A5042002060- Distributed Control Multi-Agent Systems
- Modular Robots and Swarm Intelligence
- Robotic Path Planning Algorithms
- Model Reduction and Neural Networks
- Optimization and Search Problems
- Radiomics and Machine Learning in Medical Imaging
- Quantum chaos and dynamical systems
- AI in cancer detection
- Advanced Control Systems Optimization
- Robotics and Sensor-Based Localization
- Nonlinear Dynamics and Pattern Formation
- Digital Radiography and Breast Imaging
- Reinforcement Learning in Robotics
- Underwater Vehicles and Communication Systems
- Target Tracking and Data Fusion in Sensor Networks
- Opportunistic and Delay-Tolerant Networks
- Fault Detection and Control Systems
- Simulation Techniques and Applications
- Control Systems and Identification
- MRI in cancer diagnosis
- Gene Regulatory Network Analysis
- Insect Pheromone Research and Control
- Medical Imaging Techniques and Applications
- Energy Efficient Wireless Sensor Networks
- Advanced Manufacturing and Logistics Optimization
University of Pennsylvania
2016-2025
Montclair State University
2021
California University of Pennsylvania
2016-2020
Mechanics' Institute
2020
Drexel University
2008-2017
United States Naval Research Laboratory
2016
Massachusetts General Hospital
2016
The University of Texas MD Anderson Cancer Center
2013-2014
There are currently no proven treatments to reduce the risk of mild cognitive impairment and dementia.To evaluate effect intensive blood pressure control on dementia.Randomized clinical trial conducted at 102 sites in United States Puerto Rico among adults aged 50 years or older with hypertension but without diabetes history stroke. Randomization began November 8, 2010. The was stopped early for benefit its primary outcome (a composite cardiovascular events) all-cause mortality August 20,...
We present a scalable approach to dynamically allocating swarm of homogeneous robots multiple tasks, which are be performed in parallel, following desired distribution. employ decentralized strategy that requires no communication among robots. It is based on the development continuous abstraction obtained by modeling population fractions and defining task allocation problem as selection rates robot ingress egress from each task. These used determine probabilities define stochastic control...
Abstract In this paper, we present an experimental study of strategies for maintaining end‐to‐end communication links tasks such as surveillance, reconnaissance, and target search identification, where team connectivity is required situational awareness. Our main contributions are threefold: (a) We the construction a radio signal strength map that can be used to plan multi‐robot tasks, also serve useful perceptual information. show how nominal model urban environment obtained by aerial...
SUMMARY We address the synthesis of controllers for a swarm robots to generate desired two-dimensional geometric pattern specified by simple closed planar curve with local interactions avoiding collisions or maintaining relative distance constraints. The are decentralized in sense that do not need exchange know each other's state information. Instead, we assume have sensors allowing them obtain information about positions neighbors within known range. establish stability and convergence...
Abstract In this paper, we report on the integration challenges of various component technologies developed toward establishment a framework for deploying an adaptive system heterogeneous robots urban surveillance. our integrated experiment and demonstration, aerial generate maps that are used to design navigation controllers plan missions team. A team ground constructs radio‐signal strength map is as aid planning missions. Multiple establish mobile ad hoc communication network aware between...
OBJECTIVE Type 2 diabetes increases the accumulation of brain white matter hyperintensities and loss tissue. Behavioral interventions to promote weight through dietary changes increased physical activity may delay these adverse consequences. We assessed whether participation in a successful 10-year lifestyle intervention was associated with better profiles structure. RESEARCH DESIGN AND METHODS At enrollment Action for Health Diabetes clinical trial, participants had type diabetes, were...
In this letter, we consider the problem of deriving and incorporating accurate dynamic models for model predictive control (MPC) with an application to quadrotor control. MPC relies on precise achieve desired closed-loop performance. However, presence uncertainties in complex systems environments they operate poses a challenge obtaining sufficiently representations system dynamics. make use deep learning tool, knowledge-based neural ordinary differential equations (KNODE), augment obtained...
Background: Increased breast density is a strong risk factor for cancer and also decreases the sensitivity of mammographic screening. The purpose our study was to compare black white women using quantitative measures. Methods: Breast assessed among 5282 4216 screened digital mammography. Imaging-Reporting Data System (BI-RADS) obtained from radiologists' reports. Quantitative measures dense area, area percent (PD), volume, volume were estimated validated, automated software. categorized as...
We consider the problem of distributing a large group heterogeneous robots among set tasks that require specialized capabilities in order to be completed. model system as community species, which each species (robot type) is defined by traits (capabilities) it owns. In solve distribution problem, we develop centralized well decentralized methods efficiently control swarm robots. Our assume knowledge underlying task topology and are based on continuous defines transition rates from tasks, for...
We present M3ED, the first multi-sensor event camera dataset focused on high-speed dynamic motions in robotics applications. M3ED provides high-quality synchronized and labeled data from multiple platforms, including ground vehicles, legged robots, aerial operating challenging conditions such as driving along off-road trails, navigating through dense forests, performing aggressive flight maneuvers. Our also covers demanding operational scenarios for cameras, scenes with high egomotion...
Nonamnestic Alzheimer disease (AD) variants, including posterior cortical atrophy and the logopenic variant of primary progressive aphasia, differ from amnestic AD in distributions tau aggregates neurodegeneration. We evaluated whether <sup>18</sup>F-flortaucipir (also called <sup>18</sup>F-AV-1451) PET, targeting aggregates, detects these differences, we compared results with MRI measures gray matter (GM) atrophy. <b>Methods:</b> Five subjects atrophy, 4 6 age-matched patients AD, control...
Autonomous surface and underwater vehicles (ASVs AUVs) are increasingly being used for persistent monitoring of ocean phenomena.Typically, these deployed long periods time must operate with limited energy budgets.As a result, there is increased interest in recent years on developing efficient motion plans that leverage the dynamics surrounding flow field.In this paper, we present graph search based method to plan optimal paths field where kinematic actuation constraints captured our cost...
Abstract We analyzed DCE-MR images from 132 women with locally advanced breast cancer the I-SPY1 trial to evaluate changes of intra-tumor heterogeneity for augmenting early prediction pathologic complete response (pCR) and recurrence-free survival (RFS) after neoadjuvant chemotherapy (NAC). Utilizing image registration, voxel-wise including tumor deformations in DCE-MRI kinetic features were computed characterize heterogeneous within tumor. Using five-fold cross-validation, logistic...
Lagrangian coherent structures (LCSs) are separatrices that delineate dynamically distinct regions in general dynamical systems and can be viewed as the extensions of stable unstable manifolds to time-dependent systems. Identifying LCS is useful for many applications, including oceanography weather prediction. In this paper, we present a collaborative robotic control strategy designed track systems, ocean flows. The technique does not require global information about dynamics, based on local...
In this paper, a new control structure is presented to extract maximum power from wind regime. novel approach, discrete-time higher order sliding-mode controller designed as an observer construct the reference value for extractable based on condition that it operates. This possible by tracking optimal tip speed ratio with manipulating voltages of rotor in doubly fed induction generator (DFIG) configuration. The improves performance under abrupt changes and can be used any type optimum active...
The formation of coherent patterns in swarms interacting self-propelled autonomous agents is a subject great interest wide range application areas, ranging from engineering and physics to biology. In this paper, we model experimentally realize mixed-reality large-scale swarm delay-coupled agents. coupling term modeled as delayed communication relay position. Our analyses, assuming communicating over an Erdös-Renyi network, demonstrate the existence stable that can be achieved only with delay...
Autonomous marine vehicles (AMVs) are typically deployed for long periods of time in the ocean to monitor different physical, chemical, and biological processes. Given their limited energy budgets, it makes sense consider motion plans that leverage dynamics surrounding flow field so as minimize usage these vehicles. In this letter, we present a graph-search-based method compute optimal paths AMVs 2-D time-varying flows. The novelty proposed algorithm lies use an adaptive discretization...
Deformable image registration (DIR), aiming to find spatial correspondence between images, is one of the most critical problems in domain medical analysis. In this paper, we present a novel, generic, and accurate diffeomorphic framework that utilizes neural ordinary differential equations (NODEs). We model each voxel as moving particle consider set all voxels 3D high-dimensional dynamical system whose trajectory determines targeted deformation field. Our method leverages deep networks for...
We present an approach for the dynamic assignment and reassignment of a large team homogeneous robotic agents to multiple locations with applications search rescue, reconnaissance exploration missions. Our work is inspired by experimental studies ant house hunting empirical models that predict behavior colony faced choice between candidate nests. design stochastic control policies enable distribute themselves sites in specified ratio. Additionally, we extension our model fast convergence via...
Purpose To evaluate DRAMMS, an attribute‐based deformable registration algorithm, compared to other intensity‐based algorithms, for longitudinal breast MRI registration, and show its applicability in quantifying tumor changes over the course of neoadjuvant chemotherapy. Methods Breast magnetic resonance images from 14 women undergoing chemotherapy were analyzed. The accuracy DRAMMS versus five methods was evaluated based on 2,380 landmarks independently annotated by two experts, entire image...