DSpace@RPI (Rensselaer Polytechnic Institute)
Not a member yet
6809 research outputs found
Sort by
Deep clustering with associative memories
No full textMay2025School of ScienceClustering is a widely used unsupervised learning technique involving an intensive discrete optimization problem. Recently, there has been growing interest in making clustering end-to-end differentiable. Associative Memory models or AMs are differentiable neural networks defining a recursive dynamical system, which have been integrated with various deep learningarchitectures. However, until recently, there has been no work utilizing Associative Memory models for clustering. In this thesis, we discuss our contributions toward developing an Associative Memory-based clustering scheme. We introduce three innovations that leverage AM models, making them suitable for clustering while preserving their dynamic nature and discrete assignment properties. We first uncover a novel connection between the AM dynamics and the inherent discrete assignment necessary in clustering and then propose a novel unconstrained continuous relaxation of the discrete clustering problem, enabling End-to-end Differentiable Clustering with AM, dubbed ClAM. Leveraging the pattern completion ability of AMs, we further develop a novel self-supervised clustering loss. Our evaluations on varied datasets demonstrate that ClAM benefits from the self-supervision, and significantly improves upon both the traditional Lloyd’s k-means algorithm, and more recent continuous clustering relaxations (by upto 60% in terms of the Silhouette Coefficient). Our second contribution aims to extend ClAM by integrating autoencoder and associative memories together to perform clustering in the latent space instead of the ambient space. Deep clustering, which is joint representation learning and latent space clustering, is a well-studied problem especially in computer vision and text processing under the deep learning framework. While representation learning is generally differentiable, clustering is an inherently discrete optimization task, requiring various approximations and regularizations to fit in a standard differentiable pipeline. This leads to a somewhat disjointed representation learning and clustering. We show how Associative Memories enable a novel take on deep clustering, called DClAM, which simplifies the whole pipeline and ties together the representation learning and clustering more intricately. Our experiments showcase the advantage of DClAM, producing improved clustering quality regardless of the autoencoder architecture choice (convolutional, residual or fully-connected) or data modality (images or text).Ph
Characterizing conformational landscapes of arf gtpases using high pressure
No full textMay2025School of ScienceThe adenosine diphosphate (ADP) ribosylation factor (Arf) small guanosine triphosphate (GTP)ases function as molecular switches to activate signaling cascades that control membrane organization in eukaryotic cells. In Arf1, the GDP/GTP switch does not occur spontaneously but requires guanine nucleotide exchange factors (GEFs) and membranes. The related small GTPase Arf6, however, is able to undergo spontaneous nucleotide exchange. In both cases, exchange involves massive conformational changes, including disruption of the core β-sheet. To probe the switch mechanism, we coupled pressure perturbation with nuclear magnetic resonance (NMR), Fourier Transform infrared spectroscopy (FTIR), small-angle X-ray scattering (SAXS), fluorescence, and computation. For both proteins, pressure induced the formation of a classical molten globule (MG) ensemble, though Arf6 populates an ensemble which is energetically distinct from that of Arf1. Pressure also favored the GDP to GTP transition in both proteins, providing strong support for the notion that the MG ensemble plays a functional role in the nucleotide switch. We propose that the MG ensemble allows for switching without the requirement for complete unfolding and may be recognized by GEFs. Substitutions in helix α5 of Arf6 locally destabilize this helix relative to Arf1, in which it is the most stable element. Mutation of the α5 sequence in Arf6 to that of Arf1 resulted in both increased stability and slower switching, demonstrating “back-to-front” control of nucleotide exchange kinetics. Evolutionary covariance analysis highlighted an extensive non-interacting coupling network in the C-terminal half of Arf6 as well as many other small GTPases. Our work suggests that an MG-based switching mechanism as well as “back-to-front” control of switching could constitute pervasive features in Arfs and Arf-like GTPases, and more generally, the evolutionarily related Rags (Ras-like small GTPases) and Gα GTPases.Ph
Latent representations and fusion techniques for probabilistic structural health monitoring and state awareness
No full textMay2025School of EngineeringStructural Health Monitoring (SHM) aims to detect and characterize damage in critical components and systems, thus helping prevent catastrophic failures. As infrastructure ages and advanced aerospace and mechanical systems operate under increasingly demanding conditions, the need for reliable SHM solutions continues to grow. This dissertation presents a comprehensive approach that integrates machine learning and signal processing techniques to tackle both forward and inverse SHM challenges. Emphasizing guided waves, vibration-based diagnostics, and multi-fidelity data, the study explores how data compression methods, the fusion of deep learning with time series analysis, and statistical modeling contribute to a more accurate, resilient, and computationally efficient damage assessment framework. By integrating diverse feature extraction methods, probabilistic models, and a multimodal system, this research enhances detection and characterization capabilities, even in complex and uncertain environments. A key motivation lies in the difficulties posed by guided wave signals, which often have high dimensionality and are influenced by multiple environmental and operational conditions (EOCs). The forward problem, in which observed sensor signals must be predicted for a hypothesized damage state, is essential when available data set has limited size especially under extreme conditions. The inverse problem—inferring the damage properties from measured signals—is equally critical, particularly in real-time monitoring contexts where fast and accurate damage estimates can reduce risk and maintenance costs. Traditional forward and inverse approaches often require complex physics-based simulations or extensive data, and can be limited by computational overhead. This dissertation leverages data-driven methods with different feature extraction approaches and time series models to capture essential wave patterns while reducing signal dimensionality. After the introduction of the first chapter, Chapter II examines a machine learning-based framework that addresses both forward and inverse tasks using ultrasonic guided waves in an aluminum plate structure. Various neural network architectures were systematically tested, including multiple layer configurations, differing filter sizes, and alternative data representations designed to handle time-series signals. The latent space generated naturally by this type of model paves the way to efficient computation with reduced data dimension. Different structures of input matrices allow for the creation of time-invariant and time-varying latent space. A detailed comparison among performance of different structures are presented. The models with best-performing structures reconstruct waveforms with high fidelity, indicating that they capture critical features related to damage states. Moreover, when used in an inverse configuration, the models predict structural parameters such as damage extent and external factors simultaneously, illustrating their potential to expedite diagnostic evaluations in practical SHM systems. The approach is assessed via experiments with various model structures on the dual function of the scheme, i.e., to solve forward and inverse problems. The results of the chapter confirm the high potential and effectiveness of using the proposed scheme for multi-purpose SHM missions. Building upon the initial framework, Chapter III focuses on extending this work by comparing various data compression and data expansion techniques on the same lightweight aluminum structure under varying environmental states from the previous chapter. In this scenario, CAEs and diffusion maps (DMaps) both effectively preserves damage-relevant and envorionment-relevant information in the latent space. The near-perfect prediction accuracy leads to a more challenging test case introduced in Chapter IV where a wing is tested in a wind tunnel. Rather than collected in a static condition without significant disturbance, this time the data is recieved with high levels of noise due to airflow and structural complexity. Additional dimensionality reduction and generative methods using VAEs are employed to address the amplified uncertainty. The results reveal that the compression-expansion hybrid approaches can maintain diagnostic accuracy even when ambient conditions vary considerably, demonstrating the importance of adaptable methods for real-world SHM deployments. Recognizing that multiple sensing modalities can further enrich damage detection, the investigation in Chapter V combines information from guided wave data and vibration-based parameters. Rather than directly fusing the high-dimensional signals, it extracts lower-dimensional descriptors—latent representations from autoencoders for the guided waves and autoregressive (AR) coefficients for vibration responses. This parameter-level fusion reduces computational cost while retaining the complementary nature of local wave-based damage sensitivity and global vibration-based structural response. The effectiveness of this fusion is validated through experiments suggesting that properly combined parameters outperform either modality in isolation, especially when noise or other uncertainties challenge single-sensor methods. While these techniques can offer substantial improvements in accuracy and speed, they also rely on sufficient data—whether collected experimentally or generated through simulations. To address this challenge, Chapter VI of the dissertation introduces a multi-fidelity Gaussian Process (GP) model that links a damage index to a damage severity measure. In many SHM contexts, only a limited amount of high-fidelity experimental data is available, whereas simulation data is more plentiful but may not perfectly reflect reality. By employing a hierarchical GP framework, it becomes possible to leverage the benefits of both lower-fidelity simulation data and higher-fidelity experimental measurements. The multi-fidelity GP approach yields a more reliable mapping between measured indices and actual damage levels, thus expanding the feasibility of data-hungry machine learning strategies in practice. Collectively, these five studies illustrate comprehensive approaches to handling complex SHM scenarios. First, CAEs are shown to be effective in producing compact representations for both forward signal generation and inverse condition estimation. Second, the inclusion of diffusion maps provides a detailed comparison between the nonlinear data compression techniques. Third, VAEs expands the range of feasible dimensionality reduction approaches to tackle more disruptive noise environments. Fourth, the fusion of latent features from guided waves with AR-based vibration parameters offers an efficient means of leveraging multiple sensors without incurring the prohibitive cost of raw multi-channel data. Finally, multi-fidelity GP regression addresses the persistent gap between simulation-based modeling and real-world measurements, elevating the predictive accuracy of damage levels across a range of structures. Throughout these contributions, a consistent emphasis is placed on practical considerations, such as computational efficiency, adaptability to different environmental or operational conditions, and scalability to large or complex structures. The methods advanced here pave the way for future intelligent monitoring systems, in which data-driven models respond dynamically to evolving structural states and environmental factors. In addition to aerospace and mechanical engineering, these techniques have relevance for civil infrastructure, automotive safety, and energy sector applications, where the ability to detect damage before critical failure can save resources and lives alike. In summary, this dissertation demonstrates how data-driven approaches such as deep learning and statistical modeling, when carefully integrated, can overcome well-known bottlenecks in guided wave and vibration-based SHM. By combining forward models for signal generation, inverse methods for damage quantification, multi-modal data fusion, and multi-fidelity inference strategies, the work aims to realize accurate, robust, and operationally efficient monitoring solutions. The results confirm that these novel approaches enable more reliable and fine-grained assessments of structural health, even under conditions of strong noise or limited high-fidelity data. Such advances mark an important step toward practical deployment of next-generation SHM systems across a broad spectrum of industrial and research sectors, ultimately reinforcing the integrity and safety of critical structures worldwide. Finally, Chapter VII presents the concluding remarks and outlines future directions for this dissertation.Ph
Software/hardware design techniques to unleash the full potential of dram and flash memory for big data and ai applications
No full textMay2025School of EngineeringThe exponential growth of data-intensive applications, such as Artificial Intelligence (AI), Machine Learning (ML), and Big Data analytics, has placed unprecedented demands on memory and storage infrastructures. Traditional architectures often struggle to meet these requirements, leading to performance bottlenecks and increased operational costs. This research addresses these challenges by exploring advanced memory and storage optimization techniques to enhance data processing efficiency. This thesis first investigates methods to mitigate performance degradation associated with integrating block data compression into in-memory key-value (KV) stores. Despite extensive prior research on in-memory KV stores, minimal attention has been given to reducing memory usage through block data compression (e.g., LZ4, ZSTD) due to concerns over performance penalties. We introduce design techniques that leverage decompression streaming, latency differences between compression and decompression, and data access locality from real-world workloads. These techniques integrate seamlessly with conventional hash or B+-tree indexing structures, enabling broad applicability without altering existing core indexing frameworks. By addressing these performance challenges, this research makes it feasible to significantly reduce memory costs in KV stores, enhancing scalability and efficiency for applications that rely heavily on rapid data access and cost-effective memory usage. This thesis further investigates utilizing computational storage drives (CSDs) to reduce storage costs in security-first environments. Modern cloud computing systems face the challenging task of simultaneously achieving security, performance, and cost efficiency, particularly in data storage services. In such environments, data typically undergoes compression to reduce storage demands, followed by encryption for security, which introduces significant complexity, performance overhead, and increased costs, especially in snapshot management. Emerging CSD technology addresses these issues by offloading computationally intensive compression tasks directly to storage devices and offering virtualized logical storage space, creating new opportunities for efficient optimization. By enabling more streamlined management of compressed and encrypted data, this work significantly reduces operational complexity and costs, ultimately supporting more secure, efficient, and cost-effective cloud storage solutions. Finally, this thesis studies how to make flash memory more relevant in AI computing systems. In today's AI computing platform, flash memory plays a secondary, supportive role by mainly serving data accesses outside the core AI training/inference operations. With the emergence of AI models/workloads that demand TB-scale embeddings, it presents opportunities for flash memory to play a more essential role in the AI era. State-of-the-art SSDs (solid-state drives) are optimized for 4KB LBA (logical block address) block size and achieve only up to ~3M peak IOPS (I/O per second). This nonetheless is far inadequate for most AI systems. Given the typically smaller-than-4KB embedding vector size (e.g., 512B~2KB), this thesis reveals an encouraging potential to make future SSDs much more AI-friendly, which is realized by cohesively leveraging new flash memory device features and enhancing SSD controller architecture/firmware design.Ph
Reactive coarse-grain simulation for advanced material systems
No full textDecember 2024School of EngineeringWith advancements in computational power and algorithms, molecular dynamics (MD) simulations have become an indispensable tool in materials modeling. Well-designed simplified models, such as coarse-graining (CG) of molecular structures and using scalable potentials, enable researchers to explore larger spatial and temporal scales compared to full atomistic MD. In this thesis, we explore the utility of such models adopted very specifically for specific problems. In the first project, we set up a reactive coarse-grain simulation methodology for epoxy nanocomposite systems. In the second project, we explore the capability of a simplified hcp model to explain valuable physics. In the third and ongoing project, we implemented reactive coarse grain to prepare simulated polymer melt systems to understand the complex entanglements and their effect on the mechanical behavior. Glassy thermosetting polymers represent an important class of engineering materials known for their mechanical strength, chemical resistance, and versatility across industries. Epoxy resin, in particular, is highly valued for its exceptional adhesion, chemical and thermal stability, and electrical insulation properties, making it essential in aerospace, automotive, electronics, and structural applications. Traditional thermosetting epoxies are hard due to heavy cross-linking between the chains, however, very brittle at the same time for the same reason. Concurrent stiffening and toughening of thermosetting polymers have been a longstanding problem in material science. Experiments show that strong and stiff inclusions, such as graphene, offer some promising progress but a clear understanding of such processes is still lacking. On top of that experimental results are still mixed when it comes to simultaneously improving the stiffness and toughness of the matrix using graphene and functionalized graphene flakes. We idntified that the strength of the interface between the matrix and the filler plays an important role in determining the mechanical properties of graphene-reinforced epoxy. In this thesis, we employed reactive CG-MD to understand the effect of the interface strength on the elastic and fracture properties. We developed methodologies to model the epoxy crosslinking process using bump-LJ, a simple but reactive pairwise potential, capturing the network structure that defines their stiffness and brittleness. Reactive CG-MD enabled us to capture the brittle fracture of the epoxy resin. We identified that concurrent stiffening and toughening happens for a moderate adhesive strength between the graphene and the matrix. Both weak and strong interfaces are detrimental. Pyroelectric materials are vital in infrared sensors, thermal imaging, energy harvesting, and temperature sensing technologies. Experimental research done by our collaborators indicates that reducing film thickness enhances pyroelectric properties, making them highly effective for high-sensitivity applications. This dimensionality effect increases progressively from van der Waals (vdW) to quasi-vdW to ionic/covalent materials and is hypothesized to result from enhanced electron-phonon coupling, related to the Debye-Waller factor. In this thesis, we developed a simplified hcp structure using the bump LJ potential to simulate atomic vibrations across three material classes with varying out-of-plane bond strengths and at different thickness levels. Our findings show that Debye-Waller factor increases with reduction in membrane thickness and the enhancement is more pronounced in covalently bonded materials than in weaker vdW-bonded materials, supporting the theoretical framework and shedding light on the mechanisms driving this dimensionality effect.Ph
Sound reverberation characteristics of a coupled volume system
No full textAugust2025School of ArchitectureIn the performing arts spaces, the goal of the coupled volume system is to leverage the clarityand reverberation. This type of design and construction brings unique sound reverberance
characteristics to the coupled volume space, both in the physical and perceptual behavior. In
the physical aspects, sounds reverberation decay often manifests as multiple-slopes decay, and
also influences the interaural decorrelation of listeners. In the perceptual aspects, multipleslopes
decay in the coupled volume system may introduce directional reverberance from the
secondary space. To investigate these sound reverberation characteristics, using Bayesian
analysis and interaural decorrelation coefficient analysis, spatial and temporal reverberation
characteristics can be determined. A preliminary listening test based on experimentally
measured binaural impulse responses is conducted to investigate human listening sensitivity
to directional reverberance. The analysis results suggest that the multiple-slope behavior
is frequency independent, and the turning point time of multiple-slope increases when the
receiver distance from the aperture increases. The preliminary listening test results indicate
that the sensitivity of the human perception of directional reveberance is low. This thesis
introduces the physical analysis methods, experimental measurement process, listening test
methods, and analysis results from both the physical and perceptual sides.M
Power system analytics: anomaly detection, prediction, and mitigation
No full textAugust2025School of EngineeringPower transmission networks are critical infrastructures responsible for delivering electrical energyfrom generation sources to end-users. Traditionally, robust protection systems—including relay based
logic and automated safeguards—have successfully prevented many large-scale disruptions.
However, recent trends such as the extensive integration of renewable energy sources, growing
electricity demand, extreme weather events, aging infrastructure, and emerging cyber threats have
heightened the complexity and uncertainty faced by modern power grids. These factors significantly
elevate the risk of cascading failures and large-scale blackouts. Thus, the timely detection, accurate
prediction, and effective mitigation of such anomalies have become vital objectives for ensuring
power system reliability and resilience. To address these critical challenges, this dissertation
develops advanced, data-driven analytical methods rooted in statistical inference and graph machine
learning, tailored specifically for anomaly detection, localization, prediction, and mitigation. The first major focus of this dissertation addresses real-time detection and localization oftransmission line outages to improve grid reliability. Existing algorithms suffer from severe computational
bottlenecks, primarily due to simultaneously running multiple high-dimensional statistical
tests to detect and localize outages. This dissertation introduces a novel Graph-Guided Quickest
Change Detection (GG-QCD) framework that significantly reduces computational complexity
by decoupling outage detection from localization. Initially, a computationally lightweight one dimensional
spectral conformity metric tests the data’s conformity to the expected network structure
to rapidly detect an outage event. Upon detection, a localization stage, inspired by binary search
techniques, recursively partitions the network topology to efficiently pinpoint the affected transmission
line dramatically reducing the complexity from O(L) high-dimensional parallel tests to
O(log L) sequential tests, with each test also benefiting from significantly lower computational
complexity. Simulations on standard IEEE benchmarks demonstrate that the GG-QCD method
achieves considerable computational savings at the expense of only a modest increase in detection
delay, making it a practical and scalable solution for real-time power grid monitoring. The second contribution focuses on improving grid resilience by predicting cascading failures. Previous blackout analyses indicate that operators frequently fail to recognize incremental network changes, permitting hidden failures to accumulate until extensive disruptions occur. Existing predictive models generally struggle to capture concurrent spatio-temporal dependencies under dynamically evolving topologies, become computationally prohibitive at moderate network scales, and provide limited insight into causal relationships among network components. To addressthese issues, this dissertation introduces two complementary frameworks for cascading failure
prediction. The first framework formulates the prediction of risky fault chains as a partially
observableMarkov decision process (POMDP), approximately solved through a time-varying Graph
Recurrent Neural Network (GRNN) by employing a meta-reinforcement learning (RL) approach.
This model effectively captures the spatial and temporal dependencies inherent in power grids,
offering a scalable real-time predictive model. The second framework employs causal inference to
learn a directed latent graph that captures the cause-effect relationships among grid components,
providing a theoretical basis to quantify cascading interactions. Evaluations on IEEE benchmarks
demonstrate that both frameworks significantly enhance predictive accuracy and computational
efficiency by explicitly leveraging graph-structured representations and appropriately modeling
dependencies throughout the various cascading failure stages. The third and final contribution addresses cascading failure mitigation through sequentialremedial control actions. Large-scale failures often result from sustained congestion induced by
excessive load demands, gradually destabilizing the network. Traditional mitigation strategies
primarily emphasize bus-splitting techniques, often neglecting the potential of transmission line
disconnections and continuous generator control. To address this gap, this dissertation introduces a
novel physics-guided reinforcement learning (PG-RL) framework incorporating both discrete (line
reconnections/removals) and continuous (generator adjustments) actions within a unified hybrid
action space. By explicitly integrating sensitivity factors to guide RL exploration, the proposed
PG-RL framework substantially improves grid survival times compared to conventional black-box
RL methods. Empirical evaluations on the open-source Grid2Op platform illustrate that strategically
executed line removals can effectively delay or prevent cascading outages, highlighting previously
neglected remedial potentials. Additionally, the incorporation of continuous-valued generator
adjustments further enhances system resilience, offering a complementary alternative to traditional
bus-splitting approaches and paving the way for broader, more adaptive grid control strategies.Ph
Sound becomes site: music of the metaverse
No full textAugust2025School of Humanities, Arts, and Social SciencesThis dissertation investigates the aesthetic, conceptual and technical qualities of electronic music and sound situated ‘in’ digital media space, including video game environments, virtual reality, 3D simulations, online multi-user platforms, and multi-projector facilities with spatial audio. This project will place itself in relation to existing literature and study in the field, contemporary technical and cultural contexts, and my own creative practice. A series of conceptual frameworks will then be established, addressing the relation between sound and electronic media, the use of technical and musical metaphor regarding the virtualization of software and digital audio, as well as taxonomies of verisimilitude and abstraction in dialogue with sound in virtual media environments. These frameworks will then be leveraged to explore a number of historic and contemporary case studies of sound and music in media space.
This exploration will be grounded by research questions focused on the qualitative aspects of this emerging field. These questions ask how music or sound art in virtual environments is fundamentally different from prior creative practices, how this space operates in relation to electronic interactive media such as video games or virtual simulation, and how this relationship informs past, present and future discourse and practice.
Research for this project takes a three-pronged approach, consisting of 1) historicization of electronic music, virtual media and consumer game audio technology, 2) analysis of a range of case studies regarding sound and music in navigable media space, and 3) development and documentation of my creative works in relation to these concepts. The historicization presented in this dissertation draws novel connections across a range of fields, beginning with the advent of sound recording through the compositional practices of avant-garde composers in the mid twentieth century, the development of analog control voltage in modular synthesis through the codification of the digital MIDI protocol and finally the virtualization of sound production in software. These developments are analyzed through the conceptual frameworks presented previously, and connected to canonical developments regarding spatial sound in institutional virtual reality, consumer home computer video games, and experimental music and media art. These disparate strands are then brought together in dialogue with the rise of online ‘virtual worlds,’ and their changing relation to mainstream discourse around musical experience and the ‘metaverse’ during the COVID-19 pandemic and subsequent lockdowns. Connections across disciplines and technological contexts are examined via case studies throughout, and are further illustrated by artistic projects and technical study in my own research creation. This project aims to supplement existing scholarship across game studies, contemporary composition, and music technology discourse by offering significant qualitative findings regarding creative, conceptual and technical developments in this emerging field alongside critical analysis of historic precedents. This research offers tools for understanding and engaging with future developments regarding sound and music in virtual media, as well as documented case studies for further study. Findings from this work should be of use to artists, media and game scholars, creative technologists, and a general public exploring virtual sonic experience.Ph
The social costs of quantum futures
No full textJune2025School of Humanities, Arts, and Social SciencesThis thesis defines quantum anticipatory regimes and traces their genealogy from the Cold War. It argues that Cold War computing culture and expert communities developed ways to “technologically manage” the future, using computer-generated knowledge to produce simulated threats that empowered the government to mobilize uncertainty as an anticipatory power. Past American expert anticipatory regimes persisted beyond the Cold War through a cultural acceptance of computers as experts and algorithms as national infrastructure and as strategic resource. This thesis, therefore, anticipates and theorizes the evolution of expert anticipatory regimes in the promissory image of quantum computing futures. Furthermore, it posits gentrification as the evolutionary process of how American anticipatory regimes create their futures through technology. Through a discourse analysis of press releases, news coverage, and public events hosted by Rensselaer Polytechnic Institute (RPI) and the city of Chicago, it highlights how these entities imagine their own quantum futures and interprets the social cost of these futures as a function of gentrification, where marginalized communities and alternatives visions of the future are displaced. Ultimately, the desire and capital push for quantum computing futures is not just a national infrastructure project, but a conceptual restructuring of the guiding epistemology in how this country perceives the future. Quantum anticipatory regimes are the next evolution in how this country manages perceptions of what the future should be.M
Acoustic treatment of portals in sequential space museum environments
No full textAugust2025School of ArchitectureMuseums have a unique problem in that they consist of multipurpose non-acoustic sequential spaces connected sonically by large open doorways (portals). Yet both in terms of architectural design and functionality, room acoustics in museums have direct and measured effects on visitors enjoyment and experience. Because of the varied nature of museum room purpose and need, sound separation between rooms is crucial in maintaining the contextual and expectational limits of the room which may limit distracting or disruptive experience. This study seeks to measure the efficacy of portal acoustic treatment in limiting sound transmission in large volume sequential museum spaces to improve acoustic metrics of distraction. Sound-field modeling in Treble is employed using geometric and wave methods, in order to examine the effects of portal treatment through semi-enclosure, torqued semi-enclosure, and occluder apparatuses. Objective measures in accordance with ISO 3382-3 of distraction distance, spatial decay rate of unamplified speech, sound pressure level of unamplified speech at 4 meters, reverberation time, clarity, and A-weighted sound pressure level, were calculated under absorptive and reflective room treatment conditions. Results show strong increases in spatial decay rate of speech, sharp decreases in level of speech at 4 m and A-weighted SPL for every portal treatment, with effects most pronounced when applying occluding and torqued semi-enclosures. Future study involves in-situ testing of acoustic parameters of distraction and perceptual study of effects of portal treatment on subjective distraction metrics.M