Digital Commons Network^™

Upright-Net+: Enhanced Learning Of Upright Orientation For 3d Point Clouds, Xufang Pang, Feng Li, Hongjie Zhuang, Ning Ding, Xiaopin Zhong, Shengfeng He, Wenxi Liu, Bo Jiang

Research Collection School Of Computing and Information Systems

Automatic 3D shape analysis is heavily influenced by the pose of input 3D models, as the continuous nature of pose space introduces complexities that usually exceed the encoding capacities of standard deep learning frameworks. To tackle this challenge, we present Upright-Net+, an enhancement of our previous model, Upright-Net, specifically developed for estimating upright orientation in 3D point clouds. Our approach is grounded in the design principle that ”form ever follows function,” treating the natural base of an object as a functional structure that stabilizes it in its typical pose, influenced by physical laws and geometric properties. We reformulate the continuous …

Safe-Sora: Safe Text-To-Video Generation Via Graphical Watermarking, Zihan Su, Xuerui Qiu, Hongbin Xu, Tangyu Jiang, Jun-Hao Zhuang, Chun Yuan, Ming Li, Shengfeng He, Fei Yu

Research Collection School Of Computing and Information Systems

The explosive growth of generative video models has amplified the demand for reliable copyright preservation of AI-generated content. Despite its popularity in image synthesis, invisible generative watermarking remains largely underexplored in video generation. To address this gap, we propose Safe-Sora, the first framework to embed graphical watermarks directly into the video generation process. Motivated by the observation that watermarking performance is closely tied to the visual similarity between the watermark and cover content, we introduce a hierarchical coarse-to-fine adaptive matching mechanism. Specifically, the watermark image is divided into patches, each assigned to the most visually similar video frame, and further …

Iostom: Offline Imitation Learning From Observations Via State Transition Occupancy Matching, Quang Anh Pham, Brahmanage Janaka Chathuranga Thilakarathna, Tien Mai, Akshat Kumar

Research Collection School Of Computing and Information Systems

Offline Learning from Observations (LfO) focuses on enabling agents to imitate expert behavior using datasets that contain only expert state trajectories and separate transition data with suboptimal actions. This setting is both practical and critical in real-world scenarios where direct environment interaction or access to expert action labels is costly, risky, or infeasible. Most existing LfO methods attempt to solve this problem through state or state-action occupancy matching. They typically rely on pretraining a discriminator to differentiate between expert and non-expert states, which could introduce errors and instability—especially when the discriminator is poorly trained. While recent discriminator-free methods have emerged, …

Cssa-Fusion: Channel Selective And Spatial Alignment Infrared-Visible Image Fusion, Zhen Li, Zhi Zeng, Zhongrui Xiao, Ming Wen, Zhiyuan Zhang, Yibin Tian

Research Collection School Of Computing and Information Systems

Infrared-visible image fusion aims to integrate complementary information from two modalities to generate images with enriched semantic content. However, existing methods often neglect two critical aspects: the design of a local–global feature enhancement architecture and spatial alignment. To address these challenges, we propose Channel Selective and Spatial Alignment Fusion (CSSA-Fusion), a novel framework composed of two synergistic modules. The first is a selective channel and redundancy suppression module, which introduces a dual-branch selective channel attention mechanism to jointly capture local saliency and global channel importance for enhanced feature representation, and an informativeness–redundancy separation strategy to suppress redundant information while preserving …

The Rise Of Parameter Specialization For Knowledge Storage In Large Language Models, Yihuai Hong, Yiran Zhao, Wei Tang, Yang Deng, Yu Rong, Wenxuan Zhang

Research Collection School Of Computing and Information Systems

Over time, a growing wave of large language models from various series has been introduced to the community. Researchers are striving to maximize the performance of language models with constrained parameter sizes. However, from a microscopic perspective, there has been limited research on how to better store knowledge in model parameters, particularly within MLPs, to enable more effective utilization of this knowledge by the model. In this work, we analyze twenty publicly available open-source large language models to investigate the relationship between their strong performance and the way knowledge is stored in their corresponding MLP parameters. Our findings reveal that …

Contx: Scene Context Prediction Via Context Bank And Layout Perception, Jingxin Liang, Yangyang Xu, Haorui Song, Yuan Lu, Yuhui Deng, Yiyi Long, Yan Huang, Shengxin Liu, Jianbo Jiao, Shengfeng He

Research Collection School Of Computing and Information Systems

Scene context prediction, which seeks to infer unknown contextual information from isolated object properties, currently faces limitations due to predominant reliance on pixel-wise supervision that overlooks real-world context priors. To address this, we present ContX, a context-prior-driven, coarse-to-fine model. ContX distinctively integrates explicit linguistic-contextual knowledge in two key ways. First, it proposes a linguistic guided context bank, leveraging linguistic-statistical contextual data to guide the rationality of segmentation shapes and foster meaningful inter-class contextual interactions. Second, ContX augments contextual comprehension by correlating layouts with linguistic descriptions, enhancing layout perception through a multi-modal strategy. Comprehensive experiments demonstrate ContX's superiority and versatility, outperforming …

Pilot-C: Physics-Informed Low-Distortion Optimal Trajectory Compression, Kefei Wu, Baihua Zheng, Weiwei Sun

Research Collection School Of Computing and Information Systems

Location-aware devices continuously generate massive volumes of trajectory data, creating demand for efficient compression. Line simplification is a common solution but typically assumes 2D trajectories and ignores time synchronization and motion continuity. We propose PILOT-C, a novel trajectory compression framework that integrates frequency-domain physics modeling with error-bounded optimization. Unlike existing line simplification methods, PILOT-C supports trajectories in arbitrary dimensions, including 3D, by compressing each spatial axis independently. Evaluated on four real-world datasets, PILOT-C achieves superior performance across multiple dimensions. In terms of compression ratio, PILOT-C outperforms CISED-W, the current state-of-the-art SED-based line simplification algorithm, by an average of 19.2%. For …

Catalytic Synthesis Of Iron-Doped Graphitic Aerogels From Poly(Phloroglucinol-Terephthalaldehyde – Urethane) Precursors, Stephen Yaw Owusu, Rushi U. Soni, Chariklia Sotiriou-Leventis

Chemistry Faculty Research & Creative Works

We report a new class of graphitic carbon aerogel precursors based on iron oxide-doped poly(phloroglucinol-terephthalaldehyde–urethane) (T-POL/PU-FeOx) networks. The hybrid polymeric network incorporates a rigid aromatic triisocyanate, tris(4-isocyanatophenyl)methane, which reacts in situ with the hydroxyl groups of phloroglucinol to form a polyurethane-containing framework. Monolithic aerogels derived from this system undergo catalytic graphitization at significantly reduced temperatures (800–1500 °C) compared to conventional graphitization (2500–3300 °C). An oxidative ring fusion aromatization step (240 °C, air) prior to pyrolysis enhanced the degree of graphitization. The resulting graphitic aerogels were characterized by XRD, Raman spectroscopy, TGA, TEM, SEM, XPS, and N₂ sorption porosimetry. Compared to …

General Test-Time Backdoor Detection In Split Neural Network-Based Vertical Federated Learning, Shunjie Yuan, Xinghua Li, Xuelin Cao, Haiyan Zhang, Robert H. Deng

Research Collection School Of Computing and Information Systems

As a new distributed machine learning framework, vertical federated learning (VFL) has been widely applied in the industry. However, recent studies have demonstrated that VFL faces serious challenges from backdoor attacks, which significantly hinder its further development. Although a few studies have focused on defending against VFL backdoor attacks, these defenses either do not consider the latest attack methods or show limited effectiveness. Moreover, most existing backdoor defense efforts primarily focus on backdoor attacks in horizontal federated learning (HFL) and centralized learning. Due to the unique architecture of VFL models, these methods cannot be directly applied to backdoor defense in …

Kpiroot+: An Efficient Integrated Framework For Anomaly Detection And Root Cause Analysis In Large-Scale Cloud Systems, Wenwei Gu, Renyi Zhong, Guangba Yu, Xinying Sun, Jinyang Liu, Yintong Huo, Zhuangbin Chen, Jianping Zhang, Jiazhen Gu, Yongqiang Yang, Michael R. Lyu

Research Collection School Of Computing and Information Systems

To ensure the reliability of cloud systems, their runtime status reflecting the service quality is periodically monitored with monitoring metrics, i.e., KPIs (key performance indicators). When performance issues happen, root cause localization pinpoints the specific KPIs that are responsible for the degradation of overall service quality, facilitating prompt problem diagnosis and resolution. To this end, existing methods generally locate root-cause KPIs by identifying the KPIs that exhibit a similar anomalous trend to the overall service performance. While straightforward, solely relying on the similarity calculation may be ineffective when dealing with cloud systems with complicated interdependent services. Recent deep learning-based methods …

Fl-Cdf: Collaborative Defense Framework For Backdoor Mitigation In Federated Learning, Haiyan Zhang, Xinghua Li, Yinbin Miao, Shunjie Yuan, Mengyao Zhu, Ximeng Liu, Robert H. Deng

Research Collection School Of Computing and Information Systems

Federated learning (FL) is vulnerable to backdoor attacks due to its distributed nature. Existing unilateral defense mechanisms often fail against persistent attack strategies, primarily due to their limited perspectives. To address the challenge of model misclassification on the server side caused by overlooked model similarity drift, and gradient misjudgment on the client side caused by semantic learning imbalances across classes, this paper proposes a collaborative defense framework for federated learning, termed FL-CDF. FL-CDF establishes an end-to-end defense through a bidirectional client-server collaboration mechanism. Specifically: (1) On the client side, an adversarial perturbation-based malicious neuron detection module is introduced. This module …

Towards Inclusive Digital Futures Of Cultural Heritage: Insights From A Critical Discourse Analysis Of Unesco Dialogues, Shiqing Huang, Keng Siau, Xiaoting Chen

Research Collection School Of Computing and Information Systems

Digital technologies are shaping many aspects of cultural heritage, but very little research has examined the implications of digital transformation. Drawing on concepts from Fairclough’s three-dimensional critical discourse analysis, this research examines the discourse using seven online dialogues (available on the UNESCO website) between 18 professionals who have different backgrounds and cultures to identify social practices related to the digital transformation of cultural heritage. We identify four digital transformation discourse types in professional dialogues: documentation, management, interpretation, and interaction. We also identify seven main groups: memory institutions including libraries, archives, and museums (LAMs), governments, international organizations, art and creative supporters, …

Cropcapsnet: Enhanced Capsule Network For Crop Disease Classification, Juan Qin, Linfan Deng, Cong Li, Junjie He, Haibo Pen, Zhaoxia Wang

Research Collection School Of Computing and Information Systems

The prevention and treatment of crop diseases are crucial for the development of smart agriculture. The classification of crop diseases based on deep learning for early disease monitoring and control has become the mainstream direction of research. This paper proposes a novel deep learning model called ”CropCapsNet”, which combines Squeeze-and-Excitation Inception (SE-Inception) module and has improved capsule structure for crop disease classification. The network first extracts shallow features of input samples through double-layer convolution, then uses SE-Inception to achieve deep multi-scale feature acquisition, and finally outputs classification results through an improved capsule structure. SE-Inception adds Squeeze-and-Excitation(SE) attention after each multi-scale …

The Power Of Partnership: A Systematic Review Of Interorganizational Collaboration Among Victim Service Organizations, Mackenzie E. Allred

Boise State University Theses and Dissertations

Victim service organizations inhabit an organizational niche composed of other, adjacent organizations such as hospitals, shelters, police, and prosecutors. Effectively serving victims entails building and maintaining relationships with these adjacent organizations. Limited research has sought to discuss the role of interorganizational collaboration in the context of victim service organizations. I investigate this topic by conducting a systematic literature review on the existing research focused on interorganizational collaboration among victim service organizations. With data gathered from this review, I explore the nature and extent of interorganizational collaboration and its potential impact on victim service organizations. I close with recommendations for future …

Analysis Of Progressive Failure From Hydrofracturing Tests In Boise Sandstone, Alejandra Sanchez Arizmendi

Boise State University Theses and Dissertations

Sealed borehole laboratory hydrofracturing tests with acoustic emission monitoring were used to investigate the acoustic emission activity, damage thresholds, progressive failure, and tensile strength as a function of injection rate for twenty Boise Sandstone specimens. Four injection rates 15.7, 31.4, 62.8, and 125.6 mL/minute were used in the testing.

Increasing the injection rate initially increased and then decreased acoustic emission activity. The highest injection rate resulted in the lowest number of AE hits. The acoustic emission data was collected via two ultrasonic sensors. The highest average AE hits at the 31.4 mL/min injection rate was 613 and the lowest average …

Assessing The Effects Of Leaderboards On Motivation And Math Achievement Of 5th And 6th Grade Students, Michele Alfieri

Boise State University Theses and Dissertations

Traditional teacher-led instructional methods are increasingly disconnected with the learning preferences of students raised in digital environments. These learners often require information to be delivered more rapidly and engagingly, prompting educators to incorporate strategies such as gamification to maintain student motivation and interest. Gamification, which involves integrating game design elements into non-game settings, has been shown to enhance engagement. A common feature of gamification is the use of leaderboards, which are visual displays that show individual and peer performance rankings. While leaderboards can foster motivation through competition, their effect on student morale and achievement outcomes is mixed. The purpose of …

An Investigation Of High School Students' Perceived Well-Being In A Flexible Blended-Learning Program Through The Lens Of Self-Determination Theory, April Burton

Boise State University Theses and Dissertations

This dissertation explored how participation in a flexible blended learning (FBL) program relates to high school students’ sense of well-being, as defined by self-determination theory (SDT). SDT suggests that fulfilling three basic psychological needs is considered essential for well-being and optimal functioning. Using a mixed-methods approach, this study investigates how an FBL program affects high school students’ perceptions of the fulfillment of psychological needs — autonomy, competence, and relatedness. The study involved high school students enrolled in FBL courses in a midwestern school district in the USA. Data were collected through surveys adapted from the Students’ Basic Psychological Needs Survey …

Leveraging Disparate Wildland Fire Datasets To Address Longstanding Fire Management Questions, Kendra Fallon

Boise State University Theses and Dissertations

While wildfire season is perceived as occurring in the warm months, and expanding, wildfire management is a year-long process. Juxtaposed to wildfire seasons are the reactive seasons of mitigating for post-fire effects, namely first-order effects of potential hydrological impacts in burn footprints, and the proactive implementation of fuels treatments to modify fire behavior to lessen the reactive workload. In this dissertation, I focus on answering lingering questions that are critical to the management of the shoulder seasons of wildfire season. To assist in resource allocation and identification of post-hydrological risks, I present a model identifying the major drivers of soil …

Interconnection Among Germanic Peoples In The Roman Late Republican And Early Imperial Eras: From Historical And Archaeological Sources, Krystian Fichat

Boise State University Theses and Dissertations

This thesis evaluates the cultural interactions between the Germanic peoples and neighboring societies during the Roman Late Republican and Early Imperial Eras. Roman authors traditionally portrayed the Germani as isolated barbarians and through ethnocentric and propagandistic writings, misrepresenting the Germanic people on a large scale. By combining an analysis of historical sources, such as Roman histories and ethnographies, the examination of connection through polytheistic religious practice in Western Europe and in Rome, archaeological evidence of Germanic trade and craft, and the study of settlements common to Celtic and Germanic peoples, this research demonstrates that the Germani were actively participating in …

Deep Reinforcement Learning For Adaptive Mesh Refinement: A Training Parameter Study, Antone Chacartegui

Boise State University Theses and Dissertations

Adaptive mesh refinement (AMR) enables efficient solution of partial differential equations by dynamically allocating computational resources to regions requiring higher resolution. It has been demonstrated that deep reinforcement learning agents could learn effective mesh adaptation policies. However, practical deployment requires a systematic understanding of how training parameters affect performance across diverse computational scenarios.

This thesis presents a parameter optimization study analyzing the relationship between deep reinforcement learning for adaptive mesh refinement (DRL-AMR) training parameters and model performance. We implement an independent DRL-AMR system with a discontinuous Galerkin solver and actor-critic (A2C) algorithm for one-dimensional linear advection. The study explores four …

Combinatorics Of Trees Via Derivatives Of Polynomial Functors In Homotopy Type Theory, Warren David Hatton

Boise State University Theses and Dissertations

Polynomial functors are, essentially, polynomials whose variables take values in sets, groupoids, or some other suitable category, rather than in numbers. In this thesis, we will explore three related aspects of polynomial functors over $\infty$-groupoids in the framework of homotopy type theory: first, polynomial functors provide a foundation for inductively defined data types as wellfounded trees; second, polynomial functors have a notion of derivative which, viewed in light of the connection to data types, yields a computational interpretation of differentiation; and third, suitably finite polynomial functors over (higher) groupoids yield categorified generating functions, and thus subsume the theory of combinatorial …

Sustainability Assessment Of Ground Improvement Techniques: A Life Cycle Analysis Of Lime, Cement, Geopolymers And Biopolymers For Roadway Application, Jillian R. Frost

Boise State University Theses and Dissertations

Ground improvement design (GID) is a vital part of constructing safe, long-lasting infrastructure. Traditionally, this is done with a chemical additive such as lime or cement that is mixed with in-situ soil to improve soil parameters such as compressibility, and strength. These stabilizers produce high amounts of carbon emissions. As a response, engineers and researchers are beginning to develop new stabilization methods using biopolymers and geopolymers in hopes of achieving comparable soil stability results as well as reduced environmental impacts.

This thesis work integrates a life-cycle analysis (LCA) and life-cycle-cost-analysis (LCCA) framework to evaluate and compare four soil stabilizer types: …

Shifting Grounds: Knowledge, Power, And Place In Changing Western Rangelands, Molly C. Levy

Boise State University Theses and Dissertations

Public rangelands in the American West are sites of enduring contestation, where ecological change, competing values, and institutional complexity converge. Long-standing debates over livestock grazing, wildlife conservation, and land stewardship highlight fundamental questions of whose knowledge counts, whose authority is legitimate, and how resource use should adapt under shifting social and ecological conditions. This dissertation examines the intersections of knowledge, power, and land use in collaborative governance of contested landscapes. Using the Thunder Basin ecoregion (TBER) in northeastern Wyoming as a case study, I adopt a mixed-methods approach that integrates qualitative interviews, participant observation, archival research, and quantitative analysis of …

A Comparative Study Of Novel Methods For Variances, Taoreed Muritala

Boise State University Theses and Dissertations

Understanding variability is fundamental to knowledge advancement across various disciplines, including manufacturing, clinical research, biology and genetics. Population variances play a crucial role in processes such as quality control, treatment evaluation and the interpretation of biological mechanisms. However, statistical procedures for comparing variances across multiple populations remain less developed than those for comparing means. Classical omnibus tests, such as Bartlett's and Levene's, can detect overall variance heterogeneity but fail to identify which populations differ, thereby limiting their usefulness in multi-population analyses and increasing the risk of inflated family-wise error rates through repeated testing.

This thesis develops and evaluates three multiple …

Abelian Sandpile Models On Edge Periodic Graphs, Payton Lyons

Boise State University Theses and Dissertations

The abelian sandpile model is a Markov chain that is able to decompose any recurrent configuration into a basic alive divisor, some amount of sand placed on the sink vertex, and a series of vertex firings. In this paper we begin to explore some of the dynamics of this system when the edges of the graph are allowed to alternate between two different edge sets. This system will be framed in a similar fashion as the classical model, and then some basic numerical simulations were used to observe the threshold behavior of the system. We lay some of the initial …

Harnessing Bioscaffold-Coupled Stimulation Through Electroactive Graphene Foam For Enhanced Cellular And Mechanical Responses: Applications In Cartilage Tissue Engineering, Mone't Sawyer

Boise State University Theses and Dissertations

Osteoarthritis is a leading cause of joint degeneration, with limited treatment options that fail to restore native cartilage. Tissue engineering offers a promising strategy by combining cells, scaffolds, and bioactive cues to regenerate functional tissue, though challenges remain in developing systems that integrate and precisely control these signals in three-dimensional environments. This work establishes a scaffold-coupled electrical stimulation (ES) platform using electroactive graphene foam (GF) to modulate cellular and mechanical responses relevant to cartilage tissue engineering. Custom stereolithography-printed bioreactors were developed to deliver low-voltage biphasic square waves (20–60 mVpp, 1 kHz) directly to GF scaffolds under submerged culture, maintaining waveform …

Stimulation And Recording Interfaces For Data Transmission To And From A Micro Neural Stimulation Device, Morgan Riley

Boise State University Theses and Dissertations

Advancements in neuromodulation for treating neurological disorders increasingly rely on selective peripheral nerve stimulation rather than whole-nerve activation. Traditional approaches engage all fascicles, causing off-target effects such as involuntary muscle contractions and pain. To address these challenges, this research proposes a minimally invasive microdevice that integrates wireless galvanic impulse communication with an epineural multi-contact nerve cuff. This design facilitates high-throughput, low-power stimulation, recording, and data transfer. Development efforts include optimizing neural stimulation protocols, validating deep tissue galvanic transmission, and fabricating a multi-channel nerve cuff for stable electrode–tissue interfacing. In parallel, custom depth-controlled intramuscular arrays enable high-density electromyography (EMG) recording during …

An Intelligent Healthcare System For Rare Disease Diagnosis Utilizing Electronic Health Records Based On A Knowledge-Guided Multimodal Transformer Framework, Ahed Abugabah, Prashant Kumar Shukla, Piyush Kumar Shukla, Ankur Pandey

All Works

Rare diseases are a common problem with millions of patients globally, but their diagnosis is difficult because of varied clinical presentations, small sample size, and disparate biomedical data sources. Current diagnostic tools are not able to combine multimodal information effectively, which results in a timely or wrong diagnosis. To fill this gap, this paper suggests a smart multimodal healthcare framework integrating electronic health records (EHRs), genomic sequences, and medical imaging to improve the detection of rare diseases. The framework uses Swin Transformer to extract hierarchical visual features in radiographic scans, Med-BERT and Transformer-XL to learn semantic and long-term temporal relations …

Big Data Transfer Service Architecture For Cloud Data Centers: Problems, Methods, Applications, And Future Trends, Muhammad Umar Majigi, Ismaila Idris, Shafi’I Muhammad Abdulhamid, Richard A. Ikuesan

All Works

Data volume, velocity, and structure have significantly evolved over the years. The complex networking architectures of current infrastructures, and the development, and accessibility of cloud services to a diverse user base have introduced numerous challenges which have raised concerns regarding the quality-of-service performance in data processing for both service providers and customers. Key issues identified in the context of big data transfer services for cloud data centers include storage, big data transfer, service transfer architecture, data processing, bandwidth, and security, all of which demand extensive research. After thoroughly screening selected peer-reviewed articles, the primary open issues are: incorporating a data …

A Hybrid Fog-Edge Computing Architecture For Real-Time Health Monitoring In Iomt Systems With Optimized Latency And Threat Resilience, Umar Islam, Mohammed Naif Alatawi, Ali Alqazzaz, Sulaiman Alamro, Babar Shah, Fernando Moreira

All Works

The advancement of the Internet of Medical Things (IoMT) has transformed healthcare delivery by enabling real-time health monitoring. However, it introduces critical challenges related to latency and, more importantly, the secure handling of sensitive patient data. Traditional cloud-based architectures often struggle with latency and data protection, making them inefficient for real-time healthcare scenarios. To address these challenges, we propose a Hybrid Fog-Edge Computing Architecture tailored for effective real-time health monitoring in IoMT systems. Fog computing enables processing of time-critical data closer to the data source, reducing response time and relieving cloud system overload. Simultaneously, edge computing nodes handle data preprocessing …