Matching Items (2)
Filtering by
- All Subjects: human-computer interaction
- Genre: Masters Thesis
- Creators: Burleson, Wnslow
Description
Brain Computer Interfaces are becoming the next generation controllers not only in the medical devices for disabled individuals but also in the gaming and entertainment industries. In order to build an effective Brain Computer Interface, which accurately translates the user thoughts into machine commands, it is important to have robust and fail proof signal processing and machine learning modules which operate on the raw EEG signals and estimate the current thought of the user.
In this thesis, several techniques used to perform EEG signal pre-processing, feature extraction and signal classification have been discussed, implemented, validated and verified; efficient supervised machine learning models, for the EEG motor imagery signal classification are identified. To further improve the performance of system unsupervised feature learning techniques have been investigated by pre-training the Deep Learning models. Use of pre-training stacked autoencoders have been proposed to solve the problems caused by random initialization of weights in neural networks.
Motor Imagery (imaginary hand and leg movements) signals are acquire using the Emotiv EEG headset. Different kinds of features like mean signal, band powers, RMS of the signal have been extracted and supplied to the machine learning (ML) stage, wherein, several ML techniques like LDA, KNN, SVM, Logistic regression and Neural Networks are applied and validated. During the validation phase the performances of various techniques are compared and some important observations are reported. Further, deep Learning techniques like autoencoding have been used to perform unsupervised feature learning. The reliability of the features is analyzed by performing classification by using the ML techniques mentioned earlier. The performance of the neural networks has been further improved by pre-training the network in an unsupervised fashion using stacked autoencoders and supplying the stacked autoencoders’ network parameters as initial parameters to the neural network. All the findings in this research, during each phase (pre-processing, feature extraction, classification) are directly relevant and can be used by the BCI research community for building motor imagery based BCI applications.
Additionally, this thesis attempts to develop, test, and compare the performance of an alternative method for classifying human driving behavior. This thesis proposes the use of driver affective states to know the driving behavior. The purpose of this part of the thesis was to classify the EEG data collected from several subjects while driving simulated vehicle and compare the classification results with those obtained by classifying the driving behavior using vehicle parameters collected simultaneously from all the subjects. The objective here is to see if the drivers’ mental state is reflected in his driving behavior.
In this thesis, several techniques used to perform EEG signal pre-processing, feature extraction and signal classification have been discussed, implemented, validated and verified; efficient supervised machine learning models, for the EEG motor imagery signal classification are identified. To further improve the performance of system unsupervised feature learning techniques have been investigated by pre-training the Deep Learning models. Use of pre-training stacked autoencoders have been proposed to solve the problems caused by random initialization of weights in neural networks.
Motor Imagery (imaginary hand and leg movements) signals are acquire using the Emotiv EEG headset. Different kinds of features like mean signal, band powers, RMS of the signal have been extracted and supplied to the machine learning (ML) stage, wherein, several ML techniques like LDA, KNN, SVM, Logistic regression and Neural Networks are applied and validated. During the validation phase the performances of various techniques are compared and some important observations are reported. Further, deep Learning techniques like autoencoding have been used to perform unsupervised feature learning. The reliability of the features is analyzed by performing classification by using the ML techniques mentioned earlier. The performance of the neural networks has been further improved by pre-training the network in an unsupervised fashion using stacked autoencoders and supplying the stacked autoencoders’ network parameters as initial parameters to the neural network. All the findings in this research, during each phase (pre-processing, feature extraction, classification) are directly relevant and can be used by the BCI research community for building motor imagery based BCI applications.
Additionally, this thesis attempts to develop, test, and compare the performance of an alternative method for classifying human driving behavior. This thesis proposes the use of driver affective states to know the driving behavior. The purpose of this part of the thesis was to classify the EEG data collected from several subjects while driving simulated vehicle and compare the classification results with those obtained by classifying the driving behavior using vehicle parameters collected simultaneously from all the subjects. The objective here is to see if the drivers’ mental state is reflected in his driving behavior.
ContributorsManchala, Vamsi Krishna (Author) / Redkar, Sangram (Thesis advisor) / Rogers, Bradley (Committee member) / Sugar, Thomas (Committee member) / Arizona State University (Publisher)
Created2015
Description
In the modern age, where teams consist of people from disparate locations, remote team training is highly desired. Moreover, team members' overlapping schedules force their mentors to focus on individual training instead of team training. Team training is an integral part of collaborative team work. With the advent of modern technologies such as Web 2.0, cloud computing, etc. it is possible to revolutionize the delivery of time-critical team training in varied domains of healthcare military and education. Collaborative Virtual Environments (CVEs), also known as virtual worlds, and the existing worldwide footprint of high speed internet, would make remote team training ubiquitous. Such an integrated system would potentially help in assisting actual mentors to overcome the challenges in team training. ACLS is a time-critical activity which requires a high performance team effort. This thesis proposes a system that leverages a virtual world (VW) and provides an integrated learning platform for Advanced Cardiac Life Support (ACLS) case scenarios. The system integrates feedback devices such as haptic device so that real time feedback can be provided. Participants can log in remotely and work in a team to diagnose the given scenario. They can be trained and tested for ACLS within the virtual world. This system is well equipped with persuasive elements which aid in learning. The simulated training in this system was validated to teach novices the procedural aspect of ACLS. Sixteen participants were divided into four groups (two control groups and two experimental groups) of four participants. All four groups went through didactic session where they learned about ACLS and its procedures. A quiz after the didactic session revealed that all four groups had equal knowledge about ACLS. The two experimental groups went through training and testing in the virtual world. Experimental group 2 which was aided by the persuasive elements performed better than the control group. To validate the training capabilities of the virtual world system, final transfer test was conducted in real world setting at Banner Simulation Center on high fidelity mannequins. The test revealed that the experimental groups (average score 65/100) performed better than the control groups (average score 16/100). The experimental group 2 which was aided by the persuasive elements (average score 70/100) performed better than the experimental group 1 (average score 55/100). This shows that the persuasive technology can be useful for training purposes.
ContributorsParab, Sainath (Author) / Kahol, Kanav (Thesis advisor) / Burleson, Wnslow (Thesis advisor) / Li, Baioxin (Committee member) / Arizona State University (Publisher)
Created2010