A Rapid Detection of Parkinson’s Disease using Smart Insoles: A Statistical and Machine Learning Approach

D'Arco, Luigi; Wang, Haiying; Zheng, Huiru

doi:10.1109/bibm55620.2022.9995237

Cited by 5 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Preceding its input into the FSM, the data from smart insoles were comprehensively preprocessed involving sensor aggregation, noise reduction, and data normalisation. Analysing the pressure sensors data, utilising Pearson's correlation coefficient (r), revealed a strong correlation (r > 0.5) among pressure sensors situated within the same foot zone, aligning with findings from prior research 31 . Consequently, a magnitude calculation was employed to combine pressure sensors within the back, middle, and front zones.…”

Section: Extraction Of Gait Phasessupporting

confidence: 79%

“…The proposed approach leverages the use of the pressure sensors of the smart insoles by using a FSM for the identification of the different states of the gait cycles. This approach has been proven efficient and powerful in a previous study where the goal was the identification of a limited number of gait sub-phases in both healthy and PD individuals 28 . However, in this study, a profound transformation has been employed to improve the number of recognisable gait phases and to best fit the data collected during the use of the exoskeleton.…”

Section: Extraction Of Gait Phasesmentioning

confidence: 99%

See 1 more Smart Citation

Integration of Smart Insoles for Gait Assessment in Exoskeleton-assisted Rehabilitation

D'Arco,

Wang,

Zheng

2024

Preprint

View full text Add to dashboard Cite

A robotic exoskeleton enables individuals with limited or no mobility to engage in moderate exercises, promoting physical fitness and overall well-being. Exoskeletons, however, do not provide insights into gait patterns monitoring and analysis over time. This study proposes the integration of smart insoles as a cost-effective and non-invasive assistant for gait assessment in exoskeleton-assisted rehabilitation. The study, spanning 12 weeks, comprised three assessment sessions involving a total of 10 participants, including three healthy individuals, one stroke, one spinal cord injury, one traumatic brain injury, and four multiple sclerosis subjects. Gait phases were identified using a Finite State Machine with transitions guided by the predictions of a fuzzy c-means clustering algorithm. Kinematic and kinetic analyses highlighted disparities in stride time, cadence, stance time, and the trajectories of the centre of pressure. Despite these differences, individuals with multiple sclerosis showed no statistical differences from healthy subjects, underscoring the influence of the exoskeleton even in the absence of lower limb power. An analysis of acceptability demonstrated that participants found the smart insoles comfortable and expressed a willingness to employ them for future rehabilitation purposes. In conclusion, smart insoles can provide additional insights about users' gait compared to exoskeletons alone, allowing the progress of individuals involved in rehabilitation to be assessed over time, and helping clinicians to develop tailored rehabilitation plans.

show abstract

Section: Extraction Of Gait Phasessupporting

confidence: 79%

Section: Extraction Of Gait Phasesmentioning

confidence: 99%

Integration of Smart Insoles for Gait Assessment in Exoskeleton-assisted Rehabilitation

D'Arco,

Wang,

Zheng

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…In our previous study [30], an artificial neural network (ANN) was implemented for the recognition of ambulation activities. Three volunteers were involved in the study and were asked to wear a pair of smart insoles and complete a series of activities from a predefined set, including downstairs, sit to stand, sitting, standing, upstairs, and walking (slow, normal, and fast).…”

Section: Related Workmentioning

confidence: 99%

DeepHAR: a deep feed-forward neural network algorithm for smart insole-based human activity recognition

D'Arco

Wang

Zheng

2023

Neural Comput & Applic

View full text Add to dashboard Cite

Health monitoring, rehabilitation, and fitness are just a few domains where human activity recognition can be applied. In this study, a deep learning approach has been proposed to recognise ambulation and fitness activities from data collected by five participants using smart insoles. Smart insoles, consisting of pressure and inertial sensors, allowed for seamless data collection while minimising user discomfort, laying the baseline for the development of a monitoring and/or rehabilitation system for everyday life. The key objective has been to enhance the deep learning model performance through several techniques, including data segmentation with overlapping technique (2 s with 50% overlap), signal down-sampling by averaging contiguous samples, and a cost-sensitive re-weighting strategy for the loss function for handling the imbalanced dataset. The proposed solution achieved an Accuracy and F1-Score of 98.56% and 98.57%, respectively. The Sitting activities obtained the highest degree of recognition, closely followed by the Spinning Bike class, but fitness activities were recognised at a higher rate than ambulation activities. A comparative analysis was carried out both to determine the impact that pre-processing had on the proposed core architecture and to compare the proposed solution with existing state-of-the-art solutions. The results, in addition to demonstrating how deep learning solutions outperformed those of shallow machine learning, showed that in our solution the use of data pre-processing increased performance by about 2%, optimising the handling of the imbalanced dataset and allowing a relatively simple network to outperform more complex networks, reducing the computational impact required for such applications.

show abstract

U2FSM: Unsupervised Square Finite State Machine for Gait Events Estimation from Instrumented Insoles

D’Arco,

Wang,

Zheng

2024

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

A Rapid Detection of Parkinson’s Disease using Smart Insoles: A Statistical and Machine Learning Approach

Cited by 5 publications

References 28 publications

Integration of Smart Insoles for Gait Assessment in Exoskeleton-assisted Rehabilitation

Integration of Smart Insoles for Gait Assessment in Exoskeleton-assisted Rehabilitation

DeepHAR: a deep feed-forward neural network algorithm for smart insole-based human activity recognition

U2FSM: Unsupervised Square Finite State Machine for Gait Events Estimation from Instrumented Insoles

Contact Info

Product

Resources

About