Computer Sciences Commons^™

Gc-106 - Emotion Recognition Using Wireless Signals, Jui Mhatre

C-Day Computing Showcase

No abstract provided.

Gc-113 - Nlp Sentiment Analysis On Amazon Reviews, Sushma Aladhalli Shivakumar, Swetha Pailla, Sireesha Hasti

C-Day Computing Showcase

No abstract provided.

Gc-132 - Microsoft Azure Sentinel To Connectwise Integration, Christine Neal, Miseker Birega, Ryan James, Charul Patel, L. Renee Davis Townsend, Matthew Parker

C-Day Computing Showcase

No abstract provided.

Uc-072 - Authenticating Middleware Implementing Dns-Based Identity, Brooklyn Crowe, Jade Godwin, Marilyn Marcos, Aaron Moore, Ricardo Rojo, Noah Starr

C-Day Computing Showcase

No abstract provided.

Uc-080 - It Deployment Aoa, Trexell T. Bailey, Elijah Deputy, Sabiha Iqbal, James Diaz, Evan Dillon, Kathryn S. Highers

C-Day Computing Showcase

No abstract provided.

Gc-125 - Covid-19 Prediction Using Symtpoms, Yagna Gurjala, Chalamayya Batchu, Shruthi Pethe

C-Day Computing Showcase

No abstract provided.

Uc-082 - Remote Presence Robot In The Classroom, Noah Trinite, Anna Furrow, Christopher Lyons, Joshua Odeyemi, George Tatge, James Perdue, Dylan Sloan

C-Day Computing Showcase

No abstract provided.

Uc-087 - Hibernate Funds: Back Office Portals For Fundraisers, Phillip Blackwell, Kasey L. Merritt, Patrick A. Krouba, Daniel Duran, Diana Calixto, Logan Miller

C-Day Computing Showcase

No abstract provided.

Uc-138 - 3d Extraction From Physics Exercise Videos, Zachary Matthews, Lhakpa N. Sherpa, Francisco J. Alvarez, Sam Guan, Philip Mcfarland, Cole Bruton

C-Day Computing Showcase

No abstract provided.

Uc-116 - Security Solution For A Small Business, Jessica Casasola, Craig Englert, Phuc Nguyen, Charles Pegram, James Vesper

C-Day Computing Showcase

No abstract provided.

Developing A Practice In Remote Sensing For Next-Generation Human Rights Researchers, Theresa Harris, Jonathan Drake, Umesh K. Haritashya, Wumi Asubiaro Dada, Fredy Cumes

Biennial Conference: The Social Practice of Human Rights

Remote sensing is increasingly recognized as an important tool for documenting human rights abuses. When used alongside interviews, case studies, surveys, forensic science, and other well-established research methods in human rights and humanitarian practice, remotely sensed data can effectively geolocate and establish chronologies for mass graves, forced displacement, destruction of cultural heritage sites, and other violations. But as a highly technical field of science that relies on ever-changing technologies, remote sensing and geospatial analysis are not readily accessible for human rights and humanitarian practitioners. The community of practice grew out of innovative work by practitioners at NGOs and specialized inter-governmental …

Ready, Willing, And Able, Gerry Boyle

Colby Magazine

So what gives? How, after four years on Mayflower Hill, do these Colby alumni have an outsized impact in a fintech company that is focused on, for example, changing the way municipal bonds are traded? What makes them able to dive in and figure it out? “That’s part of the liberal arts education,” said Associate Professor of History John Turner, who taught Tagg Martin ’13, history major turned MarketAxess go-to analyst. “You’re always learning. … You are always going to be mastering something, as opposed to having mastered.”

Ow-Detr: Open-World Detection Transformer, Akshita Gupta, Sanath Narayan, K.J. Joseph, Salman Khan, Fahad Shahbaz Khan, Mubarak Shah

Computer Vision Faculty Publications

Open-world object detection (OWOD) is a challenging computer vision problem, where the task is to detect a known set of object categories while simultaneously identifying unknown objects. Additionally, the model must incrementally learn new classes that become known in the next training episodes. Distinct from standard object detection, the OWOD setting poses significant challenges for generating quality candidate proposals on potentially unknown objects, separating the unknown objects from the background and detecting diverse unknown objects. Here, we introduce a novel end-to-end transformer-based framework, OW-DETR, for open-world object detection. The proposed OW-DETR comprises three dedicated components namely, attention-driven pseudo-labeling, novelty classification …

Analyze And Examine Wildfire Events In California, Aleena Hoodith, Sakim Zaman, Safoan Hossain, Jiehao Huang

Publications and Research

•A wildfire is an unplanned, unwanted, uncontrolled fire in an area of combustible vegetation starting in rural areas and urban areas. •Recent studies have shown that the effect of anthropogenic climate change has fueled the wildfire events, leading to an increase in the annual burned areas and number of events. •California is one of the places having the most deadliest and destructive wildfire seasons. With the global warming effect of 1°C since 1850, the 20 largest wildfires events that have occurred in California, 8 of them were in 2017. (Center For Climate And Energy Solutions) •Climate change is primarily caused …

Semantically Meaningful Sentence Embeddings, Rojina Deuja

School of Computing: Dissertations, Theses, and Student Research

Text embedding is an approach used in Natural Language Processing (NLP) to represent words, phrases, sentences, and documents. It is the process of obtaining numeric representations of text to feed into machine learning models as vectors (arrays of numbers). One of the biggest challenges in text embedding is representing longer text segments like sentences. These representations should capture the meaning of the segment and the semantic relationship between its constituents. Such representations are known as semantically meaningful embeddings. In this thesis, we seek to improve upon the quality of sentence embeddings that capture semantic information.

The current state-of-the-art models are …

Hsva: Hierarchical Semantic-Visual Adaptation For Zero-Shot Learning, Shiming Chen, Guo Sen Xie, Yang Liu, Qinmu Peng, Baigui Sun, Hao Li, Xinge You, Ling Shao

Machine Learning Faculty Publications

Zero-shot learning (ZSL) tackles the unseen class recognition problem, transferring semantic knowledge from seen classes to unseen ones. Typically, to guarantee desirable knowledge transfer, a common (latent) space is adopted for associating the visual and semantic domains in ZSL. However, existing common space learning methods align the semantic and visual domains by merely mitigating distribution disagreement through one-step adaptation. This strategy is usually ineffective due to the heterogeneous nature of the feature representations in the two domains, which intrinsically contain both distribution and structure variations. To address this and advance ZSL, we propose a novel hierarchical semantic-visual adaptation (HSVA) framework. …

Automated Discovery And Interpretation Of Ada-Compliant Door Placards, John J. Feilmeier

Computer Science and Information Technology Faculty

A familiar difficulty to any new student on campus is making one’s way from classroom A to classroom B. Facilities with different wings, multiple floors, and irregular floorplans can magnify this challenge, while students with vision impairments are impacted even more by the challenge of identifying the destination. This thesis explored different methods of discovering Americans with Disabilities Act (ADA)- compliant room identifying placards (“plaques”) and identifying the text on the sign. The plaque detection was accomplished with both standard image manipulation techniques and a Histogram of Oriented Gradients (HOG) (Dalal & Triggs, 2005) object detector. The text reading utilized …

Contrastive Learning For Unsupervised Auditory Texture Models, Christina Trexler

Computer Science and Computer Engineering Undergraduate Honors Theses

Sounds with a high level of stationarity, also known as sound textures, have perceptually relevant features which can be captured by stimulus-computable models. This makes texture-like sounds, such as those made by rain, wind, and fire, an appealing test case for understanding the underlying mechanisms of auditory recognition. Previous auditory texture models typically measured statistics from auditory filter bank representations, and the statistics they used were somewhat ad-hoc, hand-engineered through a process of trial and error. Here, we investigate whether a better auditory texture representation can be obtained via contrastive learning, taking advantage of the stationarity of auditory textures to …

Winect: 3d Human Pose Tracking For Free-Form Activity Using Commodity Wifi, Y. Ren, Z. Wang, Sheng Tan, Y. Chen, J. Yang

Computer Science Faculty Research

WiFi human sensing has become increasingly attractive in enabling emerging human-computer interaction applications. The corresponding technique has gradually evolved from the classification of multiple activity types to more fine-grained tracking of 3D human poses. However, existing WiFi-based 3D human pose tracking is limited to a set of predefined activities. In this work, we present Winect, a 3D human pose tracking system for free-form activity using commodity WiFi devices. Our system tracks free-form activity by estimating a 3D skeleton pose that consists of a set of joints of the human body. In particular, we combine signal separation and joint movement modeling …

Negations Of Probability Distributions: A Survey, Ildar Z. Baryrshin, Nailya I. Kubysheva, Venera R. Bayrasheva, Olga Kosheleva, Vladik Kreinovich

Departmental Technical Reports (CS)

In recent years many papers have been devoted to the analysis and applications of negations of finite probability distributions (PD), first considered by Ronald Yager. This paper gives a brief overview of some formal results on the definition and properties of negations of PD. Negations of PD are generated by negators of probability values transforming element-by-element PD into a negation of PD. Negators are non-increasing functions of probability values. There are two types of negators: PD-independent and PD-dependent negators. Yager's negator is fundamental in the characterization of linear PD-independent negators as a convex combination of Yager's negator and uniform negator. …

(R1494) Approximate Solutions Of The Telegraph Equation, Ilija Jegdić

Applications and Applied Mathematics: An International Journal (AAM)

In this paper the initial boundary value problems for the linear telegraph equation in one and two space dimensions are considered. To find approximate solutions, a recently proposed optimization-free approach that utilizes artificial neural networks with one hidden layer is used, in which the connecting weights from the input layer to the hidden layer are chosen randomly and the weights from the hidden layer to the output layer are found by solving a system of linear equations. One of the advantages of this method, in comparison to the usual discretization methods for the two-dimensional linear telegraph equation, is that this …

Psl-An Expert System To Evaluate Degree Plans, Robert Swanson

Computer Science & Engineering Student Projects

This paper describes a general-purpose expert system to evaluate degree plans according to the individual preferences of a college student. This system implements a preference specification language (PSL) on top of this expert system to allow for the textual expression of certain requirements and preferences that the system uses for evaluation. The PSL evaluator produces a single value to describe how well it meets the student’s preferences, which a plan generation system could use to create a degree plan optimized according to the specification.

Deep Learning Strategies For Pool Boiling Heat Flux Prediction Using Image Sequences, Connor Heo

Graduate Theses and Dissertations

The understanding of bubble dynamics during boiling is critical to the design of advanced heater surfaces to improve the boiling heat transfer. The stochastic bubble nucleation, growth, and coalescence processes have made it challenging to obtain mechanistic models that can predict boiling heat flux based on the bubble dynamics. Traditional boiling image analysis relies on the extraction of the dominant physical quantities from the images and is thus limited to the existing knowledge of these quantities. Recently, machine-learning-aided analysis has shown success in boiling crisis detection, heat flux prediction, real-time image analysis, etc., whereas most of the existing studies are …

Respiratory Compensated Robot For Liver Cancer Treatment: Design, Fabrication, And Benchtop Characterization, Mishek Jair Musa

Graduate Theses and Dissertations

Hepatocellular carcinoma (HCC) is one of the leading causes of cancer-related death in the world. Radiofrequency ablation (RFA) is an effective method for treating tumors less than 5 cm. However, manually placing the RFA needle at the site of the tumor is challenging due to the complicated respiratory induced motion of the liver. This paper presents the design, fabrication, and benchtop characterization of a patient mounted, respiratory compensated robotic needle insertion platform to perform percutaneous needle interventions. The robotic platform consists of a 4-DoF dual-stage cartesian platform used to control the pose of a 1-DoF needle insertion module. The active …

How To Select Typical Objects, Mariana Benitez, Jeffrey Weidner, Vladik Kreinovich

Departmental Technical Reports (CS)

In many practical situations, we have a large number of objects, too many to be able to thoroughly analyze each of them. To get a general understanding, we need to select a representative sample. For us, this problem was motivated to analyze the possible effect of an earthquake on buildings in El Paso, Texas. In this paper, we provide a reasonable formalization of this problem, and provide a feasible algorithm for solving thus formalized problem.

How To Simulate If We Only Have Partial Information But We Want Reliable Results?, Vladik Kreinovich, Olga Kosheleva

Departmental Technical Reports (CS)

The main objective of a smart energy system is to make control decisions that would make energy systems more efficient and more reliable. To select such decisions, the system must know the consequences of different possible decisions. Energy systems are very complex, they cannot be described by a simple formula, the only way to reasonably accurately find such consequences is to test each decision on a simulated system. The problem is that the parameters describing the system and its environment are usually known with uncertainty, and we need to produce reliable results -- i.e., results that will be true for …

Book Review: Is Law Computable?: Critical Perspectives On Law And Artificial Intelligence, F. Tim Knight

Librarian Publications & Presentations

No abstract provided.

Natively Implementing Deep Reinforcement Learning Into A Game Engine, Austin Kincer

Undergraduate Honors Theses

Artificial intelligence (AI) increases the immersion that players can have while playing games. Modern game engines, a middleware software used to create games, implement simple AI behaviors that developers can use. Advanced AI behaviors must be implemented manually by game developers, which decreases the likelihood of game developers using advanced AI due to development overhead.

A custom game engine and custom AI architecture that handled deep reinforcement learning was designed and implemented. Snake was created using the custom game engine to test the feasibility of natively implementing an AI architecture into a game engine. A snake agent was successfully trained …

Extracting Clinical Event Sequence By Using Association Rule Mining To Predict Clinical Events From Health Records, Aashara Shrestha

Computer Science and Engineering Dissertations - Archive

Data mining is the process of extracting useful information from large amounts of data. Data mining has been around for a long time, and there are many multiple methods of performing data mining. However, the abundance of data that has become available in the last decade has made it possible to mine through this data to uncover important patterns and sequences. The relationship between variables and the way in which they can lead to a specific outcome is an interesting area of research. Today's healthcare industry faces a number of challenges. Providers must reduce costs, improve transparency, and improve the …

Adaptive Human-Robot Motion Transfer For Complete Body Imitation, Francisco Villa

Computer Science and Engineering Theses - Archive

Programming robot systems to perform certain tasks is a big challenge especially if such programming is to be performed by persons who are not experts in robotics. For example, when programming a robot to serve as an exercise trainer, the person defining the motions might more naturally be a person in the exercise domain rather than a robotics expert. To address this, this thesis investigates programming by demonstration or teleoperation using full direct body motion. The goal is to reproduce gaits, gestures, and postures on a humanoid robot from observed human demonstrations. Fine motor movements such as movement of fingers …