Abnormal Gait Recognition Algorithm Based on LSTM-CNN Fusion Network

Gao, Jing; Gu, Pei Shang; Ren, Qing; Zhang, Jinde; Song, Xin

doi:10.1109/access.2019.2950254

Cited by 58 publications

(25 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…With deep neural networks, the amount of data for training is the leading factor for obtaining high accuracy. However, despite reporting high accuracies in the order of more than 90%, existing studies [22,25], confirmed that lack of enough training data hinders the algorithm results.…”

Section: Resultsmentioning

confidence: 98%

“…To make positioning of this work in gait recognition studies clear, we recall some basic definitions. Gait recognition could refer to distinguishing between normal and pathological gait [25,26], pathological gaits, evaluation of the gait efficiency, or identifying an individual by gait [4,5]. The latter subdivides into identification, verification, and authentication [4,27].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Identity Recognition by Walking Outdoors Using Multimodal Sensor Insoles

et al. 2020

View full text Add to dashboard Cite

Recently, gait attracts attention as a practical biometric for devices that naturally possess walking pattern sensing. In the present study, we explored the feasibility of using a multimodal smart insole for identity recognition. We used sensor insoles designed and implemented by us to collect kinetic and kinematic data from 59 participants that walked outdoors. Then, we evaluated the performance of four neural network architectures, which are a baseline convolutional neural network (CNN), a CNN with a multi-stage feature extractor, a CNN with an extreme learning machine classifier using sensor-level fusion and CNN with extreme learning machine classifier using feature-level fusion. The networks were trained with segmented insole data using 0%, 50%, and 70% segmentation overlap, respectively. For 70% segmentation overlap and both-side data, we obtained mean accuracies of 72.8% ±0.038, 80.9% ±0.036, 80.1% ±0.021 and 93.3% ±0.009, for the four networks, respectively. The results suggest that multimodal sensor-enabled footwear could serve biometric purposes in the next generation of body sensor networks.

show abstract

Section: Resultsmentioning

confidence: 98%

Section: Introductionmentioning

confidence: 99%

Identity Recognition by Walking Outdoors Using Multimodal Sensor Insoles

et al. 2020

View full text Add to dashboard Cite

show abstract

“…It is capable of learning the characteristics of complex data faster than other RNN models [17]. Further, this technique has been employed for gait analysis and has become popular among scientists in recent studies [18][19][20].…”

Section: Feature Labelingmentioning

confidence: 99%

Gait Phase Estimation by Using LSTM in IMU-Based Gait Analysis—Proof of Concept

Sarshar

Polturi

Schega

2021

Sensors

View full text Add to dashboard Cite

Gait phase detection in IMU-based gait analysis has some limitations due to walking style variations and physical impairments of individuals. Therefore, available algorithms may not work properly when the gait data is noisy, or the person rarely reaches a steady state of walking. The aim of this work was to employ Artificial Intelligence (AI), specifically a long short-term memory (LSTM) algorithm, to overcome these weaknesses. Three supervised LSTM-based models were designed to estimate the expected gait phases, including foot-off (FO), mid-swing (MidS) and foot-contact (FC). For collecting gait data two tri-axial inertial sensors were located above each ankle. The angular velocity magnitude, rotation matrix magnitude and free acceleration magnitude were captured for data labeling and turning detection and to strengthen the model, respectively. To do so, a train dataset based on a novel movement protocol was acquired. A validation dataset similar to a train dataset was generated as well. Five test datasets from already existing data were also created to independently evaluate the models. After testing the models on validation and test datasets, all three models demonstrated promising performance in estimating desired gait phases. The proposed approach proves the possibility of employing AI-based algorithms to predict labeled gait phases from a time series of gait data.

show abstract

“…This limits the usability of IMU-based methods in clinical gait analysis. Similarly, Jing Gao et al [28] proposed an IMU-based abnormal gait recognition algorithm. Their algorithm uses a long shortterm memory network and convolutional neural network for detecting tiptoe, hemiplegic, and cross-threshold gait abnormal gait.…”

Section: A Literature Reviewmentioning

confidence: 99%

A-GAS: a Probabilistic Approach for Generating Automated Gait Assessment Score for Cerebral Palsy Children

Bajpai¹,

Joshi²

2021

Preprint

View full text Add to dashboard Cite

Gait disorders in children with cerebral palsy (CP) affect their mental, physical, economic, and social lives. Gait assessment is one of the essential steps of gait management. It has been widely used for clinical decision making and evaluation of different treatment outcomes. However, most of the present methods of gait assessment are subjective, less sensitive to small pathological changes, time-taking and need a great effort of an expert. This study proposes an automated, comprehensive gait assessment score (A-GAS) for gait disorders in CP. Kinematic data of 356 CP and 41 typically developing subjects is used to validate the performance of A-GAS. For the computation of A-GAS, instance abnormality index (AII) and abnormality index (AI) are computed. AII quantifies gait abnormality of a gait cycle instance, while AI quantifies gait abnormality of a joint angle profile. AII is calculated for all gait cycle instances by performing probabilistically and statistical tests. Abnormality index (AI) is a weighted sum of AII, computed for each joint angle profile. A-GAS is a weighted sum of AI, calculated for a lower limb. Moreover, a graphical representation of the gait assessment report, including AII, AI, and A-GAS is generated to understand the results better. Furthermore, the study compares A-GAS with a present rating-based gait assessment scores to understand fundamental differences between them. Finally, AGAS’s performance is verified for a high-cost multicamera set-up using nine joint angle profiles and a low-cost single camera set-up using three joint angle profiles. Results show no significant differences in performance of A-GAS for both the set-ups. Therefore, A-GAS for both the set-ups can be used interchangeably.

show abstract

Abnormal Gait Recognition Algorithm Based on LSTM-CNN Fusion Network

Cited by 58 publications

References 24 publications

Identity Recognition by Walking Outdoors Using Multimodal Sensor Insoles

Identity Recognition by Walking Outdoors Using Multimodal Sensor Insoles

Gait Phase Estimation by Using LSTM in IMU-Based Gait Analysis—Proof of Concept

A-GAS: a Probabilistic Approach for Generating Automated Gait Assessment Score for Cerebral Palsy Children

Contact Info

Product

Resources

About