Data Movement Research Articles

An innovative approach to automate BIM data retrieval and processing for building acoustic comfort calculations based on the IFC standard

Nowadays, there is a growing demand for deep renovation projects aimed at improving the energy efficiency of buildings while enhancing indoor comfort conditions for the inhabitants, both thermal and acoustic. To design effective renovation strategies, technicians need to know the current state of the building to propose acoustic or only thermal improvements. However, evaluating indoor acoustic comfort requires time-consuming and tedious calculations, which can be prone to errors when handled manually. While Building Information Modelling (BIM) can facilitate this process by leveraging the extensive contained data and offering the potential to automate these processes, such automation is not yet widespread. Typically, only geometric data is retrieved automatically from BIM models in acoustic software, while acoustic parameters must be provided manually. This paper addresses these challenges by introducing a novel approach that integrates automated data extraction from BIM with acoustic simulation tools. Specifically, an Extract, Transform and Load (ETL) solution was designed to automatically retrieve both geometric and acoustic data for an Acoustic Comfort tool, which calculates an estimation of indoor acoustic comfort, from an Industry Foundation Classes (IFC). This approach was tested in a demonstration case located in Spain, showing a significant reduction in processing time and increased accuracy compared to traditional methods of manually extracting data from BIM for acoustic assessment. This research represents a significant advance in acoustic simulations by integrating IFC data with automated processing, improving accuracy and offering practical advantages for developing more efficient and reliable BIM-based applications, thus supporting the design of deep renovation projects.

GPU-enabled extreme-scale turbulence simulations: Fourier pseudo-spectral algorithms at the exascale using OpenMP offloading

Fourier pseudo-spectral methods for nonlinear partial differential equations are of wide interest in many areas of advanced computational science, including direct numerical simulation of three-dimensional (3-D) turbulence governed by the Navier-Stokes equations in fluid dynamics. This paper presents a new capability for simulating turbulence at a new record resolution up to 35 trillion grid points, on the world's first exascale computer, Frontier, comprising AMD MI250x GPUs with HPE's Slingshot interconnect and operated by the US Department of Energy's Oak Ridge Leadership Computing Facility (OLCF). Key programming strategies designed to take maximum advantage of the machine architecture involve performing almost all computations on the GPU which has the same memory capacity as the CPU, performing all-to-all communication among sets of parallel processes directly on the GPU, and targeting GPUs efficiently using OpenMP offloading for intensive number-crunching including 1-D Fast Fourier Transforms (FFT) performed using AMD ROCm library calls. With 99% of computing power on Frontier being on the GPU, leaving the CPU idle leads to a net performance gain via avoiding the overhead of data movement between host and device except when needed for some I/O purposes. Memory footprint including the size of communication buffers for MPI_ALLTOALL is managed carefully to maximize the largest problem size possible for a given node count.Detailed performance data including separate contributions from different categories of operations to the elapsed wall time per step are reported for five grid resolutions, from 20483 on a single node to 327683 on 4096 or 8192 nodes out of 9408 on the system. Both 1D and 2D domain decompositions which divide a 3D periodic domain into slabs and pencils respectively are implemented. The present code suite (labeled by the acronym GESTS, GPUs for Extreme Scale Turbulence Simulations) achieves a figure of merit (in grid points per second) exceeding goals set in the Center for Accelerated Application Readiness (CAAR) program for Frontier. The performance attained is highly favorable in both weak scaling and strong scaling, with notable departures only for 20483 where communication is entirely intra-node, and for 327683, where a challenge due to small message sizes does arise. Communication performance is addressed further using a lightweight test code that performs all-to-all communication in a manner matching the full turbulence simulation code. Performance at large problem sizes is affected by both small message size due to high node counts as well as dragonfly network topology features on the machine, but is consistent with official expectations of sustained performance on Frontier. Overall, although not perfect, the scalability achieved at the extreme problem size of 327683 (and up to 8192 nodes — which corresponds to hardware rated at just under 1 exaflop/sec of theoretical peak computational performance) is arguably better than the scalability observed using prior state-of-the-art algorithms on Frontier's predecessor machine (Summit) at OLCF. New science results for the study of intermittency in turbulence enabled by this code and its extensions are to be reported separately in the near future.

VeriFog: A Generic Model-based Approach for Verifying Fog Systems at Design Time and Generating Deployment Configurations

Fog Computing is a paradigm decentralizing the Cloud by geographically distributing computation, storage, network resources and related services. It provides benefits such as reducing the number of bottlenecks, limiting unwanted data movements, etc. However, managing the size, complexity and heterogeneity of the Fog systems to be engineered is challenging and can quickly become costly. According to best practices in software engineering, verification tasks could be performed on a system design prior to its implementation and deployment. We propose a generic model-based approach for verifying Fog systems at design time, also enabling the automatic generation of corresponding deployment configuration files. Named VeriFog, this approach is notably based on a customizable Fog Modeling Language (FML). We experimented in practice by modeling three use cases, from three different application domains, and by considering three main types of non-functional properties to be verified. From this modeling and verification effort, we show that we are able to automatically generate usable deployment configuration files for different deployment tools. In direct collaboration with our industrial partner Smile, the approach and underlying language presented in this paper are necessary steps towards a more global model-based support for the complete life cycle of Fog systems.

My Holistic Data Share: A WEB3 Data Share Application: Extending Beyond Finance to Privacy-Protected Decentralized Share of Multi-Dimensional Data to Enhance Global Healthcare

Abstract WEB3.0 technologies on network architectures, distributed ledgers, and decentralized artificial intelligence represents a transformative shift in how data are handled, stored and shared. These innovations promise to significantly enhance consumer data privacy rights by addressing fundamental vulnerabilities associated with traditional centralized systems and self-custody wallets. Data breaches in traditional systems operated mainly by third parties are more common, resulting in significant data leaks because of centralized storage and excessive data movement, sometimes unnecessarily. Healthcare data breaches have been a growing concern globally. Several hospitals faced operational halts on account of the impact of ransomware on patient care and privacy. WEB3 Wallets are a vital component emerging as a significant force for global financial inclusion, especially in developing economies. They promote inclusion, reduce costs and empower individuals through self-custody. Though major improvements are needed in these wallets, their use is rising steadily. The global cryptocurrency user base is expected to reach over 500 million by 2025, with substantial growth in emerging markets, according to a report by Statista in 2023. This paper introduces a concept beyond cryptocurrencies and finance into everyday real-world use cases that need combinatorial access to a person’s holistic data, including financial and health records, genomic data, and advanced directives, among others, that need to be privacy protected and shared with specific actors identified for their roles in the WEB3 ecosystem through decentralized identifiers and non-fungible token badges identifying particular recipients. The author introduced the concept at ETHBoston in April 2024, won accolades for a primitive implementation using underlying threshold cryptography technologies, and enhanced it into a conceptual holistic data share application for global healthcare, as presented in this paper.

Clinical Data Warehousing: A Scoping Review

INTRODUCTION: A clinical data warehouse (CDW) is a powerfulresource that supports clinical decision-making and secondary data use byintegrating and presenting heterogeneous data sources. Despite considerableeffort within healthcare organizations (HCOs) to develop CDWs, scientific literaturesurrounding clinical data warehousing methods is limited.OBJECTIVES: The scoping review aims to characterize thecurrent state of CDW methods within HCOs, to identify extant evidence forpractice recommendations, and ultimately to advance the design, implementation,and use of CDWs. METHODS: The review encompasses CDW articles publishedfrom 2011 through 2021 identified through a systematic PubMed search. Articleabstracts were systematically screened by two authors. Full-text articles werereviewed and abstracted independently by two authors with discrepanciesresolved through consensus.   RESULTS: 137 articles, from 55 journals and 3conference proceedings, were categorized and analyzed.  Areas for increased CDW focus include dataintegration of increased data types and sources; extract-transform-load (ETL)optimization; data quality improvement processes; semantic data representation;support tools/documentation and data literacy efforts for staff and end-users;data governance; business model/financial support for CDWs including staffing. CONCLUSION:  Thestudy indicates the topics that have been significantly developed and theaspects needing additional focus and reporting in CDW between existing generaldata management best practices and recently articulated requirements forresearch data. Also, more multi-site and multi-aspect studies are needed tofoster maturity at CDWs.

Smoothing and approximation of grassland fire loading data for engineering structures by Capped Extended Support Vector Regression

This research proposes a machine learning-aided data smoothing and approximation scheme to investigate grassland fire loading for engineering structures. The investigations on grassland fire loading have significant impacts on wildfire-resistant design, building codes, regulations, and the like in specific regions. Real-world data collection systems inevitably introduce imperfections, such as noise, outliers, and the like. Furthermore, the collected data are normally discretized on time and location, and thus the information between them is completely absent. Achieving a smooth fit to data and reducing these imperfections are desired to facilitate subsequent analyses. Accordingly, a supervised machine learning algorithm is developed to smooth and approximate grassland fire loading data. Within the proposed algorithm, a convex optimization programming is established, which provides theoretical support to the accuracy of the algorithm. Then, through the proposed scheme, the grassland fire loading data can be approximated into an explicit regression model, which continuously completes the missing information during the observations. Moreover, attributed to the sparsity feature of the developed algorithm, the model can be simplified in its expression to further improve its applicability in engineering. Finally, real-world experimental data and numerical simulation results are separately investigated to demonstrate the effectiveness of the proposed scheme.

Fatigue damage accumulation in a bolted joint subjected to the random loading

Fatigue damage in structures, which escalates with cyclic loading, is traditionally analyzed using blocks of constant amplitude. This study aims to derive the fatigue loading spectrum for the Cirrus SR20 multipurpose airplane and predict the fatigue life of its main spar connection. Using available reference loading data from acrobatic and training aircraft, the loading spectrum was established, and constant amplitude loading blocks were determined through the Rainflow cycle counting and statistical methods. Fatigue damage in the bolted joint was assessed using both linear and nonlinear Miner rules, revealing that results from nonlinear criteria tend to converge towards those from linear predictions as loading blocks increase. This approach provides a robust predictive framework for assessing the fatigue life of airplane components under variable amplitude loadings, potentially enhancing maintenance protocols and structural design durability.

Thermally tuned on-chip optical memory

Phase-change materials, known as Chalcogenide alloys, are a promising alternative to traditional random-access memory. They possess characteristics that are particularly beneficial for non-volatile storage applications. The features of the Phase change material Ge-Sb-Te alloy (GST) used for substrate-integrated optical memory include scaling, quick switching times, minimal switching energy, and exceptional thermal stability. The material has two tuneable states, amorphous and crystalline, with the amorphous layer for loading data optically. In contrast, the crystalline state holds the data longer without significant loss. The study designed a classic thermally tuned optical memory on a silicon substrate. It demonstrated a dependency of lattice structure on external voltage and revealed a large storage capacity for information in the form of an optical signal. The heat transport simulation utilized the Heat Transport (HEAT) solver of the Finite Element Eigenmode (FEEM) solver. At the same time, the optical response analysis involved the Finite Difference Time Domain (FDTD) solver of Lumerical. The proposed structure exhibits a memory-switching phenomenon when a temperature shift of about 60 °C from room temperature is induced by a change in the external voltage of 147 mV. These findings have substantial implications for non-volatile storage memory development, providing a potential solution for high-capacity, low-energy data storage.

MeDaX: A Knowledge Graph on FHIR.

In Germany, the standard format for exchange of clinical care data for research is HL7 FHIR. Graph databases (GDBs), well suited for integrating complex and heterogeneous data from diverse sources, are currently gaining traction in the medical field. They provide a versatile framework for data analysis which is generally challenging for raw FHIR-formatted data. For generation of a knowledge graph (KG) for clinical research data, we tested different extract-transform-load (ETL) approaches to convert FHIR into graph format. We designed a generalised ETL process and implemented a prototypic pipeline for automated KG creation and ontological structuring. The MeDaX-KG prototype is built from synthetic patient data and currently serves internal testing purposes. The presented approach is easy to customise to expand to other data types and formats.

Multi-Source Data ETL (Extract, Transform, Load) for a Genetic Epilepsy Diagnosis and Treatment Dashboard.

The growing number of genes identified in relation to epilepsy represents a major breakthrough in diagnosis and treatment, but experts face the challenge of efficiently accessing and consolidating the vast amount of genetic data available. Therefore, we present the process of transforming data from different sources and formats into an Entity-Attribute-Value (EAV) model database. Combined with the use of standard coding systems, this approach will provide a scalable and adaptable database to present the data in a comprehensive way to experts via a dashboard.

From Near-Sensor to In-Sensor: A State-of-the-Art Review of Embedded AI Vision Systems.

In modern cyber-physical systems, the integration of AI into vision pipelines is now a standard practice for applications ranging from autonomous vehicles to mobile devices. Traditional AI integration often relies on cloud-based processing, which faces challenges such as data access bottlenecks, increased latency, and high power consumption. This article reviews embedded AI vision systems, examining the diverse landscape of near-sensor and in-sensor processing architectures that incorporate convolutional neural networks. We begin with a comprehensive analysis of the critical characteristics and metrics that define the performance of AI-integrated vision systems. These include sensor resolution, frame rate, data bandwidth, computational throughput, latency, power efficiency, and overall system scalability. Understanding these metrics provides a foundation for evaluating how different embedded processing architectures impact the entire vision pipeline, from image capture to AI inference. Our analysis delves into near-sensor systems that leverage dedicated hardware accelerators and commercially available components to efficiently process data close to their source, minimizing data transfer overhead and latency. These systems offer a balance between flexibility and performance, allowing for real-time processing in constrained environments. In addition, we explore in-sensor processing solutions that integrate computational capabilities directly into the sensor. This approach addresses the rigorous demand constraints of embedded applications by significantly reducing data movement and power consumption while also enabling in-sensor feature extraction, pre-processing, and CNN inference. By comparing these approaches, we identify trade-offs related to flexibility, power consumption, and computational performance. Ultimately, this article provides insights into the evolving landscape of embedded AI vision systems and suggests new research directions for the development of next-generation machine vision systems.

Proposal for a Patient Centered Health Information Framework for Clinical and Personal Data Movement.

This paper focuses on defining a framework to allow individual patients to track their own health related data. We propose a Patient Centered Information Framework (PCIF) allowing patient to manage their own data by using discharge letters. Discharge letters summarize information from a hospital stay, such as medical history, diagnoses, treatments and follow up, needed for continuity of care. It enables patients to share data with different organizations ensuring personal data protection, even when moving from different places and countries. A record of clinical management may thus be guaranteed when moving among different health structures as well as simplifying obtaining medications. We propose an approach to allow citizens to manage their health related data in a cross borders fashion. We compare the regulation of discharge letters among a sample of countries. We propose a management protocol for using a commonly adopted patient discharge letter framework within a PCIF.

Outbreak detector: a web application to boost disease surveillance systems and timely detection of infectious disease epidemics

ObjectiveDigital technologies have improved the performance of surveillance systems through early detection of outbreaks and epidemic control. The aim of this study is to introduce an outbreak detection web application called OBDETECTOR (Outbreak Detector), which as a professional web application has the ability to process weekly or daily reported data from disease surveillance systems and facilitates the early detection of disease outbreaks.ResultsOBDETECTOR generates a histogram that exhibits the trend of infection within a time range selected by the user. The output comprises red triangles and plus signs, where the former denotes outbreak days determined by the algorithm applied to the data, and the latter represents days identified as outbreaks by the researcher. The graph also displays threshold values and its symbols enable researchers to compute evaluation criteria for outbreak detection algorithms, including sensitivity and specificity. OBDETECTOR allows users to modify algorithm parameters based on their research objectives immediately after loading data. The implementation of automatic web applications results in immediate reporting, precise analysis, and prompt alert notification. Moreover, Public Health authorities and other stakeholders of surveillance can benefit from the widespread accessibility and user-friendliness of these tools, enhancing their knowledge and skills for better engagement in surveillance programs.

AI-Enabled Clinical Decision Support System Modeling for the Prediction of Cirrhosis Complications

Background and ObjectiveUtilizing artificial intelligence (AI), a clinical decision support system (CDSS), can help physicians anticipate possible complications of cirrhosis patients before prescribing more accurate treatments. This study aimed to establish a prototype of AI-CDSS modeling using electronic health records to predict five complications for cirrhosis patients who were controlled for oral antiviral drugs, lamivudine (LAM) or entecavir (ETV). MethodsOur modeling attained a web-based AI-CDSS with four steps – data extraction, sample normalization, AI-enabled machine learning (ML), and system integration. We designed the extract-transform-load (ETL) procedure to filter the analytics features from a clinical database. The data training process applied 10-fold cross-validation to verify diverse ML models due to possible feature patterns with medications for predicting the complications. In addition, we applied both statistical means and standard deviations of the realistic datasets to create the simulative datasets, which contained sufficient and balanced data to train the most efficient models for evaluation. The modeling combined multiple ML methods, such as support vector machine (SVM), random forest (RF), extreme gradient boosting, naive Bayes, and logistic regression, for training fourteen features to generate the AI-CDSS's prediction functionality. ResultsThe models achieving an accuracy of 0.8 after cross-validations would be qualified for the AI-CDSS. SVM and RF models using realistic data predicted jaundice with an accuracy of over 0.82. Furthermore, the SVM models using simulative data reached an accuracy of over 0.85 when predicting patients with jaundice. Our approaches implied that the simulative datasets based on the same distributions as that of the features in the realistic dataset were adequate for training the ML models. The RF model could reach an AUC of up to 0.82 for multiple complications by testing with the un-trained data. Finally, we successfully installed twenty models of the suitable ML methods in the AI-CDSS to predict five complications for cirrhosis patients prescribed with LAM or ETV. ConclusionsOur modeling integrated a self-developed AI-CDSS with the approved ML models to predict cirrhosis complications for aiding clinical decision making.

Predicting the Healing of Lower Extremity Fractures Using Wearable Ground Reaction Force Sensors and Machine Learning.

Lower extremity fractures pose challenges due to prolonged healing times and limited assessment methods. Integrating wearable sensors with machine learning can help overcome these challenges by providing objective assessment and predicting fracture healing. In this retrospective study, data from a gait monitoring insole on 25 patients with closed lower extremity fractures were analyzed. Continuous underfoot loading data were processed to isolate steps, extract metrics, and feed them into three white-box machine learning models. Decision tree and Lasso regression aided feature selection, while a logistic regression classifier predicted days until fracture healing within a 30-day range. Evaluations via 10-fold cross-validation and leave-one-out validation yielded stable metrics, with the model achieving a mean accuracy, precision, recall, and F1-score of approximately 76%. Feature selection revealed the importance of underfoot loading distribution patterns, particularly on the medial surface. Our research facilitates data-driven decisions, enabling early complication detection, potentially shortening recovery times, and offering accurate rehabilitation timeline predictions.

How to customize common data models for rare diseases: an OMOP-based implementation and lessons learned

BackgroundGiven the geographical sparsity of Rare Diseases (RDs), assembling a cohort is often a challenging task. Common data models (CDM) can harmonize disparate sources of data that can be the basis of decision support systems and artificial intelligence-based studies, leading to new insights in the field. This work is sought to support the design of large-scale multi-center studies for rare diseases.MethodsIn an interdisciplinary group, we derived a list of elements of RDs in three medical domains (endocrinology, gastroenterology, and pneumonology) according to specialist knowledge and clinical guidelines in an iterative process. We then defined a RDs data structure that matched all our data elements and built Extract, Transform, Load (ETL) processes to transfer the structure to a joint CDM. To ensure interoperability of our developed CDM and its subsequent usage for further RDs domains, we ultimately mapped it to Observational Medical Outcomes Partnership (OMOP) CDM. We then included a fourth domain, hematology, as a proof-of-concept and mapped an acute myeloid leukemia (AML) dataset to the developed CDM.ResultsWe have developed an OMOP-based rare diseases common data model (RD-CDM) using data elements from the three domains (endocrinology, gastroenterology, and pneumonology) and tested the CDM using data from the hematology domain. The total study cohort included 61,697 patients. After aligning our modules with those of Medical Informatics Initiative (MII) Core Dataset (CDS) modules, we leveraged its ETL process. This facilitated the seamless transfer of demographic information, diagnoses, procedures, laboratory results, and medication modules from our RD-CDM to the OMOP. For the phenotypes and genotypes, we developed a second ETL process. We finally derived lessons learned for customizing our RD-CDM for different RDs.DiscussionThis work can serve as a blueprint for other domains as its modularized structure could be extended towards novel data types. An interdisciplinary group of stakeholders that are actively supporting the project's progress is necessary to reach a comprehensive CDM.ConclusionThe customized data structure related to our RD-CDM can be used to perform multi-center studies to test data-driven hypotheses on a larger scale and take advantage of the analytical tools offered by the OHDSI community.

Harmonizing Norwegian registries onto OMOP common data model: Mapping challenges and opportunities for pregnancy and COVID-19 research

ObjectiveNorwegian health registries covering entire population are used for administration, research, and emergency preparedness. We harmonized these data onto the Observational Medical Outcomes Partnership common data model (OMOP CDM) and enrich real-world data in OMOP format with COVID-19 related data. MethodsData from six registries (2018–2021) covering birth registrations, selected primary and secondary care events, vaccinations, and communicable disease notifications were mapped onto the OMOP CDM v5.3. An Extract-Transform-Load (ETL) pipeline was developed on simulated data using data characterization documents and scanning tools. We ran dashboard quality checks, cohort generations, investigated differences between source and mapped data, and refined the ETL accordingly. ResultsWe mapped 1.5 billion rows of data of 5,673,845 individuals. Among these, there were 804,277 pregnancies, 483,585 mothers together with 792,477 children, and 472,948 fathers. We identified 382,516 positive tests for COVID-19 in 380,794 patients. These figures are consistent with results from source data. In addition to 11 million source codes mapped automatically, we mapped 237 non-standard codes to standard concepts and introduced 38 custom concepts to accommodate pregnancy-related terminologies that were not supported by OMOP CDM vocabularies. A total of 3,700/3,705 (99.8%) checks passed. The 5 failed checks could be explained by the nature of the data and only represent a small number of records. Discussion and conclusionNorwegian registry data were successfully harmonized onto OMOP CDM with high level of concordance and provides valuable source for federated COVID-19 related research. Our mapping experience is highly valuable for data partners with Nordic health registries.

Ultralow Power In-Sensor Neuronal Computing with Oscillatory Retinal Neurons for Frequency-Multiplexed, Parallel Machine Vision.

In-sensor and near-sensor computing architectures enable multiply accumulate operations to be carried out directly at the point of sensing. In-sensor architectures offer dramatic power and speed improvements over traditional von Neumann architectures by eliminating multiple analog-to-digital conversions, data storage, and data movement operations. Current in-sensor processing approaches rely on tunable sensors or additional weighting elements to perform linear functions such as multiply accumulate operations as the sensor acquires data. This work implements in-sensor computing with an oscillatory retinal neuron device that converts incident optical signals into voltage oscillations. A computing scheme is introduced based on the frequency shift of coupled oscillators that enables parallel, frequency multiplexed, nonlinear operations on the inputs. An experimentally implemented 3 × 3 focal plane array of coupled neurons shows that functions approximating edge detection, thresholding, and segmentation occur in parallel. An example of inference on handwritten digits from the MNIST database is also experimentally demonstrated with a 3 × 3 array of coupled neurons feeding into a single hidden layer neural network, approximating a liquid-state machine. Finally, the equivalent energy consumption to carry out image processing operations, including peripherals such as the Fourier transform circuits, is projected to be <20 fJ/OP, possibly reaching as low as 15 aJ/OP.

Assessing Cross-Border Telemedicine Data Exchange in the European Union: A Call to Action.

Background: Telemedicine offers potential benefits for health care delivery. However, evidence of cross-border telemedicine data exchange within the European Union (EU) remains limited. The objective of this communication provides a brief outline of the regulatory framework, initiatives, and challenges associated with cross-border telemedicine data exchange in the EU, setting the stage for a comprehensive evidence assessment. Methods: We explore the current regulatory landscape (European Health Data Space), existing initiatives (the European Electronic Health Record Exchange Format), and interoperability challenges (e.g., legal, technical, semantic) facing EU cross-border telemedicine data exchange. Results: There is a need for thorough evidence assessment of cross-border telemedicine and related data movements. Conclusion: Understanding the current landscape of cross-border telemedicine is crucial. This article highlights the need for evidence assessment through a formal review to inform future research and policy initiatives in this domain.

The Antigravity Treadmill as a Postoperative and Injury Rehabilitation Tool: Reduction in Contact Forces and Muscle Activity With Reduced Weight Running.

To investigate the effects of reduced weight running on the antigravity (AG) treadmill on maintenance of normal muscle activation and reduction of plantar forces in healthy subjects. Descriptive laboratory study. Clinical sports medicine center. Twenty healthy subjects (10 male and 10 female) aged 18 to 29 years. Subjects running at 6.5 miles per hour on a standard treadmill and on the AG treadmill at 100%, 90%, 80%, 70%, 60%, and 50% of bodyweight levels. Dynamic plantar loading data were recorded using pressure insoles. Surface electromyography electrodes with imbedded accelerometers were used to estimate timing and magnitude of muscle activity, stride length, and cadence. There was a significant, sequential reduction in peak pressure, maximum force, and force time integral (FTI) with decreasing bodyweight. A 50% bodyweight reduction resulted in a 51% reduction in maximum force and a 59% reduction in FTI in the heel, as compared with 19% to 28% at the metatarsal heads. There was reduced contact area in the heel and midfoot at and below 70% BW. Lower limb muscle activity decreases with reduced bodyweight while maintain normal muscle recruitment timing. The AG treadmill provides a reduction in loading forces while maintaining normal muscle recruitment patterns. Decreased BW running preferentially unloads the hindfoot. The AG treadmill can be an effective rehabilitation tool following foot or ankle injury and may prove superior to other limited weight-bearing methods.