Development of a Wearable Electrical Impedance Tomographic Sensor for Gesture Recognition With Machine Learning

Yao, Jiafeng; Chen, Huaijin; Xu, Zifei; Huang, Jingshi; Li, Jianping; Jia, Jiabin; Wu, Hongtao

doi:10.1109/jbhi.2019.2945593

Cited by 42 publications

(21 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The image reconstruction of the EIT technique is a process to find the resistivity distribution inside the conductor when a set of injection currents and generated voltages are known, which is a nonlinear inverse problem. The main difficulty is that the small changes in the boundary data may lead to large changes in the reconstructed image …”

Section: Eit For Artificial Sensitive Skinsmentioning

confidence: 99%

Artificial Sensitive Skin for Robotics Based on Electrical Impedance Tomography

Wang

et al. 2020

Advanced Intelligent Systems

Self Cite

View full text Add to dashboard Cite

Electrical impedance tomography (EIT) is a noninvasive measurement technique that estimates the internal resistivity distribution based on the boundary voltage–current data measured from the surface of the conductor. If a thin stretchable soft material with a certain piezoresistive property is used as the electrical conductor, EIT has the ability to reconstruct the position where the resistivity changes due to the inside pressure contact, so that a large‐scale artificial sensitive skin is provided for robotics. First, the different conduction principles and material types of artificial sensitive skins are discussed, which is next followed by the different driving modes and image reconstruction techniques. Then, details on how EIT is used for robotic skin applications are described. Finally, the development trends and future potentials of EIT‐based robotic skins are expounded.

show abstract

Section: Eit For Artificial Sensitive Skinsmentioning

confidence: 99%

Artificial Sensitive Skin for Robotics Based on Electrical Impedance Tomography

Wang

et al. 2020

Advanced Intelligent Systems

Self Cite

View full text Add to dashboard Cite

show abstract

“…Yao et al ( 2020 ) tested six subjects performing three distinct hand gestures with the device attached on the wrist. For each electrode setup, 10 measurements per gesture were recorded without taking the device off.…”

Section: State Of the Artmentioning

confidence: 99%

“…This layout proved to be slightly superior as it can measure the muscle tension at two different locations. Yao et al (2020) compared gesture recognition rates of different electrode materials and shapes, using a portable 8electrode EIT device. They tested rectangular copper, curved copper, conductive cloth, and (circular) medical electrodes.…”

Section: Electrical Impedance Tomography (Eit) For Hand Gesture Recognitionmentioning

confidence: 99%

Toward More Robust Hand Gesture Recognition on EIT Data

et al. 2021

View full text Add to dashboard Cite

Striving for more robust and natural control of multi-fingered hand prostheses, we are studying electrical impedance tomography (EIT) as a method to monitor residual muscle activations. Previous work has shown promising results for hand gesture recognition, but also lacks generalization across multiple sessions and users. Thus, the present paper aims for a detailed analysis of an existing EIT dataset acquired with a 16-electrode wrist band as a prerequisite for further improvements of machine learning results on this type of signal. The performed t-SNE analysis confirms a much stronger inter-session and inter-user variance compared to the expected in-class variance. Additionally, we observe a strong drift of signals within a session. To handle these challenging problems, we propose new machine learning architectures based on deep learning, which allow to separate undesired from desired variation and thus significantly improve the classification accuracy. With these new architectures we increased cross-session classification accuracy on 12 gestures from 19.55 to 30.45%. Based on a fundamental data analysis we developed three calibration methods and thus were able to further increase cross-session classification accuracy to 39.01, 55.37, and 56.34%, respectively.

show abstract

“…Also, for the development of the device, the works in which the data was processed using convolutional neural networks were analyzed [41][42][43][44][45][46][47][48][49][50][51][52][53][54][55]. Measured data was packed to dataset X: every sample has 3 columns (x, y, z acceleration).…”

Section: No Punch (Np)mentioning

confidence: 99%

Recognition Punches in Karate Using Acceleration Sensors and Convolution Neural Networks

et al. 2021

View full text Add to dashboard Cite

Coaches and athletes need to understand the kinematics and dynamics of karate kicks to improve the training process and results. The research was aimed at studying the automatic recognition of punches in karate using only linear acceleration sensors. Accelerometers were part of the Inertial Measurement Units (IMUs), which were attached to the left and right wrist of the athlete. To develop a model of punches, highly qualified athletes with 3-7 years of karate experience participated in the research. We analyzed the acceleration fields of various karate punches: Yun Tsuki, Mawashi Tsuki, Age of Tsuki, Uraken. A simpler approach to extracting features without calculating their statistical characteristics is proposed. To solve the classification problem, various architectures of convolutional neural networks are used: multilayer perceptron, 1-and 2-dimension Convolution Networks. Since the recognition of punches was carried out in the conditions of a shadow fight, in addition to the recognition of punches, another output parameter was introducedmovement without punches. Studies have shown a high level of punch recognition based on the developed models. The multi-class accuracy value is 0.96, and the average F1 value is 0.97 for five different punch classes. Thus, the proposed approach is more suitable for practical implementation in automatic learning systems.

show abstract

Development of a Wearable Electrical Impedance Tomographic Sensor for Gesture Recognition With Machine Learning

Cited by 42 publications

References 24 publications

Artificial Sensitive Skin for Robotics Based on Electrical Impedance Tomography

Artificial Sensitive Skin for Robotics Based on Electrical Impedance Tomography

Toward More Robust Hand Gesture Recognition on EIT Data

Recognition Punches in Karate Using Acceleration Sensors and Convolution Neural Networks

Contact Info

Product

Resources

About