Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach
This paper aims to summarise the studies on the human gait cycle analysis that applied an Artificial Intelligent Algorithm (AI) based on inertial sensor data, verifying whether it can support the clinical evaluation. This study focuses on the research on the main databases, particularly from the yea...
| id |
Kamaruzaman F.F.A.; Izhar C.A.A.; Fauzilan A.S.; Setumin S.; Hussain Z.; Abdullah M.F. |
|---|---|
| spelling |
Kamaruzaman F.F.A.; Izhar C.A.A.; Fauzilan A.S.; Setumin S.; Hussain Z.; Abdullah M.F. 2-s2.0-85136505986 Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach 2022 2021 6th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2021 10.1109/ICRAIE52900.2021.9703983 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136505986&doi=10.1109%2fICRAIE52900.2021.9703983&partnerID=40&md5=0c48a5e24d3bafaefa89f055a98ee12d This paper aims to summarise the studies on the human gait cycle analysis that applied an Artificial Intelligent Algorithm (AI) based on inertial sensor data, verifying whether it can support the clinical evaluation. This study focuses on the research on the main databases, particularly from the year 2015 to 2021. Fifteen studies were identified that have met the inclusion criteria. This paper also discussed the Machine Learning (ML) approach applied to classify and predict the gait cycle. The ML algorithm proposed are SVM, MC and ANN. Features such as swing and stance are the most selected features for healthy subjects, extracted from ground reaction force (GRF) during gait. © 2021 IEEE. Institute of Electrical and Electronics Engineers Inc. English Conference paper |
| author |
2-s2.0-85136505986 |
| spellingShingle |
2-s2.0-85136505986 Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| author_facet |
2-s2.0-85136505986 |
| author_sort |
2-s2.0-85136505986 |
| title |
Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| title_short |
Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| title_full |
Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| title_fullStr |
Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| title_full_unstemmed |
Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| title_sort |
Systematic Literature Review: Recognition of Human Gait Cycle Using Machine Learning Approach |
| publishDate |
2022 |
| container_title |
2021 6th IEEE International Conference on Recent Advances and Innovations in Engineering, ICRAIE 2021 |
| container_volume |
|
| container_issue |
|
| doi_str_mv |
10.1109/ICRAIE52900.2021.9703983 |
| url |
https://www.scopus.com/inward/record.uri?eid=2-s2.0-85136505986&doi=10.1109%2fICRAIE52900.2021.9703983&partnerID=40&md5=0c48a5e24d3bafaefa89f055a98ee12d |
| description |
This paper aims to summarise the studies on the human gait cycle analysis that applied an Artificial Intelligent Algorithm (AI) based on inertial sensor data, verifying whether it can support the clinical evaluation. This study focuses on the research on the main databases, particularly from the year 2015 to 2021. Fifteen studies were identified that have met the inclusion criteria. This paper also discussed the Machine Learning (ML) approach applied to classify and predict the gait cycle. The ML algorithm proposed are SVM, MC and ANN. Features such as swing and stance are the most selected features for healthy subjects, extracted from ground reaction force (GRF) during gait. © 2021 IEEE. |
| publisher |
Institute of Electrical and Electronics Engineers Inc. |
| issn |
|
| language |
English |
| format |
Conference paper |
| accesstype |
|
| record_format |
scopus |
| collection |
Scopus |
| _version_ |
1828987868283928576 |