Estimation of forearm movement from EMG signal and application to prosthetic hand control

Morita, Shigeyuki; Kondo, Toshiyuki; Ito, Kaiki

doi:10.1109/robot.2001.933192

Cited by 34 publications

(15 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Researchers have proposed many methods of feature extraction and classification [1][2][3][6][7][8], and have made comparisons of these methods [4,5]. This paper employs a relatively general method, namely, it uses the mean absolute value and Fourier transform for feature extraction, and employs a feed-forwarded artificial neural network [11].…”

Section: Electromyogram To Forearm Motionmentioning

confidence: 99%

“…In addition, the motor information includes some types of motion. There are discrete quantities such as "thumb flexion" [1][2][3][4][5], continuous quantities such as imaginary tension [6] and torque in each articulation [7], and their combinations [8]. Most studies presume temporal invariance of the feature space generated by the feature vectors, and therefore, they acquire the learning data only once, on the first occasion.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

On‐line supervising mechanism for learning data in surface electromyogram motion classifiers

Nishikawa

Yokoi

et al. 2002

Systems & Computers in Japan

View full text Add to dashboard Cite

SUMMARYThis paper proposes a mechanism that supervises the learning data set for the classification from electromyogram to forearm motion. The supervising mechanism contains automatic data addition and automatic data elimination processes. It also contains manual data addition that is the same as our former algorithm. Both the automatic addition and elimination processes evaluate success or failure of classification from the continuity of the classifier's outputs. These processes assume that a person cannot change his motion within a certain interval. In experiments, a system with the supervising mechanism embedded classifies ten forearm motions from two channels of the electromyogram. First, this paper makes it clear that the proposed mechanism is effective by comparison with six settings, including the absence of a supervising pattern. Next, it is verified that the system can adapt to alteration of the operator's characteristics by a sensor-shifting test in which we move one sensor after the operator's training. From the experimental results, it is concluded that the proposed mechanism can adjust the generated decision boundaries for improvement of classification ability, and in addition is capable of tracking the alteration of the operator's characteristics through time.

show abstract

Section: Electromyogram To Forearm Motionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

On‐line supervising mechanism for learning data in surface electromyogram motion classifiers

Nishikawa

Yokoi

et al. 2002

Systems & Computers in Japan

View full text Add to dashboard Cite

show abstract

“…S URFACE electromyogram (EMG), which measures a voltage waveform produced by skeletal muscles on a skin, is an important tool for applications detecting the human will of motion, such as for prosthetic hands [1]- [3]. In this paper, electrodes for measuring surface EMG are focused on, Manuscript as shown in Fig.…”

Section: Introductionmentioning

confidence: 99%

1 <formula formulatype="inline"><tex Notation="TeX">$\mu$</tex></formula>m-Thickness Ultra-Flexible and High Electrode-Density Surface Electromyogram Measurement Sheet With 2 V Organic Transistors for Prosthetic Hand Control

Fuketa

Yoshioka

Shinozuka

et al. 2014

IEEE Trans. Biomed. Circuits Syst.

View full text Add to dashboard Cite

A 64-channel surface electromyogram (EMG) measurement sheet (SEMS) with 2 V organic transistors on a 1 μm-thick ultra-flexible polyethylene naphthalate (PEN) film is developed for prosthetic hand control. The surface EMG electrodes must satisfy the following three requirements; high mechanical flexibility, high electrode density and high signal integrity. To achieve high electrode density and high signal integrity, a distributed and shared amplifier (DSA) architecture is proposed, which enables an in-situ amplification of the myoelectric signal with a fourfold increase in EMG electrode density. In addition, a post-fabrication select-and-connect (SAC) method is proposed to cope with the large mismatch of organic transistors. The proposed SAC method reduces the area and the power overhead by 96% and 98.2%, respectively, compared with the use of conventional parallel transistors to reduce the transistor mismatch by a factor of 10.

show abstract

“…SEMG signal-based machine control also can compensate the inherent delay of a machine, leading to natural interaction with a user, as the onset of the signals precedes actual human movements. Previous research presented prediction possibilities of the upper limb joint torque and related trajectories using sEMG signals [15][16][17][18][19][20]; a algorithms such as artificial neural network and fuzzy logic were used for the prediction. Although the results of these studies showed promise, most studies have been off-line analysis.…”

Section: Introductionmentioning

confidence: 99%

Real-time upper limb motion prediction from noninvasive biosignals for physical human-machine interactions

Kwon

Kim

2009

2009 IEEE International Conference on Systems, Man and Cybernetics

View full text Add to dashboard Cite

Human motion and its intention sensing from noninvasive biosignals is one of the significant issues in the field of physical human-machine interactions (pHMI). This paper presents a real-time upper limb motion prediction method using surface electromyography (sEMG) signals for pHMI. The sEMG signals from 5 channels were collected and used to predict the motion by an artificial neural network (ANN) algorithm. We designed a human-machine interaction system to verify the proposed method. Interaction experiments were performed with or without physical contact, and the effects of instances of contact were investigated. The experimental results were compared with controlled experiments using a customized goniometer, which is able to measure upper limb flexion-extension. The results showed that the proposed method was not superior to the use of direct angle measurements; however, it provides sufficient accuracy and a fast response speed for interactions. SEMG-based interactions will become more natural with further studies of human-machine combination models.

show abstract

Estimation of forearm movement from EMG signal and application to prosthetic hand control

Cited by 34 publications

References 8 publications

On‐line supervising mechanism for learning data in surface electromyogram motion classifiers

On‐line supervising mechanism for learning data in surface electromyogram motion classifiers

1 <formula formulatype="inline"><tex Notation="TeX">$\mu$</tex></formula>m-Thickness Ultra-Flexible and High Electrode-Density Surface Electromyogram Measurement Sheet With 2 V Organic Transistors for Prosthetic Hand Control

Real-time upper limb motion prediction from noninvasive biosignals for physical human-machine interactions

Contact Info

Product

Resources

About