Joshua Ryan New

Fusion of multi-modality volumetric medical imagery

Ongoing efforts at our laboratory have targeted the development of techniques for fusing medical imagery of various modalities (i.e. MRI, CT, PET, SPECT, etc.) into single image products. Past results have demonstrated the potential for user performance improvements and workload reduction. While these are positive results, a need exists to address the three-dimensional nature of most medical image data sets. In particular, image fusion of three-dimensional imagery (e.g. MRI slices) must account for information content not only within a given slice but also across adjacent slices. In this paper, we describe extensions made to our 2D image fusion system that utilize 3D convolution kernels to determine locally relevant fusion parameters., Representative examples are presented for fusion of MRI and SPECT imagery. We also present these examples in the context of a GUI platform under development aimed at improving user-computer interaction for exploration and mining of medical data.

Calibrating building energy models using supercomputer trained machine learning agents

Building energy modeling (BEM) is an approach to model the energy usage in buildings for design and retrofit purposes. EnergyPlus is the flagship Department of Energy software that performs BEM for different types of buildings. The input to EnergyPlus can often extend in the order of a few thousand parameters that have to be calibrated manually by an expert for realistic energy modeling. This makes it challenging and expensive thereby making BEM unfeasible for smaller projects. In this paper, we describe the ‘Autotune’ research that employs machine learning algorithms to generate agents for the different kinds of standard reference buildings in the US building stock. The parametric space and the variety of building locations and types make this a challenging computational problem necessitating the use of supercomputers. Millions of EnergyPlus simulations are run on supercomputers that are subsequently used to train machine learning algorithms to generate agents. These agents, once created, can then run in a fraction of the time thereby allowing cost‐effective calibration of building models. Published 2014. This article is a US Government work and is in the public domain in the USA.

Provenance in sensor data management

A cohesive, independent solution for bringing provenance to scientific research.

Simulation and big data challenges in tuning building energy models

EnergyPlus is the flagship building energy simulation software used to model whole building energy consumption for residential and commercial establishments. A typical input to the program often has hundreds, sometimes thousands of parameters which are typically tweaked by a buildings expert to “get it right”. This process can sometimes take months. “Autotune” is an ongoing research effort employing machine learning techniques to automate the tuning of the input parameters for an EnergyPlus input description of a building. Even with automation, the computational challenge faced to run the tuning simulation ensemble is daunting and requires the use of supercomputers to make it tractable in time. In this paper, we describe the scope of the problem, particularly the technical challenges faced and overcome, and the software infrastructure developed/in development when taking the EnergyPlus engine, which was primarily designed to run on desktops, and scaling it to run on shared memory supercomputers (Nautilus) and distributed memory supercomputers (Frost and Titan). The parametric simulations produce data in the order of tens to a couple of hundred terabytes. We describe the approaches employed to streamline and reduce bottlenecks in the workflow for this data, which is subsequently being made available for the tuning effort as well as made available publicly for open-science.

Advances in the use of neurophysiologycally-based fusion for visualization and pattern recognition of medical imagery

The ever increasing number of image modaliiies available io dociors for diagnosis purposes has established an imporiani, need io develop techniques ihai suppori work-load reduciion and information maximizaiion. To ihis end, we have improved on an image firsion architeciure jirsi developedfor night vision applicaiions. This iechnique, presenied ai Fusion 2002, uiilizes 30 operaiors io combine volumeiric image seis while maximizing informaiion conieni. In our approach, we have combined ihe use of image fusion and user- dejinedpaiiern recognition wiihin a 30 human-compuier inferface. Here, we present our latest advances iowards enhancing informarion visualization and supporting paiiem recognition. We also report on resulis of applying image firsion across a variety of patient cases. Finally, we have also begun ihe assessmeni of paiiem recognition based on 2D vs. 30 fused image feaiures. Initial results indicaie an advaniage io firsing imagery across all ihree dimensions sa as io take advaniage ofihe volumetric information available in medical daia seis. A description of the system and a number of examples will serve io ilhistraie our ongoing results.

Autonomous correction of sensor data applied to building technologies using filtering methods

Sensor data validity is extremely important in a number of applications, particularly building technologies. An example of this is Oak Ridge National Laboratorys ZEBRAlliance research project, which consists of four single-family homes located in Oak Ridge, TN. The homes are outfitted with a total of 1,218 sensors to determine the performance of a variety of different technologies integrated within each home. Issues arise with such a large amount of sensors, such as missing or corrupt data. This paper aims to eliminate these problems using: (1) Kalman filtering and (2) linear predictive coding (LPC) techniques. Simulations show the Kalman filtering method performed best in predicting temperature, humidity, pressure, and airflow data, while the LPC method performed best with energy consumption data.

Estimating building simulation parameters via Bayesian structure learning

Many key building design policies are made using sophisticated computer simulations such as EnergyPlus (E+), the DOE flagship whole-building energy simulation engine. E+ and other sophisticated computer simulations have several major problems. The two main issues are 1) gaps between the simulation model and the actual structure, and 2) limitations of the modeling engines capabilities. Currently, these problems are addressed by having an engineer manually calibrate simulation parameters to real world data or using algorithmic optimization methods to adjust the building parameters. However, some simulations engines, like E+, are computationally expensive, which makes repeatedly evaluating the simulation engine costly. This work explores addressing this issue by automatically discovering the simulations internal input and output dependencies from ~20 Gigabytes of E+ simulation data, future extensions will use ~200 Terabytes of E+ simulation data. The model is validated by inferring building parameters for E+ simulations with ground truth building parameters. Our results indicate that the model accurately represents parameter means with some deviation from the means, but does not support inferring parameter values that exist on the distributions tail.

A Comparison of Simulation Capabilities for Ducts

Reports produced before January 1, 1996, may be purchased by members of the public from the following source. Reports are available to DOE employees, DOE contractors, Energy Technology Data Exchange (ETDE) representatives, and International Nuclear Information System (INIS) representatives from the following source. Government nor any agency thereof, nor any of their employees, makes any warranty, express or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise, does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof. Figure 1. Comparison of energy impacts of 4% leaky ducts in an attic with a sealed floor versus 10%, and 20% leaky ducts in attic space without a sealed floor,. ABSTRACT Typically, the cheapest way to install a central air conditioning system in residential buildings is to place the ductwork in the attic. Energy losses due to duct-attic interactions can be great, but current whole-house models are unable to capture the dynamic multi-mode physics of the interactions. The building industry is notoriously fragmented and unable to devote adequate research resources to solve this problem. Builders are going to continue to put ducts in the attic because floor space is too expensive to closet them within living space, and there are both construction and aesthetic issues with other approaches such as dropped ceilings. Thus, there is a substantial need to publicly document duct losses and the cost of energy used by ducts in attics so that practitioners, builders, homeowners and state and federal code officials can make informed decisions leading to changes in new construction and additional retrofit actions. Thus, the goal of this study is to conduct a comparison of AtticSim and EnergyPlus simulation algorithms to identify specific features for potential inclusion in EnergyPlus that would allow higher-fidelity modeling of HVAC operation and duct transport of conditioned air. It is anticipated that the resulting analysis from these simulation tools will inform energy decisions relating to the role of ducts in future building energy codes and standards.

In-Depth Analysis of Simulation Engine Codes for Comparison with DOE s Roof Savings Calculator and Measured Data

...................................................................................................................................................... vii

EnergyPlus Air Source Integrated Heat Pump Model

This report summarizes the development of the EnergyPlus air-source integrated heat pump model. It introduces its physics, sub-models, working modes, and control logic. In addition, inputs and outputs of the new model are described, and input data file (IDF) examples are given.