Computer Sciences Commons^™

Architectural Elements Contributing To Interpretability Of Deep Neural Networks (Dnns), Emily Barnes, James Hutson

Faculty Scholarship

The interpretability of Deep Neural Networks (DNNs) has become a critical focus in artificial intelligence and machine learning, particularly as DNNs are increasingly used in high-stakes applications like healthcare, finance, and autonomous driving. Interpretability refers to the extent to which humans can understand the reasons behind a model's decisions, which is essential for trust, accountability, and transparency. However, the complexity and depth of DNN architectures often compromise interpretability as these models function as "black boxes." This article reviews key architectural elements of DNNs that affect their interpretability, aiming to guide the design of more transparent and trustworthy models. The primary …

Navigating The Complexities Of Ai: The Critical Role Of Interpretability And Explainability In Ensuring Transparency And Trust, Emily Barnes, James Hutson

Faculty Scholarship

The interpretability and explainability of deep neural networks (DNNs) are paramount in artificial intelligence (AI), especially when applied to high-stakes fields such as healthcare, finance, and autonomous driving. The need for this study arises from the growing integration of AI into critical areas where transparency, trust, and ethical decision-making are essential. This paper explores the impact of architectural design choices on DNN interpretability, focusing on how different architectural elements like layer types, network depth, connectivity patterns, and attention mechanisms affect model transparency. Methodologically, the study employs a comprehensive review of case studies and experimental results to analyze the balance between …

Combinatorial Creativity: Knowledge Graphs And Idea Generation In Crowdsourcing Innovation, Zhi Wei Vincent Mack

Dissertations and Theses Collection (Open Access)

This dissertation explores the dynamic interplay between combinatorial creativity and technology-driven innovation within various knowledge-intensive fields. It critically examines the role of combinatorial creativity in generating groundbreaking innovations by amalgamating existing ideas and technologies. This research incorporates a detailed examination of how knowledge, whether tacit or explicit, can be transformed into actionable data to foster innovation in crowdsourcing contexts. Chapter 2 provides an overview of the relevant literature on how Artificial Intelligence and Knowledge Management Systems can support combinatorial creativity. The study further delves into the transformative impact of knowledge management systems, particularly focusing on crowdsourcing platforms that leverage collective …

Evaluating Methods For Assessing Interpretability Of Deep Neural Networks (Dnns), Emily Barnes, James Hutson

Faculty Scholarship

The interpretability of deep neural networks (DNNs) is a critical focus in artificial intelligence (AI) and machine learning (ML), particularly as these models are increasingly deployed in high-stakes applications such as healthcare, finance, and autonomous systems. In the context of these technologies, interpretability refers to the extent to which a human can understand the cause of a decision made by a model. This article evaluates various methods for assessing the interpretability of DNNs, recognizing the significant challenges posed by their complex and opaque nature. The review encompasses both quantitative metrics and qualitative evaluations, aiming to identify effective strategies that enhance …

Securing The Inbox: Advancing Phishing Email Detection With Fine-Tuned Bert, Fatima Rashed Al Saedi

Theses

In recent years, phishing attacks have persisted as a widespread threat in the contemporary digital environment, presenting substantial risks to individuals and organizations. Cybercriminals are devising increasingly sophisticated strategies to deceive users through malicious emails. In response to this challenge, this research focuses on developing a new tool for detecting phishing emails utilizing the BERT algorithm. The tool aims to enhance email security by accurately identifying deceptive emails and protecting users from potential cyber threats. The primary objective of this study is to investigate how leveraging the BERT algorithm can improve the detection of phishing emails compared to traditional methods. …

Prescribed-Time Nash Equilibrium Seeking For Pursuit-Evasion Game, Lei Xue, Jianfeng Ye, Yongbao Wu, Jian Liu, D. C. Wunsch

Electrical and Computer Engineering Faculty Research & Creative Works

Dear Editor, this letter is concerned with prescribed-time Nash equilibrium (PTNE) seeking problem in a pursuit-evasion game (PEG) involving agents with second-order dynamics. In order to achieve the prior given and user-defined convergence time for the PEG, a PTNE seeking algorithm has been developed to facilitate collaboration among multiple pursuers for capturing the evader without the need for any global information. Then, it is theoretically proved that the prescribed-time convergence of the designed algorithm for achieving Nash equilibrium of PEG. Eventually, the effectiveness of the PTNE method was validated by numerical simulation results.

Design And Implementation Of A Vision-Based Deep-Learning Protocol For Kinematic Feature Extraction With Application To Stroke Rehabilitation, Juan Diego Luna Inga

Master's Theses

Stroke is a leading cause of long-term disability, affecting thousands of individuals annually and significantly impairing their mobility, independence, and quality of life. Traditional methods for assessing motor impairments are often costly and invasive, creating substantial barriers to effective rehabilitation. This thesis explores the use of DeepLabCut (DLC), a deep-learning-based pose estimation tool, to extract clinically meaningful kinematic features from video data of stroke survivors with upper-extremity (UE) impairments.

To conduct this investigation, a specialized protocol was developed to tailor DLC for analyzing movements characteristic of UE impairments in stroke survivors. This protocol was validated through comparative analysis using peak …

Navigating The Ethical Terrain Of Ai In Higher Education: Strategies For Mitigating Bias And Promoting Fairness, Emily Barnes, James Hutson

Faculty Scholarship

Artificial intelligence (AI) and machine learning (ML) are transforming higher education by enhancing personalized learning and academic support, yet they pose significant ethical challenges, particularly in terms of inherent biases. This review critically examines the integration of AI in higher education, underscoring the dual aspects of its potential to innovate educational paradigms and the essential need to address ethical implications to avoid perpetuating existing inequalities. The researchers employed a methodological approach that analyzed case studies and literature as primary data collection methods, focusing on strategies to mitigate biases through technical solutions, diverse datasets, and strict adherence to ethical guidelines. Their …

Interpretable Learning In Multivariate Big Data Analysis For Network Monitoring, José Camacho, Katarzyna Wasielewska, Rasmus Bro, David Kotz

Dartmouth Scholarship

There is an increasing interest in the development of new data-driven models useful to assess the performance of communication networks. For many applications, like network monitoring and troubleshooting, a data model is of little use if it cannot be interpreted by a human operator. In this paper, we present an extension of the Multivariate Big Data Analysis (MBDA) methodology, a recently proposed interpretable data analysis tool. In this extension, we propose a solution to the automatic derivation of features, a cornerstone step for the application of MBDA when the amount of data is massive. The resulting network monitoring approach allows …

Accessible Real-Time Eye-Gaze Tracking For Neurocognitive Health Assessments, A Multimodal Web-Based Approach, Daniel C. Tisdale

Master's Theses

We introduce a novel integration of real-time, predictive eye-gaze tracking models into a multimodal dialogue system tailored for remote health assessments. This system is designed to be highly accessible requiring only a conventional webcam for video input along with minimal cursor interaction and utilizes engaging gaze-based tasks that can be performed directly in a web browser. We have crafted dynamic subsystems that capture high-quality data efficiently and maintain quality through instances of user attrition and incomplete calls. Additionally, these subsystems are designed with the foresight to allow for future re-analysis using improved predictive models, as well as enable the creation …

On Coresets For Fair Clustering In Metric And Euclidean Spaces And Their Applications, Sayan Bandyapadhyay, Fedor V. Fomin, Kirill Simonov

Computer Science Faculty Publications and Presentations

Fair clustering is a constrained clustering problem where we need to partition a set of colored points. The fraction of points of each color in every cluster should be more or less equal to the fraction of points of this color in the dataset. The problem was recently introduced by Chierichetti et al. (2017) [1]. We propose a new construction of coresets for fair clustering for Euclidean and general metrics based on random sampling. For the Euclidean space Rd, we provide the first coreset whose size does not depend exponentially on the dimension d. The question of whether such constructions …

A Generic Blood Banking And Transfusion Process-Oriented Architecture For Virtual Organizations, Anwar Rjoop, Shaima Elhaj, Dina Tbaishat, Yousra Odeh, Asem Mansour, Mohammed Odeh

All Works

Background Blood banks are an important part of healthcare systems. They embrace critical processes that start with donor recruitment and blood collection, followed by blood processing to produce different types of blood components used in transfusions, blood storage, blood distribution, and transfusion. Blood components must be generated at high quality, preserved safely, and transfused in a timely manner. This can be achieved by operating interrelated processes within a complex network. There is no comprehensive blueprint of Blood Banking and Transfusion (BB&T) processes and their relationships; therefore, this study aims to develop and evaluate a BB&T process architecture using the Riva …

Strategic Integration Of Ai In Higher Education And Industry: The Ai8-Point Model, Emily Barnes, James Hutson

Faculty Scholarship

The AI8-Point Model, derived from extensive experience in technology, AI, and higher education administration, addresses the critical need for cost-effective, high-impact strategies tailored to higher education. Despite the transformative potential of AI in enhancing student engagement, optimizing processes, and improving educational outcomes, institutions often struggle with practical implementation. The AI8-Point Model fills this gap by offering strategies that balance cost and impact. Visualized as a circle divided into four quadrants, the model encompasses phases of student engagement and institutional interaction: pre-enrollment beyond institutional control, pre-enrollment within institutional control, post-enrollment within institutional control, and post-enrollment beyond institutional control. Each quadrant contains …

Snpaimer: R Package For Evaluating Ancestry Informative Marker Contributions In Non-Model Population Diagnostics, Kim L. Vertacnik, Oksana V. Vernygora, Julian R. Dupuis

Entomology Faculty Publications

Motivation: Single nucleotide polymorphism (SNP) markers are increasingly popular for population genomics and inferring ancestry for individuals of unknown origin. Because large SNP datasets are impractical for rapid and routine analysis, diagnostics rely on panels of highly informative markers. Strategies exist for selecting these markers, however, resources for efficiently evaluating their performance are limited for non-model systems.

Results: snpAIMeR is a user-friendly R package that evaluates the efficacy of genomic markers for the cluster assignment of unknown individuals. It is intended to help minimize panel size and genotyping effort by determining the informativeness of candidate diagnostic markers. Provided genotype data …

(R2073) Analysis Of Mmap/Ph(1), Ph(2)/1 Preemptive Priority Queueing Model With Single Vacation, Repair And Impatient Customers, S. Meena, G. Ayyappan

Applications and Applied Mathematics: An International Journal (AAM)

In this paper, we analyse a single server preemptive priority queue with phase-type vacation and repair, feedback, working breakdown, close-down and impatient customers. Customers arrive according to the Marked Markovian Arrival Process and their service time according to Phase-type distribution. If the High Priority customers need feedback, they lose their priority and join the Low Priority queue. At any instant, if the server is broken down, the server provide service with slow mode for that current customer and then the server will go into a repair process. When there are no customers present in both the queues, the server close-down …

(R2081) Analysis Of A Flexible Group Service Map/Ph/1 Queueing Model With Soft Failure And Reneging, S. Kalaiarasi, G. Ayyappan

Applications and Applied Mathematics: An International Journal (AAM)

Queueing models where services are offered in groups (or blocks or batches) have shown to be very helpful in real-world applications and these queues have been well studied in the literature. In this paper we see one such group service queueing model with soft failure and reneging; here, by soft failure, we mean an emergency arrival. The arrival process is a Markovian arrival, whereas the emergency arrival follows an exponential distribution. Customers are served in groups ranging in size from 1 to a fixed constant, let’s say N. A batch’s service time is determined by the phase-type distribution that corresponds …

Present Case Studies Highlighting Practical Implications Of Architectural Design Choices, Emily Barnes, James Hutson

Faculty Scholarship

The interpretability of deep neural networks (DNNs) has become a crucial focus within artificial intelligence and machine learning, particularly as these models are increasingly used in high-stakes applications such as healthcare, finance, and autonomous driving. This article explores the impact of architectural design choices on the interpretability of DNNs, emphasizing the importance of transparency, trust, and accountability in AI systems. By presenting case studies and experimental results, the article highlights how different architectural elements—such as layer types, network depth, connectivity patterns, and attention mechanisms—affect model interpretability and performance. The discussion is structured into three main sections: real-world applications, architectural trade-offs, …

College Course Assignment: Maximality, Fairness, Scheduling, Emily Y. Gao

Computer Science Senior Theses

Course selection processes in universities are crucial for shaping students’ academic experiences. At Dartmouth College, undergraduates participate in a structured course selection process each term, governed by specific constraints and priorities. This thesis examines the optimization of course assignment algorithms within Dartmouth’s environment to enhance student satisfaction and maximize course enrollment. An initial investigation reveals that Dartmouth’s registrar effectively fills course seats but identifies areas for improving student satisfaction. Hypothetical scenarios beyond Dartmouth’s framework, such as indistinct priorities and excess course selections, are also explored, proposing efficient solutions with polynomial time complexity.

This thesis emphasizes fairness in the optimization process, …

Does Generative Ai Facilitate Investor Trading? Evidence From Chatgpt Outages, Qiang Cheng, Pengkai Lin, Yue Zhao

Research Collection School Of Accountancy

In this paper, we use ChatGPT outages to investigate whether investors rely on generative artificial intelligence (GAI) to perform trading-related tasks and the associated impact on stock price informativeness. We first document a significant decline in stock trading volume during ChatGPT outages and find that the effect is stronger for firms with corporate news released immediately before or during the outages. We further document similar declines in the short-run price impact, return variance, and bid-ask spreads, consistent with a reduction in informed trading during the outage periods. Lastly, we use trading volume changes during outages to construct a firm-level measure …

Crime Prediction Using Agent-Based Modeling, Yifei Gong

Dissertations, Theses, and Capstone Projects

Crime risk evaluation and crime prediction using agent-based modeling (ABM) have gained popularity in the field of computational criminology in recent years. Traditionally, researchers rely on statistical methods and machine learning models to predict crimes using historical data. ABM generates macro-level crime patterns in a bottom-up fashion by simulating the daily behaviors of autonomous entities, such as citizens and offenders. ABM takes into consideration the non-linear interactions between agents under complex social contexts. Currently, the comprehensive usage of ABM for criminological theory testing and urban policy evaluations calls for a unified software framework. In this research, we introduce CARESim, an …

Context In Computer Vision: A Taxonomy, Multi-Stage Integration, And A General Framework, Xuan Wang

Dissertations, Theses, and Capstone Projects

Contextual information has been widely used in many computer vision tasks, such as object detection, video action detection, image classification, etc. Recognizing a single object or action out of context could be sometimes very challenging, and context information may help improve the understanding of a scene or an event greatly. However, existing approaches design specific contextual information mechanisms for different detection tasks.

In this research, we first present a comprehensive survey of context understanding in computer vision, with a taxonomy to describe context in different types and levels. Then we proposed MultiCLU, a new multi-stage context learning and utilization framework, …

Communication Challenges In Underwater Wireless Networks: Mac Protocols And Software Solutions, Dmitrii Dugaev

Dissertations, Theses, and Capstone Projects

Underwater wireless networks (UWNs) represent a diverse and intriguing research domain, encompassing a wide array of scientific and industrial applications. This dissertation delves into the communication challenges at the Medium Access Control (MAC) layer within UWNs, stemming from the distinctive signal propagation conditions and the harshness of the deployment environment. The manuscript provides comprehensive coverage of key aspects of UWNs, including potential applications, communication protocols, methodologies employed in such networks, and existing software solutions that facilitate simulation, emulation, and real testbed scenarios for underwater research endeavors. Furthermore, this research introduces innovative software and communication solutions designed to facilitate the seamless …

Assessing Job Vulnerability And Employment Growth In The Era Of Large Language Models (Llms), Prudence P. Brou

Dissertations, Theses, and Capstone Projects

This paper explores the impact of Large Language Models (LLMs) and artificial intelligence (AI) on white-collar occupations in the context of job vulnerability and employment growth. Utilizing the Kaggle dataset "Occupation Salary and Likelihood of Automation," the study employs a data-driven approach to analyze trends across states. Through interactive data visualization, the project aims to provide actionable insights for affected workers, businesses, and policymakers navigating the changing dynamics of the workforce amidst technological advancements.

The Efficacy Of Using Machine Learning Techniques For Identifying And Classifying “Fake News”, Muhammad Islam

Dissertations, Theses, and Capstone Projects

In today's digital world, detecting fake news has emerged as a critical challenge, one that has significant effects on democracy and public discourse at large both regionally and globally. This research studies how diversity of news sources in training datasets affects how well machine learning models can classify fake vs true news. I used the Linear Support Vector Classification (LinearSVC) to create and compare two classification models: one was trained on a dataset that only had real news from a singular source, Reuters (Dataset 1), and the other was trained on a dataset that contained real news from Reuters, The …

Fish-Eye Camera-Based Real-Time Pedestrian Crossing Predicting System, Mohammed Abdulla Almesafri

Theses

Fisheye cameras are widely used in traffic monitoring for their broad view, yet their distortion challenges deep-learning models in pedestrian detection and tracking. Despite available datasets like FishEye8K, collected in Hsinchu, Taiwan, and the availability of several studies that have delved into pedestrian prediction systems, a notable gap remains: the absence of datasets specifically designed for the cultural context of the UAE. This study aims to address this gap by introducing an in-house fisheye dataset tailored to enhance the prediction and tracking of pedestrians in fisheye footage within the UAE's environment. The present study addresses the development of a Graphical …

Visualizing Privately Protected Data: Exploring The Privacy-Utility Trade-Offs, Sarah Hayi Alkaabi

Theses

In a data-driven era, achieving a balance between privacy and utility is crucial. Organizations often utilize data for research, analysis, and enhancement of services, which emphasizes the significance of effective privacy-preserving techniques to protect individuals' privacy and comply with regulations. This equilibrium is vital in data visualization to derive insightful decisions from data representations. The goal is to evaluate the trade-off between privacy preservation and data utility, understanding how differentially private parameters impact effective visualizations. Valuable insights will guide strategies for achieving optimal privacy-preserving visualization techniques. The study aims to investigate the effects on privacy and data utility in different …

Let’S Think Outside The Box: Exploring Leap-Of-Thought In Large Language Models With Multimodal Humor Generation, Shanshan Zhong, Zhongzhan Huang, Shanghua Gao, Wushao Wen, Liang Lin, Marinka Zitnik, Pan Zhou

Research Collection School Of Computing and Information Systems

Chain-of-Thought (CoT) [2, 3] guides large language models (LLMs) to reason step-by-step, and can motivate their logical reasoning ability. While effective for logical tasks, CoT is not conducive to creative problem-solving which often requires out-of-box thoughts and is crucial for innovation advancements. In this paper, we explore the Leap-of-Thought (LoT) abilities within LLMs — a nonsequential, creative paradigm involving strong associations and knowledge leaps. To this end, we study LLMs on the popular Oogiri game which needs participants to have good creativity and strong associative thinking for responding unexpectedly and humorously to the given image, text, or both, and thus …

Learning Transferable Negative Prompts For Out-Of-Distribution Detection, Tianqi Li, Guansong Pang, Xiao Bai, Wenjun Miao, Jin Zheng

Research Collection School Of Computing and Information Systems

Existing prompt learning methods have shown certain capabilities in Out-of-Distribution (OOD) detection, but the lack of OOD images in the target dataset in their training can lead to mismatches between OOD images and In-Distribution (ID) categories, resulting in a high false positive rate. To address this issue, we introduce a novel OOD detection method, named ‘NegPrompt’, to learn a set of negative prompts, each representing a negative connotation of a given class label, for delineating the boundaries between ID and OOD images. It learns such negative prompts with ID data only, without any reliance on external out-lier data. Further, current …

Anomaly Heterogeneity Learning For Open-Set Supervised Anomaly Detection, Jiawen Zhu, Choubo Ding, Yu Tian, Guansong Pang

Research Collection School Of Computing and Information Systems

Open-set supervised anomaly detection (OSAD) - a recently emerging anomaly detection area - aims at utilizing a few samples of anomaly classes seen during training to detect unseen anomalies (i.e., samples from open-set anomaly classes), while effectively identifying the seen anomalies. Benefiting from the prior knowledge illustrated by the seen anomalies, current OSAD methods can often largely reduce false positive errors. However, these methods are trained in a closed-set setting and treat the anomaly examples as from a homogeneous distribution, rendering them less effective in generalizing to unseen anomalies that can be drawn from any distribution. This paper proposes to …

Zero-Shot Out-Of-Distribution Detection With Outlier Label Exposure, Choubo Ding, Guansong Pang

Research Collection School Of Computing and Information Systems

As vision-language models like CLIP are widely applied to zero-shot tasks and gain remarkable performance on in-distribution (ID) data, detecting and rejecting out-of-distribution (OOD) inputs in the zero-shot setting have become crucial for ensuring the safety of using such models on the fly. Most existing zero-shot OOD detectors rely on ID class label-based prompts to guide CLIP in classifying ID images and rejecting OOD images. In this work we instead propose to leverage a large set of diverse auxiliary outlier class labels as pseudo OOD class text prompts to CLIP for enhancing zero-shot OOD detection, an approach we called Outlier …