Computer Sciences Commons^™

Macruby: User Defined Macro Support For Ruby, Arushi Singh

Master's Projects

Ruby does not have a way to create custom syntax outside what the language already offers. Macros allow custom syntax creation. They achieve this by code generation that transforms a small set of instructions into a larger set of instructions. This gives programmers the opportunity to extend the language based on their own custom needs.

Macros are a form of meta-programming that helps programmers in writing clean and concise code. MacRuby is a hygienic macro system. It works by parsing the Abstract Syntax Tree(AST) and replacing macro references with expanded Ruby code. MacRuby offers an intuitive way to declare macro …

Driving Simulator : Driving Performance Under Distraction, Kaushik Pilligundla

Master's Projects

This pilot study used a driving simulator experiment to look into how podcast consumption affects driving performance as a continuous distraction. Three volunteers conducted three trials in the study, each with a different driving scenario. Data analysis was done to compare two conditions. The first condition is the Audio, where volunteers listen to podcasts while driving. The second condition is no-audio condition.. The no-audi condition had nothing to play in the background. We used eye-tracking technology to gather gaze data. The study's findings using the post survey and eye fixation data indicate that listening to podcasts leads to continuous distraction …

Yelp Restaurant Popularity Score Calculator, Sneh Bindesh Chitalia

Master's Projects

Yelp is a popular social media platform that has gained much traction over the last few years. The critical feature of Yelp is it has information about any small or large-scale business, as well as reviews received from customers. The reviews have both a 1 to 5 star rating, as well as text. For a particular business, any user can view the reviews, but the stars are what most users check because it is an easy and fast way to decide. Therefore, the star rating is a good metric to measure a particular business’s value. However, there are other attributes …

Detecting Botnets Using Hidden Markov Model, Profile Hidden Markov Model And Network Flow Analysis, Rucha Mannikar

Master's Projects

Botnet is a network of infected computer systems called bots managed remotely by an attacker using bot controllers. Using distributed systems, botnets can be used for large-scale cyber attacks to execute unauthorized actions on the targeted system like phishing, distributed denial of service (DDoS), data theft, and crashing of servers. Common internet protocols used by normal systems for regular communication like hypertext transfer (HTTP) and internet relay chat (IRC) are also used by botnets. Thus, distinguishing botnet activity from normal activity can be challenging. To address this issue, this project proposes an approach to detect botnets using peculiar traits in …

Hate Speech Detection In Hindi, Pranjali Prakash Bansod

Master's Projects

Social media is a great place to share one’s thoughts and to express oneself. Very often the same social media platforms become a means for spewing hatred.The large amount of data being shared on these platforms make it difficult to moderate the content shared by users. In a diverse country like India hate is present on social media in all regional languages, making it even more difficult to detect hate because of a lack of enough data to train deep/ machine learning models to make them understand regional languages.This work is our attempt at tackling hate speech in Hindi. We …

Steganographic Capacity Of Selected Machine Learning And Deep Learning Models, Lei Zhang

Master's Projects

As machine learning and deep learning models become ubiquitous, it is inevitable that there will be attempts to exploit such models in various attack scenarios. For example, in a steganographic based attack, information would be hidden in a learning model, which might then be used to gain unauthorized access to a computer, or for other malicious purposes. In this research, we determine the steganographic capacity of various classic machine learning and deep learning models. Specifically, we determine the number of low-order bits of the trained parameters of a given model that can be altered without significantly affecting the performance of …

Leveraging Tweets For Rapid Disaster Response Using Bert-Bilstm-Cnn Model, Satya Pranavi Manthena

Master's Projects

Digital networking sites such as Twitter give a global platform for users to discuss and express their own experiences with others. People frequently use social media to share their daily experiences, local news, and activities with others. Many rescue services and agencies frequently monitor this sort of data to identify crises and limit the danger of loss of life. During a natural catastrophe, many tweets are made in reference to the tragedy, making it a hot topic on Twitter. Tweets containing natural disaster phrases but do not discuss the event itself are not informational and should be labeled as non-disaster …

Application Of Adversarial Attacks On Malware Detection Models, Vaishnavi Nagireddy

Master's Projects

Malware detection is vital as it ensures that a computer is safe from any kind of malicious software that puts users at risk. Too many variants of these malicious software are being introduced everyday at increased speed. Thus, to guarantee security of computer systems, huge advancements in the field of malware detection are made and one such approach is to use machine learning for malware detection. Even though machine learning is very powerful, it is prone to adversarial attacks. In this project, we will try to apply adversarial attacks on malware detection models. To perform these attacks, fake samples that …

Phys 275: Intro To Scientific Computing, David Goldberg

Open Educational Resources

No abstract provided.

Dynamic Field Programmable Logic-Driven Soft Exosuit, Frances Cleary, Witawas Srisa-An, David C. Henshall, Sasitharan Balasubramaniam

School of Computing: Faculty Publications

The next generation of etextiles foresees an era of smart wearable garments where embedded seamless intelligence provides the ability to sense, process and perform. Core to this vision is embedded textile functionality enabling dynamic configuration. In this paper we detail a methodology, design and implementation of a dynamic field programmable logic-driven fabric soft exosuit. Dynamic field programmability allows the soft exosuit to alter its functionality and adapt to specific exercise programs depending on the wearers need. The dynamic field programmability is enabled through motion based control arm movements of the soft exosuit triggering momentary sensors embedded in the fabric exosuit …

A Light-Weight Technique To Detect Gps Spoofing Using Attenuated Signal Envelopes, Xiao Wei, Muhammad Naveed Aman, Biplab Sikdar

School of Computing: Faculty Publications

Global Positioning System (GPS) spoofing attacks have attracted more attention as one of the most effective GPS attacks. Since the signals from an authentic satellite and the spoofer undergo different attenuation, the captured envelope of fake GPS signals exhibits distinctive transmission characteristics due to short transmission paths. This can be utilized for GPS spoofing detection. The existing technique for GPS spoofing are either computationally too expensive, require specialize hardware/ software updates, or are not accurate enough. To solve these issues, we propose a light-weight GPS spoofing detection method based on a dynamic threshold and captured signal envelope. We validate the …

A Markovian Error Model For False Negatives In Dnn-Based Perception-Driven Control Systems, Kruttidipta Samal, Thomas Walton, Tran Hoang-Dung, Marilyn Wolf

School of Computing: Faculty Publications

vehicles and other perception-driven control systems. Many modern autonomous systems rely on DNN-driven perception-based control/ planning methodologies such as autonomous navigation, where the perception errors significantly affect the control/planning performance and the systems’ safety. The traditional independent, identically-distributed (IID) perception error model is inadequate for perception-based control/planning applications because image sequences supplied to a DNN-based perception module are not independent in the real world. Based on this observation, we develop a novel Markov model to describe the error behavior of a DNN perception model—an error in one frame is likely to signal errors in successive frames, effectively reducing sample rate …

Ethical Design Of Computers: From Semiconductors To Iot And Artificial Intelligence, Sudeep Pasricha, Marilyn Wolf

School of Computing: Faculty Publications

Computing systems are tightly integrated today into our professional, social, and private lives. An important consequence of this growing ubiquity of computing is that it can have significant ethical implications of which computing professionals should take account. In most real-world scenarios, it is not immediately obvious how particular technical choices during the design and use of computing systems could be viewed from an ethical perspective. This article provides a perspective on the ethical challenges within semiconductor chip design, IoT applications, and the increasing use of artificial intelligence in the design processes, tools, and hardware-software stacks of these systems.

Robots And Reference Services, Abdullahi Olayinka Isiaka, Biliamin Abiola Aremu, Abdulfatai Soliu, Fahisat Romoke Isiaq

Library Philosophy and Practice (e-journal)

Abstract

This paper explores the integration of robots into reference services in various library and information settings. The use of robots in these contexts has gained momentum in recent years, offering innovative solutions to enhance user experiences, improve access to information, and expand the capabilities of reference librarians. This paper reviews the current state of robots in reference services, discusses their potential benefits and challenges, and examines case studies to illustrate their practical applications. Furthermore, it offers insights into the future prospects and ethical considerations associated with the integration of robots in this domain. This paper delves into the fascinating …

Automatic Detection And Analysis Towards Malicious Behavior In Iot Malware, Sen Li, Mengmeng Ge, Ruitao Feng, Xiaohong Li, Kwok Yan Lam

Research Collection School Of Computing and Information Systems

Our society is rapidly moving towards the digital age, which has led to a sharp increase in IoT networks and devices. This growth requires more network security professionals, who are focused on protecting IoT systems. One crucial task is to analyze malicious software to gain a deeper understanding of its functionalities and response methods. However, malware analysis is a complex process that requires the use of various analysis tools, including advanced reverse engineering techniques. For beginners, parsing complex binary data can be particularly challenging as they may be strange with these tools and the basic principles of analysis. Even for …

Structured Dialogue State Management For Task-Oriented Dialogue Systems, Anh Duong Trinh

Doctoral

Human-machine conversational agents have developed at a rapid pace in recent years, bolstered through the application of advanced technologies such as deep learning. Today, dialogue systems are useful in assisting users in various activities, especially task-oriented dialogue systems in specific dialogue domains. However, they continue to be limited in many ways. Arguably the biggest challenge lies in the complexity of natural language and interpersonal communication, and the lack of human context and knowledge available to these systems. This leads to the question of whether dialogue systems, and in particular task-oriented dialogue systems, can be enhanced to leverage various language properties. …

Artificial Intelligence-Based Medical Device Technologies Implementation Strategies In The Nigerian Health Care Industry, Oliver Chikaodinaka Iheme

Walden Dissertations and Doctoral Studies

Artificial intelligence (AI)-based medical device technologies can aid medical professionals in delivering faster and more accurate treatment, but health care leaders are concerned with eliminating challenges that impede implementation. Grounded in the technology-organization-environment and technology acceptance models, the purpose of this qualitative multi-case study was to explore strategies health care leaders in Nigeria use to obtain, adopt, and implement AI-based medical device technologies. The participants were 11 health care leaders in Nigeria who successfully implemented AI-based medical device technologies in their hospitals. Data were collected using semi-structured interviews and the review of organizational documents. Through thematic analysis, five themes were …

Technical Training To Nonprofit Managers Influences Using Big Data Technology In Business Operations, Dr. Arslan Isaac Phd

Walden Dissertations and Doctoral Studies

This nonexperimental, survey-based online quantitative study on nonprofit managers’ technical training measures the extent of the influence on big data technology use. The unified theory of acceptance and use of technology is a theoretical framework to determine whether business managers are trained to have know-how in using big data technology. This study followed a quantitative methodology to help narrow the gap in research between what is not known in relation to the nonprofit manager’s technical training on the use of big data technology. Today’s data is the most critical asset, but progress toward big data technology-oriented usage needs to be …

Strategies For Proper Security Practices In Small Financial Institutions, Adam Leffell

Walden Dissertations and Doctoral Studies

Financial institutions remain high targets for threat actors because of potentially lucrativefinancial gains from security breaches. Information technology (IT) security professionals in financial institutions are concerned about weak security strategies that could lead to security breaches. Grounded in the technology acceptance model (TAM), the purpose of this qualitative multiple case study was to explore strategies IT security professionals use to implement proper security practices to prevent security breaches. The participants were three IT security professionals from three different financial institutions that oversee the implementation of security policies and procedures. Data collection involved conducting semi-structured interviews and public documents. Through thematic …

Analyzing Small Business Strategies To Prevent External Cybersecurity Threats, Dr. Kevin E. Moore

Walden Dissertations and Doctoral Studies

Some small businesses’ cybersecurity analysts lack strategies to prevent their organizations from compromising personally identifiable information (PII) via external cybersecurity threats. Small business leaders are concerned, as they are the most targeted critical infrastructures in the United States and are a vital part of the economic system as data breaches threaten the viability of these organizations. Grounded in routine activity theory, the purpose of this pragmatic qualitative inquiry was to explore strategies small business organizations utilize to prevent external cybersecurity threats. The participants were nine cybersecurity analysts who utilized strategies to defend small businesses from external threats. Data were collected …

Perceptions And Knowledge Of Information Security Policy Compliance In Organizational Personnel, Jesus M. Mosqueda

Walden Dissertations and Doctoral Studies

All internet connected organizations are becoming increasingly vulnerable to cyberattacks due to information security policy noncompliance of personnel. The problem is important to information technology (IT) firms, organizations with IT integration, and any consumer who has shared personal information online, because noncompliance is the single greatest threat to cybersecurity, which leads to expensive breaches that put private information in danger. Grounded in the protection motivation theory, the purpose of this quantitative study was to use multiple regression analysis to examine the relationship between perceived importance, organizational compliance, management involvement, seeking guidance, and rate of cybersecurity attack. The research question for …

Knowledge-Sharing Practice As A Tool In Organizational Development In Nigerian Higher Educational Institutions, Emmanuel Ajiri Ojo

Walden Dissertations and Doctoral Studies

AbstractUnderstanding knowledge management is key to understanding organizational development and innovations. Inadequate knowledge-sharing practices in Nigerian educational institutions has impeded innovation and management development. The purpose of this qualitative modified Delphi study was to seek consensus among administrators from Nigerian educational institutions and scholars from Nigerian universities regarding knowledge-sharing practices that nourish innovation in Nigerian higher educational institutions. The organizational development framework was used to guide the study. Data collection included a nonprobability purposive sampling of 25 participants and three rounds of surveys administered online. A consensus was reached on eight factors after coding and thematic analysis: setting knowledge-sharing expectations, …

Leadership Strategies Supply Chain Managers Use In Adopting Innovative Technology, Bukola Loveth Olowo

Walden Dissertations and Doctoral Studies

Supply chain managers face challenges when adopting new technologies to remain competitive and satisfy consumer demands involving expedited delivery of food and services. Supply chain managers who fail to adopt new technology have a decreased propensity to stay competitive. Grounded in the transformation leadership theory, the purpose of this qualitative multiple-case study was to explore leadership strategies supply chain managers use in adopting innovative technology. Participants were six supply chain managers who successfully used leadership strategies to adopt new innovative technology. Sources for data collection were semistructured interviews, company archival documents, and field notes. Research data were analyzed via thematic …

Neighbor-Anchoring Adversarial Graph Neural Networks, Zemin Liu, Yuan Fang, Yong Liu, Vincent W. Zheng

Research Collection School Of Computing and Information Systems

Graph neural networks (GNNs) have witnessed widespread adoption due to their ability to learn superior representations for graph data. While GNNs exhibit strong discriminative power, they often fall short of learning the underlying node distribution for increased robustness. To deal with this, inspired by generative adversarial networks (GANs), we investigate the problem of adversarial learning on graph neural networks, and propose a novel framework named NAGNN (i.e., Neighbor-anchoring Adversarial Graph Neural Networks) for graph representation learning, which trains not only a discriminator but also a generator that compete with each other. In particular, we propose a novel neighbor-anchoring strategy, where …

Anchorage: Visual Analysis Of Satisfaction In Customer Service Videos Via Anchor Events, Kam Kwai Wong, Xingbo Wang, Yong Wang, Jianben He, Rong Zhang, Huamin Qu

Research Collection School Of Computing and Information Systems

Delivering customer services through video communications has brought new opportunities to analyze customer satisfaction for quality management. However, due to the lack of reliable self-reported responses, service providers are troubled by the inadequate estimation of customer services and the tedious investigation into multimodal video recordings. We introduce , a visual analytics system to evaluate customer satisfaction by summarizing multimodal behavioral features in customer service videos and revealing abnormal operations in the service process. We leverage the semantically meaningful operations to introduce structured event understanding into videos which help service providers quickly navigate to events of their interest. supports a comprehensive …

Fortifying The Seams Of Software Systems, Hong Jin Kang

Dissertations and Theses Collection (Open Access)

A seam in software is a place where two components within a software system meet. There are more seams in software now than ever before as modern software systems rely extensively on third-party software components, e.g., libraries. Due to the increasing complexity of software systems, understanding and improving the reliability of these components and their use is crucial. While the use of software components eases the development process, it also introduces challenges due to the interaction between the components.

This dissertation tackles problems associated with software reliability when using third-party software components. Developers write programs that interact with libraries through …

Enhancing The Performance Of Federated Learning With Diffusion Models: Leveraging Synthetic Data To Address Non-Iid Data Challenges, Karin Huangsuwan

Chulalongkorn University Theses and Dissertations (Chula ETD)

In the context of machine learning in healthcare, federated learning (FL) is frequently seen as an effective approach to tackling issues of data privacy and distribution. Nonetheless, many real-world datasets exhibit non-identical and independently distributed (non-IID) characteristics, meaning that data features vary across different institutions. This non-IID nature presents challenges for FL model convergence, such as client drifting, where model weights lean towards local optima rather than global optimum. To address these issues, we introduce a new framework called "FedDrip (Federated Learning with Diffusion Reinforcement at Pseudo-site)," which leverages diffusion-generated synthetic data to mitigate data-related problems in non-IID settings. Our …

Patent Trends Detection Using Keywords In Patent Keywords Network, Krisanapong Yodprechavigit

Chulalongkorn University Theses and Dissertations (Chula ETD)

The process of extracting insights and information from patent data is known as patent analysis. Several patent analysis methodologies strive to forecast technological trends by analyzing patent keywords and networks. Nevertheless, existing methodologies often fall short in accurately predicting the magnitude of shifts within these trends. This study aims to propose an alternative patent analysis method that combines author-keyword network analysis with various regression models, including Linear Regression, Artificial Neural Network, and Long Short-Term Memory, to predict upcoming keyword trends along with its magnitude of change. To evaluate the effectiveness of the proposed method, we constructed a patent author-keyword network …

Predicting Newcomer’S Turnover Using Predictive Analytics : A Case Study Of Thai Financial Firm In Bangkok, Thailand, Meena Kittikunsiri

Chulalongkorn University Theses and Dissertations (Chula ETD)

Employee turnover, a critical issue impacting workplace productivity, has prompted organizations to leverage machine learning techniques for predictive analysis. This study specifically targets the prediction of turnover among new employees, utilizing data obtained from a survey conducted at a Thai financial firm in Bangkok, Thailand. Through an evaluation of various machine learning models, the results indicate that the Random Forest model surpasses others. Furthermore, this research highlights crucial factors influencing newcomer turnover, such as comfort with workplace culture, work-from-home policies, onboarding programs, and satisfaction with the recruitment process. These findings offer actionable insights for HR professionals to focus on these …

Data Ethics And The Dilemma Created By Turing's Learning Machines, Jacob Kuhn

Honors Program Theses

The main purpose of this research is to shed light on the good and bad that has come about from the interaction of Big Data and Artificial Intelligence in society. Transparency with the public is paramount for the future of Artificial Intelligence. Without awareness, the public is blind to the parts of the Data Revolution that could help them or hinder them. The key question is what AI advancements are being made and what ethical problems do they pose to the general population? To help answer this question, it is best to examine the founding of Artificial Intelligence and the …