Deep neural networks for human’s fall-risk prediction using force-plate time series signal

Savadkoohi, Marzieh; Oladunni, Timothy; Thompson, Lara

doi:10.1016/j.eswa.2021.115220

Cited by 36 publications

(19 citation statements)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the forecast data and curve fitting results, the annual patent application volume has been rising continuously since 2021, reaching the inflection point, and has been declining since then; The patent level has been declining since 2021; The technical strength has increased year by year since 2021, which is consistent with the trend of the number of patent applications, and the accuracy of the prediction is verified. The prediction results of the above three characteristics are in line with the trend from maturity to recession in the standard curve model [8][9][10].…”

Section: Prediction Resultssupporting

confidence: 64%

Application of technology maturity assessment and achievement selection based on LSTM time series prediction

Du,

Chen,

2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

Section: Prediction Resultssupporting

confidence: 64%

Application of technology maturity assessment and achievement selection based on LSTM time series prediction

Du,

Chen,

2023

International Conference on Algorithms, High Performance Computing, and Artificial Intelligence (AHPCAI 2023)

View full text Add to dashboard Cite

“…With the recent advancement in neural networks, deep learning started to play a dynamic role in assessing the risk of fall. In 2021, Savadkoohi et al [ 66 ] proposed a one-dimensional convolutional Neural network (CNN) trained in posturographic trajectories to predict the outcomes from a questionnaire about the fear of falling (the Falls Efficacy Scale (FES) score). FES was separated into three groups (low, moderate, and high fear of falling).…”

Section: Methodological Approach and Resultsmentioning

confidence: 99%

Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

et al. 2022

View full text Add to dashboard Cite

Nowadays, it becomes of paramount societal importance to support many frail-prone groups in our society (elderly, patients with neurodegenerative diseases, etc.) to remain socially and physically active, maintain their quality of life, and avoid their loss of autonomy. Once older people enter the prefrail stage, they are already likely to experience falls whose consequences may accelerate the deterioration of their quality of life (injuries, fear of falling, reduction of physical activity). In that context, detecting frailty and high risk of fall at an early stage is the first line of defense against the detrimental consequences of fall. The second line of defense would be to develop original protocols to detect future fallers before any fall occur. This paper briefly summarizes the current advancements and perspectives that may arise from the combination of affordable and easy-to-use non-wearable systems (force platforms, 3D tracking motion systems), wearable systems (accelerometers, gyroscopes, inertial measurement units-IMUs) with appropriate machine learning analytics, as well as the efforts to address these challenges.

show abstract

“…BP neural network, as a multilayer feedforward neuron network with one-way propagation, generally consists of an input layer, an intermediate layer, and an output layer, and each layer is connected in sequence. Each layer consists of several artificial neurons, and all the neurons in each layer are completely connected, but there is no connection among the neurons in the same layer, and the output of the neurons in the previous layer is used as the input of the neurons in the next layer [ 19 ]. Therefore, when the input sample, the connection weight ω ij between the input layer and the middle layer, and the threshold θ j of each unit in the middle layer calculate the input s j of each unit in the middle layer, then the transfer function can calculate the output b j .…”

Section: Methodsmentioning

confidence: 99%

Prediction Model of International Trade Risk Based on Stochastic Time-Series Neural Network

Gui-cai

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

With the extreme deterioration of domestic and foreign trade environment, international competition is becoming increasingly fierce. At the same time, many enterprises have loopholes in industrial structure and finance, resulting in many risks in their international trade. Therefore, we must take corresponding measures to effectively manage and avoid risks and realize the healthy and sustainable development of foreign trade enterprises and enterprise economy. This paper designs and proposes a risk prediction model combining ARIMA and BP neural network. The model can get good prediction in different time series and effectively avoid the risk. The model proposed in this paper optimizes the structure of the design model with the support of ARIMA algorithm and BP neural network algorithm and has good accuracy and error control for different time series. The purpose of establishing time series prediction model is to improve the prediction accuracy of the model, and it is also an effective way to enhance the practicability of the prediction model. Applying intersequence analysis method to financial risk prediction can greatly improve efficiency and save cost and has broad application prospects.

show abstract

Deep neural networks for human’s fall-risk prediction using force-plate time series signal

Cited by 36 publications

References 51 publications

Application of technology maturity assessment and achievement selection based on LSTM time series prediction

Application of technology maturity assessment and achievement selection based on LSTM time series prediction

Preventing falls: the use of machine learning for the prediction of future falls in individuals without history of fall

Prediction Model of International Trade Risk Based on Stochastic Time-Series Neural Network

Contact Info

Product

Resources

About