Real-time Gait Pattern Classification Using Artificial Neural Networks

Robles, Diego Torrente; Benchekroun, Mouna; Lira, Andrea; Taramasco, Carla; Zalc, Vincent; Irazzoky, Igor; Istrate, Dan

doi:10.1109/metrolivenv54405.2022.9826927

Cited by 2 publications

(3 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such dataset, to the best of authors knowledge, is the first to feature a combination of normal and abnormal steps in one dataset. Other existing datasets focus on normal gait pattern, or have all steps abnormal in the dataset [34], [30], [31], [32]. Such steps, switching from normal to abnormal, could be seen in the real life scenario, especially on former patients who can experience bad step patterns when being tired or for other reasons.…”

Section: Discussionmentioning

confidence: 99%

“…Real-time algorithms, such as convolutional long short-term memory neural network (CLSTM-NN), heuristic and fast complementary filter (FCF) algorithms are widely studied for classification of gait terrain and walking modes, such as overground walking, stair ascend or descend and others [30], [31], [32]. Lastly, real-time gait trajectory prediction [33] and gait pattern classification for full steps are implemented using a convolutional neural network (CNN) [34].…”

mentioning

confidence: 99%

“…According to our previous study [35], SVM-based methods are the most widely used for automated gait analysis, followed by CNN. SVM's advantages include the capability to operate with relatively small datasets (10's to 100's of samples), and high computational efficiency [15], [36], whereas CNN tends to require larger datasets for good classification performance, for which the datasets have close to or more than 1000's of samples [34], [30]. However, there is a lack of research for analyzing how well machine learning methods, particularly SVM, perform in detecting real-time typical gait deviations caused by neurodegenerative diseases.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Novel Real-time In-step Gait Anomaly Detection Algorithms

Rostovski,

Krivošei,

Kuusik

et al. 2024

Preprint

View full text Add to dashboard Cite

Goal: Real-time abnormality detection in gait analysis is an open challenge. The existing state-of-the-art is limited by the fact that it does not take into account ’in-step’ anomaly detection. Timely detection of gait abnormalities during the mid-swing phase of the step (i.e., within 50ms detection time) is required to make informed gait correction. To meet this requirement and overcome state of the art limitations, we present real-time anomaly detection algorithms, a new dataset, and a framework to estimate performance of anomaly detection algorithms. Methods: We propose real-time in-step anomaly detection algorithms namely, i) real-time tslearn support vector machines anomaly detection (RTtsSVM-AD), ii) real-time one class support vector machines anomaly detection (RTOCSVMAD), and iii) signal shape tracking anomaly detection (SSTAD). For comparative assessment, twenty-two healthy volunteers realistically simulated eight different characteristic deviations in human gait of certain lower extremity disabilities. Motion patterns were recorded using an inertial motion unit (IMU) placed on the forefoot. F1 score, recall, precision, real-time factor (RTF), as well as ”earliness” measures are estimated and analyzed. The ”earliness” is a new metric which defines the time between the beginning of a step and the moment in time when the step is classified as abnormal. Results: The achieved results demonstrate that the proposed algorithms can detect gait abnormalities in real-time during the mid-swing phase of an ongoing step. The average accuracy and F1 score achieved by the three algorithms are: 91% and 81% for SST-AD; 74% and 54.9% for RTOCSVM-AD; and 64.5% and 49.2% for RTtsSVMAD, respectively. The best average earliness is achieved by the SST-AD algorithm at 0.4 second from the initial-swing phase start. Conclusion: Based on the results, SST-AD is the best suited algorithm for real-time gait anomaly detection and should be considered to be used in future embedded assistive devices.

show abstract

Section: Discussionmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Novel Real-time In-step Gait Anomaly Detection Algorithms

Rostovski,

Krivošei,

Kuusik

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

Real-Time Gait Anomaly Detection Using 1D-CNN and LSTM

Rostovski,

Ahmadilivani,

Krivošei

et al. 2024

Communications in Computer and Information Science

View full text Add to dashboard Cite

Anomaly detection and fall prevention represent one of the key research areas within gait analysis for patients suffering from neurological disorders. Deep Learning has penetrated into healthcare applications, encompassing disease diagnosis and anomaly prediction. Connected wearable medical sensors are emerging due to computationally expensive machine learning tasks, which traditionally require use of remote PC or cloud computing. However, to reduce needs for wireless communication channel throughput, for data processing latency, and increase service reliability and safety, on device machine learning is gaining attention. This paper presents an innovative approach that leverages one dimensional convolutional neural network (1D-CNN) and long-short term memory (LSTM) neural network for the real-time detection of abnormal gait patterns during the step. Real-time anomaly detection pertains to the algorithm’s ability to promptly detect true gait abnormality occurrence during the swing phase of an ongoing step.For the experiments, we have collected eight different common gait anomalies, simulated by 22 persons, using motion sensors containing multidimensional inertial measurement units (IMUs).Results have demonstrated that the proposed 1D-CNN-AD algorithm achieves an average accuracy of 95% and an average F1-score of 88% for all gait types and can run in true real-time. Average earliness for 1D-CNN-AD algorithm was 0.6 s, which is mid-swing phase of the step. Proposed LSTM-AD algorithm achieved average accuracy of 87% and average F1-score of 70% for all gait types.

show abstract

Real-time Gait Pattern Classification Using Artificial Neural Networks

Cited by 2 publications

References 29 publications

Novel Real-time In-step Gait Anomaly Detection Algorithms

Novel Real-time In-step Gait Anomaly Detection Algorithms

Real-Time Gait Anomaly Detection Using 1D-CNN and LSTM

Contact Info

Product

Resources

About