Open Access. Powered by Scholars. Published by Universities.®

Digital Commons Network™

Open Access. Powered by Scholars. Published by Universities.®

Discipline
Institution
Keyword
Publication Year
Publication
Publication Type
File Type

Articles 69061 - 69090 of 1112563

Full-Text Articles in Entire DC Network

Lineation To Liberation: The Transformative Power Of Poetic Rhetoric, Amber Rae Alvarez Jan 2025

Lineation To Liberation: The Transformative Power Of Poetic Rhetoric, Amber Rae Alvarez

Cal Poly Humboldt theses and projects

This project explores the transformative power of poetic rhetoric and examines how poetry as a form of expressive art serves as a means of reclamation in the aftermath of encounters with the American criminal justice system. I contend that poetry provides a space where folks can reimagine (and reclaim) their identities, asserting their agency in empowering and authentic ways. Taking a Cultural Studies and Critical Prison Studies informed approach, this project engages the concept of lineation to liberation to conduct a close reading analysis of artist (Reginald) Dwayne Betts’ poetry. Betts’ work not only provides a powerful example of how …

Go to article

Wait... Homework Can Be Fun?! A Pilot Homework System Study, Caroline Brock Jan 2025

Wait... Homework Can Be Fun?! A Pilot Homework System Study, Caroline Brock

Cal Poly Humboldt theses and projects

Homework has been a long-debated topic in schools. Regardless of where people stand on the issue, the evidence shows that quality homework can be an effective tool to help students be successful in school. Beyond academics, homework can also be used as a tool to help students develop important foundational study skills that are critical for future success. But how can school districts get all stakeholders behind a homework system if they do not see the value of homework, or if the homework is a point of individual or familial stress. Through an action research project using mixed methods, parents …

Go to article

University Of New Mexico Health Sciences Center Discovery Research Annual Report 2025, Michael Haderle, Kandace Donaldson, Brianna Mortensen, Christina V. Rodriguez, Jill Rothenberg, Bryan Schroeder Jan 2025

University Of New Mexico Health Sciences Center Discovery Research Annual Report 2025, Michael Haderle, Kandace Donaldson, Brianna Mortensen, Christina V. Rodriguez, Jill Rothenberg, Bryan Schroeder

Research Annual Reports

Annual research report from the University of New Mexico Health Sciences Center.

Go to article

Some Types Of Hyperneutrosophic Set (1): Bipolar, Pythagorean, Double-Valued, Interval-Valued Set, Takaaki Fujita, Florentin Smarandache Jan 2025

Some Types Of Hyperneutrosophic Set (1): Bipolar, Pythagorean, Double-Valued, Interval-Valued Set, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

The Neutrosophic Set is a mathematical framework designed to manage uncertainty, characterized by three membership functions: truth (T), indeterminacy (I), and falsity (F). In recent years, extensions such as the Hyperneutrosophic Set and SuperHyperneutrosophic Set have been introduced to address more complex scenarios. This paper proposes new concepts by extending Bipolar Neutrosophic Sets, Interval-Valued Neutrosophic Sets, Pythagorean Neutrosophic Sets, and Double-Valued Neutrosophic Sets using the frameworks of Hyperneutrosophic and SuperHyperneutrosophic Sets. Additionally, a brief analysis of these extended concepts is presented.

Go to article

Superhypergraph Neural Networks And Plithogenic Graph Neural Networks: Theoretical Foundations, Takaaki Fujita, Florentin Smarandache Jan 2025

Superhypergraph Neural Networks And Plithogenic Graph Neural Networks: Theoretical Foundations, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Hypergraphs extend traditional graphs by allowing edges to connect multiple nodes, while superhypergraphs further generalize this concept to represent even more complex relationships. Neural networks, inspired by biological systems, are widely used for tasks such as pattern recognition, data classification, and prediction. Graph Neural Networks (GNNs), a well-established framework, have recently been extended to Hypergraph Neural Networks (HGNNs), with their properties and applications being actively studied. The Plithogenic Graph framework enhances graph representations by integrating multi-valued attributes, as well as membership and contradiction functions, enabling the detailed modeling of complex relationships. In the context of handling uncertainty, concepts such as …

Go to article

Some Types Of Hyperneutrosophic Set (6): Multineutrosophic Set And Refined Neutrosophic Set, Takaaki Fujita, Florentin Smarandache Jan 2025

Some Types Of Hyperneutrosophic Set (6): Multineutrosophic Set And Refined Neutrosophic Set, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

This paper builds on the foundational advancements introduced in [22, 29–32]. The Neutrosophic Set pro-vides a flexible mathematical framework for managing uncertainty by utilizing three membership functions: truth, indeterminacy, and falsity. Recent extensions, such as the HyperNeutrosophic Set and the SuperHy-perNeutrosophic Set, have been developed to address increasingly complex and multidimensional challenges. Comprehensive formal definitions of these concepts are provided in [26]. In this paper, we further extend various specialized classes of Neutrosophic Sets. Specifically, we explore extensions of the MultiNeutrosophic Set and the Refined Neutrosophic Set using HyperNeutrosophic Sets and 𝑛-SuperHyperNeutrosophic Sets, providing detailed analysis and examples.

Go to article

Some Types Of Hyperneutrosophic Set (4): Cubic, Trapozoidal, Q-Rung Orthopair, Overset, Underset, And Offset, Florentin Smarandache, Takaaki Fujita Jan 2025

Some Types Of Hyperneutrosophic Set (4): Cubic, Trapozoidal, Q-Rung Orthopair, Overset, Underset, And Offset, Florentin Smarandache, Takaaki Fujita

Branch Mathematics and Statistics Faculty and Staff Publications

This paper builds upon the foundational work presented in [38–40]. The Neutrosophic Set provides a comprehensive mathematical framework for managing uncertainty, defined by three membership functions: truth, indeterminacy, and falsity. Recent advancements have introduced extensions such as the Hyperneutrosophic Set and the SuperHyperneutrosophic Set, which are specifically designed to address increasingly complex and multidimensional problems. The formal definitions of these sets are available in [30]. In this paper, we extend the Neutrosophic Cubic Set, Trapezoidal Neutrosophic Set, q-Rung Orthopair Neutrosophic Set, Neutrosophic Overset, Neutrosophic Underset, and Neutrosophic Offset using the frameworks of the Hyperneutrosophic Set and the SuperHyperneutrosophic Set. Furthermore, …

Go to article

Forestfuzzy, Forestneutrosophic, Forestplithogenic, And Forestrough Set, Takaaki Fujita, Florentin Smarandache Jan 2025

Forestfuzzy, Forestneutrosophic, Forestplithogenic, And Forestrough Set, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Concepts such as Fuzzy Sets [30, 72], Neutrosophic Sets [53, 55], Rough Sets [37], and Plithogenic Sets [59] have been extensively studied to address uncertainty, with diverse applications across various fields. Recently, TreeFuzzy, TreeNeutrosophic, TreePlithogenic, and TreeRough Sets have been defined [15]. This work examines their extensions: ForestFuzzy, ForestNeutrosophic, ForestPlithogenic, and ForestRough Sets.

Go to article

Some Types Of Hyperneutrosophic Set (3): Dynamic, Quadripartitioned, Pentapartitioned, Heptapartitioned, M-Polar, Takaaki Fujita, Florentin Smarandache Jan 2025

Some Types Of Hyperneutrosophic Set (3): Dynamic, Quadripartitioned, Pentapartitioned, Heptapartitioned, M-Polar, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

This paper builds upon the foundation established in [50, 51]. The Neutrosophic Set provides a robust mathematical framework for handling uncertainty, defined by three membership functions: truth, indeterminacy, and falsity. Recent developments have introduced extensions such as the Hyperneutrosophic Set and SuperHyperneutrosophic Set to tackle increasingly complex and multidimensional problems. In this study, we explore further extensions, including the Dynamic Neutrosophic Set, Quadripartitioned Neutrosophic Set, Pentapartitioned Neutrosophic Set, Heptapartitioned Neutrosophic Set, and m-Polar Neutrosophic Set, to address advanced challenges and applications.

Go to article

Local-Neutrosophic Logic And Local-Neutrosophic Sets: Incorporating Locality With Applications, Florentin Smarandache, Takaaki Fujita Jan 2025

Local-Neutrosophic Logic And Local-Neutrosophic Sets: Incorporating Locality With Applications, Florentin Smarandache, Takaaki Fujita

Branch Mathematics and Statistics Faculty and Staff Publications

The study of uncertainty has been a significant area of research, with concepts such as fuzzy sets [87], fuzzy graphs [51], and neutrosophic sets [58] receiving extensive attention. In Neutrosophic Logic, indeterminacy often arises from real-world complexities. This paper explores the concept of locality as a key factor in determining indeterminacy, building upon the framework introduced by F. Smarandache in [73]. Locality refers to processes constrained within a specific region, where an object or system is directly influenced by its immediate surroundings. In contrast, nonlocality involves effects that transcend spatial or temporal boundaries, where changes in one location have direct …

Go to article

Neutrosophic Treesoft Expert Set And Forestsoft Set, Takaaki Fujita, Florentin Smarandache Jan 2025

Neutrosophic Treesoft Expert Set And Forestsoft Set, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Concepts such as Fuzzy Sets [28,57],Neutrosophic Sets [42,44], and Plithogenic Sets [48] have been extensively studied to address uncertainty, finding diverse applications across various fields. The Soft Set provides a framework that associates each parameter with subsets of a universal set, enabling flexible approximations [31]. The TreeSoft Set extends the Soft Set by introducing hierarchical, tree-structured parameters, allowing for multi-level data representation [53]. In this paper, we revisit the concept of the Neutrosophic TreeSoft Set, which has been discussed in other studies [8, 34]. Additionally, we propose and examine the Neutrosophic TreeSoft Expert Set by incorporating the framework of the …

Go to article

Plithogenic Duplets And Plithogenic Triplets, Takaaki Fujita, Florentin Smarandache Jan 2025

Plithogenic Duplets And Plithogenic Triplets, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

A Neutrosophic Set is a mathematical framework that represents degrees of truth, indeterminacy, and falsehood to address uncertainty in membership values [41, 42]. In contrast, a Plithogenic Set extends this concept by incorporating attributes, their possible values, and the corresponding degrees of appurtenance and contradiction [50]. Among the related concepts of Neutrosophic Sets, Neutrosophic Duplets and Neutrosophic Triplets are well-known. This paper defines Plithogenic Duplets and Plithogenic Triplets as extensions of these concepts using the Plithogenic Set framework and briefly examines their relationship with existing concepts.

Go to article

Quantified Neutrosophic Set (Qtns)-Based Mcdm Algorithms For Sustainable Material Selection For Anti-Microbial Bio-Fabricated Textile Manufacturing, Muhammad Saeed, Neha Andaleeb Khalid, Florentin Smarandache Jan 2025

Quantified Neutrosophic Set (Qtns)-Based Mcdm Algorithms For Sustainable Material Selection For Anti-Microbial Bio-Fabricated Textile Manufacturing, Muhammad Saeed, Neha Andaleeb Khalid, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

This paper proposes a modified structure for the neutrosophic set called the Quantified Neutrosophic Set (QtNS) with a parameterized setting. Unlike conventional approaches, the QtNS provides a quantified environment for the indeterminacy by its dependence on truthness and falsity components. This innovative approach quantifies the uncertainty and improves the assessment process via expert-guided opinions, customising it according to the specific situations in real-world decision-making scenarios. Some QtNS operations along with useful characteristics are addressed. Furthermore, two algorithms, QtNSUI and QtNSAO, are developed for the proposed operations of union, intersection, AND, and OR based on QtNS. In the world of sustainable …

Go to article

Some Types Of Hyperneutrosophic Set (2): Complex, Single-Valued Triangular, Fermatean, And Linguistic Sets, Takaaki Fujita, Florentin Smarandache Jan 2025

Some Types Of Hyperneutrosophic Set (2): Complex, Single-Valued Triangular, Fermatean, And Linguistic Sets, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

This paper is a continuation of the work presented in [35]. The Neutrosophic Set provides a mathematical framework for managing uncertainty, characterized by three membership functions: truth, indeterminacy, and falsity. Recent advancements have introduced extensions such as the Hyperneutrosophic Set and SuperHyperneutrosophic Set to address more complex and multidimensional challenges. In this study, we extend the Complex Neutrosophic Set, Single-Valued Triangular Neutrosophic Set, Fermatean Neutrosophic Set, and Linguistic Neutrosophic Set within the frameworks of Hyperneutrosophic Sets and SuperHyperneutrosophic Sets. Furthermore, we investigate their mathematical structures and analyze their connections with other set-theoretic concepts.

Go to article

Some Graph Parameters For Superhypertree-Width And Neutrosophictree-Width, Takaaki Fujita, Florentin Smarandache Jan 2025

Some Graph Parameters For Superhypertree-Width And Neutrosophictree-Width, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Graph characteristics are often studied through various parameters, with ongoing research dedicated to exploring these aspects. Among these, graph width parameters—such as treewidth—are particularly important due to their practical applications in algorithms and real-world problems. A hypergraph generalizes traditional graph theory by abstracting and extending its concepts [77]. More recently, the concept of a SuperHyperGraph has been introduced as a further generalization of the hypergraph. Neutrosophic logic [133], a mathematical framework, extends classical and fuzzy logic by allowing the simultaneous consideration of truth, indeterminacy, and falsity within an interval. In this paper, we explore Superhypertree-width, Neutrosophic treewidth, and t-Neutrosophic tree-width.

Go to article

Plithogenic Superhypersoft Set And Plithogenic Forest Superhypersoft Set, Takaaki Fujita, Florentin Smarandache Jan 2025

Plithogenic Superhypersoft Set And Plithogenic Forest Superhypersoft Set, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

No abstract provided.

Go to article

Autopoietic Energy Transition Towards Clean And Renewable Energy For Developing Countries, Victor Christianto, Florentin Smarandache Jan 2025

Autopoietic Energy Transition Towards Clean And Renewable Energy For Developing Countries, Victor Christianto, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

The global economy's reliance on energy supply and distribution necessitates a shift towards clean and renewable energy sources. This article explores how the economies of energy producers and consumers can be better modeled through the lens of autopoiesis, a concept developed by Humberto Maturana and further elaborated by Fritjof Capra (cf. Web of Life). By viewing energy systems as self-producing and self-maintaining entities, we can gain insights into the dynamics of energy transition in developing countries and identify strategies for fostering sustainable and resilient energy ecosystems.

Go to article

Ppg-Based Sleep Stage Classification Using Pulse Wave Feature Fusion And Explainable Ai, Florentin Smarandache, Satyasri Akula, Saleh Alzahrani, Farrukh Arslan, Amir Ijaz Jan 2025

Ppg-Based Sleep Stage Classification Using Pulse Wave Feature Fusion And Explainable Ai, Florentin Smarandache, Satyasri Akula, Saleh Alzahrani, Farrukh Arslan, Amir Ijaz

Branch Mathematics and Statistics Faculty and Staff Publications

Sleep monitoring plays a crucial role in understanding and managing various health conditions, including sleep disorders, cardiovascular diseases, and mental health. Traditional sleep monitoring methods rely on Electroencephalography (EEG) and Polysomnography (PSG) in clinical settings. However, these methods are expensive, difficult to administer, and unsuitable for home-based monitoring. In recent years, photoplethysmogram (PPG) has emerged as a promising noninvasive technology that is widely used in wearable devices and holds great potential for sleep assessment. Yet, most current sleep monitoring methods rely on deep learning models, which are inherently "black-box" and challenging in the clinical decision-making process. In this paper, we …

Go to article

Soft Directed N-Superhypergraphs With Some Real-World Applications, Takaaki Fujita, Florentin Smarandache Jan 2025

Soft Directed N-Superhypergraphs With Some Real-World Applications, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

This paper introduces the Directed Soft Super Hyper Graph, a unified framework for modeling complex, multi-layered directed networks. It combines directionality, recursive hyperstructure, and soft-set parameterization to address the integration of Soft Super HyperGraphs and Directed SuperHyperGraphs, which remains largely unexplored. The paper provides formal definitions, core operations, and real-world examples, such as urban infrastructure and transportation networks, to demonstrate the framework's effectiveness in managing deep hierarchies and uncertain relationships simultaneously.

Go to article

A Critical Evaluation Of The Criticisms Against Neutrosophic Statistical Methods, Muhammad Aslam, Abdulrahman Alaita, Florentin Smarandache Jan 2025

A Critical Evaluation Of The Criticisms Against Neutrosophic Statistical Methods, Muhammad Aslam, Abdulrahman Alaita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Neutrosophic statistical analysis has gained attention for incorporating the degree of indeterminacy when analyzing imprecise and interval data under uncertainty—an aspect often overlooked by classical statistics, fuzzy statistical analysis, and interval statistics. Recently, critical discussions have emerged regarding the use and applications of neutrosophic statistics, with some questioning its usefulness and validity. In this paper, we present a critical assessment of the existing literature, focusing on areas where misunderstandings and misinterpretations of neutrosophic statistical methods have occurred. We also examine flawed comparisons made between the results of neutrosophic statistics and interval statistics. Furthermore, substantial issues have been identified in the …

Go to article

A Family Of Neutrosophic Estimators For Estimating Mean: An Application To Real Data, Bavita Singh, Abhishek Singh, Florentin Smarandache Jan 2025

A Family Of Neutrosophic Estimators For Estimating Mean: An Application To Real Data, Bavita Singh, Abhishek Singh, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

In the realm of sample survey research, the classical statistics approach primarily deals with precise and definitive types of data to estimate population parameters when additional information is available. However, this approach fails when faced with data indeterminacies. To address such ambiguities, neutrosophic statistics emerges as an extension of both fuzzy and classical statistics. Thus, in light of the challenges posed by indeterminacy in sampling, we have introduced a proficient neutrosophic class of estimators, with and without Searls technique (optimization tool) for estimating the mean utilizing additional (ancillary) information under neutrosophic simple random sampling (NeSRS). The expression for the Bias …

Go to article

Neutrosophic Stance Detection And Fsqca-Based Necessary Condition Analysis For Causal Hypothesis Assessment In Ai-Enhanced Learning, Jesús Rafael Hechavarría-Hernández, Maikel Y. Leyva Vazquez, Florentin Smarandache Jan 2025

Neutrosophic Stance Detection And Fsqca-Based Necessary Condition Analysis For Causal Hypothesis Assessment In Ai-Enhanced Learning, Jesús Rafael Hechavarría-Hernández, Maikel Y. Leyva Vazquez, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

This study addresses the ambiguities in empirical findings on artificial intelligence (AI) in education by proposing a new methodological framework that combines neutrosophic stance detection and Fuzzy Set Qualitative Comparative Analysis (fsQCA). This approach explicitly models truth, indeterminacy, and falsity, allowing for the synthesis of contradictory research. The authors evaluated four causal hypotheses related to AI-based learning, using a survey of 24 university participants to explore the necessary conditions for perceived learning improvements. The results indicate that the digital divide is a perfectly necessary condition for effective AI-enhanced learning. The findings also reveal that AI feedback and AI platform use …

Go to article

Competition Super-Hypergraphs: Revealing Hierarchical Competition In Real-World Networks, Takaaki Fujita, Florentin Smarandache Jan 2025

Competition Super-Hypergraphs: Revealing Hierarchical Competition In Real-World Networks, Takaaki Fujita, Florentin Smarandache

Branch Mathematics and Statistics Faculty and Staff Publications

Graph theory provides a powerful language for modeling pairwise connections through vertices and edges [9, 20]. Hypergraphs generalize this idea by permitting hyperedges that join any number of vertices simultaneously [7], while super-hypergraphs iterate the Power-set operation to capture multi-level, hierarchical relationships among hyperedges [40, 22]. A competition hypergraph associates each prey species with a hyperedge containing all its predators, thereby encoding multi-way competition in ecological networks. In this work, we introduce the competition super-hypergraph, which lifts the competition concept to higher tiers of aggregation. We present its formal definition, explore theoretical properties, and illustrate its practical use in real-world …

Go to article

Cvitlnn: A Hybrid Approach Based On Vision Transformer And Liquid Neural Network For Covid-19 Detection, Muhammad Waqaq, Florentin Smarandache, Muhammad Yasir, Farrukh Arslan, Anum Ali Jan 2025

Cvitlnn: A Hybrid Approach Based On Vision Transformer And Liquid Neural Network For Covid-19 Detection, Muhammad Waqaq, Florentin Smarandache, Muhammad Yasir, Farrukh Arslan, Anum Ali

Branch Mathematics and Statistics Faculty and Staff Publications

The COVID-19 pandemic has underscored the need for accurate and rapid diagnostic tools to assist clinical decision-making. Conventional deep learning models for COVID-19 detection in Chest X-Ray (CXR) images face challenges in poor generalization across imaging conditions and high computational demands. To address these issues, this study proposes CviTLNN, a novel hybrid model combining Vision Transformers (ViTs) and Liquid Neural Networks (LNNs) to improve feature extraction and classification. Specifically, CviTLNN employs a ViT with 24 transformer encoder blocks for efficient extraction of spatial features. The self-attention mechanism of ViTs effectively captures global and local dependencies in CXR images. Furthermore, …

Go to article

Harmony Or Discord? A Study On The Alignment Between National Objectives And Reformed Social Studies Textbooks In Egypt, Lina Yehia Jan 2025

Harmony Or Discord? A Study On The Alignment Between National Objectives And Reformed Social Studies Textbooks In Egypt, Lina Yehia

Theses and Dissertations

Education systems, in many parts of the world, have served as a channel for communicating national goals to students, and Egypt has not been an exception. This study examines how public textbooks effectively align with equipping future generations of Egyptians to fulfill the nation’s development policy goals set for 2030. Utilizing a qualitative research design, this study employed textbook and document analyses of the published national policy goals of the current administration, along with the most recently reformed social studies textbooks of Grades 4, 5, and 6, a product of EDU 2.0. Based on an analysis of national documents, the …

Go to article

Performance Evaluation Of Newsql Databases In A Distributed Architecture, Zhiyao Zhang, Alan @ Ali Madjelisi Megargel, Lingxiao Jiang Jan 2025

Performance Evaluation Of Newsql Databases In A Distributed Architecture, Zhiyao Zhang, Alan @ Ali Madjelisi Megargel, Lingxiao Jiang

Research Collection School Of Computing and Information Systems

In the last decade, application architectures have evolved drastically, moving from monolithic architectures to distributed architectures where deployment has shifted from dedicated on-premises servers to the cloud. Distributed architectures and cloud computing has enabled businesses to scale their application components across different geographical locations. While it is easy to scale the application layer, scaling its database layer that relies on traditional SQL databases is challenging and often is a common source of bottlenecks when it comes to application performance. This paper evaluates the performance characteristics between two NewSQL databases solutions, MySQL NDB Cluster vs. TIBCO ActiveSpaces IMDG. Serving as an …

Go to article

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo Jan 2025

Interactive Video Search With Multi-Modal Llm Video Captioning, Yu-Tong Cheng, Jiaxin Wu, Zhixin Ma, Jiangshan He, Xiao-Yong Wei, Chong-Wah Ngo

Research Collection School Of Computing and Information Systems

Cross-modal representation learning is essential for interactive text-to-video search tasks. However, the representation learning is limited by the size and quality of video-caption pairs. To improve the search accuracy, we propose to enlarge the size of available video-caption pairs by leveraging multi-model LLM on video captioning. Specifically, we use LLM to generate video captions for a large video collection (i.e., WebVid dataset) and use the generated video-caption pairs to pre-train a text-to-video search model. Additionally, we use LLM to generate fine-grained captions for test video collections to enable text-to-caption retrieval. Furthermore, we build a semantic overview of the retrieved rank …

Go to article

Adapting Installation Instructions In Rapidly Evolving Software Ecosystems, Haoyu Gao, Christoph Treude, Mansooreh Zahedi Jan 2025

Adapting Installation Instructions In Rapidly Evolving Software Ecosystems, Haoyu Gao, Christoph Treude, Mansooreh Zahedi

Research Collection School Of Computing and Information Systems

files play an important role in providing installation-related instructions to software users and are widely used in open source software systems on platforms such as GitHub. Software projects evolve rapidly alongside their dependencies in dynamic software ecosystems, requiring frequent updates to installation instructions. These instructions are crucial for users to start with a software project. Despite their significance, there is a lack of systematic understanding regarding the documentation efforts invested in README files and the triggers behind them. To fill the research gap, we conducted a qualitative study, investigating 400 GitHub repositories with 1,163 README commits that focused on updates …

Go to article

Adversarial Generative Flow Network For Solving Vehicle Routing Problems, Ni Zhang, Jingfeng Yang, Zhiguang Cao, Xu Chi Jan 2025

Adversarial Generative Flow Network For Solving Vehicle Routing Problems, Ni Zhang, Jingfeng Yang, Zhiguang Cao, Xu Chi

Research Collection School Of Computing and Information Systems

Recent research into solving vehicle routing problems (VRPs) has gained significant traction, particularly through the application of deep (reinforcement) learning for end-to-end solution construction. However, many current construction-based neural solvers predominantly utilize Transformer architectures, which can face scalability challenges and struggle to produce diverse solutions. To address these limitations, we introduce a novel framework beyond Transformer-based approaches, i.e., Adversarial Generative Flow Networks (AGFN). This framework integrates the generative flow network (GFlowNet)-a probabilistic model inherently adept at generating diverse solutions (routes)-with a complementary model for discriminating (or evaluating) the solutions. These models are trained alternately in an adversarial manner to improve …

Go to article

Double Oracle Neural Architecture Search For Game Theoretic Deep Learning Models, Aye Phyu Phyu Aung, Xinrun Wang, Ruiyu Wang, Hau Chan, Bo An, Xiaoli Li, J. Senthilnath Jan 2025

Double Oracle Neural Architecture Search For Game Theoretic Deep Learning Models, Aye Phyu Phyu Aung, Xinrun Wang, Ruiyu Wang, Hau Chan, Bo An, Xiaoli Li, J. Senthilnath

Research Collection School Of Computing and Information Systems

In this paper, we propose a new approach to train deep learning models using game theory concepts including Generative Adversarial Networks (GANs) and Adversarial Training (AT) where we deploy a double-oracle framework using best response oracles. GAN is essentially a two-player zero-sum game between the generator and the discriminator. The same concept can be applied to AT with attacker and classifier as players. Training these models is challenging as a pure Nash equilibrium may not exist and even finding the mixed Nash equilibrium is difficult as training algorithms for both GAN and AT have a large-scale strategy space. Extending our …

Go to article

First Prev Next Last