Using LSTM for Automatic Classification of Human Motion Capture Data

Silva, Rogério Eduardo da; Ondřej, Jan; Smolić, Aljoša

doi:10.5220/0007349902360243

Cited by 4 publications

(1 citation statement)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, some studies are using ML models [27][28][29] and DL in human action recognition [5,30,31]. However, these studies only focus on developing RNN and Long Short Term Memory (LSTM) models to predict but do not care about the characteristics of the object and extraction feature methods …”

Section: Evaluation Of Resultsmentioning

confidence: 99%

Human action recognition method based on conformal geometric algebra and recurrent neural network

Nguyen

Pham

Hao

et al. 2020

ICS

View full text Add to dashboard Cite

Deep Learning (DL) plays an important role in machine learning and artificial intelligence. DL is widely applied in many fields with high dimensional data, including natural language processing, image recognition. High dimensional data can lead to problems in machine learning such as overfitting, degradation of accuracy. To address these issues, some methods, such as Principal Components Analysis (PCA), principal component regression (PCR), Multi-class Linear Discriminant Analysis (MLDA), were proposed to reduce dimensions of the data and computational complexity simultaneously. The drawback of these methods is that they only work well on data distributed on the plane. In the case of the data distributed on the hyper-sphere, such as objects moving in space, the processing results are not so good as expected. In this paper, we propose the use of Conformal Geometric Algebra (CGA) to extract features and simultaneously reduce the dimensionality of a dataset for human activity recognition using Recurrent Neural Network (RNN). First, human activity data in a 3-dimensional coordinate system is pre-processed and normalized by calculating deviations from the mean coordinate. Next, the data is transformed to vectors in CGA space and its dimensions are reduced to return the feature vectors. Finally, we use the RNN model to train feature vectors. Empirical results performed on the CMU eight actions dataset show that the CGA combined with RNN gave the best test results of 92.5%.

show abstract

Section: Evaluation Of Resultsmentioning

confidence: 99%

Human action recognition method based on conformal geometric algebra and recurrent neural network

Nguyen

Pham

Hao

et al. 2020

ICS

View full text Add to dashboard Cite

show abstract

A motion recognition technique based on linear matrix representation to improve Parkinson’s disease treatments

Moreau

Durand²,

Bosche³

et al. 2021

2021 9th International Conference on Systems and Control (ICSC)

View full text Add to dashboard Cite

Mapping Surgeons Hand/Finger Movements to Surgical Tool Motion During Conventional Microsurgery Using Machine Learning

Sani

Ascione

Dogramadzi

2021

J. Med. Robot. Res.

View full text Add to dashboard Cite

Purpose: Recent developments in robotics and artificial intelligence (AI) have led to significant advances in healthcare technologies enhancing robot-assisted minimally invasive surgery (RAMIS) in some surgical specialties. However, current human–robot interfaces lack intuitive teleoperation and cannot mimic surgeon’s hand/finger sensing required for fine motion micro-surgeries. These limitations make teleoperated robotic surgery not less suitable for, e.g. cardiac surgery and it can be difficult to learn for established surgeons. We report a pilot study showing an intuitive way of recording and mapping surgeon’s gross hand motion and the fine synergic motion during cardiac micro-surgery as a way to enhance future intuitive teleoperation. Methods: We set to develop a prototype system able to train a Deep Neural Network (DNN) by mapping wrist, hand and surgical tool real-time data acquisition (RTDA) inputs during mock-up heart micro-surgery procedures. The trained network was used to estimate the tools poses from refined hand joint angles. Outputs of the network were surgical tool orientation and jaw angle acquired by an optical motion capture system. Results: Based on surgeon’s feedback during mock micro-surgery, the developed wearable system with light-weight sensors for motion tracking did not interfere with the surgery and instrument handling. The wearable motion tracking system used 12 finger/thumb/wrist joint angle sensors to generate meaningful datasets representing inputs of the DNN network with new hand joint angles added as necessary based on comparing the estimated tool poses against measured tool pose. The DNN architecture was optimized for the highest estimation accuracy and the ability to determine the tool pose with the least mean squared error. This novel approach showed that the surgical instrument’s pose, an essential requirement for teleoperation, can be accurately estimated from recorded surgeon’s hand/finger movements with a mean squared error (MSE) less than 0.3%. Conclusion: We have developed a system to capture fine movements of the surgeon’s hand during micro-surgery that could enhance future remote teleoperation of similar surgical tools during micro-surgery. More work is needed to refine this approach and confirm its potential role in teleoperation.

show abstract

Using LSTM for Automatic Classification of Human Motion Capture Data

Cited by 4 publications

References 0 publications

Human action recognition method based on conformal geometric algebra and recurrent neural network

Human action recognition method based on conformal geometric algebra and recurrent neural network

A motion recognition technique based on linear matrix representation to improve Parkinson’s disease treatments

Mapping Surgeons Hand/Finger Movements to Surgical Tool Motion During Conventional Microsurgery Using Machine Learning

Contact Info

Product

Resources

About