Matching Items (23)
Filtering by
- All Subjects: engineering
- Creators: Sugar, Thomas
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
The sensor industry is a growing industry that has been predicted by Allied Market Research to be a multi-billion industry by 2022. One of the many key drives behind this rapid growth in the sensor industry is the increase incorporation of sensors into portable electrical devices. The value for sensor technologies are increased when the sensors are developed into innovative measuring system for application uses in the Aerospace, Defense, and Healthcare industries. While sensors are not new, their increased performance, size reduction, and decrease in cost has opened the door for innovative sensor combination for portable devices that could be worn or easily moved around. With this opportunity for further development of sensor use through concept engineering development, three concept projects for possible innovative portable devices was undertaken in this research. One project was the development of a pulse oximeter devise with fingerprint recognition. The second project was prototyping a portable Bluetooth strain gage monitoring system. The third project involved sensors being incorporated onto flexible printed circuit board (PCB) for improved comfort of wearable devices. All these systems were successfully tested in lab.
ContributorsNichols, Kevin William (Author) / Redkar, Sangram (Thesis advisor) / Rogers, Brad (Committee member) / Sugar, Thomas (Committee member) / Arizona State University (Publisher)
Created2018
Description
Recent research and study have showed the potential of auto-parametric system in controlling stability and parametric resonance. In this project, two different designs for auto-parametrically excited mass-spring-damper systems were studied. The theoretical models were developed to describe the behavior of the systems, and simulation models were constructed to validate the analytical results. The error between simulation and theoretical results was within 2%. Both theoretical and simulation results showed that the implementation of auto-parametric system could help reduce or amplify the resonance significantly.
ContributorsLe, Thao (Author) / Redkar, Sangram (Thesis advisor) / Sugar, Thomas (Committee member) / Rogers, Brad (Committee member) / Arizona State University (Publisher)
Created2018
Description
The goal of this project is to gain and use knowledge of sustainability topics as a value-adding function for a business in the Tempe, AZ area and to develop the skills to approach and consult with business owners and staff about sustainable business options. Sustainability searches for a balance between society, economy and the environment where all three can thrive; therefore, the ideal project partner was a business that values the wellbeing of mankind, is locally owned and operated and promotes environmental stewardship. The Original Chop Shop Co in Tempe Arizona was appropriately selected. Throughout the duration of our partnership, I observed their daily routine, interviewed employees and managers and used the collected information to identify three areas of focus that have the largest potential to reduce The Original Chop Shop Company's impact on the environment. Information on the areas of recycling, composting, and food sourcing was researched and synthesized to make suggestions for ecofriendly changes to business practices. The scope of the project includes small changes in daily practices such as implementing a recycling and composting program and employee training sessions and minor investments such as purchasing a micro washer and silverware in order to eliminate nonrenewable plastic utensils. The scope does not include major renovations or investments in technology. The suggestions offered position The Original Chop Shop to conduct business in a way that does not compromise the health of the environment, society, or economy.
ContributorsFerry, Brianna Aislinn (Author) / Dooley, Kevin (Thesis director) / Darnall, Nicole (Committee member) / Barrett, The Honors College (Contributor) / W. P. Carey School of Business (Contributor) / School of Politics and Global Studies (Contributor)
Created2015-05
Description
The client detailed in this report is a premier continuing healthcare education organization providing a variety of homeopathic therapy classes for its students. The purpose of this paper is to showcase a business plan that will help dictate the basic structure of the client's business once they are independent of their current managing company. Extensive analysis, primarily based upon online market research and personal correspondence with the client, was conducted for this report. Detailed within this paper are several areas where the client can significantly lower costs and increase future revenues by modifying practices employed by the managing company. From the analysis provided, the client has the opportunity to create and grow a well-organized, profitable business with a sustainable future.
ContributorsMionis, Erika (Co-author) / Lee, Betty (Co-author) / Coult, Natasha (Co-author) / Brooks, Dan (Thesis director) / Chikly, Bruno (Committee member) / Barrett, The Honors College (Contributor) / Department of Supply Chain Management (Contributor) / Department of Finance (Contributor) / School of International Letters and Cultures (Contributor) / School of Life Sciences (Contributor) / W. P. Carey School of Business (Contributor)
Created2015-05
Description
Derived from the idea that the utilization of sustainable practices could improve small business practice, this honors thesis offers a full business assessment and recommendations for improvements of a local, family-owned coffee shop, Gold Bar. A thorough analysis of the shop's current business practices and research on unnecessary expenses and waste guides this assessment.
ContributorsSorden, Clarissa (Co-author) / Boden, Alexandra (Co-author) / Darnall, Nicole (Thesis director) / Dooley, Kevin (Committee member) / Barrett, The Honors College (Contributor) / School of Sustainability (Contributor) / W. P. Carey School of Business (Contributor) / Department of Management (Contributor) / Department of Supply Chain Management (Contributor)
Created2015-05
Description
Volume depletion can lead to migraines, dizziness, and significant decreases in a subject's ability to physically perform. A major cause of volume depletion is dehydration, or loss in fluids due to an imbalance in fluid intake to fluid excretion. Because proper levels of hydration are necessary in order to maintain both short and long term health, the ability to monitor hydration levels is growing in clinical demand. Although devices capable of monitoring hydration level exist, these devices are expensive, invasive, or inaccurate and do not offer a continuous mode of measurement. The ideal hydration monitor for consumer use needs to be characterized by its portability, affordability, and accuracy. Also, this device would need to be noninvasive and offer continuous hydration monitoring in order to accurately assess fluctuations in hydration data throughout a specified time period. One particular method for hydration monitoring that fits the majority of these criteria is known as bioelectric impedance analysis (BIA). Although current devices using BIA do not provide acceptable levels of accuracy, portability, or continuity in data collection, BIA could potentially be modified to fit many, if not all, desired customer specifications. The analysis presented here assesses the viability of using BIA as a new standard in hydration level measurement. The analysis uses data collected from 22 subjects using an existing device that employs BIA. A regression derived for estimating TBW based on the parameters of age, weight, height, sex, and impedance is presented. Using impedance data collected for each subject, a regression was also derived for estimating impedance based on the factors of age, weight, height, and sex. The derived regression was then used to calculate a new impedance value for each subject, and these new impedance values were used to estimate TBW. Through a paired-t test between the TBW values derived by using the direct measurements versus the calculated measurements of impedance, the two samples were found to be comparable. Considerations for BIA as a noninvasive measurement of hydration are discussed.
ContributorsTenorio, Jorge Antonio (Author) / LaBelle, Jeffrey (Thesis director) / Pizziconi, Vincent (Committee member) / Spano, Mark (Committee member) / Barrett, The Honors College (Contributor) / W. P. Carey School of Business (Contributor) / Harrington Bioengineering Program (Contributor)
Created2013-05
Description
For the past two years, New Venture Group (nVg) and the Havasupai Tribe have worked together on a variety of community development projects. The purpose of this paper is to provide descriptions and documentation for these projects and how they are related to the economic development of the community. The partnership with the Havasupai Tribe has allowed nVg to learn the history and culture of one of Arizona's oldest communities. It has been necessary to understand the traditional values of the Havasupai to design projects that will benefit the tribe and gain support from its members. The products that nVg has worked on under the direction of the Havasupai include: - Computer training sessions - A tribal website - Financial analyses of Supai enterprises - Data management resources These and additional activities will be explained in the following pages. They were created following several meetings with tribal members and Enterprise Managers in Tempe and Supai, Arizona over the last two years. The goal of these projects is to contribute to the economic development of Supai and the Havasupai people more generally. Economic development means combining the existing strengths of the Havasupai community with nVg's business management experience, creating a stronger and more productive economy that contributes to the overall quality of life for the Havasupai.
ContributorsWhile, Kate Sophie (Author) / Brooks, Daniel (Thesis director) / LePine, Marcie (Committee member) / Walker, Beth (Committee member) / Barrett, The Honors College (Contributor) / Department of Economics (Contributor) / W. P. Carey School of Business (Contributor) / School of Politics and Global Studies (Contributor)
Created2013-05
Description
The objective of this research study is to assess the effectiveness of a poster-based messaging campaign and engineering-based activities for middle school and high school students to encourage students to explore and to pursue chemical engineering. Additionally, presentations are incorporated into both methods to provide context and improve understanding of the presented poster material or activity. Pre-assessments and post-assessments are the quantitative method of measuring effectiveness. For the poster campaign, ASU juniors and seniors participated in the poster campaign by producing socially relevant messages about their research or aspirations to address relevant chemical engineering problems. For the engineering-based activity, high school students participated in an Ira A. Fulton Schools of Engineering program "Young Engineers Shape the World" in which the students participated in six-hour event learning about four engineering disciplines, and the chemical engineering presentation and activity was conducted in one of the sessions. Pre-assessments were given at the beginning of the event, and the post-assessments were provided towards the end of the event. This honors thesis project will analyze the collected data.
ContributorsBueno, Daniel Tolentino (Author) / Ganesh, Tirupalavanam (Thesis director) / Parker, Hope (Committee member) / Chemical Engineering Program (Contributor) / School of Historical, Philosophical and Religious Studies (Contributor) / W. P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2017-05
Description
The aim of this thesis is to improve the user experience within FedEx's eProcurement system, directly address feedback received from customer surveys, and to make recommendations for the Sourcing and Procurement Division within FedEx. In the first part, the overall client engagement is outlined with the specific timeline between New Venture Group and FedEx. The thesis encompasses three deliverables that were integral parts to the semester-long consulting engagement. The thesis then dives into methodology and each deliverable individually. After months of conference calls and best practice research, consulting efforts are summarized in the results. In a detailed discussion sections, the thesis forecasts opportunities for FedEx within sourcing and procurement. Here, the thesis draws on sources from various companies and research. Furthermore, overall recommendations are given to FedEx and acknowledgements are made. In conclusion, the thesis hopes to offer FedEx improvements to leverage improved functionality of eProcurement that will become available in the next upgrade of the Performance Management System.
ContributorsRuhlman, Payne (Co-author) / Pollack, Amanda (Co-author) / Peterson, Andrew (Co-author) / Taylor, Todd (Thesis director) / Choi, Thomas (Committee member) / Halvorson, Joel (Committee member) / Department of Information Systems (Contributor) / Department of Supply Chain Management (Contributor) / Department of Finance (Contributor) / Department of Economics (Contributor) / School of International Letters and Cultures (Contributor) / W. P. Carey School of Business (Contributor) / Barrett, The Honors College (Contributor)
Created2016-12