Enhancing Stress Detection Systems Using Real-World Data and Deep Neural Networks

187320-Thumbnail Image.png
Description
As threats emerge and change, the life of a police officer continues to intensify. To better support police training curriculums and police cadets through this critical career juncture, this thesis proposes a state-of-the-art framework for stress detection using real-world data

As threats emerge and change, the life of a police officer continues to intensify. To better support police training curriculums and police cadets through this critical career juncture, this thesis proposes a state-of-the-art framework for stress detection using real-world data and deep neural networks. As an integral step of a larger study, this thesis investigates data processing techniques to handle the ambiguity of data collected in naturalistic contexts and leverages data structuring approaches to train deep neural networks. The analysis used data collected from 37 police training cadetsin five different training cohorts at the Phoenix Police Regional Training Academy. The data was collected at different intervals during the cadets’ rigorous six-month training course. In total, data were collected over 11 months from all the cohorts combined. All cadets were equipped with a Fitbit wearable device with a custom-built application to collect biometric data, including heart rate and self-reported stress levels. Throughout the data collection period, the cadets were asked to wear the Fitbit device and respond to stress level prompts to capture real-time responses. To manage this naturalistic data, this thesis leveraged heart rate filtering algorithms, including Hampel, Median, Savitzky-Golay, and Wiener, to remove potentially noisy data. After data processing and noise removal, the heart rate data and corresponding stress level labels are processed into two different dataset sizes. The data is then fed into a Deep ECGNet (created by Prajod et al.), a simple Feed Forward network (created by Sim et al.), and a Multilayer Perceptron (MLP) network for binary classification. Experimental results show that the Feed Forward network achieves the highest accuracy (90.66%) for data from a single cohort, while the MLP model performs best on data across cohorts, achieving an 85.92% accuracy. These findings suggest that stress detection is feasible on a variate set of real-world data using deepneural networks.
Date Created
2023
Agent

Development of Affordable Metal-Capable Desktop CNC Mill

186267-Thumbnail Image.png
Description
The CNC mill is a highly valuable tool for engineering design, allowing for the creation of precise and complex metal parts. However, due to their high cost, many engineers do not have access to these machines until they enter industry,

The CNC mill is a highly valuable tool for engineering design, allowing for the creation of precise and complex metal parts. However, due to their high cost, many engineers do not have access to these machines until they enter industry, limiting the knowledge and experience of engineering students. This also restricts the level of engineering design they can participate in as they are limited to lower strength materials and processes. To expand the possibilities for engineering students, hobbyists, and small businesses, we created a reliable and affordable desktop CNC mill. Our machine is capable of cutting non-ferrous metals such as aluminum with 70μm repeatable part precision and be compatible with coolant and vacuum systems.
Date Created
2023-05
Agent

Acid Rain Monitoring and Catchment System

Description

As a result of the increase of pollution related to industrialization in Vietnam, acid rain has become a prevalent issue for Vietnamese farmers who are forced to rinse their crops – risking damage due to overwatering and poor harvest. Thus,

As a result of the increase of pollution related to industrialization in Vietnam, acid rain has become a prevalent issue for Vietnamese farmers who are forced to rinse their crops – risking damage due to overwatering and poor harvest. Thus, the team was motivated to develop a solution to harmful impacts of acidic rainwater by creating a system with the ability to capture rainwater and determine its level of acidity in order to optimize the crop watering process, and promote productive crops. By conducting preliminary research on rainfall and tropical climate in Vietnam, existing products on the market, and pH sensors for monitoring and device material, the team was able to design a number of devices to collect, store, and measure the pH of rainwater. After developing a number of initial design requirements based on the needs of the farmers, a final prototype was developed using the best aspects of each initial design. Tests were conducted with varying structural and aqueous materials to represent a broad range of environmental conditions. While the scope of the project was ultimately limited to prototyping purposes, the principles explored throughout this thesis project can successfully be applied to a fully-functioning production model available for commercial use on Vietnamese farms. Given more time for development, improvements would be made in the extent of materials tested, and the configuration of electronics and data acquisition, in order to further optimize the process of determining rainwater acidity.

Date Created
2023-05
Agent

Acid Rain Monitoring and Catchment System

Description

As a result of the increase of pollution related to industrialization in Vietnam, acid rain has become a prevalent issue for Vietnamese farmers who are forced to rinse their crops – risking damage due to overwatering and poor harvest. Thus,

As a result of the increase of pollution related to industrialization in Vietnam, acid rain has become a prevalent issue for Vietnamese farmers who are forced to rinse their crops – risking damage due to overwatering and poor harvest. Thus, the team was motivated to develop a solution to harmful impacts of acidic rainwater by creating a system with the ability to capture rainwater and determine its level of acidity in order to optimize the crop watering process, and promote productive crops. By conducting preliminary research on rainfall and tropical climate in Vietnam, existing products on the market, and pH sensors for monitoring and device material, the team was able to design a number of devices to collect, store, and measure the pH of rainwater. After developing a number of initial design requirements based on the needs of the farmers, a final prototype was developed using the best aspects of each initial design. Tests were conducted with varying structural and aqueous materials to represent a broad range of environmental conditions. While the scope of the project was ultimately limited to prototyping purposes, the principles explored throughout this thesis project can successfully be applied to a fully-functioning production model available for commercial use on Vietnamese farms. Given more time for development, improvements would be made in the extent of materials tested, and the configuration of electronics and data acquisition, in order to further optimize the process of determining rainwater acidity.

Date Created
2023-05
Agent

Acid Rain Monitoring and Catchment System

Description

As a result of the increase of pollution related to industrialization in Vietnam, acid rain has become a prevalent issue for Vietnamese farmers who are forced to rinse their crops – risking damage due to overwatering and poor harvest. Thus,

As a result of the increase of pollution related to industrialization in Vietnam, acid rain has become a prevalent issue for Vietnamese farmers who are forced to rinse their crops – risking damage due to overwatering and poor harvest. Thus, the team was motivated to develop a solution to harmful impacts of acidic rainwater by creating a system with the ability to capture rainwater and determine its level of acidity in order to optimize the crop watering process, and promote productive crops. By conducting preliminary research on rainfall and tropical climate in Vietnam, existing products on the market, and pH sensors for monitoring and device material, the team was able to design a number of devices to collect, store, and measure the pH of rainwater. After developing a number of initial design requirements based on the needs of the farmers, a final prototype was developed using the best aspects of each initial design. Tests were conducted with varying structural and aqueous materials to represent a broad range of environmental conditions. While the scope of the project was ultimately limited to prototyping purposes, the principles explored throughout this thesis project can successfully be applied to a fully-functioning production model available for commercial use on Vietnamese farms. Given more time for development, improvements would be made in the extent of materials tested, and the configuration of electronics and data acquisition, in order to further optimize the process of determining rainwater acidity.

Date Created
2023-05
Agent

Co-Bot Integration For High-Volume Manufacturing of Aerospace Components

Description

Over the years, American manufacturing has been offshored due to the competitive labor conditions in other countries. In addition, the COVID-19 pandemic exposed the fragility of the international supply chain, highlighting the importance of reshoring manufacturing and industry. However, reshoring

Over the years, American manufacturing has been offshored due to the competitive labor conditions in other countries. In addition, the COVID-19 pandemic exposed the fragility of the international supply chain, highlighting the importance of reshoring manufacturing and industry. However, reshoring alone cannot solve the underlying issues that caused offshoring in the first place, such as shortages of skilled labor and extensive regulation. To address these issues, the implementation and scaling of automation and Industry 4.0 technologies are necessary. The aerospace industry is a prime example of the need for skilled labor. Abiding by rigorous specifications and achieving the tight tolerances required by aerospace specifications is a highly specialized skill that requires experience and training. The shortage of skilled labor puts those working in aerospace at a disadvantage, often leading to long strenuous work hours to meet demand. To address this, a collaboration with two ASU manufacturing student research teams aided the development of two co-bot solutions that can work alongside technicians and operators to reduce downtime, increase efficiency, and free up human operators to focus on more complex tasks. While many automated solutions are available on the market, co-bots are not often used to their full capability. The proposed solutions demonstrate the possibilities of implementing co-bots in the aerospace industry by using them in machine tending and blending processes for aerospace parts. In traditional manufacturing processes, human operators are still responsible for performing repetitive and often mundane tasks, such as loading and removing workpieces from a CNC workstation and starting a CNC machine for repetitive parts. The current blending process requires a technician to manually sand damaged areas for Depot, Repair, and Overhaul (DRO), which is time-consuming and strenuous. By using a co-bot for this process, the technician's workload is significantly reduced, decreasing lead times and increasing quality control. Inspiration for this thesis came from observing the demands of companies like SpaceX, which require mass manufacturing of rocket engines to meet testing and launch schedules. The SpaceX Raptor engine is a complex, precise system that is aimed at being produced in high volume, which is a prime target for co-bot integration to help meet production targets. Implementing more co-bots into manufacturing has been shown to increase efficiency, reduce cost, and relieve stress on human operators. The integration of co-bots into the manufacturing process for the Raptor engine has the potential to improve efficiency and productivity, making high-volume manufacturing a possibility. Overall, the implementation of co-bots in the aerospace industry can offer a competitive advantage by increasing productivity and efficiency while reducing costs and relieving stress on human operators. This thesis provides proof of the possibilities of implementing co-bots in a versatile industry like aerospace and demonstrates the potential benefits of integrating co-bots into the manufacturing process for rocket engines like the Raptor. By doing so, the aerospace industry can move towards a more automated and efficient future, helping to address the challenges faced by American manufacturing today.

Date Created
2023-05
Agent

The Exploration, Design, and Construction of Roller Coasters

Description

This thesis presents a comprehensive investigation into the design of roller coasters. The study includes an overview of various roller coaster types, cart design, brake design, lift hill and launch design, support design, and roller coaster safety. Utilizing No Limits

This thesis presents a comprehensive investigation into the design of roller coasters. The study includes an overview of various roller coaster types, cart design, brake design, lift hill and launch design, support design, and roller coaster safety. Utilizing No Limits 2 to design the layout and CAD software for component design, a scale model roller coaster was designed. The physics of the roller coaster and its structures were analyzed and a scale model was produced. Afterward, an accelerometer was used to collect G force data as the cart moved along the track. However, the collected data differed from the expected results, as the launch speed was higher than predicted due to more friction than anticipated. As a result, further optimization of the design and models used to design the scale model roller coasters is necessary.

Date Created
2023-05
Agent

The Exploration, Design, and Construction of Roller Coasters

Description

This thesis presents a comprehensive investigation into the design of roller coasters. The study includes an overview of various roller coaster types, cart design, brake design, lift hill and launch design, support design, and roller coaster safety. Utilizing No Limits

This thesis presents a comprehensive investigation into the design of roller coasters. The study includes an overview of various roller coaster types, cart design, brake design, lift hill and launch design, support design, and roller coaster safety. Utilizing No Limits 2 to design the layout and CAD software for component design, a scale model roller coaster was designed. The physics of the roller coaster and its structures were analyzed and a scale model was produced. Afterward, an accelerometer was used to collect G force data as the cart moved along the track. However, the collected data differed from the expected results, as the launch speed was higher than predicted due to more friction than anticipated. As a result, further optimization of the design and models used to design the scale model roller coasters is necessary.

Date Created
2023-05
Agent