: -Sensor Plantar Pressure Measurement Insolementioning

confidence: 99%

Peer Review #1 of "Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study (v0.1)"

2020

0

View full text Add to dashboard Cite

Background: Wearable activity trackers are regarded as a new opportunity to deliver health promotion interventions. The algorithms typically contain two stages: 1) activity classification and 2) quantification of energy expenditures by applying activity-specific regression equations. Although the predictions of traditional activity trackers rely primarily on the processing of accelerometer sensor data, the emergence of smart clothes with multi-sensing capacities could contribute to a more accurate evaluation of daily physical behaviors. This study aims to 1) develop an activity recognition algorithm based on the processing of plantar pressure information provided by a smart-shoe prototype and 2) to determine the optimal hardware and software configurations. Method: Seventeen subjects wore a pair of smart-shoe prototypes composed of plantar pressure measurement insoles, and they performed the following nine activities: sitting, standing, walking on a flat surface, walking upstairs, walking downstairs, walking up a slope, running, cycling, and completing office work. The insole featured seven pressure sensors. For each activity, four minutes of plantar pressure data were collected. The plantar pressure data were cut in overlapping windows of different lengths and 167 features were extracted for each window. A random forest model was trained to recognize activity using some selected sensor configurations and different numbers of data features. The resulting activity recognition algorithms were evaluated using data samples specifically directed to validation trials. Results: Using all the sensors and all 167 features, the smart shoes predicted the activities with an average success of 89%. "Running" demonstrated the highest percentage of good predictions (100%). "Walking up a slope" was linked with the lowest performance (63%), with the majority of the false positives being "walking on a flat surface" and "walking upstairs." Some 2-and 3-sensor configurations were linked with an

show abstract

“…Nine daily life activities are considered. The smart-insole prototype used in the present study is equipped with the 7-sensor plantar pressure measurement insole, described elsewhere (Saito et al, 2011;Nakajima et al, 2014). The data analysis is conducted using machine learning methods.…”

Section: Introductionmentioning

confidence: 99%

Peer Review #2 of "Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study (v0.1)"

2020

0

View full text Add to dashboard Cite

Background: Wearable activity trackers are regarded as a new opportunity to deliver health promotion interventions. The algorithms typically contain two stages: 1) activity classification and 2) quantification of energy expenditures by applying activity-specific regression equations. Although the predictions of traditional activity trackers rely primarily on the processing of accelerometer sensor data, the emergence of smart clothes with multi-sensing capacities could contribute to a more accurate evaluation of daily physical behaviors. This study aims to 1) develop an activity recognition algorithm based on the processing of plantar pressure information provided by a smart-shoe prototype and 2) to determine the optimal hardware and software configurations. Method: Seventeen subjects wore a pair of smart-shoe prototypes composed of plantar pressure measurement insoles, and they performed the following nine activities: sitting, standing, walking on a flat surface, walking upstairs, walking downstairs, walking up a slope, running, cycling, and completing office work. The insole featured seven pressure sensors. For each activity, four minutes of plantar pressure data were collected. The plantar pressure data were cut in overlapping windows of different lengths and 167 features were extracted for each window. A random forest model was trained to recognize activity using some selected sensor configurations and different numbers of data features. The resulting activity recognition algorithms were evaluated using data samples specifically directed to validation trials. Results: Using all the sensors and all 167 features, the smart shoes predicted the activities with an average success of 89%. "Running" demonstrated the highest percentage of good predictions (100%). "Walking up a slope" was linked with the lowest performance (63%), with the majority of the false positives being "walking on a flat surface" and "walking upstairs." Some 2-and 3-sensor configurations were linked with an

show abstract

Measuring gait pattern in elderly individuals by using a plantar pressure measurement device

Cited by 15 publications

References 28 publications

Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study

Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study

Peer Review #1 of "Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study (v0.1)"

Peer Review #2 of "Random forest algorithms for recognizing daily life activities using plantar pressure information: a smart-shoe study (v0.1)"

Contact Info

Product

Resources

About