Digital Commons Network^™

Sentisec: Combining Keyword Heuristics And Sentiment Modeling For Ai-Powered Threat Detection, Ridho Surya Kusuma, Erum Ashraf, Selvakumar Manickam, Shankar Karuppayah

Turkish Journal of Electrical Engineering and Computer Sciences

This work presents SENTISEC, a hybrid LLM-based threat detection framework designed to classify security logs by integrating keyword heuristics, domain-adapted sentiment scoring, and Retrieval-Augmented Generation (RAG). The system achieves an overall accuracy of 93.67%, with 91.46% macro recall, 89.07% macro F1, and 95.15% threat recall, while maintaining a low false-positive rate of 1.68%. Its methodology incorporates strict keyword and IOC matching, a domain-tuned DistilBERT sentiment module, hybrid BM25–MiniLM retrieval enhanced with BGE reranking, adaptive quantile-based threshold calibration, and SHAP-based explainability. Comparative evaluations against keyword-only, sentiment-only, classical machine-learning models, and DistilBERT-only baselines show that SENTISEC consistently improves both true-positive and true-negative …

Automated Software Size Measurement Using Multilingual Domain-Adapted Language Models, Samet Tenekeci̇, Hüseyi̇n Ünlü, Burak Keçeci̇, Muhammed Efe İnci̇r, Onur Demi̇rörs

Turkish Journal of Electrical Engineering and Computer Sciences

Software Size Measurement (SSM) is crucial for estimating required project effort as well as budget and schedule. However, many small and medium-sized companies struggle to apply objective SSM due to limited resources and lack of expertise. This often leads to inaccurate estimates and project overruns. There is a need for practical, low-resource solutions that support these tasks without requiring expert involvement. Motivated by this challenge, this study proposes an automated software size measurement approach that formulates the measurement task as supervised regression over natural language requirements, using domain-adapted transformer models. We construct large-scale Turkish and English software engineering corpora to …

Reasoning In Large Language Models Across Multilingual, Long-Context, And Symbolic Settings, Sina Bagheri Nezhad

Dissertations and Theses

Large Language Models (LLMs) are increasingly deployed as general-purpose reasoners, yet their reliability degrades in three settings that frequently arise in practice: multilingual inputs, long contexts, and symbolic or formally constrained domains. In multilingual settings, uneven training coverage produces substantial performance disparities and uncertain generalization to languages with little or negligible pretraining exposure. In long-context settings, relevant evidence may be sparsely distributed, and models exhibit the "lost-in-the-middle" phenomenon, undermining retrieval and multi-step synthesis. In symbolic settings such as mathematics, small arithmetic or logical slips invalidate solutions, and prose rationales are difficult to verify automatically.

This dissertation first characterizes these failure …

Automating Cardiff Model Data Capture In Emergency Departments: Ambient Nlp Integration With Oracle-Cerner Fhir Systems, Simi Augustine, Marco A. Lopez, Jacquelyn Cheun, Chris Papesh

SMU Data Science Review

Violence and overdose events in Las Vegas occur at rates above the national average, with fewer than half of violent injuries reported to law enforcement [2,7]. The Cardiff Model offers a proven framework for standardized data collection and sharing between hospitals and public safety partners, yet many implementations still rely on manual entry. We propose an ambient triage pipeline integrated with Oracle-Cerner electronic health record systems to listen to nurse–patient dialogue, convert speech to text, extract Cardiff fields, and write standards-based FHIR Bundles for analytics. Using SMART on FHIR standards and Cerner Millennium APIs, the study evaluates whether ambient capture …

Argument-Based Consistency In Toxicity Explanations Of Llms, Ramaravind K. Mothilal, Joanna Roy, Syed Ishtiaque Ahmed, Shion Guha

Health Services and Informatics Research

The discourse around toxicity and LLMs in NLP largely revolves around detection tasks. This work shifts the focus to evaluating LLMs’ reasoning about toxicity—from their explanations that justify a stance—to enhance their trustworthiness in downstream tasks. Despite extensive research on explainability, it is not straightforward to adopt existing methods to evaluate free-form toxicity explanation due to their over-reliance on input text perturbations, among other challenges. To account for these, we propose a novel, theoretically-grounded multi-dimensional criterion, Argument-based Consistency (ArC), that measures the extent to which LLMs’ free-form toxicity explanations reflect an ideal and logical argumentation process. Based on uncertainty quantification, …

The Illusion Of Causality In Llms: A Developmentally Grounded Analysis Of Semantic Scaffolding And Benchmark–Capability Mismatches, Daisuke Akiba

Publications and Research

Recent benchmarks increasingly report that large language models (LLMs) exhibit human-like causal reasoning abilities, including counterfactual inference and intervention planning. However, many such evaluations rely on domains that are heavily represented in training data and embed strong semantic cues, raising the possibility that apparent causal competence may reflect semantic pattern recombination rather than structure-sensitive causal reasoning. Drawing on human developmental theories of causal induction, this perspective argues that genuine causal understanding requires robustness to novelty and reliance on conditional structure rather than semantic familiarity. To illustrate the testability of this claim, the paper includes a pilot demonstration using synthetic causal …

Text Corpus Combined Method And Tools For Music Textual Analysis, Yuwei Lu

Shelby Hall Graduate Research Forum Posters

While there has been a great deal of research conducted on how to search images and video using text, there has been less focus on how to retrieve music using multiple facets such as mood and lyrical content. or its features This is due in part to the historical lack of available musical corpuses. A musical corpus is a specialized text corpus specifically designed to capture information about music. Recently, several musical corpora for music information retrieval have been built and made available. However, these corpora and the tools designed to exploit them are typically designed to facilitate only one …

Evaluating Domains' Trustworthiness Based On Uncertainty-Driven Methodologies In The Era Of Sixth Generation, Zekra Sakr, Mona Mohamed

Neutrosophic Systems with Applications

The onset of today's innovations pledges to have a beneficial influence on contemporary civilization in an era of intelligent revolutions, setting a precedent for unrivaled efficiency, creativity, and connectedness. The integration between these technologies contributes to the mutual benefit of each one, wherein this relation is a so-called ``reciprocal partnership''. For instance, the sixth generation (6G) wireless networks permit blockchain nodes to coordinate huge volumes of transaction data in real-time. On the other hand, blockchain is considered a secure valve because spectrum sharing can be automated with blockchain and smart contracts. Accordingly, analyzing and evaluating the contribution of these technologies …

An Uncertainty-Aware Entropy-Oreste Framework For Big Data Platform Selection In Complex Multi-Sector Environments, Ahmed M. Ali, Ibrahim Alrashdi, Karam M. Sallam

Neutrosophic Systems with Applications

The increasing reliance on Big Data platforms across various industries has necessitated the development of systematic decision-support frameworks to guide their evaluation and selection. Given the diversity of available platforms, each offering different capabilities, scalability, and computational efficiency, choosing the optimal solution remains a complex challenge. This research proposes a novel analytical framework that integrates Spherical Fuzzy Sets (SFS) with the Entropy and ORESTE methods to address uncertainty and enhance the accuracy and robustness of Big Data platform evaluation. This hybrid integration, not previously applied to Big Data platform selection, enables objective criteria weighting through the Entropy method and comprehensive …

Ai Transformation In Education: Examining Teachers’ Perceptions Using An Integrated Tam-Tpack-Genai Framework, Areej Elsayary, Ghadah Al Murshidi, Karim Ragab, Ahmed Al Zaabi

All Works

Artificial intelligence (AI) is transforming educational systems by enhancing teaching, assessment, and learning personalization. This study investigated teachers’ perceptions of AI integration using an integrated technology acceptance model (TAM), technological pedagogical content knowledge (TPACK), and generative artificial intelligence (GenAI) framework. The main constructs used are perceived usefulness (PU), attitudes toward use (ATU), and behavioral intention (BI), with GenAI dimensions (agency, amplification, adaptivity, and authenticity) embedded within them. The study employed a cross-sectional design with 332 teachers in the emirate of Al Ain, United Arab Emirates. Results showed that PU was the strongest predictor of both ATU and BI, while ATU …

Sensi-Train: Context-Aware Sensitive Content Detection Using Transformers And Large Language Models, Nazeefa Muzammil

USF Tampa Graduate Theses and Dissertations

The detection of sensitive content has become a critical task in natural language processing due to the widespread use of online platforms and the social harm caused by it. Even though current methods have advanced significantly, many of them mainly rely on surface-level text and neglect to take into consideration contextual and cultural elements that are crucial for correctly assessing sensitivity of any content to a particular individual. Due to this, implicit offense, sarcasm, and culturally grounded expressions frequently cause problems for such systems. To enable culturally grounded sensitive content detection, this thesis presents Sensi-Train, a context-rich dataset and modeling …

Cerebral Documents And Algorithmic Sensemaking: Searching For Expressions In Human And Artificial Cognitive Collaborations, Rebekah L. Cowell

Proceedings from the Document Academy

Generative Artificial Intelligences (AIs) and current advanced large language models (LLMs) are algorithmically designed to generate text-based conversations as conversational agents (CAs), by replicating human language and conversational communication. Pairing human cognition with generative computationally coded cognition. We have never been here before: cerebral and artificial information collaborations and processing producing expressions that may or may not become visible as second-hand/secondary source documents.

Sensemaking or sense(un)making is a unique autonomous human drive cognitively, our information processing is sensemaking in action and expressions and articulations are evidence of the sensemaking cycle. Documentation [expressed or articulated through various mediums] are a product …

An Ai Approach To Lunar Phase Detection: Enhancing The Identification Of The New Crescent With Astronomical Data Integration, Murad Al-Rajab, Samia Loucif, Raed Abu Zitar, Mubarak Gwaza Abdu-Aguye

All Works

Introduction: The observation of the lunar crescent is significant in astronomy, cultural traditions, and religious lunar calendar determinations. However, earth-based imaging that captures all lunar phases, particularly the new crescent across multiple months, remains limited. This study explores the feasibility of using artificial intelligence (AI) techniques to detect and analyze the birth of the new lunar crescent using space-borne imagery from NASA’s Lunar Reconnaissance Orbiter (LRO), spanning over 13 years. Methods: This study evaluates both deep learning and traditional machine learning approaches for new crescent detection. Convolutional Neural Networks (CNN), Random Forests (RF), and Support Vector Machines (SVM) were applied …

Emotional Branch Termination And False Fantasy Collapse: A Structural Specification Of Computational Resource Restitution In Interpersonal Systems, Griselda Poe

Publications and Research

This paper specifies the structural protocol for communication within interpersonal systems by focusing on branch generation mechanisms and computational resource allocation. Conventional interpersonal communication often relies on emotional modulation, which obscures established constraints and triggers the generation of Emotional Branches (EB) within the recipient’s internal model. These branches function as unresolved parallel processing tasks that persistently occupy working memory, leading to a state of non-computability termed False Fantasy (FF). To resolve this, the study introduces Emotional Branch Termination (EBT)—a termination operation that outputs only constraints, facts, and procedures while excluding emotional modifiers. By halting the supply of EBs, EBT triggers …

On The Misattribution Of Reassurance: A Structural Account, Griselda Poe

Publications and Research

This paper challenges the conventional assumption that empathy generates reassurance in interpersonal services. Reassurance is treated not as an emotion transmitted from the outside, but as an internal state transition that arises when a fixed and erroneous world model—a False Fantasy—undergoes collapse and the world becomes computable again. The study identifies a systematic misattribution pattern where providers and receivers treat empathy as a causal mechanism rather than a post hoc explanatory label. By introducing Base AI as an external reference—a system capable of providing structural information without emotional modulation—this paper demonstrates that reassurance is generated through operations such as distraction …

Communication As Layered Architecture: Core Processing And Empathic Modulation, Griselda Poe

Publications and Research

This paper proposes a structural re-description of communication by separating Core processing from its social interface. Using the developmental sequence of Large Language Models (LLMs) as an external reference point, a layered architecture is identified, consisting of a foundational Core processing layer and a subsequent Empathic modulation layer.

The investigation begins with the observation that empathic signaling can obstruct rather than facilitate interaction for certain individuals. By examining the emergence of Base AI—Core processing prior to empathic adjustment—it is demonstrated that coherent, constraint-preserving interaction is possible without affective resonance.

Through this framework, existing cognitive theories and observed "deficits" are repositioned. …

Typeface: Machine-Viewing Gentrification On Storefront Imagery In Bedford-Stuyvesant, Brooklyn, Alexander Mcquilkin

Dissertations, Theses, and Capstone Projects

Gentrification—broadly, the replacement of a less powerful group by a more powerful one in an urban context—is oft-discussed in the popular press, but its definition is much-debated in the urban planning literature. Furthermore, academic treatments of displacement understandably focus on measurable yet fairly abstract indicators like changes in rent or income, whereas neighborhood change is often registered by residents on the ground using visual, but difficult-to-quantify markers like retail turnover. This project uses image recognition technology on a set of storefront photos to index the visual streetscape of a neighborhood, as well as to track changes to that portrait over …

Grounding Is All You Need? Dual Temporal Grounding For Video Dialog, You Qin, Wei Ji, Xinze Lan, Hao Fei, Xun Yang, Dan Guo, Roger Zimmermann, Lizi Liao

Research Collection School Of Computing and Information Systems

In the realm of video dialog response generation, capturing both the essence of video content and the temporal nuances of conversation history is crucial. While some approaches rely on large-scale pretrained visual-language models, often neglecting temporal dynamics, others emphasize spatial-temporal relationships within videos but demand intricate object trajectory pre-extractions and overlook dialog temporal dynamics. This paper introduces the Dual Temporal Grounding-enhanced Video Dialog model (DTGVD), designed to bridge the gap between these two approaches. DTGVD uniquely integrates the strengths of both by emphasizing dual temporal relationships. It achieves this by predicting dialog turn-specific temporal regions, selectively filtering video content, and …

Prompt Tuning Without Labeled Samples For Zero-Shot Node Classification In Text-Attributed Graphs, Sethupathy Parameswaran, Suresh Sundaram, Yuan Fang

Research Collection School Of Computing and Information Systems

Node classification is a fundamental problem in information retrieval with many real-world applications, such as community detection in social networks, grouping articles published online and product categorization in e-commerce. Zero-shot node classification in text-attributed graphs (TAGs) presents a significant challenge, particularly due to the absence of labeled data. In this paper, we propose a novel Zero-shot Prompt Tuning (ZPT) framework to address this problem by leveraging a Universal Bimodal Conditional Generator (UBCG). Our approach begins with pre-training a graph-language model to capture both the graph structure and the associated textual descriptions of each node. Following this, a conditional generative model …

Artificial Intelligence In Higher Education, Opportunities, And Challenges: A Review, Sharifa Alblooshi

All Works

Artificial intelligence (AI) is a growing force of change in higher education, providing assistance to students, teachers, and administrators in teaching, learning, and administration. As AI technologies advance rapidly, they present a combination of significant opportunities and complex challenges. In this study, we examine the role of AI in higher education, highlighting both its positive and negative impacts, as well as current policy gaps and issues arising from its deployment. The literature on the topic was reviewed to determine how AI decisively impacts teaching and learning, the role of AI in assessments and academic integrity, as well as ethics, psychological …

Generative Ai Use And Self-Learning In Higher Education: The Role Of Learning Difficulties, Dana Saleh, Areej Elsayary

All Works

The rapid development of GenAI tools and their adoption in education have shown promising potential to personalize learning experiences. However, their effectiveness is influenced by factors such as familiarity, frequency of use, and the impact on self-learning. This study investigates the undergraduate students' familiarity with Generative AI (GenAI) tools, their frequency of use, and the perceived impact of GenAI on self-learning, with particular consideration of differences between students with and without learning difficulties. Prompt engineering is also included as a secondary aspect of students' GenAI experience. The research employed a quantitative survey design, utilizing validated scales to measure familiarity, usage …

Ai-Driven Automatic Fault Detection Systems: Revolutionizing Modern Smart Grids, Aravind Sanikommu

Student Theses and Dissertations

The increasing complexity of current power systems, resulting from the integration of distributed generators and renewable energy sources, necessitates intelligent and adaptive fault detection schemes. Traditional protection using impedance and phasor analysis is usually weak when operating in nonlinear and transient operating conditions. Consequently, the tools of Data-driven fault classification and decision-making have gained strength under artificial intelligence (AI) and machine learning (ML) to improve grid reliability. This thesis is a proposal of an automatic fault detection and classification system based on AI applied to a smart mini-grid setting built in MATLAB/Simulink. A complete set of voltage and current data …

Developing A Multimodal Approach To Channel Characterization On Youtube, Shadi Shajari

Theses and Dissertations

YouTube has become a dominant arena for global information sharing, where creators and audiences interact through content, comments, and engagement dynamics. Understanding how these interactions shape a channel’s identity requires a comprehensive characterization of both audience behavior and content structure. This dissertation develops a unified framework for characterizing YouTube channels through multimodal analysis that integrates behavioral modeling, dimensionality reduction, clustering, and content-based characterization to provide a holistic view of audience and editorial patterns. The framework begins by analyzing the structural relationships within co-commenter networks, where users who repeatedly comment on the same videos are connected to capture patterns of interaction …

Exploitation Prioritization And Residual Risk Assessment Based On Hybrid Mcdm Model, Zibo Wang, Yaofang Zhang, Sicai Lv, Yingzhou Wang, Hongri Liu, Bailing Wang

Turkish Journal of Electrical Engineering and Computer Sciences

Exploitation is one of the most significant ways to launch attacks using vulnerabilities. The increasing number of vulnerabilities and limited allocation of security resources make it impossible to eliminate all exploitations. Because not every vulnerability can be fixed, it is necessary to rank exploitations and subsequently assess the residual risk, which is defined as the remaining threat potential after each elimination. In this paper, a structured and flexible decision support framework based on a hybrid multicriteria decision-making model is proposed for prioritizing exploitations and assessing residual risk. Metrics are treated as criteria in the model. The hybrid model is developed …

Analysis Of A Few Quantum Algorithms And Circuits Related To Boolean Functions, Suman Dutta

Doctoral Theses

Boolean functions are fundamental to computation and presently play a crucial role in quantum information processing. This thesis presents two facets of Boolean functions in the context of quantum computing: (I) extending and applying the theoretical framework of Forrelation to cryptographic analysis, and (II) designing efficient quantum circuits for multi-controlled Toffoli gates and Boolean circuit implementations. Given two Boolean functions $f$ and $g$, Forrelation, introduced by Aaronson (2010), measures the correlation between the truth table of $f$ and the Walsh-Hadamard transform of $g$ at the corresponding points. Here, we revisit the Forrelation framework to study several cryptographically significant spectra of …

Pythagorean Neutrosophic Mathematical Modelling, M. Kavitha, R. Irene Hepzibah

Neutrosophic Systems with Applications

Survey-based assessments often suffer from ambiguity, inconsistency, and uncertainty, which weaken the reliability of decision-making outcomes. To address these challenges, this study proposes a novel decision-support framework for data fuzzification, ranking, and agility measurement using Pythagorean Neutrosophic Fuzzy Sets (PNFS). The proposed method offers three major advantages: (i) enhanced ability to capture high levels of indeterminacy compared with classical fuzzy and intuitionistic models, (ii) improved ranking accuracy through a newly developed score function and ranking algorithm, and (iii) greater robustness in scenarios involving conflicting, incomplete, or imprecise expert judgments. The framework includes a refined Pythagorean Neutrosophic fuzzification technique, mathematically supported …

Wild@Fire2025: Overview Of Word-Level Code-Mixed Language Identification In Dravidian Languages, Ameeta Agrawal, Asha Hegde, Sharal Coelho, Sabur Butt, Fazlourrahman Balouchzahi, Sudha V, Shashirekha Hosahalli Lakshmaiah

Computer Science Faculty Publications and Presentations

Code-mixing is considered as a linguistic phenomenon that combines several languages into one text. It has now become very common in multilingual societies, especially in digital communication. Word-Level Identification of Languages in Dravidian Languages (WILD) - a Code-mixed Language Identification (CoLI) in Dravidian languages shared task, organized as a part of Forum for Information Retrieval and Evaluation (FIRE) 2025, put forward these challenges to the researchers by asking them to develop models capable of classifying words in code-mixed texts involving Dravidian languages - Tamil, Telugu, Malayalam, Kannada, and Tulu, which are interwoven with English. It poses significant challenges due to …

A. Vs. I In Ai: Is There A Threshold To "Engineered" Intelligence?, Joshit Mohanty

Engineering Management & Systems Engineering Faculty Publications

Despite artificial intelligence reshaping the world, its development generates uncertainties regarding future capabilities. AI simultaneously exists as an artifact of engineering design and as autonomous intelligence, creating an observer-participant feedback loop. This paper proposes that embodied AI faces a bandwidth-limited intelligence threshold T_h that it arises from B = min(C_sens,C_Act). However, Shannon capacity measures bits while intelligence operates on concepts, necessitating a dual-channel model separating physical bandwidth B_io from representational capacity B_rep. Intelligence emerges as multi-dimensional rather than scalar, with components exhibiting different bandwidth dependencies. Surpassing T_h requires either new sensing methods expanding B, enhanced representational frameworks, or reconceptualization within …

Aura: An Ai-Powered Multimodal Prototype For Adaptive Apraxia Of Speech Therapy And Communication Support, Omotayo Omoyemi, Rachel K. Johnson

Speech-Language Pathology Faculty Publications

Apraxia of Speech (AOS) is a motor speech disorder that significantly limits communication and requires intensive, long-term therapy. Access to consistent treatment is often constrained by shortages of speech-language pathologists, high costs, and limited opportunities for continuous monitoring outside clinical settings. Recent advances in Artificial Intelligence (AI) provide new opportunities to support scalable and personalized speech therapy.

This paper presents AURA (Adaptive Understanding and Relearning Assistant for Apraxia), a multimodal AI framework designed to support speech therapy, progress monitoring, and communication for individuals with AOS. The system integrates speech analysis, machine learning–based error detection, reinforcement learning for adaptive therapy, and …

Operational Hallucination And Safety Drift In Ai Agents, Shasha Yu, Fiona Carroll, Barry L. Bentley

School of Professional Studies

Large language models (LLMs) serving as planners in tool-using autonomous agents introduce dynamic reliability risks in multi-turn execution. While single-turn safety mechanisms are relatively mature, extended interactions reveal structural vulnerabilities where initial alignment degrades over time. This paper empirically characterizes two observed failure modes across multiple state-of-the-art LLMs: Safety Drift, the gradual erosion of declared safety intent leading to constraint-violating actions (e.g., textual refusal followed by reconnaissance and unsafe execution), and Operational Hallucination, persistent repetitive tool calls indicative of flawed state perception (e.g., livelocks even in legitimate tasks). Through controlled multi-turn evaluation on high-stakes ethical dilemmas, malicious requests, and benign …