Digital Commons Network^™

Brain-Adapter: Enhancing Neurological Disorder Analysis With Adapter-Tuning Multimodal Large Language Models, Jing Zhang, Xiaowei Yu, Yanjun Lyu, Lu Zhang, Tong Chen, Chao Cao, Yan Zhuang, Minheng Chen, Tianming Liu, Dajiang Zhu

Computer Science Faculty Research & Creative Works

Understanding brain disorders is crucial for accurate clinical diagnosis and treatment. Recent advances in Multimodal Large Language Models (MLLMs) offer a promising approach to interpreting medical images with the support of text descriptions. However, previous research has primarily focused on 2D medical images, leaving richer spatial information of 3D images under-explored, and single-modality-based methods are limited by overlooking the critical clinical information contained in other modalities. To address this issue, this paper proposes Brain-Adapter, a novel approach that incorporates an extra bottleneck layer to learn new knowledge and instill it into the original pre-trained knowledge. The major idea is to …

Classiffication Of Mild Cognitive Impairment Based On Dynamic Functional Connectivity Using Spatio-Temporal Transformer, Jing Zhang, Yanjun Lyu, Xiaowei Yu, Lu Zhang, Chao Cao, Tong Chen, Minheng Chen, Yan Zhuang, Tianming Liu, Dajiang Zhu

Computer Science Faculty Research & Creative Works

Dynamic functional connectivity (dFC) using resting-state functional magnetic resonance imaging (rs-fMRI) is an advanced technique for capturing the dynamic changes of neural activities and can be very useful in the studies of brain diseases such as Alzheimer's disease (AD). Yet, existing studies have not fully leveraged the sequential information embedded within dFC that can potentially provide valuable information when identifying brain conditions. In this paper, we propose a novel framework that jointly learns the embedding of both spatial and temporal information within dFC based on the transformer architecture. Specifically, we first construct dFC networks from rs-fMRI data through a sliding …

Exploring The Trade-Offs: Unified Large Language Models Vs Local Fine-Tuned Models For Highly-Specific Radiology Nli Task, Zihao Wu, Lu Zhang, Chao Cao, Xiaowei Yu, Zhengliang Liu, Lin Zhao, Yiwei Li, Haixing Dai, Chong Ma, Gang Li, Wei Liu, Quanzheng Li, Dinggang Shen, Xiang Li, Dajiang Zhu, Tianming Liu

Computer Science Faculty Research & Creative Works

Recently, ChatGPT and GPT-4 have emerged and gained immense global attention due to their unparalleled performance in language processing. Despite demonstrating impressive capability in various open-domain tasks, their adequacy in highly specific fields like radiology remains untested. Radiology presents unique linguistic phenomena distinct from open-domain data due to its specificity and complexity. Assessing the performance of large language models (LLMs) in such specific domains is crucial not only for a thorough evaluation of their overall performance but also for providing valuable insights into future model design directions: whether model design should be generic or domain specific. To this end, in …

Reindsplit: Reinforced Dynamic Split Learning For Pest Recognition In Precision Agriculture, Vishesh Kumar Tanwar, Soumik Sarkar, Asheesh K. Singh, Sajal K. Das

Computer Science Faculty Research & Creative Works

To empower precision agriculture through distributed machine learning (DML), split learning (SL) has emerged as a promising paradigm, partitioning deep neural networks (DNNs) between edge devices and servers to reduce computational burdens and preserve data privacy. However, conventional SL frameworks' one-split-fits-all strategy is a critical limitation in agricultural ecosystems where edge insect monitoring devices exhibit vast heterogeneity in computational power, energy constraints, and connectivity. This leads to straggler bottlenecks, inefficient resource utilization, and compromised model performance. Bridging this gap, we introduce ReinDSplit, a novel reinforcement learning (RL)-driven framework that dynamically tailors DNN split points for each device, optimizing efficiency without …

Fuzzy-Based Deep Reinforcement Learning For Suicidal Ideation Detection In Online Social Networks, Greeshma Lingam, Sajal K. Das

Computer Science Faculty Research & Creative Works

Suicidal ideation is a major psychological problem, and preventing this social risk is recognized as an important research topic. In reality, there can be several reasons why a person experiences suicidal ideation. Each individual can express views, emotions, and several types of symptoms related to suicidal ideation on the most popular social media platforms. In online social networks (OSNs), identification of suicidal ideation is one of the major challenging tasks. Existing studies have shown that the delay in understanding and identifying various risk factors can cause the suicidal event to occur. Due to the scarcity of data and understanding, the …

When Federated Learning Meets Quantum Computing: Survey And Research Opportunities, Aakar Mathur, Ashish Gupta, Sajal K. Das

Computer Science Faculty Research & Creative Works

Quantum Federated Learning (QFL) is an emerging field that harnesses advances in Quantum Computing (QC) to improve the scalability and efficiency of decentralized Federated Learning (FL) models. This paper provides a systematic and comprehensive survey of the emerging problems and solutions when FL meets QC, from research protocol to a novel taxonomy, particularly focusing on both quantum and federated limitations, such as their architectures, Noisy Intermediate Scale Quantum (NISQ) devices, and privacy preservation, so on. With the introduction of two novel metrics, qubit utilization efficiency and quantum model training strategy, we present a thorough analysis of the current status of …

Circa: A Framework For Collaborative Identification Of Root Cause Analysis In Iot Microservices, Xingguo Jiang, Hong Luo, Yan Sun, Sajal K. Das

Computer Science Faculty Research & Creative Works

With continuous growth of IoT applications, service failures are quite inevitable. Due to the complexity and dynamics of IoT services, the root cause analysis (RCA) following an alert can assist in quickly resolving the possible faults. However, the time scales of metrics (e.g., CPU utilization, memory usage) generated by microservices and the dynamic topologies generated by calls between the Application Program Interfaces (APIs) are different. Moreover, the status of devices is an important aspect of RCA in IoT. All these make it extremely challenging to learn failure features of microservice metrics and API calls. Therefore, we propose a novel framework …

Mgco: Mobility-Aware Generative Computation Offloading In Edge-Cloud Systems., Aswini Ghosh, Nelson Sharma, Shivendu Mishra, Rajiv Misra, Sajal K. Das

Computer Science Faculty Research & Creative Works

Mobility introduces significant challenges for optimal computation offloading, latency minimization, and efficient re source utilization in multi-access edge computing (MEC) systems. A key difficulty lies in leveraging real user trajectories to jointly optimize horizontal (inter-edge) and vertical (edge-to-cloud) task offloading decisions. This paper proposes a two-dimensional offloading scheme for a multi-layer edge–cloud architecture that enables collaborative task execution among resource-constrained edge nodes under mobility conditions. We present MGCO (Mobility-Aware Generative Computation Offloading), a generative AI–driven Transformer-based sequence-to-sequence Deep Q-Network (s2s-DQN) framework that learns from real-time trajectory data to anticipate user movement and optimize task placement dynamically. The Transformer architecture is …

Real-Time Testbed For Studying Cyberattacks And Defense In Der-Integrated Smart Inverter Systems, M. Maliha, A. Oluyomi, M. Booge, S. Bhattacharjee, N. Braasch, P. Gomez, Sajal K. Das

Computer Science Faculty Research & Creative Works

In this paper, we propose a Hardware-in-the-Loop (HIL) simulation testbed suitable for the implementation and testing of realistic cyberattacks on grid-tied smart inverter systems integrated with Distributed Energy Resources (DER) that use the Distributed Network Protocol-3 (DNP3) protocol for communications between grid components. Specifically, our testbed combines a Real-Time Digital Simulator (RTDS) NovaCor device, outfitted with GNETx2 network interface cards, a grid-tied DER topology implemented via the RTDS software package RSCAD, and a custom virtual network that emulates a man-in-the-middle (MITM) attacker. The MITM attacker captures DNP3 traffic and falsifies telemetry data in DNP3 packets to trigger unwarranted commands from …

Grace-Fl: Green Resource-Aware Communication-Efficient Federated Learning, Dipanwita Thakur, Antonella Guzzo, Giancarlo Fortino, Sajal K. Das

Computer Science Faculty Research & Creative Works

Federated Learning (FL) enables collaborative model training across distributed clients while preserving data privacy, but its deployment on resource-constrained devices is hindered by high communication overhead, inefficient energy usage, and poor convergence under non-IID data distributions. To address these challenges, we propose GRACE-FL: a Green Resource-Aware Communication-Efficient Federated Learning framework that explicitly incorporates device energy capacity into training. Each client adapts its learning rate, number of local epochs, and gradient quantization bit-width based on its available energy, allowing high-capacity devices to sustain more intensive training while low-capacity devices operate with lighter configurations. A novel energy-weighted aggregation strategy ensures that clients …

Drone-Based Multimodal Sensing On Vegetations And Data Analytics For Early Detection Of Gas Leakage From Underground Pipelines, Pengfei Ma

Doctoral Dissertations

"This study explored the feasibility of using multimodal remote sensors in the early detection of natural gas leaks from underground pipelines, as vegetation situated above pipelines can discern microbial changes in soil when affected by gas and exhibit physiological stress symptoms on leaves. Three sensors (RBG, thermal, and hyperspectral cameras) were utilized to monitor vegetation stress as an indicator of gas leaks. A laboratory experiment was conducted to evaluate the workability of vegetation for gas leak detection. Regular hyperspectral imagery was collected from test vegetations to identify gas stress and distinguish it from other environmental stressors such as salinity impact, …

The Evolving Use Of Strategic Planning Tools In The Manufacturing Environment: Implications For Quality 4.0 And Beyond, Richard Lee Wilson

Doctoral Dissertations

"Having a strong strategic plan is critical for success for any business no matter the size of the organization, the product or service they provide, or the industry they serve. There are many methods businesses use to develop their strategic plans. One such method is known as Hoshin Kanri, which has been in use for decades. However, recent years have seen an increase in artificial intelligence, big data, data analytics, and other technology tools to create cyber physical systems on the manufacturing floor. The increase in technology in manufacturing to integrate cyber systems with physical systems spawned a new industrial …

Development And Testing Of Irradiation-Tolerant High-Entropy Alloys, Matthew John Luebbe

Doctoral Dissertations

"High entropy alloys (HEAs) are a novel class of alloys made of multiple principal elements in near equal proportions. They have been observed to possess an array of useful engineering properties, such as good ductility and fracture toughness, high temperature strength, oxidation and corrosion resistance and irradiation resistance. This makes them promising candidates for harsh environments, especially nuclear reactors. These properties could potentially realize advanced Gen IV nuclear reactor designs. However, most HEA compositions contain Co, which activates under irradiation, generating safety and waste management concerns. This work studies three compositions of Co-free HEAs whose strength and microstructures are evaluated …

Ceramic Dielectrics For High Temperature Capacitor Applications, Alan Daniel Devoe

Doctoral Dissertations

Technical progress in microelectronics is allowing operation in environments that were previously considered impossible. Building complete electronic circuits for applications above 450 degrees C, such as the planned NASA missions to Venus, require a variety of active and passive components, including multilayer ceramic capacitors (MLCC).

This study explores calcium zirconate CaZrO3 and magnesium oxide MgO based dielectric compositions for MLCC applications that are capable of operating at extreme temperatures between 450 degrees C and 600 degrees C. Both materials were characterized with respect to impurities, dopants, crystal structure and microstructural development. Dielectric properties were measured to determine permittivity, dissipation factor, …

Assessing And Comparing Geophysical Methods For Resolving Shallow Subsurface Geology, Abdullah Basaloom

Doctoral Dissertations

Geophysical methods are essential tools for investigating shallow subsurface structures, offering non-invasive means to characterize geological features and detect anomalies. Techniques such as electrical resistivity tomography (ERT), towed Transient Electromagnetic (tTEM), seismic refraction, magnetic, gravity, and magnetotelluric (MT) are commonly employed to image subsurface conditions with high resolution.

This study started with an in-depth analysis of comparing results co-located in space to assess uncertainties and resolution in the obtained resistivity models in the Kansas River Alluvial Aquifer (KRAA). Our results provided a quantitative interpretation of resistivity estimates between different geo-electrical methods (ERT, tTEM and DPEC). Following this, we provided a …

Enhanced Optimization Of Mass Transfer For Carbon Capture And Wastewater Remediation In Algal Systems Through Algorithmic And Bioprocessing Techniques, Peter Ofuje Obidi

Doctoral Dissertations

The scalability and industrial deployment of algal cultivation systems are limited by suboptimal mass transfer, constraining their effectiveness in carbon capture and wastewater remediation. This research investigated these challenges through integrated optimization methodologies that combine algorithmic frameworks with enhanced bioprocessing techniques to enhance efficiency, economy, and scalability. A System-of-Systems (SoS) meta-architecture was developed using genetic algorithms and fuzzy assessor functions to demonstrate a pathway toward cost reduction. Rigorous mechanical and chemical characterizations were quantitatively analyzed to reveal existing optimization strategies and further evaluated the best strategies to use in enhancing mass transfer for improved biomass yield. The work also integrates …

Class-Wise Histogram Matching-Based Domain Adaptation In Deep Learning-Based Bridge Element Segmentation, Tarutal Ghosh Mondal, Zhenhua Shi, Haibin Zhang, Genda Chen

Civil, Architectural and Environmental Engineering Faculty Research & Creative Works

This study focused on the problem of domain shift in deep learning-based bridge element segmentation. The impracticability of accounting for all possible variabilities vis-à-vis structural shape, size, color, texture, illumination, and other operational conditions in the training process leads to the deterioration in the model performance when applied to test data from novel unseen domains. In such situations, rebuilding the model with labeled training data from the target domain becomes prohibitively expensive and time-consuming in many practical cases. Recent advancements in unsupervised domain adaptation techniques are known to provide viable solutions to this problem. However, it was observed in this …

Existential Resilience In The City, Shane Ray Epting

Arts, Languages and Philosophy Faculty Research & Creative Works

Severe weather continues to challenge cities worldwide. Typhoons, wildfires, floods, and extreme temperatures test urban systems, communities, and governments at all scales. To combat such effects, resilience has emerged as a term geared towards increasing their ability to address impacts, strengthen infrastructure, and deal with cleanup measures. Although this business sounds straightforward to non-philosophers, ethical and existential elements remain out of view for the sciences and require investigation. This article fleshes them out. The first step is to identify relevant stakeholder groups and competing interests. The second is discovering equitable ways to bring professionals and city dwellers together to develop …

Reflections On Linear B: An Egyptian Hieroglyphic Component, (Draft #2), Gerald Leonard Cohen

Arts, Languages and Philosophy Faculty Research & Creative Works

Most Linear B signs are presently regarded as being of unknown origin, with a general consensus that Egyptian hieroglyphs are at best of minimal help in solving the mysteries. But the present article revisits this subject and suggests that the Egyptian hieroglyphic component goes beyond a borrowing or two. Along the way I noticed that for some Linear B signs a familiarity with Egyptian religious mythology is essential in this effort.

For example, the mysterious Linear B sign 75 is pronounced /we/ and looks like a backwards letter S. I suggest it can be explained as the cobra goddess Wadjet …

From Normal To Disaster Response Mode: How Can Virtual Communities Reconfigure Themselves To Respond Effectively To A Disaster?, Mahmudul Hasan, Cecil Eng Huang Chua, Michael David Myers, Varqa Shamsi Bahar

Business and Information Technology Faculty Research & Creative Works

During a disaster, many people seek information from virtual communities. However, information overload, falsehoods and unrelated topics hinder information flow in virtual communities, putting disaster victims at risk. Given many disasters are generally of a short duration, we explore how virtual communities can quickly reconfigure themselves to respond effectively to a disaster. Drawing on risk society theory, our findings suggest reconfiguration is done via a series of cycles initially involving community members and subsequently featuring both community members and moderators working together to mitigate risks. We contribute to virtual community discourse on disaster response by showing how a virtual community …

Managing Digital Transformation With Blockchain: Distributed Ledger Innovation Platforms, Nobuyuki Fukawa, Gregory J. Fisher

Business and Information Technology Faculty Research & Creative Works

Realizing its overarching potential in achieving digital transformation, leading organizations, such as Air New Zealand, have recently employed blockchain technology to manage 3D printing innovation. Despite the potential benefits, including the key role of blockchain as a supporting technology in Industry 5.0, these applications of blockchain technology in 3D printing are still at a nascent stage in practice and mostly limited to producer innovation. Additionally, 3D printing and blockchain technologies are often independently revolutionizing value capture and value creation, whereas the theoretical implications of their combined impacts on innovation management remain an underexplored domain. Limited digital transformation efforts have been …

Modeling Ion-Specific Effects In Polyelectrolyte Brushes: A Modified Poisson-Nernst-Planck Model, William J. Ceely, Marina Chugunova, Ali Nadim, James D. Sterling

Business and Information Technology Faculty Research & Creative Works

Polyelectrolyte brushes consist of a set of charged linear macromolecules, each tethered at one end to a surface. An example is the glycocalyx which refers to hair-like negatively charged sugar molecules that coat the outside membrane of all cells. We consider the transport and equilibrium distribution of ions and the resulting electrical potential when such a brush is immersed in a salt buffer containing monovalent cations (sodium and/or potassium). The Gouy-Chapman model for ion screening at a charged surface captures the effects of the Coulombic force that drives ion electrophoresis and diffusion but neglects non-Coulombic forces and ion pairing. By …

The Antibiofilm Efficacy Of Copper And Zinc-Enhanced Borate Bioactive Glasses On Polymicrobial Biofilms, Sarah Fakher, David J. Westenberg

Biological Sciences Faculty Research & Creative Works

Healthcare-acquired infections (HAIs) are a significant global challenge driven by biofilm-forming pathogens. Polymicrobial biofilms, involving interactions between multiple microbial species, exacerbate treatment difficulties due to their enhanced resistance to antimicrobial therapies. Borate bioactive glasses (BBGs) are an emerging class of biomaterials that have attracted significant interest in infection control. The incorporation of copper and zinc into the BBG matrix can effectively disrupt biofilm formation and bacterial colonization. This study investigates the antibiofilm efficacy of copper and zinc-doped BBGs against polymicrobial biofilms formed by S. epidermidis, E. coli, and P. aeruginosa. Using static and dynamic biofilm models, BBGs were applied through …

Cold Atmospheric Plasma Induced Degradation Of Organophosphate Pesticides On Kevlar Swatches, Ta Chun Lin, Victor Somtochukwu Mbanugo, Boluwatife Stephen Ojo, Yue-Wern Huang, Marek Locmelis, Frank Daoru Han

Biological Sciences Faculty Research & Creative Works

Cold atmospheric plasma (CAP) was evaluated for degrading organophosphate pesticide (OP) residues (acephate, malathion, and dimethoate) from Kevlar fabrics. Fourier transform-Infrared (FTIR) spectroscopy, scanning electron microscope (SEM) imaging and tensile strength testing confirmed that CAP treatment preserved Kevlar's structural integrity and mechanical properties. Results show degradation efficiency increased with higher power, shorter discharge gaps, and longer exposure duration. Hyperspectral imaging supported the detection of plasma-induced spectral changes, reinforcing the presence of reactive species. The strong oxidative potential of CAP facilitated the rapid breakdown of OPs into nontoxic byproducts. These findings demonstrate the potential of CAP as a portable, energy-efficient solution …

Metal-Free Photoredox Catalysis For The S-Trifluoromethylation Of Thiols, Raheemat Rafiu, Puspa Aryal, V. Prakash Reddy

Chemistry Faculty Research & Creative Works

The S-trifluoromethylation of thiols is accomplished using a simple and cost-effective organic catalyst (diacetyl) along with a bench-stable and environmentally friendly trifluoro methylating reagent (Langloi's reagent). Under optimized conditions (2.5 equivalents of Langlois reagent, Blue LED irradiation, 48-h reaction time at room temperature), the reaction yielded up to 81% S-trifluoro methylated product. This method's high yields, compatibility with a broad substrate scope (aliphatic, heteroaromatic, and aromatic thiols), and environmentally friendly conditions demonstrate its potential for broader synthetic applications. In contrast to traditional methods that rely on organometallic catalysts and environmentally hazardous reagents, this novel photoredox catalysis method offers a more …

Characterizing The Transient Emission Of Particles And Gases From A Single Puff Of Electronic Cigarette Smoke, Kashala Fabrice Kapiamba, Steven Achterberg, Ta Chun Lin, Philip D. Whitefield, Yue-Wern Huang, Yang Wang

Chemistry Faculty Research & Creative Works

This study employed high-time-resolution systems to examine the transient properties of aerosols and gases emitted from electronic cigarette (EC) puffs. Using a fast aerosol sizer, we measured particle size distributions (PSDs) across various EC brands (JUUL, VUSE, VOOPOO), revealing sizes ranging from 5 to 1000 nm at concentrations of 107 to 1010 cm-3. Most aerosols were found to be in the ultrafine range (below 100 nm), with JUUL-, VUSE-, and VOOPOO-producing aerosols with geometric mean sizes of 19.9, 47.3, and 29.4 nm, respectively. Applying the International Commission on Radiological Protection (ICRP) deposition model and assuming no further evolution of aerosols …

Formation Of Hydrocarbons And Carbon Oxides In Mxene Reactions With Water Under Varying Oxidative Conditions, Shuohan Huang, Guanglei Xiang, Vadym Mochalin

Chemistry Faculty Research & Creative Works

Titanium carbide / carbonitride MXenes have garnered significant attention due to their remarkable properties, versatile solution processability, and broad range of potential applications. However, when exposed to the environment, MXenes are susceptible to degradation, which ultimately leads to the formation of metal oxides, a process that may be regarded as either disadvantageous or beneficial, depending on the application of a MXene and our knowledge about the underlying mechanisms. Therefore, it is very important to understand the reactivity of MXenes in different environments and conditions. Although researchers have made efforts to understand MXene degradation in air and water, our knowledge of …

Instantaneous Hydrolysis Of Methyl Paraoxon Nerve Agent Simulant Is Catalyzed By Nontoxic Aminoguanidine Imines, Emmanuel Kingsley Darkwah, Puspa Aryal, Chi Zhang, Charles B. Musgrave, William A. Goddard, V. Prakash Reddy

Chemistry Faculty Research & Creative Works

Exposure to organophosphate-based nerve agents and pesticides poses health and security threats to civilians, soldiers, and first responders. Thus, there is a need to develop effective decontamination agents that are nonhazardous to human health. To address this, we demonstrate that instantaneous hydrolysis of methyl paraoxon (Me-POX), a nerve agent simulant, can be achieved in the presence of aminoguanidine imines at pH 10: ● the pyridine-4-aldehyde aminoguanidine-imine (1) and ● the 2,3-butanedione aminoguanidine-imine (2). The hydrolysis of Me-POX under these conditions is substantially faster than that of the state-of-the-art decontaminating agent, Dekon-139 (2,3-butanedione oxime, potassium salt). Furthermore, Dekon-139 shows adverse effects …

Synthesis And Characterization Of Free Radical Scavenging Dendrimer Nanogels Via Cross-Linking Reaction-Enabled Flash Nanoprecipitation, Lin Qi, Da Huang, Huari Kou, Anna Chernatynskaya, Nuran Ercal, Hu Yang

Chemistry Faculty Research & Creative Works

This work reports the development and evaluation of dendrimer-based nanogels based on Poly amidoamine (PAMAM) dendrimer generation 5, engineered to act as a carrier with reactive oxygen species (ROS)-scavenging capabilities. We developed a cross-linking reaction-enabled flash nanoprecipitation method in which the cross-linking reaction occurs during the flash nanoprecipitation process to form a cross-linked nanostructure. Using this approach, an N-hydroxy succinimide (NHS)-functionalized ROS-responsive thioketal cross-linker (TK-NHS) was synthesized and utilized to cross-link DAB-core PAMAM dendrimer G5, resulting in the formation of G5-TK nanogels. The resulting nanogels were characterized using dynamic light scattering and transmission electron microscopy, and their cytocompatibility, irritancy, cellular …

Pla-Based Bone Tissue Engineering Scaffolds Incorporating Hydroxyapatite And Bioactive Glass Using Digital Light Processing, Engin Gepek, Fateme Fayyazbakhsh, Lev Suliandziga, Vadym Mochalin, Osman Iyibilgin, Yue-Wern Huang, Ming C. Leu

Chemistry Faculty Research & Creative Works

Bone tissue engineering (BTE) aims to repair bone defects using biocompatible materials with tailored geometries and pore structures, providing appropriate mechanical support and control over biodegradation kinetics to promote bone growth. In this study, we utilized digital light processing (DLP) 3D printing to fabricate scaffolds with varying pore sizes using polymer–ceramic slurries composed of polylactic acid (PLA) as the main polymer matrix, incorporated with hydroxyapatite (HA) and bioactive borate glass (BBG) at various ratios. We studied the effect of composition on rheological behavior, printability, mechanical properties, bioactivity, degradation rate, and biocompatibility. While HA increased viscosity and reduced printing accuracy, it …