Student

Unsupervised Anomaly Detection in Brain MRIComparison Analysis between 3D AutoEncoder vs 3D Denoising Diffusion Probabilistic Model

My name is Kenny Shema, and I am a class of 2025 student pursuing a major in Computer Science and Economics. Project: My project consists of a personalized music recommendation system that uses real-time heartbeat data to suggest songs matching the user’s current mood or energy level. Built with a focus on integrating wearable sensor … Read more

Introduction My name is Helena Aleluya José, and I’m an international student from Angola. I’m also a Computer Science and Theater double major, and an African and African-American Studies and Creative Writing double minor. As both a computer scientist and a playwright, I wanted to create a project that reflects the intersection of my passions. … Read more

Pet identification is important for veterinary care, pet ownership,and animal welfare and control. This proposal presents a solutionfor identifying dog breeds using dog images. The proposed methodapplies a deep learning approach to identify the dog breeds. Thestarting point for this method is transfer learning by retrainingexisting pre-trained convolutional neural networks on the StanfordDog database. Three … Read more

https://drive.google.com/file/d/1yBK7uZNzXtXtgwcIjN8yK_OHUAvJ-nBo/view?usp=sharing

https://drive.google.com/file/d/15QPCIknb-98ExVGaiHMRalbu-9zoQ7Dg/view?usp=sharing

The new version is the one used for the project but ver 5 was the last version to still include the sources for pitch A.

Abstract: This paper presents the structure and design of a novel open-source textual database named the Brick Database for Minecraft settlements. Aimed at addressing the current lack of comprehensive datasets for model training in the Generative Design in Minecraft Competition (GDMC), this study explores the methodologies and potential challenges in creating a textual database and … Read more

Machine learning to automatized music composition This project aims to build a system that uses machine learning algorithms to generate original music compositions based on original ones. This project will be studying machine learning techniques for pattern recognition.  The feedback I received from this seems to be more approachable than my first pitch, but I … Read more

Idea #1  My research question:  What algorithms can be used to simulate policy making? Public policy should obviously be for all citizens, but people often feel that their voices and real needs are not reflected in policy. In my home country of Japan, I have witnessed many voices on Twitter (now called X) about the … Read more

Facial Expression Recognition: This pitch will focus on facial expression recognition (FER) using convolutional neural networks (CNNs), which helps people with difficulties in communication, analyzes human’s emotion, and helps with development of AI in supporting humans during their daily life. Dataset: CK+ : 48×48 pixels images in grayscale format; face cropped; emotions includes anger (45 … Read more

Pitch 1: Reduce the encounter of local minima in heuristic search space. In the heuristic search space of heuristic algorithms, there are areas where the nodes appear to be closer to the goal state, but when the algorithm encounters these areas, they actually wasted more resources to reach the goal. These areas are called local … Read more

Pitch #1: “Online Child Safety: Using deep learning to detect inappropriate video content for children.”:  In today’s digital world, where online content is easily accessible, my project aims to use deep learning and machine learning techniques, such as Neural Networks, to tackle the challenge of inappropriate content on video platforms like YouTube. Using advanced image … Read more

Saki Pitches Data visualization (information visualization)I would like to create data visualizations about the rate of females in STEM areas in different countries /eras. One of the visualizations I can think of is a map visualization since I would like to focus on areas. I specifically would like to explore the cause why Korean females … Read more

This is a test

This is a test

About Me: I am Andex Nguyen, a Senior who’s majoring in Data Science. Introduction: Since 2020 when the pandemic struck us for the first time, Covid-19 has always been a globally noteworthy issue. In this project, the questions that I am trying to find the answers for are how different countries in 1 region, specifically … Read more

Uprisings are an act of resistance/rebellion. Uprisings could be the general population rising against the government (such as the protests in Zimbabwe as people protest over the poor economic conditions) or it could be people with morally questionable intentions against the general populace such as the Boko Haram in Nigeria. It is important to predict … Read more

Hi, my name is Overpower Gore but everyone calls me OPG. I am a senior Data Science student at Earlham College with a passion for information technology. I have held multiple internships impacting positive organizational outcomes through software development, data analysis, and data visualization.

1) I am interested in completing research related to the use of machine learning to generate decision trees which control non-player character behavior in video games. Decision trees are relatively interpretable and have a high-level correspondence to behavior trees, which are used in the most common approach to AI for video games (Świechowski, 2022). I … Read more

1) I am interested in completing research related to the use of machine learning to generate decision trees which control non-player character behavior in video games. Decision trees are relatively interpretable and have a high-level correspondence to behavior trees, which are used in the most common approach to AI for video games (Świechowski, 2022). I … Read more

Machine Learning and Dueling: A fighters skill comes from their training, their learned experience through failure, and thousands of reps. This is also exactly how reinforcement learning agents gain their skills– I propose a mutli-agent learning experiment where we attempt to teach two agents how to fight with swords and shields. There are a couple … Read more

About me My name is Hang “Hailee” Dang. I am a senior majoring in Data Science with interest in Finance, Data and Business Analytics. My project Abstract Purpose: This paper aims to find a new metric on predicting a technology company’s stock performance besides 5 fundamentals metrics that have been proved and frequently used in … Read more

Hello! My name is Tamara and I am a senior Computer Science Major at Earlham College and this is my capstone project. I am interested in applying machine learning and other computational techniques for better understanding of social issues. Here is the abstract of my capstone project proposal. Unmanned Aerial Vehicles (UAVs) have only recently … Read more

Hello! My name is Tamara and I am a senior Computer Science Major at Earlham College and this is my capstone project. I am interested in applying machine learning and other computational techniques for better understanding of social issues. Here is the abstract of my capstone project proposal. Unmanned Aerial Vehicles (UAVs) have only recently … Read more

My name is Khoa, and I am a senior, double-major in Quantitative Economics and Data Science. My tentative project focuses on the application of Machine Learning to study the physical-chemical properties of different molecule structures, which has been proven useful in many fields like drug discovery, materials science, biology, etc.

Hi everyone, I am Devin. I’m a Data Science major and a senior. For my project, I am creating a win probability model for the National Hockey League. Hockey has been one of my favorite sports since I was a little kid and applying statistical concepts to one of my favorite sports excites me. Ultimately, … Read more

I am Tra-Vaughn James, a Computer Science major, and Junior: Today, Bioinformatics is an evolving field, in which computing resources have become more powerful, readily available and workflows have increased in complexity. New workflow management tools (WMT) attempt to develop software that fully harnesses this computational power, creating intuitive implementations utilizing machine learning techniques. This … Read more

Abstract A low-cost portable sensor system allows users to monitor the different components of the air quality around them. There is a need for a sensor system like this because of the millions of deaths and diseases that occur every year due to air pollution worldwide. My planned contribution is for the prototype sensor system … Read more

Final Proposal: https://drive.google.com/file/d/1G8MKPq0wwN7Z83wQYncKorOK_4xJpni6/view?usp=sharing Presentation: https://drive.google.com/file/d/1UC4GmRP-SzGlXY010vyLMKU9AB8n6Y7C/view?usp=sharing

Link: https://docs.google.com/document/d/14-kZlVRu6MqjkvnUXy2IIli00XBygPaH0rUzN811xeY/edit?usp=sharing

Pitch 1: Website that creates tangible, engaging visualizations of probabilities. Humans are poor at conceptualizing probability. I notice that one common reason anti-vaxxers use for refusing the vaccine is that they’d rather take their chances with catching covid than get the shot and come down with complications, which is far rarer than the chance of … Read more

Code project: https://code.cs.earlham.edu/ldhoang18/cs488-capstone

Pitch #1 The  use of computing resources allows the processing of biological data and computational analysis. However in order to conver this data into useful information requires the us of a large number oftools, parameters, and dynamically changing reference data. As a result workflow managers such asSnake and OpenWDL were created to make these workflow … Read more

Idea #1 Using machine learning to identify if a webpage is malicious, sometimes websites are blacklisted and that’s how they are identified as malicious but its cumbersome to do that for every website and constant new sites, use ML to identify malicious sites based on keyword density and improve upon existing methods. Other factors that … Read more

Idea 1 : Maze Generation I would like to examine maze generation algorithms for the purpose of generating more challenging domains for search algorithms to solve. Creating domains that challenge existing search algorithms can assist in the development of more robust search algorithms that can avoid certain pitfalls of existing algorithms. Additionally, mazes are widely … Read more

Maze generation and solving: Hai, Zhou, Maze Router: Lee Algorithm These slides from Northwestern University give a great overview of maze routing algorithms. They discuss Lee algorithm, Handlock’s algorithm, Soukup’s algorithm, and more, along with their strengths and weaknesses, and runtime comparisons. This will be a useful resource to learn a little bit about various … Read more

I want to create a tool that will protect a web application from malicious attacks. As a start, I would like to build a simple website where multiple users are able to sign up, authenticate and store information. Then, I will attempt ethical hacking using injection attacks, like cross-site scripting (XSS) and SQL injection (SQLi). … Read more

Pitch #1 We all at some point have received that suspicious message stating that we are being watched or an annoying pop up in which insists that our devices are riddled with virus’s. I seek to find out how often and by what measure are people being trully attacked on there smart devices. As many … Read more

ABSTRACT: Voting is an important Ensemble Learning technique. However, there has not been much discussion about leveraging the base classifiers’ consensus on unlabeled data to better inform the final prediction. My proposed method identifies the data points where the ensemble reaches consensus and where conflict arises in the unlabeled space. A meta weighted KNN model … Read more

Chest X-Ray Abnormalities Detection with a focus on Infiltration Abstract Navigating chest X-rays is an obligatory step to determine lung and heart diseases. Since many people now believe that Chest X-ray radiographs can detect COVID-19, the disease of the decade, the problem of Chest X-ray Abnormalities Detection has gained increasing attention from researchers. Numerous machine … Read more

Project abstract: Heuristic evaluation is one of the most popular methods for usability evaluation in Human-Computer Interaction (HCI). However, most heuristic models only provide generic heuristic evaluation for the entire application as a whole, even though different parts of an application might serve users in different contexts, leading HCI practitioners to miss out on context-dependent … Read more

Predicting cryptocurrency price movements is a well-known problem of interest. In this modern age, social media represents the public sentiment about current events. Twitter especially has attracted a lot of attention from researchers who are studying the public sentiments. Recent studies in natural language processing develop automatic techniques in analyzing sentiment in social media information. … Read more

Software demo video Software Architecture Diagram:

dongcao_research_paper_draft1.pdf

Annotated Bibliography 1 – Topic: Recommender System using Collaborative Filtering algorithm Annotated Bibliography 2 – Topic: Optical Character Recognition Literature Review Research Proposal

dongcao_final_proposal.pdf

dongcao_annotated_bibliography.pdf

Pitch 1 – Develop an API for Sensor I was hoping to work with sensors to develop an interface/app that would be more useful forindividuals’ projects. Say there was this sensor that measured water quality that was inexpensive,but pretty rudimentary and it doesn’t really have a good API already, I could make an app thatwould … Read more

Pitch 1 Social media sentiments to predict mental health of people during the stages of pandemic in the United States I think it is important to know how people are feeling, whether they are hopeful, devastated, excited, or feeling fine during the pandemic. With new variants showing up, people’s sentiments may keep changing. So, I … Read more

Cryptocurrency price prediction This would predict crypto currency prices using deep learning. As cryptocurrency popularity is increasing in the modern age and the money flow is increasing this is making cryptocurrencies more volatile and the patterns are changing. Some of the problems faced are as unlike the stock market cryptocurrencies are dependent on factors such … Read more

A new voting ensemble scheme Voting is a popular technique in Machine Learning to aggregate the predictions of multiple models and produce a more robust prediction. Some of the most widely used voting schemes are majority voting, rank voting, etc. I hope to propose a new voting system that particularly focuses on solving the issue … Read more

Final Paper A final version of the paper can be found here. Final Repository A final version of the repository can be found here. Changes Demographic weighting was added, as was a file that turns Rhode Island into 3 districts. Unfortunately, Pennsylvania and Kentucky data was never added due to time constraints, and such has … Read more

Abstract Modern internet architecture faces the challenge of centralized services by big tech companies, which capitalizes on the users’ information. Most of the well-known chat services at the moment have to depend on a third party server which stores the users’ conversation. We also have to face the challenge of regulation, and government authorization. To … Read more