Digital Commons Network^™

Analyzing And Addressing Data-Driven Fairness Issues In Machine Learning Models Used For Societal Problems, Vishnu S. Pendyala, Hyungkyun Kim

Faculty Research, Scholarly, and Creative Activity

This work aims to systematically analyze and address fairness issues arising in machine learning models because of class imbalances present in data, specifically used for addressing societal problems and providing unique insights. Using a specific data set, spectral analysis is first performed to present evidence and characterize the fairness issues. Subsequently, a series of class imbalance correction techniques are applied before the data is used to generate various machine learning models. The models so generated are then evaluated using multiple metrics. The results are then analyzed to compare the various approaches to determine the relative merits of each. As the …

Scholarworks Profiles Policy, Sjsu Scholarworks Staff

SJSU ScholarWorks Policies

Policy for creating and updating ScholarWorks profiles.

Illuminating Chinese Aesthetics With Kant’S Account Of Genius? Possibility And Difficulty, Kefu Zhu

Comparative Philosophy

Many scholars interpret Chinese Aesthetics with the Kantian theory of genius because they seem to form a parallel: similar innate and spontaneous mental talents that exceed normal cognition and imagination generates beautiful arts with similar extraordinary qualities. I argue that projecting Kant’s genius to illuminate the creative power analogically, i.e., the carefree-wandering mind, is infeasible. The theory of genius assumes a critical project that stipulates a valuable way to exercise the power of judgment. Genius is only a postulated idea for successfully making aesthetic judgments on artworks. In contrast, the carefree-wandering mind assumes a Daoist metaphysical-ethical theory centering on the …

Zero, Śūnya And Pūrṇa: A Comparative Analysis, Animisha Tewari

Comparative Philosophy

Due to apparent duality in this world, one has to face a lot of difficulties while searching for the Truth. Our ego is the root cause for perception of duality and this in turn leads to suffering. This suffering can only be extinguished by attainment of the Truth, i.e, non-duality. However, in order to enable the finite intellect to comprehend the incomprehensible non-duality, this undifferentiated whole is sometimes denoted by nothingness (śūnya) or fullness (pūrṇa). Non-duality is usually understood by the numeral ‘1’ which stands for unity or oneness. The main aim of this paper is …

How Al-Farabi’S Interpretative Method Can Engage With Aristotle’S Method In Cognition And Practical Philosophy, Meysam Shirvani

Comparative Philosophy

Following Aristotle, al-Farabi divides philosophy into theoretical and practical each of which requires some specific methodology both in interpretation and cognition. Based on this division, there may arguably be four methodologies for four parts: 1) cognition of theoretical philosophy 2) interpretation of practical philosophy 3) cognition of practical philosophy 4) interpretation of practical philosophy. This paper focuses on the last one: the methodology of interpreting practical philosophy. Al-Farabi has an undeniably significant contribution to practical philosophy as a commentator on Greek philosophy and as a founder. In this paper, I investigate how al-Farabi (870-950 AD) read classical practical philosophy to …

The Best Confucian Hybrid Meritocracy-Democracy For Liberal Democracies, John J. Park

Comparative Philosophy

Several contemporary Confucian philosophers have posited differing hybrid views fusing meritocracy to democracy. There is a good deal of interest in a meritocracy in contemporary Confucian thought, and such a view perhaps should receive more serious consideration in liberal democratic thought since it may make for a stronger form of government when appended to democracy. In this paper, four contemporary hybrid theorists who combine elements of a meritocracy with a democracy are critically analyzed concerning an ability for their views to be instantiated in liberal democracies for the legislative branch only. Finally, I provide a modified hybrid view for the …

Ineffability, Emptiness And The Aesthetics Of Logic, Andreas Kapsner

Comparative Philosophy

In this essay, I explore the nature of the logical analysis of Buddhist thought that Graham Priest has offered in his book The Fifth Corner of Four (5of4). The paper traces the development of a logical value in- troduced in 5of4, which Priest has called e. The paper points out that certain criticisms I have made earlier still stand, but focuses on a recon- ceptualization of 5of4 in which these arguments carry less weight. This new perspective on the book, inspired by a response to my arguments by Priest himself, sees the logical analysis of Buddhism …

Social Justice In India: A Comparative Study Of Rawls And Ambedkar, Abinash Darnal

Comparative Philosophy

Justice has always been central to political philosophy over a period of time. No doubt, throughout the ages, countless philosophers have understood justice in different ways. Nevertheless, they have consented that a good society is a just society. Moreover, justice is a distributive concept and is concerned with the distribution of wealth, leisure, liberty, friendship, love, etc. Twentieth century justice came to be discussed usually in relation to social life in general, and the distribution of material rewards in particular and usually came to be known as ‘Social Justice’. Social justice as such came to be accepted as the fair …

Information Needs And Seeking Behaviour Of Commercial Bus Drivers In Obio/Akpo Local Government Area, Rivers State, Augustine Chineme Opurum

Library Philosophy and Practice (e-journal)

The study examined the information needs and seeking behaviour of commercial bus drivers in Obio/Akpo Local Government Area, Rivers State. It employed a descriptive research design. The study population comprises 150 commercial bus drivers from Rumuokoro and Choba Park in Obio/Akpo Local Government Area of Rivers State. The accidental sampling technique was used to select 100 commercial bus drivers from Rumuokoro and Choba Park in Obio/Akpo Local Government Area of Rivers State which stood as the sample for the study. The instrument used for data collection was a structured questionnaire titled: Information Needs and Seeking Behaviour of Commercial Bus Drivers …

Evolution Of Research On Prison Library: A Bibliometric Study, Andreu Sulé, Jordi Ardanuy

Library Philosophy and Practice (e-journal)

The primary objective of the article is to present the historical evolution and current state of research in the field of prison libraries: what has been published, when, where, how and by whom it was published, the topic covered, etc. The study is based on the results obtained from the bibliographic databases LISA (ProQuest) and LISTA (EBSCO Publishing) up to early 2023. Entries were manually checked for irrelevant publications, and filters and specific tools, such as OpenRefine, followed by a final manual check, were used to remove duplicate entries. The same mechanisms were used for detecting duplicated entries regarding author, …

Cultivating Parental Participation And Community Engagement Through Building A Culinary Garden And Teaching Kitchen: Latinx Perspectives On Parental Participation In A Community School, Jaclynne Michelle Medina

Dissertations

This study researched how a school could increase parental participation and community engagement while building a new Culinary Garden and Teaching Kitchen project. This engagement was foundational for expanding parental participation opportunities and further developing the community school. The study explored ways to balance power relationships between the home and school to develop an implementation plan that better reflects the community being served. Theoretical lenses such as CRT and LatCrit were the basis for centering the voices of Latinx families and valuing their various forms of capital consistent with the Community Cultural Model. Participants influenced the design of the garden …

Classification Of Darknet Traffic By Application Type, Shruti Sharma

Master's Projects

The darknet is frequently exploited for illegal purposes and activities, which makes darknet traffic detection an important security topic. Previous research has focused on various classification techniques for darknet traffic using machine learning and deep learning. We extend previous work by considering the effectiveness of a wide range of machine learning and deep learning technique for the classification of darknet traffic by application type. We consider the CICDarknet2020 dataset, which has been used in many previous studies, thus enabling a direct comparison of our results to previous work. We find that XGBoost performs the best among the classifiers that we …

Prediction Of 2024 Indian Pm Election Results Using Sentiment Analysis On Twitter Data, Surabhi Gupta

Master's Projects

This sentiments analysis study presents a methodical approach to predict the 2024 Indian Prime Minister Election. Data collected spanning from 2020 to 2023 from Twitter using hashtags such as IndianPMElection2024 and on topics such as the revocation of the special status of Jammu and Kashmir, the Farm Bill, and the Digital India initiative, form the core of this research. We utilized a combination of sentiment extraction tools-namely, the NLP Town's Bidirectional Encoder Representations from Transformers (BERT)-based multilingual uncased sentiment model, Valance Aware Dictionary for Sentiment Reasoning (VADER), and TextBlob. Additionally, we used a well-established machine learning model Naive Bayes, deep …

Automated Evaluation For Distributed System Assignments, Nimesh Nischal

Master's Projects

A distributed system can exist in numerous states, including many erroneous permutations that could have been addressed in the code. As distributed systems such as cloud computing and microservices gain popularity, involving distributed com- puting assignments is becoming increasingly crucial in Computer Science and related fields. However, designing such systems poses various challenges, such as considering parallel executions, error-inducing edge cases, and interactions with external systems. Typically, distributed assignments require students to implement a system and run multiple instances of the same code to behave as distributed. However, such assign- ments do not encourage students to consider the potential edge …

Ubiquitous Application Data Collection In A Disconnected Distributed System, Deepak Munagala

Master's Projects

Despite some incredible advancements in technology, a significant population of the world does not have internet connectivity. These people lack access to crucial information that is easily available to the rest of the world. To solve this problem, we implement a Delay Tolerant Network (DTN) that allows users in disconnected regions access to the internet. This is enabled by collecting all data requests on the users’ phones and passing them to a device that can carry them to a connected region. This device can then collect the necessary information and give it back to the users in the disconnected region. …

Graph Deep Learning Based Hashtag Recommender For Reels On Social Media, Sriya Balineni

Master's Projects

Many businesses, including Facebook, Netflix, and YouTube, rely heavily on a recommendation system. Recommendation systems are algorithms that attempt to provide consumers with relevant suggestions for items such as movies, videos, or reels (microvideos) to watch, hashtags for their posts, songs to listen to, and products to purchase. In many businesses, recommender systems are essential because they can generate enormous amounts of revenue and make the platform stand out when compared to others. Reels are a feature of the social media platforms that enable users to create and share videos of up to sixty seconds in length. Individuals, businesses, and …

Context Aware Neural Machine Translation Using Graph Encoders, Saurabh Kale

Master's Projects

Machine translation presents its root in the domain of textual processing that focuses on the usage of computer software for the purpose of translation of sentences. Neural machine translation follows the same idea and integrates machine learning with the help of neural networks.Various techniques are being explored by researchers and are famously used by Google Translate, Bing Microsoft Translator, Deep Translator, etc. However, these neural machine translation techniques do not incorporate the context of the sentences and are only determined by the phrasesor sentence structure. This report explores the neural machine translation technique dedicated to context-aware translations. It also provides …

Spartan Price Oracle: A Schelling-Point Based Decentralized Pirce Oracle, Sihan He

Master's Projects

Nakamoto’s Bitcoin is the first decentralized digital cash system that utilizes a blockchain to manage transactions in its peer-to-peer network. The newer generation of blockchain systems, including Ethereum, extend their capabilities to support deployment of smart contracts within their peer-to-peer networks. However, smart contracts cannot acquire data from sources outside the blockchain since the blockchain network is isolated from the outside world. To obtain data from external sources, smart contracts must rely on Oracles, which are agents that bring data from the outside world to a blockchain network. However, guaranteeing that the oracle’s off-chain nodes are trustworthy remains a challenge. …

The New Student: The Enhancement Of An Ebook To Support Emotional Connection, Rebecca Zumaeta

Master's Projects

EBooks are a form of multimedia applications that encourage cognitive learning. Multimedia can also influence readers to have a deeper connection to the story. Understanding the influence of a static picture book versus an animated and audio guided eBook can prove valuable in developing learning media and other forms of content. In this research we take a published children's book and apply the content into a multimedia eBook. The purpose of the creation of the eBook is to compare the interest of a reader on a story when static format, when some multimedia is added and when the story is …

Video Sign Language Recognition Using Pose Extraction And Deep Learning Models, Shayla Luong

Master's Projects

Sign language recognition (SLR) has long been a studied subject and research field within the Computer Vision domain. Appearance-based and pose-based approaches are two ways to tackle SLR tasks. Various models from traditional to current state-of-the-art including HOG-based features, Convolutional Neural Network, Recurrent Neural Network, Transformer, and Graph Convolutional Network have been utilized to tackle the area of SLR. While classifying alphabet letters in sign language has shown high accuracy rates, recognizing words presents its set of difficulties including the large vocabulary size, the subtleties in body motions and hand orientations, and regional dialects and variations. The emergence of deep …

Classifying World War Ii Era Ciphers With Machine Learning, Brooke Dalton

Master's Projects

We examine whether machine learning and deep learning techniques can classify World War II era ciphers when only ciphertext is provided. Among the ciphers considered are Enigma, M-209, Sigaba, Purple, and Typex. For our machine learning models, we test a variety of features including the raw ciphertext letter sequence, histograms, and n-grams. The classification is approached in two scenarios. The first scenario considers fixed plaintext encrypted with fixed keys and the second scenario considers random plaintext encrypted with fixed keys. The results show that histograms are the best feature and classic machine learning methods are more appropriate for this kind …

Malware Classification Using Opcode N-Grams And Word Embeddings, Siddhita Joshi

Master's Projects

Malware is a serious risk to any software application whether it is standalone or over the network. In order to protect computer systems, it is essential to detect and classify malware effectively. Modern malware classification research focuses on Machine Learning and Deep Learning techniques to identify advanced malicious software. This project explores malware classification by combining two robust methods: n-grams and word embedding. By extracting opcode n-grams, we make use of sequential nature of malware execution to identify any local patterns within the malware executable.

We use word embedding methods such as Word2Vec, Doc2Vec, and FastText to produce dense vector …

Evaluation Of The Effect Of Walnut Extract On Sp1-Related Pathways, Jihan Yehia

Master's Projects

Walnut extract (WE) has shown promising anti-cancer effects, such as inducing apoptosis and moderating cell cycle progression. A previous study by Dr. Brandon White’s Lab at San Jose State University hypothesizes that WE can downregulate the expression of the pro-tumoral specificity protein 1 (Sp1) in triple negative breast cancer (TNBC). This project builds an RNA-seq pipeline that runs differential gene expression (DGE) analysis to study the effect of WE on TNBC, thereby offering a wider perspective on genes that may be affected by this treatment. The data used in this project originated from Illumina and Nanopore sequencing methods, and DGE …

Evalsql - Automated Assessment Of Database Queries, Damanpreet Kaur

Master's Projects

In computer science programs, database is a fundamental subject taught through several undergraduate courses. These courses develop theoretical and practical concepts of databases. Building queries is a key aspect of this learning process, and students are assessed through assignments and quizzes. However, grading these assignments can be time-consuming for professors, and students usually receive feedback only after the deadlines have passed. As a result, students may miss the opportunity to improve their work and achieve better grades. To address this issue, it would be beneficial to provide students with immediate feedback on their submissions. EvalSQL is an automated system that …

Gesture Recognition Of Sign Language Alphabet Using Machine Learning Techniques, Gursimran Singh

Master's Projects

With the rising incidence of hearing loss, effective sign language recognition has become crucial for enhancing communication for individuals with hearing impairments. Traditional sensor-based recognition systems have been challenged by the complexities of realworld settings, prompting a shift toward more adaptable vision-based recognition systems. Distinct from previous studies, this work pioneers the use of ensemble methods with advanced filtering techniques on the Sign Language MNIST dataset, offering a novel perspective on sign language recognition. This research delves into the intersection of machine learning and image processing to develop a robust framework for sign language recognition. A range of filters, including …

The U.S. Invasion Of The Dominican Republic: From Cooperation To Conquest, Andrew Defabio

Master's Theses

This paper explores the political and military relationship between the U.S. and the Dominican Republic from the Eisenhower administration to the Johnson administration’s invasion in 1965. The U.S. intervention in the Dominican Republic was a military operation that had been planned and prepared for by administrations prior and not simply a reactive decision to prevent a Communist takeover. Analysis of multiple administrations places the invasion of the Dominican Republic in a larger context of U.S. – Dominican relations. The U.S.’s desire to dominate military and political aspects of the Dominican Republic is consistent with U.S. Cold War Latin American policy.

Qualifying Quantifiers: A Usage-Based, Diachronic Analysis Of Quantifier Constructions, Danielle Miles Angier

Master's Theses

Adnominal quantifiers have been a source of contention in existing research, owing to their unique distributional patterns that do not match those of adjectives or determiners. Traditional accounts have typically focused on one aspect of quantifier behavior without looking at the group as a whole, and existing theories are disparate and inconsistent. This study tackles the problem of quantifier variation from a diachronic, usage-based, constructionist perspective. The goal of this paper is to identify patterns of change that can explain the variation exhibited by quantifiers today, focused on whether they are best classified as adjectives, determiners, or both; why every …

A New Fire Initialization Method For Operational Coupled Fire-Atmosphere Models: Assimilation Of Infrared Perimeters And Satellite Detections, Kathleen Nicole Clough

Master's Theses

For coupled fire-atmosphere forecast models, such as WRF-SFIRE, the method used to initialize wildfire within the model can greatly impact meteorological, fire, and smoke extent forecasts. A well-constructed ignition process must be integrated within models to assure the atmospheric component of the model is not destabilized by excessive heat flux released during ignition and realistic fire-induced atmospheric circulation is established. Two ignition methods are tested on the 2020 Creek fire. Analyses indicate a gradual perimeter ignition with selective “masking”, fuel removal, provides the best results in terms of resolving the fire-induced vertical circulation and fire spread, and is thus preferred …

Phosphate And Silicate Analysis In Seawater Using Programmable Flow Injection: Optimization And Applications Of Benchtop And In Situ Methodologies, Marine A. Lebrec

Master's Theses

Oceanographic nutrient monitoring efforts still largely rely on discrete sampling at irregular intervals, hindering the advancement of high-resolution biogeochemical observations and models. Benchtop analytical instrumentation for macronutrient analysis is expensive, complex, and requires large reagent volumes and highly trained operators. This thesis describes the development and optimization of a novel and commercially available class of automated nutrient analyzers called programmable Flow Injection (pFI) for benchtop and unattended in situ operations with a focus on phosphate and silicate analysis. While pFI is an ideal candidate for unattended deployments due to its compact size, low reagent volume requirements, and ability measure multiple …

Blockchain For Online Video Game Integrity, Philip Salire

Master's Theses

With the growing level competition in video games, especially with regards to competitively played video games known as ”e-sports,” many players are searching for methods of gaining competitive advantages. As such, there is growing demand in software exploits of video games that aim to provide players unfair competitive advantages. Colloquially, these software exlpoits are referred to as “cheats” or “hacks.” Video game developers counteract these exploits by implementing “anti-cheat” technologies. Anti-cheats employ a myriad of complex methods across software, network, and hardware to detect and prevent cheats. They can be implemented both client-side and server-side with current research and implementations …