Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease
Robust gait segmentation is the basis for mobile gait analysis. A range of methods have been applied and evaluated for gait segmentation of healthy and pathological gait bouts. However, a unified evaluation of gait segmentation methods in Parkinson’s disease (PD) is missing. In this paper, we compar...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2018-01-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/18/1/145 |
| _version_ | 1797999956763607040 |
|---|---|
| author | Nooshin Haji Ghassemi Julius Hannink Christine F. Martindale Heiko Gaßner Meinard Müller Jochen Klucken Björn M. Eskofier |
| author_facet | Nooshin Haji Ghassemi Julius Hannink Christine F. Martindale Heiko Gaßner Meinard Müller Jochen Klucken Björn M. Eskofier |
| author_sort | Nooshin Haji Ghassemi |
| collection | DOAJ |
| description | Robust gait segmentation is the basis for mobile gait analysis. A range of methods have been applied and evaluated for gait segmentation of healthy and pathological gait bouts. However, a unified evaluation of gait segmentation methods in Parkinson’s disease (PD) is missing. In this paper, we compare four prevalent gait segmentation methods in order to reveal their strengths and drawbacks in gait processing. We considered peak detection from event-based methods, two variations of dynamic time warping from template matching methods, and hierarchical hidden Markov models (hHMMs) from machine learning methods. To evaluate the methods, we included two supervised and instrumented gait tests that are widely used in the examination of Parkinsonian gait. In the first experiment, a sequence of strides from instructed straight walks was measured from 10 PD patients. In the second experiment, a more heterogeneous assessment paradigm was used from an additional 34 PD patients, including straight walks and turning strides as well as non-stride movements. The goal of the latter experiment was to evaluate the methods in challenging situations including turning strides and non-stride movements. Results showed no significant difference between the methods for the first scenario, in which all methods achieved an almost 100% accuracy in terms of F-score. Hence, we concluded that in the case of a predefined and homogeneous sequence of strides, all methods can be applied equally. However, in the second experiment the difference between methods became evident, with the hHMM obtaining a 96% F-score and significantly outperforming the other methods. The hHMM also proved promising in distinguishing between strides and non-stride movements, which is critical for clinical gait analysis. Our results indicate that both the instrumented test procedure and the required stride segmentation algorithm have to be selected adequately in order to support and complement classical clinical examination by sensor-based movement assessment. |
| first_indexed | 2024-04-11T11:12:44Z |
| format | Article |
| id | doaj.art-27a0043e0c394f03a58139effd5f7aa3 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T11:12:44Z |
| publishDate | 2018-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-27a0043e0c394f03a58139effd5f7aa32022-12-22T04:27:26ZengMDPI AGSensors1424-82202018-01-0118114510.3390/s18010145s18010145Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s DiseaseNooshin Haji Ghassemi0Julius Hannink1Christine F. Martindale2Heiko Gaßner3Meinard Müller4Jochen Klucken5Björn M. Eskofier6Machine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen 91058, GermanyMachine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen 91058, GermanyMachine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen 91058, GermanyDepartment of Molecular Neurology, University Hospital Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Schwabachanlage 6, Erlangen 91054, GermanyInternational Audio Laboratories Erlangen, Erlangen 91058, GermanyDepartment of Molecular Neurology, University Hospital Erlangen, Friedrich-Alexander University Erlangen-Nürnberg (FAU), Schwabachanlage 6, Erlangen 91054, GermanyMachine Learning and Data Analytics Lab, Department of Computer Science, Friedrich-Alexander-University Erlangen-Nürnberg (FAU), Martensstraße 3, Erlangen 91058, GermanyRobust gait segmentation is the basis for mobile gait analysis. A range of methods have been applied and evaluated for gait segmentation of healthy and pathological gait bouts. However, a unified evaluation of gait segmentation methods in Parkinson’s disease (PD) is missing. In this paper, we compare four prevalent gait segmentation methods in order to reveal their strengths and drawbacks in gait processing. We considered peak detection from event-based methods, two variations of dynamic time warping from template matching methods, and hierarchical hidden Markov models (hHMMs) from machine learning methods. To evaluate the methods, we included two supervised and instrumented gait tests that are widely used in the examination of Parkinsonian gait. In the first experiment, a sequence of strides from instructed straight walks was measured from 10 PD patients. In the second experiment, a more heterogeneous assessment paradigm was used from an additional 34 PD patients, including straight walks and turning strides as well as non-stride movements. The goal of the latter experiment was to evaluate the methods in challenging situations including turning strides and non-stride movements. Results showed no significant difference between the methods for the first scenario, in which all methods achieved an almost 100% accuracy in terms of F-score. Hence, we concluded that in the case of a predefined and homogeneous sequence of strides, all methods can be applied equally. However, in the second experiment the difference between methods became evident, with the hHMM obtaining a 96% F-score and significantly outperforming the other methods. The hHMM also proved promising in distinguishing between strides and non-stride movements, which is critical for clinical gait analysis. Our results indicate that both the instrumented test procedure and the required stride segmentation algorithm have to be selected adequately in order to support and complement classical clinical examination by sensor-based movement assessment.http://www.mdpi.com/1424-8220/18/1/145Parkinson’s diseasegait analysisinertial sensorsstep segmentationstride segmentationaccelerometergyroscope |
| spellingShingle | Nooshin Haji Ghassemi Julius Hannink Christine F. Martindale Heiko Gaßner Meinard Müller Jochen Klucken Björn M. Eskofier Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease Sensors Parkinson’s disease gait analysis inertial sensors step segmentation stride segmentation accelerometer gyroscope |
| title | Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease |
| title_full | Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease |
| title_fullStr | Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease |
| title_full_unstemmed | Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease |
| title_short | Segmentation of Gait Sequences in Sensor-Based Movement Analysis: A Comparison of Methods in Parkinson’s Disease |
| title_sort | segmentation of gait sequences in sensor based movement analysis a comparison of methods in parkinson s disease |
| topic | Parkinson’s disease gait analysis inertial sensors step segmentation stride segmentation accelerometer gyroscope |
| url | http://www.mdpi.com/1424-8220/18/1/145 |
| work_keys_str_mv | AT nooshinhajighassemi segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease AT juliushannink segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease AT christinefmartindale segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease AT heikogaßner segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease AT meinardmuller segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease AT jochenklucken segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease AT bjornmeskofier segmentationofgaitsequencesinsensorbasedmovementanalysisacomparisonofmethodsinparkinsonsdisease |