Physical Sciences and Mathematics Commons^™

Eating Detection With A Head-Mounted Video Camera, Shengjie Bi, David Kotz

Computer Science Technical Reports

In this paper, we present a computer-vision based approach to detect eating. Specifically, our goal is to develop a wearable system that is effective and robust enough to automatically detect when people eat, and for how long. We collected video from a cap-mounted camera on 10 participants for about 55 hours in free-living conditions. We evaluated performance of eating detection with four different Convolutional Neural Network (CNN) models. The best model achieved accuracy 90.9% and F1 score 78.7% for eating detection with a 1-minute resolution. We also discuss the resources needed to deploy a 3D CNN model in wearable or …

Timescales Of Magma Transport In The Columbia River Flood Basalts, Determined By Paleomagnetic Data, Joseph Biasi, Leif Karlstrom

Other Staff Materials

Flood basalts represent major events in Earth History, in part because they are linked to large climate perturbations and mass extinctions. However, the durations of individual flood basalt eruptions, which directly impact potential environmental crises, are poorly constrained. Here we use a combination of paleomagnetic data and thermal modeling to create a magnetic geothermometer (MGT) that can constrain the active transport lifetime of magmatic conduits and intrusions. We apply the MGT technique to eight feeder dike segments of the Columbia River basalts (CRB), demonstrating that some dike segments were actively heating host rocks for less than one month, while other …

Exploiting Group Structures To Infer Social Interactions From Videos, Maksim Bolonkin

Dartmouth College Ph.D Dissertations

In this thesis, we consider the task of inferring the social interactions between humans by analyzing multi-modal data. Specifically, we attempt to solve some of the problems in interaction analysis, such as long-term deception detection, political deception detection, and impression prediction. In this work, we emphasize the importance of using knowledge about the group structure of the analyzed interactions. Previous works on the matter mostly neglected this aspect and analyzed a single subject at a time. Using the new Resistance dataset, collected by our collaborators, we approach the problem of long-term deception detection by designing a class of histogram-based features …

Counting And Sampling Small Structures In Graph And Hypergraph Data Streams, Themistoklis Haris

Dartmouth College Undergraduate Theses

In this thesis, we explore the problem of approximating the number of elementary substructures called simplices in large k-uniform hypergraphs. The hypergraphs are assumed to be too large to be stored in memory, so we adopt a data stream model, where the hypergraph is defined by a sequence of hyperedges.

First we propose an algorithm that (ε, δ)-estimates the number of simplices using O(m^1+1/k / T) bits of space. In addition, we prove that no constant-pass streaming algorithm can (ε, δ)- approximate the number of simplices using less than O( m ^1+1/k / T ) bits of space. Thus …

Identifying Optimal Course Structures Using Topic Models, Tehut Tesfaye Biru

Dartmouth College Undergraduate Theses

This research project investigates whether there exists an optimal way to structure topics in educational course content that results in higher levels of engagement among students. It is implemented by fitting topic models to transcripts of educational videos contained in the Khan Academy platform. The fitted models were used to extract topic trajectories across time for each video and subsequently clustered based on whether they have similar “shapes”. The differences in mean engagement metrics per cluster suggest that some course shapes are more palatable to students regardless of subject matter. Additionally, the topic trajectories suggest a constant progression of topics …

Line Sampling In Participating Media, Hsu Cheng

Dartmouth College Master’s Theses

Participating media, such as fog, fire, dust, and smoke, surrounds us in our daily life. Rendering participating media efficiently has always been a challenging task in physically based rendering. Line sampling has been derived to be an alternative method in direct lighting recently. Since line sampling takes visibility into account, it could reduce variance in the same render time compared to point sampling. We leverage the benefits of line sampling in the context of evaluating direct lighting in participating media. We express the direct lighting as a three-dimensional integral and perform line sampling in any one of them. We show …

A Configurable Social Network For Running Irb-Approved Experiments, Mihovil Mandic

Dartmouth College Undergraduate Theses

Our world has never been more connected, and the size of the social media landscape draws a great deal of attention from academia. However, social networks are also a growing challenge for the Institutional Review Boards concerned with the subjects’ privacy. These networks contain a monumental variety of personal information of almost 4 billion people, allow for precise social profiling, and serve as a primary news source for many users. They are perfect environments for influence operations that are becoming difficult to defend against. Motivated to study online social influence via IRB-approved experiments, we designed and implemented a flexible, scalable, …

Exploring The Relationship Between Intrinsic Motivation And Receptivity To Mhealth Interventions, Sarah Hong

Dartmouth College Undergraduate Theses

Recent research in mHealth has shown the promise of Just-in-Time Adaptive Interventions (JITAIs). JITAIs aim to deliver the right type and amount of support at the right time. Choosing the right delivery time involves determining a user's state of receptivity, that is, the degree to which a user is willing to accept, process, and use the intervention provided.

Although past work on generic phone notifications has found evidence that users are more likely to respond to notifications with content they view as useful, there is no existing research on whether users' intrinsic motivation for the underlying topic of mHealth …

Deterring Intellectual Property Thieves: Algorithmic Generation Of Adversary-Aware Fake Knowledge Graphs, Snow Kang

Dartmouth College Undergraduate Theses

Publicly available estimates suggest that in the U.S. alone, IP theft costs our economy between $225 billion and $600 billion each year. In our paper, we propose combating IP theft by generating fake versions of technical documents. If an enterprise system has n fake documents for each real document, any IP thief must sift through an array of documents in an attempt to separate the original from a sea of fakes. This costs the attacker time and money - and inflicts pain and frustration on the part of its technical staff.

Leveraging a graph-theoretic approach, we created the Clique-FakeKG algorithm …

Fine-Grained Detection Of Hate Speech Using Bertoxic, Yakoob Khan

Dartmouth College Undergraduate Theses

This thesis describes our approach towards the fine-grained detection of hate speech using deep learning. We leverage the transformer encoder architecture to propose BERToxic, a system that fine-tunes a pre-trained BERT model to locate toxic text spans in a given text and utilizes additional post-processing steps to refine the prediction boundaries. The post-processing steps involve (1) labeling character offsets between consecutive toxic tokens as toxic and (2) assigning a toxic label to words that have at least one token labeled as toxic. Through experiments, we show that these two post-processing steps improve the performance of our model by 4.16% on …

Lexical Complexity Prediction With Assembly Models, Aadil Islam

Dartmouth College Undergraduate Theses

Tuning the complexity of one's writing is essential to presenting ideas in a logical, intuitive manner to audiences. This paper describes a system submitted by team BigGreen to LCP 2021 for predicting the lexical complexity of English words in a given context. We assemble a feature engineering-based model and a deep neural network model with an underlying Transformer architecture based on BERT. While BERT itself performs competitively, our feature engineering-based model helps in extreme cases, eg. separating instances of easy and neutral difficulty. Our handcrafted features comprise a breadth of lexical, semantic, syntactic, and novel phonetic measures. Visualizations of BERT …

Interpreting Attention-Based Models For Natural Language Processing, Steven J. Signorelli Jr

Dartmouth College Undergraduate Theses

Large pre-trained language models (PLMs) such as BERT and XLNet have revolutionized the field of natural language processing (NLP). The interesting thing is that they are pre- trained through unsupervised tasks, so there is a natural curiosity as to what linguistic knowledge these models have learned from only unlabeled data. Fortunately, these models’ architectures are based on self-attention mechanisms, which are naturally interpretable. As such, there is a growing body of work that uses attention to gain insight as to what linguistic knowledge is possessed by these models. Most attention-focused studies use BERT as their subject, and consequently the field …

Improving Existing Methods For Calculating Embodied Carbon Emissions In Trade Through Feature Discovery: An Information Theoretic Approach, Sam Morton

Dartmouth College Undergraduate Theses

The continued societal and ecological risks posed by climate change have spurred renewed interest in quantitative tools that can improve policy aimed at climate mitigation. In 2008, international trade accounted for up to 26\% of global anthropogenic emissions, and therefore trade has garnered increased attention from policymakers seeking carbon mitigation. The concept of embodied carbon emissions in trade (EET) quantifies overall carbon emitted in the production and transport of goods for the purposes of trade. EET in theory could prove an indispensable tool to climate-concerned policymakers, but current implementations and data availability limit EET calculation to annual snapshots that extend …

Exploring The Long Tail, Joseph H. Hajjar

Dartmouth College Undergraduate Theses

The migration of datasets online has created a near-infinite inventory for big name retailers such as Amazon and Netflix, giving rise to recommendation systems to assist users in navigating the massive catalog. This has also allowed for the possibility of retailers storing much less popular, uncommon items which would not appear in a more traditional brick-and-mortar setting due to the cost of storage. Nevertheless, previous work has highlighted the profit potential which lies in the so-called "long tail'' of niche, unpopular items. Unfortunately, due to the limited amount of data in this subset of the inventory, recommendation systems often struggle …

Physically Based Rendering Techniques To Visualize Thin-Film Smoothed Particle Hydrodynamics Fluid Simulations, Aditya H. Prasad

Dartmouth College Undergraduate Theses

This thesis introduces a methodology and workflow I developed to visualize smoothed hydrodynamic particle based simulations for the research paper ’Thin-Film Smoothed Particle Hydrodynamics Fluid’ (2021), that I co-authored. I introduce a physically based rendering model which allows point cloud simulation data representing thin film fluids and bubbles to be rendered in a photorealistic manner. This includes simulating the optic phenomenon of thin-film interference and rendering the resulting iridescent patterns. The key to the model lies in the implementation of a physically based surface shader that accounts for the interference of infinitely many internally reflected rays in its bidirectional surface …

The Discrete-Event Modeling Of Administrative Claims (Demac) System: Dynamically Modeling The U.S. Healthcare Delivery System With Medicare Claims Data To Improve End-Of-Life Care, Rachael Chacko

Dartmouth College Undergraduate Theses

The shift of the U.S. healthcare delivery system from the treatment of acute conditions to chronic diseases requires a new method of healthcare system analysis to properly assess end- of-life (EOL) quality throughout the country. In this paper, we propose the Discrete-Event Modeling of Administrative Claims (DEMAC) system, which relies on a hetero-functional graph theory and discrete event-driven framework to dynamically model EOL care on multiple levels. The heat map visualizations produced by the DEMAC system enable the elucidation of not only patient-specific EOL care but also broader treatment patterns among providers and hospitals. As a whole, the DEMAC system …

Impulse Method For Shallow Water Simulation, Evan Muscatel

Dartmouth College Undergraduate Theses

The Shallow Water Equations is a simple method to simulate fluid in real-time. As a real-time model, the SWE is an excellent candidate for use in video games. However, the model is not often used in most fluid simulations because it does not preserve vorticity well, and therefore does not look very realistic. We present an improvement on the Shallow Water Equations by using a gauge method to preserve the vorticity of the fluid. We add a variable called impulse !, which is only weakly coupled with the velocity " of the simulation. We show that using this impulse method, …

Object Manipulation With Modular Planar Tensegrity Robots, Maxine Perroni-Scharf

Dartmouth College Undergraduate Theses

This thesis explores the creation of a novel two-dimensional tensegrity-based mod- ular system. When individual planar modules are linked together, they form a larger tensegrity robot that can be used to achieve non-prehensile manipulation. The first half of this dissertation focuses on the study of preexisting types of tensegrity mod- ules and proposes different possible structures and arrangements of modules. The second half describes the construction and actuation of a modular 2D robot com- posed of planar three-bar tensegrity structures. We conclude that tensegrity modules are suitably adapted to object manipulation and propose a future extension of the modular 2D …

Detecting Receptivity For Mhealth Interventions In The Natural Environment, Varun Mishra, Florian Künzler, Jan-Niklas Kramer, Elgar Fleisch, Tobias Kowatsch, David Kotz

Dartmouth Scholarship

Just-In-Time Adaptive Intervention (JITAI) is an emerging technique with great potential to support health behavior by providing the right type and amount of support at the right time. A crucial aspect of JITAIs is properly timing the delivery of interventions, to ensure that a user is receptive and ready to process and use the support provided. Some prior works have explored the association of context and some user-specific traits on receptivity, and have built post-study machine-learning models to detect receptivity. For effective intervention delivery, however, a JITAI system needs to make in-the-moment decisions about a user's receptivity. To this end, …

Exploring The Use Of Social Media To Infer Relationships Between Demographics, Psychographics And Vaccine Hesitancy, Abhimanyu Kapur

Computer Science Senior Theses

The growing popularity of social media as a platform to obtain information and share one's opinions on various topics makes it a rich source of information for research. In this study, we aimed to develop a framework to infer relationships between demographic and psychographic characteristics of a user and their opinion on a specific narrative - in this case, their stance on taking the COVID-19 vaccine. Twitter was the chosen platform due to the large USA user base and easily available data. Demographic traits included Race, Age, Gender, and Human-vs-Organization Status. Psychographic traits included the Big Five personality traits (Conscientiousness, …

Producing Easy-To-Verify Proofs Of Linearizability, Ugur Yavuz

Computer Science Senior Theses

Proofs of linearizability tend to be complex and lengthy, rendering their verification challenging for readers. We provide a novel technique to produce easy-to-verify proofs of linearizability, with the help of mechanical proof assistants. Specifically, we reduce the task of proving the correctness of a linearizable object implementation, to a proof of an inductive invariant of a slightly modified version of the implementation. As the latter is a task many mechanical proof systems (such as TLAPS) are well-suited to undertake, this reduction allows the verification of the proof by the reader, to only consist of a trivial syntactic check of whether …

Analyses And Creation Of Author Stylized Text, Keith Carlson

Dartmouth College Ph.D Dissertations

Written text is one of the major ways that humans communicate their thoughts. A single thought can be expressed through many different combinations of words, and the writer must choose which they will use. We call the idea which is communicated the content of the message, and the particular words chosen to express the content, the style. The same content expressed in a different style may tell something useful about the author of the text (e.g., the author's identity), may be easier to understand for different audiences, or may evoke different emotions in the reader.

In this work we explore …

Detection Of Health-Related Behaviours Using Head-Mounted Devices, Shengjie Bi

Dartmouth College Ph.D Dissertations

The detection of health-related behaviors is the basis of many mobile-sensing applications for healthcare and can trigger other inquiries or interventions. Wearable sensors have been widely used for mobile sensing due to their ever-decreasing cost, ease of deployment, and ability to provide continuous monitoring. In this dissertation, we develop a generalizable approach to sensing eating-related behavior.

First, we developed Auracle, a wearable earpiece that can automatically detect eating episodes. Using an off-the-shelf contact microphone placed behind the ear, Auracle captures the sound of a person chewing as it passes through the head. This audio data is then processed by a …

An Inside Vs. Outside Classification System For Wi-Fi Iot Devices, Paul Gralla

Dartmouth College Undergraduate Theses

We are entering an era in which Smart Devices are increasingly integrated into our daily lives. Everyday objects are gaining computational power to interact with their environments and communicate with each other and the world via the Internet. While the integration of such devices offers many potential benefits to their users, it also gives rise to a unique set of challenges. One of those challenges is to detect whether a device belongs to one’s own ecosystem, or to a neighbor – or represents an unexpected adversary. An important part of determining whether a device is friend or adversary is to …

Learning And Simulation Algorithms For Constraint Physical Systems, Shuqi Yang

Dartmouth College Master’s Theses

This thesis explores two computational approaches to learn and simulate complex physical systems exhibiting constraint characteristics. The target applications encompass both solids and fluids. On the solid side, we proposed a new family of data-driven simulators to predict the behaviors of an unknown physical system by learning its underpinning constraints. We devised a neural projection operator facilitated by an embedded recursive neural network to interactively enforce the learned underpinning constraints and to predict its various physical behaviors. Our method can automatically uncover a broad range of constraints from observation point data, such as length, angle, bending, collision, boundary effects, and …

A Foray Into Laboratory Scale Soil Incubations With Corn Stover And High Lignin Fermentation Byproduct, Michelle Wang

ENGS 88 Honors Thesis (AB Students)

As the production of biofuels increases to meet the demands of a growing low carbon economy, questions of sustainability surrounding its feedstock and waste streams have become increasingly relevant. In the biofuel production process, crop residues like corn stover are harvested from the field and converted to biofuels leaving generating a residue called high lignin fermentation byproduct (HLFB). From extensive process modelling in the literature, it is suggested that HLFB should be either combusted to fuel auxiliary conversion processes or returned to the soil in place of the crop residues that were harvested. Currently, there is little literature testing the …

Application Of Cycle-By-Cycle Analysis To Eeg Data From Individuals With Phelan-Mcdermid Syndrome, Naomi Miller

ENGS 88 Honors Thesis (AB Students)

This study aimed to analyze a novel method of processing data from electroencephalography (EEG) recordings, which implements time-domain cycle-by-cycle analysis. This "bycycle" method, developed by the Cole & Voytek laboratory, was implemented on a EEG dataset of children with and without Phelan-McDermid Syndrome in the hopes of uncovering network-level explanations for the genetic disorder. A supplemental Python pipeline was developed to organize and visualize the data. This led to the discovery of group-level differences in measures of cycle symmetry in alpha band waves over the sensorimotor electrodes. Through the same pipeline, the bycycle tool was validated as a sound EEG …

When Do Drivers Interact With In-Vehicle Well-Being Interventions? An Exploratory Analysis Of A Longitudinal Study On Public Roads, Kevin Koch, Varun Mishra, Shu Liu, Thomas Berger, Elgar Fleisch, David Kotz, Felix Wortmann

Dartmouth Scholarship

Recent developments of novel in-vehicle interventions show the potential to transform the otherwise routine and mundane task of commuting into opportunities to improve the drivers' health and well-being. Prior research has explored the effectiveness of various in-vehicle interventions and has identified moments in which drivers could be interruptible to interventions. All the previous studies, however, were conducted in either simulated or constrained real-world driving scenarios on a pre-determined route. In this paper, we take a step forward and evaluate when drivers interact with in-vehicle interventions in unconstrained free-living conditions.

To this end, we conducted a two-month longitudinal study with 10 …

On Mentzer’S Hardness Of The K-Center Problem On The Euclidean Plane., Raymond Chen

Computer Science Technical Reports

An instance of the k-center problem consists of n points in a metric space along with a positive integer k. The goal is to find the smallest radius r such that there exists a subset of k centers picked among them such that every point is within distance r of at least one center. Stuart Mentzer (Mentzer, 1988) wrote a paper showing that in the Euclidean plane, it is NP-Hard to approximate this problem up to a factor of √2 +√3 ≈ 1.93. However, his report is missing some details. In this note, we present details of his full construction.

A Multi-Resolution Graph Convolution Network For Contiguous Epitope Prediction, Lisa Oh

Dartmouth College Master’s Theses

Computational methods for predicting binding interfaces between antigens and antibodies (epitopes and paratopes) are faster and cheaper than traditional experimental structure determination methods. A sufficiently reliable computational predictor that could scale to large sets of available antibody sequence data could thus inform and expedite many biomedical pursuits, such as better understanding immune responses to vaccination and natural infection and developing better drugs and vaccines. However, current state-of-the-art predictors produce discontiguous predictions, e.g., predicting the epitope in many different spots on an antigen, even though in reality they typically comprise a single localized region. We seek to produce contiguous predicted epitopes, …