Computer Sciences Commons^™

When Do Data Collection And Use Become A Matter Of Concern? A Cross-Cultural Comparison Of U.S. And Dutch Privacy Attitudes, Jessica Vitak, Yuting Liao, Anouk Mols, Daniel Trottier, Michael Zimmer, Priya C. Kumar, Jason Pridmore

Computer Science Faculty Research and Publications

Around the world, people increasingly generate data through their everyday activities. Much of this happens unwittingly through sensors, cameras, and other surveillance tools on roads, in cities, and at the workplace. However, how individuals and governments think about privacy varies significantly around the world. In this article, we explore differences between people’s attitudes toward privacy and data collection practices in the United States and the Netherlands, two countries with very different regulatory approaches to governing consumer privacy. Through a factorial vignette survey deployed in the two countries, we identify specific contextual factors associated with concerns regarding how personal data are …

Boundary Regulation Processes And Privacy Concerns With (Non-)Use Of Voice-Based Assistants, Jessica Vitak, Priya C. Kumar, Yuting Liao, Michael Zimmer

Computer Science Faculty Research and Publications

An exemplar of human-machine communication, voice-based assistants (VBAs) embedded in smartphones and smart speakers simplify everyday tasks while collecting significant data about users and their environment. In recent years, devices using VBAs have continued to add new features and collect more data—in potentially invasive ways. Using Communication Privacy Management theory as a guiding framework, we analyze data from 11 focus groups with 65 US adult VBA users and nonusers. Findings highlight differences in attitudes and concerns toward VBAs broadly and provide insights into how attitudes are influenced by device features. We conclude with considerations for how to address boundary regulation …

Graph-Based Multi-Task Learning For Fault Detection In Smart Grid, Dibaloke Chanda, Nasim Yahyasoltani

Computer Science Faculty Research and Publications

Timely detection of electrical faults is of paramount importance for efficient operation of the smart grid. To better equip the power grid operators to prevent grid-wide cascading failures, the detection of fault occurrence and its type must be accompanied by accurately locating the fault. In this work, we propose a multi-task learning architecture that encodes the graph structure of the distribution network through a shared graph neural network (GNN) to both classify and detect faults and their locations simultaneously. Deploying GNNs allows for representation learning of the grid structure which can later be used to optimize grid operation. The proposed …

Abmr: An R Package For Agent-Based Model Analysis Of Large-Scale Movements Across Taxa, Benjamin Gochanour, Javier Fernández-López, Andrea Contina

School of Integrative Biological & Chemical Sciences Faculty Publications

1. Agent-based modelling (ABM) shows promise for animal movement studies. However, a robust, open-source and spatially explicit ABM coding platform is currently lacking.
2. We present abmR, an R package for conducting continental-scale ABM simulations across animal taxa. The package features two movement functions, each of which relies on the Ornstein–Uhlenbeck (OU) process.
3. The theoretical background for abmR is discussed and the main functionalities are illustrated using example populations.
4. Potential future additions to this open-source package may include the ability to specify multiple environmental variables or to model interactions between agents. Additionally, updates may offer opportunities for disease ecology and integration with …

S-400s, Disinformation, And Anti-American Sentiment In Turkey, Russell "Alex" Korb, Saltuk Karahan, Gowri Prathap, Ekrem Kaya, Luke Palmieri, Hamdi Kavak, Richard L. Wilson (Ed.), Major Brendan Curran (Ed.)

Political Science & Geography Faculty Publications

As social and political discourse in most countries becomes more polarized, anti-Americanism has risen not only in the Middle East and Latin America but also among the U.S. allies in Europe. Social media is one platform used to disseminate anti-American views in NATO countries, and its effectiveness can be magnified when mass media, public officials, and popular figures adopt these views. Disinformation, in particular, has gained recognition as a cybersecurity issue from 2016 onward, but disinformation can be manufactured domestically in addition to being part of a foreign influence campaign. In this paper, we analyze Turkish tweets using sentiment analysis …

The Mceliece Cryptosystem As A Solution To The Post-Quantum Cryptographic Problem, Isaac Hanna

Senior Honors Theses

The ability to communicate securely across the internet is owing to the security of the RSA cryptosystem, among others. This cryptosystem relies on the difficulty of integer factorization to provide secure communication. Peter Shor’s quantum integer factorization algorithm threatens to upend this. A special case of the hidden subgroup problem, the algorithm provides an exponential speedup in the integer factorization problem, destroying RSA’s security. Robert McEliece’s cryptosystem has been proposed as an alternative. Based upon binary Goppa codes instead of integer factorization, his cryptosystem uses code scrambling and error introduction to hinder decrypting a message without the private key. This …

The Role Of Machine Learning And Network Analyses In Understanding Microbial Composition In An Experimental Prairie, Ali Eastman Oku

Graduate Research Theses & Dissertations

Machine learning and network analyses are powerful modern tools can process and map out connections between large amount of ecological data from complex environmental communities. Random forests, an ensemble machine learning algorithm, are particularly powerful as they can capture complex patterns in data while remaining easily interpretable. These tools are specifically useful in experimental settings where different types of data are collected. The aim of this study was to demonstrate the utility of machine learning models and network analyses at analyzing diverse ecological data from dynamic plant-soil microbial communities in a prairie ecosystem. Our experimental system is an experimental prairie …

An Empirical Analysis Of Algorithms For Simple Stochastic Games, Cody William Klingler

Graduate Theses, Dissertations, and Problem Reports (ETD)

This thesis presents the findings of a computational study on algorithms for Simple Stochastic Games (SSG). Simple Stochastic Games are a restriction of the Shapley stochastic model motivated by their applications in AI planning, logic synthesis, and theoretical computer science. This thesis seeks to empirically assess the performance of these algorithms to compensate for their lack of strong complexity results. Where applicable, we include both variations of algorithms where stable strategies are computed by a linear-programming and naive approach. These algorithms are evaluated on random inputs, in addition to specific difficult cases that were identified experimentally. We are interested in …

A Longitudinal Study Of Factors That Affect User Interactions With Social Media And Email Spam, Wojciech M. Mazurek

Graduate Theses, Dissertations, and Problem Reports (ETD)

Given the rapid growth of social media and the increasing prevalence of spam, it is crucial to understand users’ interactions with unsolicited content to develop effective countermeasures against spam. This thesis focuses on exploring the factors that influence users’ decisions to interact with spam on social media and email. It builds upon prior work, which serves as a foundation for further research and conducting a longitudinal analysis. Our results are based on the analysis of 221 responses collected through an online survey. The survey not only gathered demographic information such as age, gender, and race but also collected data on …

Scene Representation And Matching For Visual Localization In Hybrid Camera Scenarios, Marcela A. Mera Trujillo

Graduate Theses, Dissertations, and Problem Reports (ETD)

Scene representation and matching are crucial steps in a variety of tasks ranging from 3D reconstruction to virtual/augmented/mixed reality applications, to robotics, and others. While approaches exist that tackle these tasks, they mostly overlook the issue of efficiency in the scene representation, which is fundamental in resource-constrained systems and for increasing computing speed. Also, they normally assume the use of projective cameras, while performance on systems based on other camera geometries remains suboptimal. This dissertation contributes with a new efficient scene representation method that dramatically reduces the number of 3D points. The approach sets up an optimization problem for the …

An Empirical Analysis Of Approximation Algorithms For The Unweighted Tree Augmentation Problem, Jacob Thomas Restanio

Graduate Theses, Dissertations, and Problem Reports (ETD)

In this thesis, we perform an experimental study of approximation algorithms for the tree augmentation problem (TAP). TAP is a fundamental problem in network design. The goal of TAP is to add the minimum number of edges from a given edge set to a tree so that it becomes 2-edge connected. Formally, given a tree T = (V, E), where V denotes the set of vertices and E denotes the set of edges in the tree, and a set of edges (or links) L ⊆ V × V disjoint from E, the objective is to find a set of edges …

Mentoring Deep Learning Models For Mass Screening With Limited Data, Suprim Nakarmi

Dissertations and Theses

Deep Learning (DL) has an extensively rich state-of-the-art literature in medical imaging analysis. However, it requires large amount of data to begin training. This limits its usage in tackling future epidemics, as one might need to wait for months and even years to collect fully annotated data, raising a fundamental question: is it possible to deploy AI-driven tool earlier in epidemics to mass screen the infected cases? For such a context, human/Expert in the loop Machine Learning (ML), or Active Learning (AL), becomes imperative enabling machines to commence learning from the first day with minimum available labeled dataset. In an …

A Survey Of Wearable Devices Pairing Based On Biometric Signals, Jafar Pourbemany, Ye Zhu, Riccardo Bettati

Electrical and Computer Engineering Faculty Publications

With the rapid growth of wearable devices, more applications require direct communication between wearable devices. To secure the communication between wearable devices, various pairing protocols have been proposed to generate common keys for encrypting the communication. Since the wearable devices are attached to the same body, the devices can generate common keys based on the same context by utilizing onboard sensors to capture a common biometric signal such as body motion, gait, heartbeat, respiration, and EMG signals. The context-based pairing does not need prior information to generate common keys. As context-based pairing does not need any human involvement in the …

Network Intrusion Detection With Two-Phased Hybrid Ensemble Learning And Automatic Feature Selection, Asanka Kavinda Mananayaka, Sunnie S. Chung

Electrical and Computer Engineering Faculty Publications

The use of network connected devices has grown exponentially in recent years revolutionizing our daily lives. However, it has also attracted the attention of cybercriminals making the attacks targeted towards these devices increase not only in numbers but also in sophistication. To detect such attacks, a Network Intrusion Detection System (NIDS) has become a vital component in network applications. However, network devices produce large scale high-dimensional data which makes it difficult to accurately detect various known and unknown attacks. Moreover, the complex nature of network data makes the feature selection process of a NIDS a challenging task. In this study, …

Comments Of The Cordell Institute On Ai Accountability, Neil M. Richards, Woodrow Hartzog, Jordan Francis

Scholarship@WashULaw

These comments are a response to the National Telecommunications and Information Administration's 2023 request for comment on AI accountability (AI Accountability RFC, NTIA–2023–0005).

Responding to NTIA’s recent inquiry into AI assurance and accountability, we offer two main arguments regarding the importance of substantive legal protections. First, a myopic focus on concepts of transparency, bias mitigation, and ethics (for which procedural compliance efforts such as audits, assessments, and certifications are proxies) is insufficient when it comes to the design and implementation of accountable AI systems. We call rules built around transparency and bias mitigation “AI half-measures,” because they provide the appearance …

Investigating Collaborative Explainable Ai (Cxai)/Social Forum As An Explainable Ai (Xai) Method In Autonomous Driving (Ad), Tauseef Ibne Mamun

Dissertations, Master's Theses and Master's Reports

Explainable AI (XAI) systems primarily focus on algorithms, integrating additional information into AI decisions and classifications to enhance user or developer comprehension of the system's behavior. These systems often incorporate untested concepts of explainability, lacking grounding in the cognitive and educational psychology literature (S. T. Mueller et al., 2021). Consequently, their effectiveness may be limited, as they may address problems that real users don't encounter or provide information that users do not seek.

In contrast, an alternative approach called Collaborative XAI (CXAI), as proposed by S. Mueller et al (2021), emphasizes generating explanations without relying solely on algorithms. CXAI centers …

Natural Language Processing In The Legal Domain, Daniel Martin Katz, Dirk Hartung, Lauritz Gerlach, Abhik Jana, Michael J. Ii Bommarito

Research Collection Yong Pung How School Of Law

In this paper, we summarize the current state of the field of NLP and Law with a specific focus on recent technical and substantive developments. To support our analysis, we construct and analyze a corpus of more than six hundred NLP and Law related papers published over the past decade. Our analysis highlights several major trends. Namely, we document an increasing number of papers written, tasks undertaken, and languages covered over the course of the past decade. We observe an increase in the sophistication of the methods which researchers deployed in this applied context. Slowly but surely, Legal NLP is …

El-Vit: Probing Vision Transformer With Interactive Visualization, Hong Zhou, Rui Zhang, Peifeng Lai, Chaoran Guo, Yong Wang, Zhida Sun, Junjie Li

Research Collection School Of Computing and Information Systems

Nowadays, Vision Transformer (ViT) is widely utilized in various computer vision tasks, owing to its unique self-attention mechanism. However, the model architecture of ViT is complex and often challenging to comprehend, leading to a steep learning curve. ViT developers and users frequently encounter difficulties in interpreting its inner workings. Therefore, a visualization system is needed to assist ViT users in understanding its functionality. This paper introduces EL-VIT, an interactive visual analytics system designed to probe the Vision Transformer and facilitate a better understanding of its operations. The system consists of four layers of visualization views. The first three layers include …

Dual-View Preference Learning For Adaptive Recommendation, Zhongzhou Liu, Yuan Fang, Min Wu

Research Collection School Of Computing and Information Systems

While recommendation systems have been widely deployed, most existing approaches only capture user preferences in the , i.e., the user's general interest across all kinds of items. However, in real-world scenarios, user preferences could vary with items of different natures, which we call the . Both views are crucial for fully personalized recommendation, where an underpinning macro-view governs a multitude of finer-grained preferences in the micro-view. To model the dual views, in this paper, we propose a novel model called Dual-View Adaptive Recommendation (DVAR). In DVAR, we formulate the micro-view based on item categories, and further integrate it with the …

Contextual Path Retrieval: A Contextual Entity Relation Embedding-Based Approach, Pei-Chi Lo, Ee-Peng Lim

Research Collection School Of Computing and Information Systems

Contextual path retrieval (CPR) refers to the task of finding contextual path(s) between a pair of entities in a knowledge graph that explains the connection between them in a given context. For this novel retrieval task, we propose the Embedding-based Contextual Path Retrieval (ECPR) framework. ECPR is based on a three-component structure that includes a context encoder and path encoder that encode query context and path, respectively, and a path ranker that assigns a ranking score to each candidate path to determine the one that should be the contextual path. For context encoding, we propose two novel context encoding methods, …

Demonstrating Multi-Modal Human Instruction Comprehension With Ar Smart Glass, Mudiyanselage Dulanga Kaveesha Weerakoon, Vigneshwaran Subbaraju, Tuan Tran, Archan Misra

Research Collection School Of Computing and Information Systems

We present a multi-modal human instruction comprehension prototype for object acquisition tasks that involve verbal, visual and pointing gesture cues. Our prototype includes an AR smart-glass for issuing the instructions and a Jetson TX2 pervasive device for executing comprehension algorithms. With this setup, we enable on-device, computationally efficient object acquisition task comprehension with an average latency in the range of 150-330msec.

Learning Large Neighborhood Search For Vehicle Routing In Airport Ground Handling, Jianan Zhou, Yaoxin Wu, Zhiguang Cao, Wen Song, Jie Zhang, Zhenghua Chen

Research Collection School Of Computing and Information Systems

Dispatching vehicle fleets to serve flights is a key task in airport ground handling (AGH). Due to the notable growth of flights, it is challenging to simultaneously schedule multiple types of operations (services) for a large number of flights, where each type of operation is performed by one specific vehicle fleet. To tackle this issue, we first represent the operation scheduling as a complex vehicle routing problem and formulate it as a mixed integer linear programming (MILP) model. Then given the graph representation of the MILP model, we propose a learning assisted large neighborhood search (LNS) method using data generated …

Crowdfa: A Privacy-Preserving Mobile Crowdsensing Paradigm Via Federated Analytics, Bowen Zhao, Xiaoguo Li, Ximeng Liu, Qingqi Pei, Yingjiu Li, Robert H. Deng

Research Collection School Of Computing and Information Systems

Mobile crowdsensing (MCS) systems typically struggle to address the challenge of data aggregation, incentive design, and privacy protection, simultaneously. However, existing solutions usually focus on one or, at most, two of these issues. To this end, this paper presents CROWD FA, a novel paradigm for privacy-preserving MCS through federated analytics (FA), which aims to achieve a well-rounded solution encompassing data aggregation, incentive design, and privacy protection. Specifically, inspired by FA, CROWD FA initiates an MCS computing paradigm that enables data aggregation and incentive design. Participants can perform aggregation operations on their local data, facilitated by CROWD FA, which supports various …

Seven Pillars For The Future Of Artificial Intelligence, Erik Cambria, Rui Mao, Melvin Chen, Zhaoxia Wang, Seng-Beng Ho

Research Collection School Of Computing and Information Systems

In recent years, AI research has showcased tremendous potential to impact positively humanity and society. Although AI frequently outperforms humans in tasks related to classification and pattern recognition, it continues to face challenges when dealing with complex tasks such as intuitive decision-making, sense disambiguation, sarcasm detection, and narrative understanding, as these require advanced kinds of reasoning, e.g., commonsense reasoning and causal reasoning, which have not been emulated satisfactorily yet. To address these shortcomings, we propose seven pillars that we believe represent the key hallmark features for the future of AI, namely: Multidisciplinarity, Task Decomposition, Parallel Analogy, Symbol Grounding, Similarity Measure, …

Predictive Taxonomy Analytics (Lasso): Predicting Outcome Types Of Cyber Breach, Jing Rong Goh, Shaun S. Wang, Yaniv Harel, Gabriel Toh

Research Collection School Of Economics

Cyber breaches are costly for the global economy and extensive efforts have gone into improving the cybersecurity infrastructure. There are numerous types of cyber breaches that vary greatly in terms of cause and impact, resulting in an extensive literature for individual cyber breach type. Our paper seeks to provide a general framework that can be easily applied to analyze different types of cyber breaches. Our framework is inspired by the taxonomy approach in the cybersecurity literature, where it was proposed that an effective set of taxonomy can provide a direction on supporting improved decision-making in cyber risk management and selecting …

Infusing K-Means For Securing Iot Services In Edge Computing, Tam Sakirin, Iqra Asif

Mesopotamian Journal of Computer Science

Accurate, timely, and safe administration of data from IoT devices is made possible by intelligent computing. As the number of IoT devices proliferates, more and more data will be collected, adding depth and breadth to the existing range of IoT services. Technology that incorporates entire systems on a single integrated circuit has improved to the point where more and more consumer electronics can support full-fledged operating systems. It is impractical to use a single computing model for the entire planet since doing so would cause severe network congestion and security holes. In order to solve this problem, we present a …

Student’S Rating System For Teachers: A Tool For Teacher Scheduling Consideration, Naomi Bajao, Jose Primo Bardoquillo, Jhay Concha, Mae Fatima Monsanto, Ma.Chrisfie Karen Mojar

Mesopotamian Journal of Computer Science

The end-of-term ratings are one of the most crucial components of improving educational institutions' ability to assess teachers' performance. The paper-based evaluation system for teachers at Cebu Technological University's Tuburan Campus is time-consuming and laborious.  During the flexible learning, the school uses Google Forms to create surveys to rate the teachers which also has shortcomings since Google Forms has limited functions. To solve these issues, the proponents created a web-based evaluation system that makes it simple for students to rate their professors and generates evaluation reports at ease. Additionally, the system gives the system administrator the ability to control colleges, …

Artificial Neural Networks: An Overview, Roheen Qamar, Baqar Ali Zardari

Mesopotamian Journal of Computer Science

Neural networks, also known as artificial neural networks (ANNs) or artificially generated neural networks (SNNs) are a subset of machine learning that provide the foundation of deep learning techniques. Their name and form are inspired by the human brain, and they replicate the way real neurons communicate with one another. Artificial neural networks (ANNs) are massively parallel systems comprised of a huge number of interconnected basic processors. This paper discuss about the artificial neural network and its basic types. This article explains the ANN and its basic outlines the fundamental neuron and the artificial computer model. It describes network structures …

View Synthesis With Scene Recognition For Cross-View Image Localization, Uddom Lee, Peng Jiang, Hongyi Wu, Chunsheng Xin

Electrical & Computer Engineering Faculty Publications

Image-based localization has been widely used for autonomous vehicles, robotics, augmented reality, etc., and this is carried out by matching a query image taken from a cell phone or vehicle dashcam to a large scale of geo-tagged reference images, such as satellite/aerial images or Google Street Views. However, the problem remains challenging due to the inconsistency between the query images and the large-scale reference datasets regarding various light and weather conditions. To tackle this issue, this work proposes a novel view synthesis framework equipped with deep generative models, which can merge the unique features from the outdated reference dataset with …

Security Of Internet Of Things (Iot) Using Federated Learning And Deep Learning — Recent Advancements, Issues And Prospects, Vinay Gugueoth, Sunitha Safavat, Sachin Shetty

Electrical & Computer Engineering Faculty Publications

There is a great demand for an efficient security framework which can secure IoT systems from potential adversarial attacks. However, it is challenging to design a suitable security model for IoT considering the dynamic and distributed nature of IoT. This motivates the researchers to focus more on investigating the role of machine learning (ML) in the designing of security models. A brief analysis of different ML algorithms for IoT security is discussed along with the advantages and limitations of ML algorithms. Existing studies state that ML algorithms suffer from the problem of high computational overhead and risk of privacy leakage. …