Linear Logistic Regression for Estimation of Lower Limb Muscle Activations

Sekiya, Masashi; Sakaino, Sho; Tsuji, Toshiaki

doi:10.1109/tnsre.2019.2898207

Cited by 20 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The participants in this study were 7 healthy males aged between 21 and 24 years. The sample size was determined according to previous studies [10]- [15]. This study was conducted in accordance with Article 16 of the Code of Ethics, which was reviewed and approved by the Ethics Committee on Research Involving Human Subjects at National University Corporation Saitama University.…”

Section: B Evaluation Contentsmentioning

confidence: 99%

See 1 more Smart Citation

Comparative Study of Foot Fixation Methods and Sensor Arrangements in Ankle Joint Torque Measurement Equipment

et al. 2022

Self Cite

View full text Add to dashboard Cite

Joint torque estimation techniques are used for evaluating human motor function. Particularly, ankle joint torque is essential for evaluating the walking function. Ankle joint torque can be derived by fixing the metatarsophalangeal (MTP) joint and ankle circumference and measuring force and torque from force sensors placed at the two fixation points. Considering implementation effort, it is desirable to use a 6-axis sensor or a sensor with fewer measurable axes. Therefore, in this study, we compared multiple sensor arrangements and calculation methods in the measurement of ankle joint torque. Through theoretical and empirical evaluations, the conditions under which these methods are effective were clarified. Based on the investigation, we propose a method to arrange a 6-axis force sensor only at the toe. One concern in the theoretical investigation was the error due to the moment caused by the fixation of the heel side. However, in measurement experiments using an ankle model and subjects, the accuracy was almost the same as when two 6-axis force sensors were used. The results indicates that the effect of this error factor is limited: hence, this method is considered to be useful as a method of both accuracy and sensor reduction.

show abstract

Section: B Evaluation Contentsmentioning

confidence: 99%

“…Specifically, methods such as hidden Markov models [8], support vector machines [9], [10], feedforward neural networks [11], and recurrent neural networks [12] are currently being utilized. Ankle torque can be estimated from the measurement data of a training device [13], and from measurements by force sensors [14], [15]. Siu et al…”

Section: Introductionmentioning

confidence: 99%

Comparative Study of Foot Fixation Methods and Sensor Arrangements in Ankle Joint Torque Measurement Equipment

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Estimation of muscular force is one of the ongoing research topics in the field of biomechanics with the aim of enhancing clinical decision making [ 4 , 12 , 13 ]. In force-based physiotherapy, feedback should always be taken from the muscular force to have a system with minimum possible error [ 14 ].…”

Section: Introductionmentioning

confidence: 99%

Muscle force estimation from lower limb EMG signals using novel optimised machine learning techniques

Mokri

Bamdad

Abolghasemi

2022

Med Biol Eng Comput

View full text Add to dashboard Cite

The main objective of this work is to establish a framework for processing and evaluating the lower limb electromyography (EMG) signals ready to be fed to a rehabilitation robot. We design and build a knee rehabilitation robot that works with surface EMG (sEMG) signals. In our device, the muscle forces are estimated from sEMG signals using several machine learning techniques, i.e. support vector machine (SVM), support vector regression (SVR) and random forest (RF). In order to improve the estimation accuracy, we devise genetic algorithm (GA) for parameter optimisation and feature extraction within the proposed methods. At the same time, a load cell and a wearable inertial measurement unit (IMU) are mounted on the robot to measure the muscle force and knee joint angle, respectively. Various performance measures have been employed to assess the performance of the proposed system. Our extensive experiments and comparison with related works revealed a high estimation accuracy of 98.67% for lower limb muscles. The main advantage of the proposed techniques is high estimation accuracy leading to improved performance of the therapy while muscle models become especially sensitive to the tendon stiffness and the slack length.

show abstract

“…Accurate modeling of respiratory system is very difficult and thus the response observed from such modeling is dubious [9][10][11][12]. Machine learning approach uses only data to analyze the system performance and therefore it gives accurate information about the system [13]. In this paper Logistic Regression algorithm is applied to distinguish different respiratory diseases by creating decision boundary.…”

Section: Introductionmentioning

confidence: 99%

System Modeling and Prediction of Respiratory Diseases using Machine Learning

Paul¹,

Naskar²,

Pal³

2022

YMER

View full text Add to dashboard Cite

In the first part of this paper a human respiratory model and their responses are presented and in the second part machine learning algorithm is used to predict the respiratory diseases from the datasets. This endeavor proposes a simple representation of the mathematical model of the human respiratory system comprises of nasal cavity, trachea, bronchi and alveolar sacs. Ranging from a very common disease called bronchitis to highly perilous diseases like emphysema are considered in this venture and the variation of responses are observed with input pressure. In the conventional computation and control the system modeling is very much essential for analysis, whereas, machine learning algorithms use computational methods to learn information directly from data without relying on a predetermined equation as a model. Logistic regression algorithm is applied to find natural patterns in respiratory data that generate insight and help to make better decision and prediction of respiratory diseases. The Logistic regression model makes a clear decision boundary between the respiratory diseases. Keywords: Bronchitis, Emphysema, Logistic regression, Mathematical model of the human respiratory system.

show abstract

Linear Logistic Regression for Estimation of Lower Limb Muscle Activations

Cited by 20 publications

References 23 publications

Comparative Study of Foot Fixation Methods and Sensor Arrangements in Ankle Joint Torque Measurement Equipment

Comparative Study of Foot Fixation Methods and Sensor Arrangements in Ankle Joint Torque Measurement Equipment

Muscle force estimation from lower limb EMG signals using novel optimised machine learning techniques

System Modeling and Prediction of Respiratory Diseases using Machine Learning

Contact Info

Product

Resources

About