Computer Sciences Commons^™

Testing Artificial Intelligence-Based Software Systems, Jaganmohan Chandrasekaran

Computer Science and Engineering Dissertations - Archive

Artificial Intelligence (AI)-based software systems are increasingly used in high-stake and safety-critical domains, including recidivism prediction, medical diagnosis, and autonomous driving. There is an urgent need to ensure the reliability and correctness of AI-based systems. At the core of AI-based software systems is a machine learning (ML) model that is used to perform tasks such as classification and prediction. Unlike software programs, where a developer explicitly writes the decision logic, ML models learn the decision logic from a large training dataset. Furthermore, many ML models encode the decision logic in the form of mathematic functions that can be quite abstract …

Optimizing The Demand And Distribution Of Power In Smart Grids, Saifullah Khalid

Computer Science and Engineering Dissertations - Archive

The electricity is generated in bulk power plants and transported to the end-user through the transmission and distribution networks. The process incurs heavy losses adding to the operational costs. Secondly, fossil fuels dominate energy generation and are a major source of greenhouse gases. Thirdly, the power grid is vulnerable to natural disasters. The smart grid addresses these challenges by integrating distributed energy resources (DERs) in the distribution system closer to the load and with greater penetration of renewable energy. Renewable energy is key to cutting carbon emissions due to fossil fuel-based electricity generation and reducing operating costs. It can also …

Nb-Iot: Iot Përmes Sistemeve Celulare Brez-Ngushta, Besart Haziri

Theses and Dissertations

Me rritjen e numrit të pajisjeve IoT në ditët e sotme, kërkesa për t’i mbështetur ato vetëm sa rritet, me rreth 7.6 miliardë pajisje IoT aktive në fund të vitit 2019, si dhe me një pritshmëri të rritjes deri në 24.1 miliardë pajisje IoT në vitin 2030. Me numër kaq të madh të pajisjeve që do të lidhen në Internet atëherë na duhet siguri dhe rrjet i besueshëm që i mbështet të gjitha këto pajisje. Mundësia më e mirë për këtë çështje është NB-IoT (Narrowband–Internet of Things).

NB-IoT mundëson konektimin e qindra-mijëra pajisjeve të vogla (sensorëve) në Internet përmes sistemeve …

The Role Of Trust In Advice Acceptance From Non-Human Actors, Rahul Banerjee

Dissertations and Theses Collection (Open Access)

Advancements in technology are now allowing non-human actors in the form of robot-advisors, driverless cars, medical assistants to perform increasingly complex tasks. While technological change is as old as civilization, these non-human actors can do novel tasks. One such task is that they provide advice which is a credence service (Dulleck, & Kerschbamer, 2006). Using a financial services context this thesis studies the role trust plays in advice acceptance.

Robo-advisors are rapidly replacing human financial advisors as the agent-provider for portfolio investment services. For centuries, it was the banker (human financial advisor) who was responsible for providing his investors with …

Cosy: Counterfactual Syntax For Cross-Lingual Understanding, Sicheng Yu, Hao Zhang, Yulei Niu, Qianru Sun, Jing Jiang

Research Collection School Of Computing and Information Systems

Pre-trained multilingual language models, e.g., multilingual-BERT, are widely used in cross-lingual tasks, yielding the state-of-the-art performance. However, such models suffer from a large performance gap between source and target languages, especially in the zero-shot setting, where the models are fine-tuned only on English but tested on other languages for the same task. We tackle this issue by incorporating language-agnostic information, specifically, universal syntax such as dependency relations and POS tags, into language models, based on the observation that universal syntax is transferable across different languages. Our approach, named COunterfactual SYntax (COSY), includes the design of SYntax-aware networks as well as …

Characterizing Search Activities On Stack Overflow, Jiakun Liu, Sebastian Baltes, Christoph Treude, David Lo, Yun Zhang, Xin Xia

Research Collection School Of Computing and Information Systems

To solve programming issues, developers commonly search on Stack Overflow to seek potential solutions. However, there is a gap between the knowledge developers are interested in and the knowledge they are able to retrieve using search engines. To help developers efficiently retrieve relevant knowledge on Stack Overflow, prior studies proposed several techniques to reformulate queries and generate summarized answers. However, few studies performed a large-scale analysis using real-world search logs. In this paper, we characterize how developers search on Stack Overflow using such logs. By doing so, we identify the challenges developers face when searching on Stack Overflow and seek …

Toward Explainable Deep Anomaly Detection, Guansong Pang, Charu Aggarwal

Research Collection School Of Computing and Information Systems

Anomaly explanation, also known as anomaly localization, is as important as, if not more than, anomaly detection in many realworld applications. However, it is challenging to build explainable detection models due to the lack of anomaly-supervisory information and the unbounded nature of anomaly; most existing studies exclusively focus on the detection task only, including the recently emerging deep learning-based anomaly detection that leverages neural networks to learn expressive low-dimensional representations or anomaly scores for the detection task. Deep learning models, including deep anomaly detection models, are often constructed as black boxes, which have been criticized for the lack of explainability …

Ava: Adversarial Vignetting Attack Against Visual Recognition, Binyu Tian, Felix Juefei-Xu, Qing Guo, Xiaofei Xie, Xiaohong Li, Yang Liu

Research Collection School Of Computing and Information Systems

Vignetting is an inherent imaging phenomenon within almost all optical systems, showing as a radial intensity darkening toward the corners of an image. Since it is a common effect for photography and usually appears as a slight intensity variation, people usually regard it as a part of a photo and would not even want to post-process it. Due to this natural advantage, in this work, we study the vignetting from a new viewpoint, i.e., adversarial vignetting attack (AVA), which aims to embed intentionally misleading information into the vignetting and produce a natural adversarial example without noise patterns. This example can …

Are Missing Links Predictable? An Inferential Benchmark For Knowledge Graph Completion, Yixin Cao, Xiang Ji, Xin Lv, Juanzi Li, Yonggang Wen, Hanwang Zhang

Research Collection School Of Computing and Information Systems

We present InferWiki, a Knowledge Graph Completion (KGC) dataset that improves upon existing benchmarks in inferential ability, assumptions, and patterns. First, each testing sample is predictable with supportive data in the training set. To ensure it, we propose to utilize rule-guided train/test generation, instead of conventional random split. Second, InferWiki initiates the evaluation following the open-world assumption and improves the inferential difficulty of the closed-world assumption, by providing manually annotated negative and unknown triples. Third, we include various inference patterns (e.g., reasoning path length and types) for comprehensive evaluation. In experiments, we curate two settings of InferWiki varying in sizes …

Learning And Exploiting Shaped Reward Models For Large Scale Multiagent Rl, Arambam James Singh, Akshat Kumar, Hoong Chuin Lau

Research Collection School Of Computing and Information Systems

Many real world systems involve interaction among large number of agents to achieve a common goal, for example, air traffic control. Several model-free RL algorithms have been proposed for such settings. A key limitation is that the empirical reward signal in model-free case is not very effective in addressing the multiagent credit assignment problem, which determines an agent's contribution to the team's success. This results in lower solution quality and high sample complexity. To address this, we contribute (a) an approach to learn a differentiable reward model for both continuous and discrete action setting by exploiting the collective nature of …

Forecasting Interaction Order On Temporal Graphs, Wenwen Xia, Yuchen Li, Jianwei Tian, Shenghong Li

Research Collection School Of Computing and Information Systems

Link prediction is a fundamental task for graph analysis and the topic has been studied extensively for static or dynamic graphs. Essentially, the link prediction is formulated as a binary classification problem about two nodes. However, for temporal graphs, links (or interactions) among node sets appear in sequential orders. And the orders may lead to interesting applications. While a binary link prediction formulation fails to handle such an order-sensitive case. In this paper, we focus on such an interaction order prediction (IOP) problem among a given node set on temporal graphs. For the technical aspect, we develop a graph neural …

Gp3: Gaussian Process Path Planning For Reliable Shortest Path In Transportation Networks, Hongliang Guo, Xuejie Hou, Zhiguang Cao, Jie Zhang

Research Collection School Of Computing and Information Systems

This paper investigates the reliable shortest path (RSP) problem in Gaussian process (GP) regulated transportation networks. Specifically, the RSP problem that we are targeting at is to minimize the (weighted) linear combination of mean and standard deviation of the path's travel time. With the reasonable assumption that the travel times of the underlying transportation network follow a multi-variate Gaussian distribution, we propose a Gaussian process path planning (GP3) algorithm to calculate the a priori optimal path as the RSP solution. With a series of equivalent RSP problem transformations, we are able to reach a polynomial time complexity algorithm with guaranteed …

Logbert: Log Anomaly Detection Via Bert, Haixuan Guo

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

When systems break down, administrators usually check the produced logs to diagnose the failures. Nowadays, systems grow larger and more complicated. It is labor-intensive to manually detect abnormal behaviors in logs. Therefore, it is necessary to develop an automated anomaly detection on system logs. Automated anomaly detection not only identifies malicious patterns promptly but also requires no prior domain knowledge. Many existing log anomaly detection approaches apply natural language models such as Recurrent Neural Network (RNN) to log analysis since both are based on sequential data. The proposed model, LogBERT, a BERT-based neural network, can capture the contextual information in …

Algorithms For Covering Barrier Points By Mobile Sensors With Line Constraint, Princy Jain

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

In this thesis, we develop efficient algorithms for the problem of covering barrier points by mobile sensors. Each sensor is represented by a point in the plane with the same covering range r so that any point within distance r from the sensor can be covered by the sensor. Given a set B of m points (called “barrier points”) and a set S of n points (representing the “sensors”) in the plane, the problem is to move the sensors so that each barrier point is covered by at least one sensor and the maximum movement of all sensors is minimized. …

Take The Lead: Toward A Virtual Video Dance Partner, Ty Farris

Master's Theses

My work focuses on taking a single person as input and predicting the intentional movement of one dance partner based on the other dance partner's movement. Human pose estimation has been applied to dance and computer vision, but many existing applications focus on a single individual or multiple individuals performing. Currently there are very few works that focus specifically on dance couples combined with pose prediction. This thesis is applicable to the entertainment and gaming industry by training people to dance with a virtual dance partner.

Many existing interactive or virtual dance partners require a motion capture system, multiple cameras …

Verification Of Piecewise Deep Neural Networks: A Star Set Approach With Zonotope Pre-Filter, Hoang-Dung Tran, Neelanjana Pal, Diego Manzanas Lopez, Patrick Musau, Xiaodong Yang, Luan Viet Nguyen, Weiming Xiang, Stanley Bak, Taylor T. Johnson

Computer Science Faculty Publications

Verification has emerged as a means to provide formal guarantees on learning-based systems incorporating neural network before using them in safety-critical applications. This paper proposes a new verification approach for deep neural networks (DNNs) with piecewise linear activation functions using reachability analysis. The core of our approach is a collection of reachability algorithms using star sets (or shortly, stars), an effective symbolic representation of high-dimensional polytopes. The star-based reachability algorithms compute the output reachable sets of a network with a given input set before using them for verification. For a neural network with piecewise linear activation functions, our approach can …

Innovative Computational Methods For Pharmaceutical Problem Solving A Review Part Ii: Serious Gaming, Heather R. Campbell, Robert A. Lodder

Pharmaceutical Sciences Faculty Publications

Serious gaming has begun to take a foothold in pharmaceutical problem-solving. Companies such as Akili's Interactive are seeing success in the form of positive clinical trial results and FDA approval of digital therapeutics. Academic researchers have begun exploring novel uses for serious gaming in the way of protein design and more with promising results. This paper provides a review of such topics in addition to topics of game repurposing- repurposing a game originally intended for entertainment into a serious game-such as Minecraft and America's Army. Reviewing these topics this paper shows the utility of serious gaming as a tool for …

Innovative Computational Methods For Pharmaceutical Problem Solving A Review Part I: The Drug Development Process, Heather R. Campbell, Robert A. Lodder

Pharmaceutical Sciences Faculty Publications

Computational methods have provided pharmaceutical scientists and engineers a means to go beyond what's possible with experimental testing alone. Providing a means to study active pharmaceutical ingredients (API), excipients, and drug interactions at or near-atomic levels. This paper provides a review of this and other innovative computational methods used for solving pharmaceutical problems throughout the drug development process. Part one of two this paper will emphasize the role of computational methods and game theory in solving pharmaceutical challenges.

Hardware For Quantized Mixed-Precision Deep Neural Networks, Andres Rios

Open Access Theses & Dissertations

Recently, there has been a push to perform deep learning (DL) computations on the edge rather than the cloud due to latency, network connectivity, energy consumption, and privacy issues. However, state-of-the-art deep neural networks (DNNs) require vast amounts of computational power, data, and energyâ??resources that are limited on edge devices. This limitation has brought the need to design domain-specific architectures (DSAs) that implement DL-specific hardware optimizations. Traditionally DNNs have run on 32-bit floating-point numbers; however, a body of research has shown that DNNs are surprisingly robust and do not require all 32 bits. Instead, using quantization, networks can run on …

A Real-World, Hybrid Event Sequence Generation Framework For Android Apps, Jun Sun

School of Computing: Dissertations, Theses, and Student Research

Generating meaningful inputs for Android apps is still a challenging issue that needs more research. Past research efforts have shown that random test generation is still an effective means to exercise User-Interface (UI) events to achieve high code coverage. At the same time, heuristic search approaches can effectively reach specified code targets. Our investigation shows that these approaches alone are insufficient to generate inputs that can exercise specific code locations in complex Android applications.

This thesis introduces a hybrid approach that combines two different input generation techniques--heuristic search based on genetic algorithm and random instigation of UI events, to reach …

Using Contextual Bandits To Improve Traffic Performance In Edge Network, Aziza Al Zadjali

School of Computing: Dissertations, Theses, and Student Research

Edge computing network is a great candidate to reduce latency and enhance performance of the Internet. The flexibility afforded by Edge computing to handle data creates exciting range of possibilities. However, Edge servers have some limitations since Edge computing process and analyze partial sets of information. It is challenging to allocate computing and network resources rationally to satisfy the requirement of mobile devices under uncertain wireless network, and meet the constraints of datacenter servers too. To combat these issues, this dissertation proposes smart multi armed bandit algorithms that decide the appropriate connection setup for multiple network access technologies on the …

Towards Machine Learning-Based Demand Response Forecasting Using Smart Grid Data, Matthew S. Johnson

Theses, Dissertations and Culminating Projects

Demand response is a valuable tool for improving the reliability, stability, and financial efficiency of smart grids. With the intention of altering customer power consumption patterns, utility companies often implement strategies such as time-of-use (TOU) programs. Although effective in some situations, TOU programs struggle to perform in highly developed countries due to the complexity of human behavior. In this study, we analyze power consumption readings from smart meters from 5567 households in London, UK from November 2011 to February 2014 to measure the success of the TOU program. We additionally consider the variability of weather conditions and customer demographics when …

Theoretical And Observational Analysis Of Ice Particles For Improvement Of Ice Microphysical Models, Vanessa Przybylo

Legacy Theses & Dissertations (2009 - 2024)

Frozen hydrometeors can grow to acquire a multitude of shapes and sizes, which influence the distribution of mass within cloud systems. Aggregates have a variety of formations based on initial ice particle size, shape, falling orientation, and the number of particles that collect. This work employs the theoretical Ice Particle and Aggregate Simulator (IPAS) as a statistical tool to repetitively collect ice crystals to derive bulk aggregate characteristics.

The Foundations Of Inference And Its Application To Fundamental Physics, Nicholas Matthew Carrara

Legacy Theses & Dissertations (2009 - 2024)

This thesis concerns the foundations of inference – probability theory,entropic inference, information geometry, etc. – and its application to the Entropic Dynamics (ED) approach to Quantum Mechanics (QM) [21, 22, 41, 53, 56–61, 150–153, 165, 195, 196, 268]. The first half of this thesis, chapters 2-6, concern the development of the inference framework. We begin in chapter 2 by discussing de- ductive inference, which involves formal logic and it’s role in access- ing the truth of propositions. We eventually discover that deductive inference is incomplete, in that it can’t address situations in which we have incomplete information. This necessitates a …

Understanding Complex Human Activities In Videos : The Study Of Concurrent Activity Detection And Group Activity Recognition, Yi Wei

Legacy Theses & Dissertations (2009 - 2024)

Human activity understanding, as one of the most important task in video analysis, has been studied for decades. Great efforts have been made to push the activity recognition models towards effective and efficient representation learning. However, it is difficult to define an explicit semantic organization of activities, even for human. Current activity recognition benchmarks only organize the activity labels with shallow hierarchies, which hinders the development of activity recognition system.

Fast Magnetic Resonance Image Reconstruction With Deep Learning Using An Efficientnet Encoder, Tahsin Rahman

Open Access Theses & Dissertations

This thesis aims to develop an efficient, deep network based method for Magnetic Resonance Imaging (MRI) acceleration through undersampled MR image reconstruction. Deep Neural Networks, particularly Deep Convolutional Networks, have been demonstrated to be highly effective in a wide variety of computer vision tasks, including MRI reconstruction. However, modern highly efficient encoder structures, such as the EfficientNet can potentially reduce reconstruction times further while improving reconstruction quality. To that end, we have developed a multi-channel U-Net MRI reconstruction network which uses an EfficientNet encoder and a custom asymmetric. The network was trained and tested using 5x undersampled multi-channel brain MR …

Modeling Of Argon Bombardment And Densification Of Low Temperature Organic Precursors Using Reactive Md Simulations And Machine Learning, Kwabena Asante-Boahen

Graduate Theses/Dissertations

In this study, an important aspect of the synthesis process for a-BxC:Hy was systematically modeled by utilizing the Reactive Molecular Dynamics (MD) in modeling the argon bombardment from the orthocarborane molecules as the precursor. The MD simulations are used to assess the dynamics associated with the free radicals that result from the ion bombardment. By applying the Data Mining/Machine Learning analysis into the datasets generated from the large reactive MD simulations, I was able to identify and quality the kinetics of these radicals. Overall, this approach allows for a better understanding of the overall mechanism at the atomistic level of …

Industrial Control System Data Resiliency, Daniel A. Bovard

Boise State University Theses and Dissertations

This thesis identifies and fortifies against a critical vulnerability in industrial control system (ICS) security. A properly designed ICS security framework consists of a multi-layered approach starting with heavy fortifications in information technology and ending with control information of operational technology. Currently, ICS security frameworks lack visibility and place blind trust in devices at the lowest level of the control hierarchy. Attaining control data visibility at the lowest level of the control hierarchy is critical to increasing the resiliency of an ICS security posture. This thesis demonstrates how this data can be captured at the lowest level of the control …

An Empirical And Theoretical Investigation Of Random Reinforced Forests And Shallow Convolutional Neural Networks, Nikhil Ganta

All Graduate Theses and Dissertations, Spring 1920 to Summer 2023

For many years, the global population of honey bees has been decreasing due to inconclusive reasons resulting in the syndrome Colony Collapse Disorder (CCD). This syndrome has been plaguing bees and affecting commercial agriculture pollination since 1998. Many researchers have suggested that pesticides, in-hive chemicals, pathogens, etc., might be the causes of CCD. Researchers also believe that any changes in a beehive can disturb the bees, which may negatively affect their health. Honey bees are the most vital among all the animal pollinators contributing to approximately 30% of the world’s commercial pollination services. As they are of keystone importance to …

Aerial Flight Paths For Communication, Alisha Bevins

School of Computing: Dissertations, Theses, and Student Research

This body of work presents an iterative process of refinement to understand naive perception of communication using the motion of an unmanned aerial vehicle (UAV). This includes what people believe the UAV is trying to communicate, and how they expect to respond through physical action or emotional response. Previous work in this area sought to communicate without clear definitions of the states attempting to be conveyed. In an attempt to present more concrete states and better understand specific motion perception, this work goes through multiple iterations of state elicitation and label assignment. The lessons learned in this work will be …