East Tennessee State University
Georgia Southern University
Iowa State University
University of Arkansas, Fayetteville
University of Tennessee, Knoxville
California Polytechnic State University, San Luis Obispo
Western Oregon University
University of Alabama, Birmingham
The Ftc And Ai Governance: A Regulatory Proposal,
2020
Seattle University School of Law
The Ftc And Ai Governance: A Regulatory Proposal, Michael Spiro
Seattle Journal of Technology, Environmental & Innovation Law
No abstract provided.
Security Camera Using Raspberry Pi,
2020
Minnesota State University Moorhead
Security Camera Using Raspberry Pi, Tejendra Khatri
Student Academic Conference
No abstract provided.
Predictive Analysis Of Ethanol Prices With Machine Learning,
2020
Minnesota State University Moorhead
Predictive Analysis Of Ethanol Prices With Machine Learning, Benjamin Schilling
Student Academic Conference
Overview of a predictive analysis regression developed using machine learning alongside ETL process techniques.
Estimating The Tempo Of Audio Files,
2020
Minnesota State University Moorhead
Estimating The Tempo Of Audio Files, Parker Ostertag
Student Academic Conference
On the market today, there exists a multitude of software that allows for the detection and prediction of beats per minute (BPM) contained in audio files. There are both free and monetized versions of these programs, but there is one thing that they all have in common: they are inaccurate. This is simply because the science behind beat detection is unfinished, and may never be. In this project, I decided to use a method of audio peak detection to help me detect the tempo that may exist in any audio file. I started by researching existing programs and the science ...
Minet Magnetic Localization,
2020
University of Mississippi
Minet Magnetic Localization, Michael Robert Drake
Honors Theses
Indoor localization is a modern problem of computer science that has no unified solution, as there are significant trade-offs involved with every technique. Magnetic localization is a less popular sub-field that is rooted in infrastructure-free design, which can allow universal setup. Magnetic localization is also often paired with probabilistic programming, which provides a powerful method of estimation, given a limited understanding of the environment. This thesis presents Minet, which is a particle filter based localization system using the Earth's geomagnetic field. It explores the novel idea of state space limitation as a method of optimizing a particle filter, by ...
Efficient Elevator Algorithm,
2020
University of Tennessee, Knoxville
Efficient Elevator Algorithm, Sean M. Toll, Owen Barbour, Carl Edwards, Daniel Nichols, Austin Day
Chancellor’s Honors Program Projects
No abstract provided.
A Capacitive Sensing Gym Mat For Exercise Classification & Tracking,
2020
University of Arkansas, Fayetteville
A Capacitive Sensing Gym Mat For Exercise Classification & Tracking, Adam Goertz
Computer Science and Computer Engineering Undergraduate Honors Theses
Effective monitoring of adherence to at-home exercise programs as prescribed by physiotherapy protocols is essential to promoting effective rehabilitation and therapeutic interventions. Currently physical therapists and other health professionals have no reliable means of tracking patients' progress in or adherence to a prescribed regimen. This project aims to develop a low-cost, privacy-conserving means of monitoring at-home exercise activity using a gym mat equipped with an array of capacitive sensors. The ability of the mat to classify different types of exercises was evaluated using several machine learning models trained on an existing dataset of physiotherapy exercises.
Lexicon Based Approaches To Sentiment Analysis Of Spanish Tweets: A Comparative Study,
2020
University of Arkansas, Fayetteville
Lexicon Based Approaches To Sentiment Analysis Of Spanish Tweets: A Comparative Study, Jean Roca
Computer Science and Computer Engineering Undergraduate Honors Theses
Sentiment analysis is a natural language processing technique that aims to classify text based on the emotions expressed in them. It is a research area that has been around for almost 20 years and has seen a lot of development. The works presented in this paper attempts to target a less-developed area in sentiment analysis known as multilingual sentiment analysis. More specifically, multilingual sentiment analysis of micro-texts. Using the existing WordNet lexicon and a domain-specific lexicon for a corpus of Spanish tweets, we analyze the effectiveness of these techniques.
Qlime-A Quadratic Local Interpretable Model-Agnostic Explanation Approach,
2020
Southern Methodist University
Qlime-A Quadratic Local Interpretable Model-Agnostic Explanation Approach, Steven Bramhall, Hayley Horn, Michael Tieu, Nibhrat Lohia
SMU Data Science Review
In this paper, we introduce a proof of concept that addresses the assumption and limitation of linear local boundaries by Local Interpretable Model-Agnostic Explanations (LIME), a popular technique used to add interpretability and explainability to black box models. LIME is a versatile explainer capable of handling different types of data and models. At the local level, LIME creates a linear relationship for a given prediction through generated sample points to present feature importance. We redefine the linear relationships presented by LIME as quadratic relationships and expand its flexibility in non-linear cases and improve the accuracy of feature interpretations. We coin ...
Vex U Robotics,
2020
Embry-Riddle Aeronautical University
Vex U Robotics, Kyle Lutterman, Jeffrey Ryan, Sierra Wong, Elizabeth Geiger
Discovery Day - Prescott
VEX U is a competition hosted by the REC Foundation for university students to get engaged in hands-on engineering. Each team produces two robots using the VEX provided parts to compete in the VEX U competition. The competition changes every year with the only constants being the size of the field, the tools and parts teams are able to use, and the size constraints of the robots. The teams compete in regional competitions in order to qualify for the World Championship Competition, which is the highest competition a team can compete in for VEX U. The VEX U teams at ...
Bracelet Reminder For Alzheimer’S,
2020
CUNY New York City College of Technology
Bracelet Reminder For Alzheimer’S, Jennifer Islam, Caroline Rodriguez, Farrukh Zia
Publications and Research
This project involves the design, construction and testing of a personal reminder device for elderly who suffer from Alzheimer’s using a clock system and LED wearable technology. The device consists of an RGB LED strip connected to a 7-segment display (which operates as a clock circuit) attached to a microcontroller board. The device uses visual output to alert the user at that certain time the color being emitted represents the reminder the user set for that time. The project involves two phases. In the first phase, an RGB LED strip will be used to make a wearable device and ...
Towards Optimized Traffic Provisioning And Adaptive Cache Management For Content Delivery,
2020
University of Massachusetts Amherst
Towards Optimized Traffic Provisioning And Adaptive Cache Management For Content Delivery, Aditya Sundarrajan
Doctoral Dissertations
Content delivery networks (CDNs) deploy hundreds of thousands of servers around the world to cache and serve trillions of user requests every day for a diverse set of content such as web pages, videos, software downloads and images. In this dissertation, we propose algorithms to provision traffic across cache servers and manage the content they host to achieve performance objectives such as maximizing the cache hit rate, minimizing the bandwidth cost of the network and minimizing the energy consumption of the servers.
Traffic provisioning is the process of determining the set of content domains hosted on the servers. We propose ...
A Comparative Evaluation Of The Detection And Tracking Capability Between Novel Event-Based And Conventional Frame-Based Sensors,
2020
Air Force Institute of Technology
A Comparative Evaluation Of The Detection And Tracking Capability Between Novel Event-Based And Conventional Frame-Based Sensors, James P. Boettiger
Theses and Dissertations
Traditional frame-based technology continues to suffer from motion blur, low dynamic range, speed limitations and high data storage requirements. Event-based sensors offer a potential solution to these challenges. This research centers around a comparative assessment of frame and event-based object detection and tracking. A basic frame-based algorithm is used to compare against two different event-based algorithms. First event-based pseudo-frames were parsed through standard frame-based algorithms and secondly, target tracks were constructed directly from filtered events. The findings show there is significant value in pursuing the technology further.
Room Management Web Application And Movement And Temperature Sensors,
2020
California Polytechnic State University, San Luis Obispo
Room Management Web Application And Movement And Temperature Sensors, Visalbotr Chan, Huy Anh Duong
Computer Engineering
There are three main parts of this system: micro-controller, database, and website. Micro-controller detects motion of people walking in and out and It also measures room temperature and humidity in a confined space then updates collected data to the database. Our system’s database contains 6 main columns: room number, room capacity, number of students, temperature in Celsius, humidity in percent and date created. Finally, this database is queried by the website to display the information on the webpage. Users could also navigate on our site to check the most and least occupy rooms, and they can also search for ...
Artificial Intelligence Ethics: Governance Through Social Media,
2020
U.S. Army CCDC-AC
Artificial Intelligence Ethics: Governance Through Social Media, Ross Arnold, Jorge Buenfil, Benjamin Abruzzo, Christopher Korpela
West Point Research Papers
A proposal is presented to facilitate machine self-learning of ethical behavior via human-curated training using online human behavioral data such as that found on social media and related sites. The proposed training data set is a mixture of human behavioral data found on social media and related sites that exhibit a wide variety of both ethical and unethical behavior which can help an artificially intelligent machine make ethical decisions during the process of solving real-world problems. The rapid proliferation of artificial intelligence (AI) applications worldwide highlights the need for normativity to protect individual rights, such as privacy, and the promotion ...
A Visual Analytics System For Making Sense Of Real-Time Twitter Streams,
2020
The University of Western Ontario
A Visual Analytics System For Making Sense Of Real-Time Twitter Streams, Amir Haghighatimaleki
Electronic Thesis and Dissertation Repository
Through social media platforms, massive amounts of data are being produced. Twitter, as one such platform, enables users to post “tweets” on an unprecedented scale. Once analyzed by machine learning (ML) techniques and in aggregate, Twitter data can be an invaluable resource for gaining insight. However, when applied to real-time data streams, due to covariate shifts in the data (i.e., changes in the distributions of the inputs of ML algorithms), existing ML approaches result in different types of biases and provide uncertain outputs. This thesis describes a visual analytics system (i.e., a tool that combines data visualization, human-data ...
Smart Collar,
2020
The University of Akron
Smart Collar, Gretchen T. Woodling, Sean Moran, Justen Bischoff, Jacob Sindelar
Williams Honors College, Honors Research Projects
The Smart Collar is a universal pet tracker, designed to be small and exceedingly comfortable for any pet to wear. GPS technology is used to locate the device, allowing the user to track their pet, via a smart phone application. This application can be used to program the device, view maps of their pet’s location and history of travel. Operating primarily on Long Range Wide Area Network (LoRaWAN) for data transfer, the device consumes very little power, allowing for several days of run-time per charge of the battery. Boasting no monthly service fees, The Smart Collar provides pet owner ...
Jc Drain And Sewer Website,
2020
Arcadia University
Jc Drain And Sewer Website, Jarod Pichler, Nathan Houman
Capstone Showcase
-
A website for a small plumbing business in Scranton, Pennsylvania. The website includes a Home, About Us, Services, Contact Us, and Testimonials page. The home page introduces the company to the website viewer. The About Us page provides information about the company and owner, to the website viewer. The Services page provides the website viewer with all of the services that the company can provide. The Contact Us page allows the website viewer to send the company an email. Finally, the Testimonials page will allow the website viewer to leave a comment about the company’s services. The website also ...
Piezoelectric Energy Harvester Improvement,
2020
The University of Akron
Piezoelectric Energy Harvester Improvement, Nathan Embaugh, Jason Mack, Jeremiah Fitzgerald, Zachary J. Lindsey
Williams Honors College, Honors Research Projects
The energy harvester is used to convert a portion of the tire deflection waste energy to power up tire embedded sensors. A piezoelectric energy harvester is designed and some preliminary tests are done on it. So far, it has been shown that this design is sufficient for tire application. The team will need to modify the design of the energy harvester, the measurement setup and add a temperature and a strain senor to the existing setup so that the tire deflection and temperature can be measured and at the same time the energy harvester should be tested to see how ...
Instructor Activity Recognition Using Smartwatch And Smartphone Sensors,
2020
Georgia Southern University
Instructor Activity Recognition Using Smartwatch And Smartphone Sensors, Zayed Uddin Chowdhury
Electronic Theses and Dissertations
During a classroom session, an instructor performs several activities, such as writing on the board, speaking to the students, gestures to explain a concept. A record of the time spent in each of these activities could be valuable information for the instructors to virtually observe their own style of instruction. It can help in identifying activities that engage the students more, thereby enhancing teaching effectiveness and efficiency. In this work, we present a preliminary study on profiling multiple activities of an instructor in the classroom using smartwatch and smartphone sensor data. We use 2 benchmark datasets to test out the ...
