StudentShare solutions
Triangle menu

Using accelerometer and EMG signals to estimate arm motion - Dissertation Example

Not dowloaded yet

Extract of sample
Using accelerometer and EMG signals to estimate arm motion

Using accelerometer and EMG signals to estimate arm motion

This study investigates a means to overcome this degradation through use of EMG signals combined with accelerometer signals to measure the upper arm static and dynamic acceleration. Both EMG signal and accelerometer inputs are fed into an artificial neural network. The artificial neural network continuously predicts arm movement trajectories. An offline time-delay Artificial Neural network (TDANN) is employed to predict the movement trajectories of the arm. The accuracy of prediction was judged by using a set of goniometer readings which provides the changes in the angles of the upper limb. All data was processed in the Matlab environment. The TDANN deployed was developed in the neural network toolbox present within the Matlab environment. The developed neural network was optimized and trained with different sets of inputs, and the results for each of the trails was noted. The results obtained clearly demonstrated that accelerometers are able to enhance pattern recognition and thus provide better prosthesis control. Neural Network Optimization and Prediction Performance The neural network structure used for the study is the TDANN. TDANN is a neural network architecture whose primary purpose is to function on continuous data. The major advantage of using TDANN on continuous data is its ability to adapt the network’s weights and activation function online by use of back propagation error method. (Fougner, et al., 2011). The networks can be visualized as a feed forward neural network which is trained for time series prediction. The architecture has continuous inputs that are delayed and sent into the network. In this study, the inputs to this neural network architecture were delayed time series; that is the previous values of 10 channels for 4 for EMG and 6 channels for accelerometers. The measured goniometer signals served as desired output of the TDANN and also as the present state of the time series. The usage of one- layer time delay artificial neural network which is a feed forward structure allow us to predict continuous trajectories which is advantageous for a coordinated and simultaneous control of multiple degrees of freedom in a natural manner. The use of delayed input signals enabled the neural network to capture dynamic input-output properties and account for the delay between the onset of the muscle activity and mechanical arm movement (the activation of the hardware motors in the prosthesis) (Fougner, et al., 2011). TDANN have also an advantage of rapid training time when compared to the dynamic neural networks with recurrent connections. We investigated using a TDANN to predict the elbow flexion degrees, wrist flexion degrees, wrist deviation degrees and forearm rotation degrees based on EMG information from the available intact muscles in transhumeral amputation patients. The EMG information was combined with the accelerometer information about the upper arm and the upper trunk orientations. A one layer time-delay artificial neural network (TDANN) was created using Matlab’s neural network toolbox; this network was used to capture the time-series data (EMG and accelerometer signals as an input with the goniometers and torsiometer signals as output). The size of the hidden layer was set by default to be 10 neurons and the network was trained then the hidden layer size was increased to 25 then to 35 and the performance of the network was monitored. TDANN with 35 neuron hidden layer size was then chosen. The network used 2 input delays to allow building a dynamic network, which has memory so ...Show more

Summary

The purpose of this study is to understand the feasibility of predicting arm movement trajectories based on features that are extracted from EMG signals, as a result of muscular action, and accelerometer input. as a result of acceleration of limbs to movement…
Author : trey11
Using accelerometer and EMG signals to estimate arm motion essay example
Read Text Preview
Save Your Time for More Important Things
Let us write or edit the dissertation on your topic
"Using accelerometer and EMG signals to estimate arm motion"
with a personal 20% discount.
Grab the best paper

Related Essays

Nurse educators' perception using simulation in teaching:Change in Technology
The discussion seeks to answer the questions: What are the perceptions of nurse educators on use of simulation in teaching? What are the issues that manipulate the insights of nurse educators on use of simulation in teaching? How does the Nurse Educators' Perception using Simulation in Teaching affect the quality of training nursing students?
9 pages (2250 words) Dissertation
Foreign Exchange Rates as Unbiased Estimate of Future Sport Rates
The objective is to establish proof that EMH in its weak form is evident in currencies, since EMH was originally developed for the equities market. Investors and businessmen seek to avoid the risks of unexpected market fluctuations which tended to raise costs and increase the chances of losses, by discovering methods of forecasting future exchange rates.
26 pages (6500 words) Dissertation
Effective risk management in software development project using different methodologies
A mixed methods approach was used that made use of both qualitative and quantitative research methods. The rationale for this approach to research will be explained in more depth in the following sections, however, it was believed that a mixed methods approach had few limitations and would provide a high amount of relevant information.
24 pages (6000 words) Dissertation
Computational modeling of cerebellar model articulation controller (CMAC) and it's application
In 1975, James Albus created the Cerebellum Model Articulation Controller (CMAC), a functional code based upon biological theory (Albus, 1975). This study is an examination of the Cerebellum Model Articulation Controller model; in particular reference to semi on line Q-learning and re-enforcement learning use in robot control.
122 pages (30500 words) Dissertation
Human Genome Project Using PCR
Comparisons of structures of annexin A5 orthologues derived form human, mouse, chick and rat have aided in the determination of conserved regulatory motifs as well as coding regions. Conversely, the functional active chains are yet to be characterized.
20 pages (5000 words) Dissertation
Consumer's Safety Concerns When Using Smart Meters
Further, this paper is produced for the fulfilment of the degree requirement of the Bachelor in Information Technology and it is not produced for any other qualification, institution and journal. Abstract This report is based on the introduction of Smart Meters, the newest and technologically sophisticated way of recording electricity usage and generating consumer consumption report.
16 pages (4000 words) Dissertation
Iris recognition system using principal component analysis
The eye images are acquired by camera and then interfaced to the software. The various stages in recognition include segmentation, normalisation, hamming distance calculation. The irises are matched or classified based on the hamming distance. The intra class and inter class hamming distances are calculated and the hamming distance for these two are seen to be in different ranges.
60 pages (15000 words) Dissertation
Evaluation of CAPM using American stock market data
The CAPM was built on the model of choice of portfolio developed by Harry Markowitz (1959). According to the model of Markowitz, an investor opts to select a portfolio at time t-1 which would generate a stochastic return at time t. The model assumes that investors are generally risk averse, and at the time of choosing their portfolio they are concerned only about the mean and variance of their return at the end of the period of investment.
12 pages (3000 words) Dissertation
Liquid Level Detection by Using Optical Sensors in Riyadh Wastewater Treatment Station
This dissertation reveals general view about some techniques to detect the liquid level especially non-contact ultrasonic sensors, compares between Optical liquid level sensors and Ultrasonic liquid level sensors in Riyadh wastewater treatment station and develops the liquid level detection system in wastewater treatment stations by using optical sensors.
33 pages (8250 words) Dissertation
Using Relationship Marketing to Improve Customer Relations
The current dissertation aims to investigate Marks & Spencer’s relationship marketing strategies and evaluate customers’ attitudes towards it. Marks & Spencer have rebranded themselves with the new ‘Your M&S’ concept and have restyled their advertising campaigns (print, billboard & TV) with for example the successful Twiggy and friends adverts.
69 pages (17250 words) Dissertation
Get a custom paper written
by a pro under your requirements!
Win a special DISCOUNT!
Put in your e-mail and click the button with your lucky finger
Your email
YOUR PRIZE:
Apply my DISCOUNT
Comments (0)
Rate this paper:
Thank you! Your comment has been sent and will be posted after moderation