A human-assisting manipulator teleoperated by EMG signals and arm motions

Fukuda, Osamu; Tsuji, Toshio; Kaneko, Makoto; Otsuka, Akihiro

doi:10.1109/tra.2003.808873

Cited by 449 publications

(214 citation statements)

References 35 publications

Supporting

Mentioning

212

Contrasting

Unclassified

Order By: Relevance

“…. , K c ), is a bias unit, and its output (2) O 0 c,k = 1. On the other hand, the unit {c, k, m} (m = 1, · · · , M c,k ) receives the output of the first layer weighted by (1) W m c,k .…”

Section: Rd-llgmn [1]mentioning

confidence: 99%

“…On the other hand, the unit {c, k, m} (m = 1, · · · , M c,k ) receives the output of the first layer weighted by (1) W m c,k . The input (2) I m c,k and the output (2) O m c,k , for (m = 0), are defined as follows:…”

Section: Rd-llgmn [1]mentioning

confidence: 99%

“…Electromyography (EMG) pattern classification has been used to devise elaborate human-machine interfaces for people with physical disabilities [2], [3]. In the recent years, multiple channels of amplitude and/or frequency information of EMG signals have been increasingly used for EMG pattern classification to achieve improved classification performance and to conduct multifunction myoelectric control [3], [4].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Pattern Classification Method for Multivariate EMG Signals Using Neural Network

Arita

Tsuji

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Feature extraction is an important issue in electromyography (EMG) pattern classification, where feature sets of high dimensionality are always used. This paper proposes a novel classification method to deal with high-dimensional EMG patterns, using a probabilistic neural network, a reduced-dimensional log-linearized Gaussian mixture network (RD-LLGMN) [1]. Since RD-LLGMN merges feature extraction and pattern classification processes into its structure, lower-dimensional feature set consistent with classification purposes can be extracted, so that, better classification performance is possible. To verify feasibility of the proposed method, phoneme classification experiments were conducted using frequency features of EMG signals measured from mimetic and cervical muscles. Filter banks are used to extract frequency features, and dimensionality of the features grows significantly when we increase resolution of frequency. In these experiments, the proposed method achieved considerably high classification rates, and outperformed traditional methods that are based on principle component analysis (PCA).

show abstract

Section: Rd-llgmn [1]mentioning

confidence: 99%

Section: Rd-llgmn [1]mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A Novel Pattern Classification Method for Multivariate EMG Signals Using Neural Network

Arita

Tsuji

2005

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…There are some existing studies (Fukuda et al 2003) that have been conducted on using SEMG signals to control prosthetic hands. According to these studies that, in many cases, some parts of the muscles remain near the amputated part and the EMG signals measured from them can be used as a control signal to the prostheses.…”

Section: Introductionmentioning

confidence: 99%

“…It has been stated in the studies that the SEMG patterns have nonlinear and non-stationary characteristics. Moreover, that SEMG patterns can change in accordance to the differences of individuals, different locations of electrodes, and time variation caused by fatigue or sweat [3]. Using SEMG signals, skeletal muscle force can be estimated to control the myoelectric prostheses.…”

Section: Introductionmentioning

confidence: 99%

Application of Genetic Algorithm for Optimization of Data in Surface Myoelectric Prosthesis for the Transradial Amputee

Torres¹,

Linsangan²

2015

IJIET

View full text Add to dashboard Cite

Abstract-Genetic algorithm (GA) is a method that can be used to discover and manage a population of useful patterns in which this study implements; specifically, in optimization. This algorithm is a powerful tool to find the best solution in problems such as prediction and data fitting due to its ability for fast adaptation in the problem environment. Continuous or discrete parameters can be optimized by GA even without requiring derivative information by simultaneously searching from a wide sampling of the cost surface even if it deals with large number of parameters. The paper makes use of this algorithm to optimize the surface electromyography (SEMG) signal from the skeletal muscle force of a transradial amputee in controlling a surface myoelectric prosthesis. The SEMG signals patterns are acquired from the two devices: the microcontroller unit and the EMG simulator. The signals from these two devices are processed and optimized using GA. The optimized signal is used to test the surface myoelectric prosthesis. Moreover, the data acquired from these signals is treated using t-test to show the significant difference of their means.Index Terms-Genetic algorithm, optimization, surface electromyography signal (SEMG), surface myoelectric prosthesis, T-test.

show abstract

Robotic Assistive Devices for Motor Disability Rehabilitation

Alamdari¹,

Krovi

2016

Wiley Encyclopedia of Electrical and Electronics Engineering

View full text Add to dashboard Cite

Mankind has traditionally developed manipulative and locomotive tools to enhance the ability and performance, increase, strength to and reduce performance variability. In a motor rehabilitation context, such devices enable people with disabilities to perform many activities of daily living, to lead independent lives, and play a more productive role in society. In this article, we present a review of the technology underlying assistive devices for people with manipulative and locomotive disabilities focusing on prosthetic limbs, robotic arms, exoskeletons, braces, and wheelchairs. We highlight the important role that robotics can play in assistive devices. There is another class of assistive devices, called teletheses, that bear a strong resemblance to the multiple degree‐of‐freedom robot arms and to the body‐powered prosthetic limbs. Finally, we discuss the design and manufacturing issues for such devices. The high degree of customization that is required and the one‐of‐a‐kind flavor of these products suggest that a computer‐integrated, automated approach to design and prototyping is necessary for manufacturing.

show abstract

A human-assisting manipulator teleoperated by EMG signals and arm motions

Cited by 449 publications

References 35 publications

A Novel Pattern Classification Method for Multivariate EMG Signals Using Neural Network

A Novel Pattern Classification Method for Multivariate EMG Signals Using Neural Network

Application of Genetic Algorithm for Optimization of Data in Surface Myoelectric Prosthesis for the Transradial Amputee

Robotic Assistive Devices for Motor Disability Rehabilitation

Contact Info

Product

Resources

About