Search NASA⌕ Search

SEARCH · Search NASA

Results for “algorithm selection”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,693 records · Page 94

A molecular line scan in the Hubble deep field north

We present a molecular line scan in the Hubble Deep Field North (HDF-N) that covers the entire 3 mm window (79-115 GHz) using the IRAM Plateau de Bure Interferometer. Our CO redshift coverage spans z ≲ 0.45, 1 ≲ z ≲ 1.9 and all z ≳ 2. We reach a CO detection limit that is deep enough to detect essentially all z > 1 CO lines reported in the literature so far. We have developed and applied different line-searching algorithms, resulting in the discovery of 17 line candidates. We estimate that the rate of false positive line detections is ∼2/17. We identify optical/NIR counterparts from the deep ancillary database of the HDF-N for seven of these candidates and investigate their available spectral energy distributions. Two secure CO detections in our scan are identified with star-forming galaxies at z = 1.784 and at z = 2.047. These galaxies have colors consistent with the 'BzK' color selection and they show relatively bright CO emission compared with galaxies of similar dust continuum luminosity. We also detect two spectral lines in the submillimeter galaxy HDF 850.1 at z = 5.183. We consider an additional nine line candidates as high quality. Our observations also provide a deep 3 mm continuum map (1σ noise level = 8.6 μJy beam{sup –1}). Via a stacking approach, we find that optical/MIR bright galaxies contribute only to <50% of the star formation rate density at 1 < z < 3, unless high dust temperatures are invoked. The present study represents a first, fundamental step toward an unbiased census of molecular gas in 'normal' galaxies at high-z, a crucial goal of extragalactic astronomy in the ALMA era.

79 ASTRONOMY AND ASTROPHYSICS↗

Network reconfiguration and distributed energy resource scheduling for improved distribution system resilience

Electric utility companies work to restore as much load as possible after power outages caused by extreme weather events. In this paper, an outage management strategy is proposed to enhance distribution system resilience through network reconfiguration and distributed energy resources (DERs) scheduling. After a line fault, the proposed algorithm can identify radial network topology based on the rank of the incidence matrix. The reconfiguration is implemented by switching tie lines and sectionalizing lines. With the new network topology, an optimal DER scheduling problem is solved to minimize the accumulative cost for dispatchable DER operation and load reduction. Finally, the optimal topology that minimizes the accumulative cost is selected from all radial topologies. The computational workload is relatively low because only linear programming needs to be solved. Using the case studies of the IEEE 69-bus and IEEE 123-bus systems, we consider the worst-case scenarios in which faults occur in the upstream feeder. The simulation results demonstrate that the proposed strategy allows for a relatively high percentage of the load to remain in service after line faults. Furthermore, compared with microgrid-formation approaches, the proposed strategy has advantages when applied to the distribution systems with several normally-open tie lines and low DER penetration.

42 ENGINEERING↗

Passive gamma analysis of the boiling-water-reactor assemblies

This research focused on the analysis of a set of stationary passive gamma measurements taken on the spent nuclear fuel assemblies from a boiling water reactor (BWR) using pulse height analysis data acquisition. The measurements were performed on 25 different BWR assemblies in 2014 at Sweden’s Central Interim Storage Facility for Spent Nuclear Fuel (Clab). This study was performed as part of the Next Generation of Safeguards Initiative–Spent Fuel project to research the application of nondestructive assay (NDA) to spent fuel assemblies. The NGSI–SF team is working to achieve the following technical goals more easily and efficiently than in the past using nondestructive assay (NDA) measurements of spent fuel assemblies: (1) verify the initial enrichment, burnup, and cooling time of facility declaration; (2) detect the diversion or replacement of pins, (3) estimate the plutonium mass, (4) estimate the decay heat, and (5) determine the reactivity of spent fuel assemblies. The final objective of this project is to quantify the capability of several integrated NDA instruments to meet the aforementioned goals using the combined signatures of neutrons, gamma rays, and heat. This report presents a selection of the measured data and summarizes an analysis of the results. Specifically, trends in the count rates measured for spectral lines from the following isotopes were analyzed as a function of the declared burnup and cooling time: 137 Cs, 154 Eu, 134Cs, and to a lesser extent, 106 Ru and 144 Ce. From these measured count rates, predictive algorithms were developed to enable the estimation of the burnup and cooling time. Furthermore, these algorithms were benchmarked on a set of assemblies not included in the standard assemblies set used by this research team.

21 SPECIFIC NUCLEAR REACTORS AND ASSOCIATED PLANTS↗

Off-Stoichiometric Restructuring and Sliding Dynamics of Hexagonal Boron Nitride Edges in Conditions of Oxidative Dehydrogenation of Propane

Boron-containing materials, such as hexagonal boron nitride (h-BN), recently shown to be active and selective catalysts for the oxidative dehydrogenation of propane (ODHP), have been shown to undergo significant surface oxyfunctionalization and restructuring. Although experimental ex situ studies have probed the change in chemical environment on the surface, the structural evolution of it under varying reaction conditions has not been established. Herein, we perform global optimization structure search with a grand canonical genetic algorithm to explore the chemical space of off-stoichiometric restructuring of the h-BN surface under ambient as well as ODHP-relevant conditions. A grand canonical ensemble representation of the surface is established, and the predicted 11B solid-state NMR spectra are consistent with previous experimental reports. In addition, we investigated the relative sliding of h-BN sheets and how it influences the surface chemistry with ab initio molecular dynamics simulations. Furthermore, the B–O linkages on the edges are found to be significantly strained during the sliding, causing the metastable sliding configurations to have higher reactivity toward the activation of propane and water.

37 INORGANIC, ORGANIC, PHYSICAL, AND ANALYTICAL CH↗

Verification and validation of developed short-term forecasting models

Recent advancements in machine learning (ML) and artificial intelligence (AI) technologies provide an opportunity for leveraging data-driven algorithms to predict future nuclear power plant (NPP) operating conditions by using recorded plant process data. Successfully implementing these models can lead to cost-reducing, conditioned-based predictive maintenance through optimized maintenance schedules and a reduction of unnecessary maintenance activities. This report discusses the verification and validation of short-term forecasting processes (i.e., data cleaning, feature selection, model optimization, and forecasting) developed in previous reports. The verification and validation (V&V) process demonstrates the expected precision and accuracy when the ML model encounters new datasets from different systems. Shapley additive explanations were used as the primary means of feature selection across these different data set. Individual models were trained for each data set, then validated through a cross-validation procedure. In this report, two different ML models were tasked to predict variables from three different plant process data sets with varying prediction horizons. The results indicate that support vector regression (SVR) outperformed long short-term memory (LSTM) neural networks in regard to each data set and each prediction horizon in this study, but further tuning and optimization could improve long short-term memory results. However, each forecasting model showed reduced performance as the prediction horizon was extended from 1 hour to 1 day ahead. Research is ongoing to evaluate the optimal input variable space, which is based on a given set of process parameters, to further improve forecasting accuracy.

46 INSTRUMENTATION RELATED TO NUCLEAR SCIENCE AND ↗

Fuel Efficient Speed Optimization for Real-World Highway Cruising

This paper introduces an eco-driving highway cruising algorithm based on optimal control theory that is applied to a conventionally-powered connected and automated vehicle. Thanks to connectivity to the cloud and/or to infrastructure, speed limit and slope along the future route can be known with accuracy. This can in turn be used to compute the control variable trajectory that will minimize energy consumption without significantly impacting travel time. Automated driving is necessary to the implementation of this concept, because the chosen control variables (e.g., torque and gear) impact vehicle speed. An optimal control problem is built up where quadratic models are used for the powertrain. The optimization is solved by applying Pontryagin’s minimum principle, which reduces the problem to the minimization of a cost function with parameters called co-states. The proposed algorithm assumes piecewise constant slopes and speed limits, and it solves the transition vehicle speeds for each junction of such segments. In addition, a method to extract route information from digital maps is presented, which complies with the proposed optimization algorithm. The algorithms are evaluated in simulation, using Autonomie, a simulation tool for vehicle energy consumption modeling. The optimal control trajectory (e.g., torque, gear) is first computed offline. It is then applied in an open-loop fashion in online simulation, using a forward-looking model of the vehicle in Autonomie. Simulation results show over 8% fuel saving for two selected real-world routes.

Simulation and modeling, Optimization, Vehicle net↗

A priori analysis on deep learning of subgrid-scale parameterizations for Kraichnan turbulence

In the present study, we investigate different data-driven parameterizations for large eddy simulation of two-dimensional turbulence in the a priori settings. These models utilize resolved flow field variables on the coarser grid to estimate the subgrid-scale stresses. We use data-driven closure models based on localized learning that employs a multilayer feedforward artificial neural network with point-to-point mapping and neighboring stencil data mapping, and convolutional neural network fed by data snapshots of the whole domain. The performance of these data-driven closure models is measured through a probability density function and is compared with the dynamic Smagorinksy model (DSM). The quantitative performance is evaluated using the cross-correlation coefficient between the true and predicted stresses. We analyze different frameworks in terms of the amount of training data, selection of input and output features, their characteristics in modeling with accuracy, and training and deployment computational time. We also demonstrate computational gain that can be achieved using the intelligent eddy viscosity model that learns eddy viscosity computed by the DSM instead of subgrid-scale stresses. Here, we detail the hyperparameters optimization of these models using the grid search algorithm.

42 ENGINEERING↗

Impact of graph structures for QAOA on MaxCut

The quantum approximate optimization algorithm (QAOA) is a promising method of solving combinatorial optimization problems using quantum computing. QAOA on the MaxCut problem has been studied extensively on graphs with specific structure; however, little is known about the general performance of the algorithm on arbitrary graphs. Here, we investigate how different graph characteristics correlate with QAOA performance at depths at most three on the MaxCut problem for all connected non-isomorphic graphs with at most eight vertices. Some good predictors of QAOA success relate to graph symmetries, odd cycles, and density. For example, on eight vertex graphs, the average probability for selecting an optimal solution for graphs that contain no odd cycles after three iterations of QAOA is 60.6% compared to 48.2% for those that do. The data generated from these studies are shared in a publicly accessible database to serve as a benchmark for QAOA calculations and experiments. Knowing the relationship between structure and performance can be used to identify classes of combinatorial problems that are likely to exhibit a quantum advantage.

97 MATHEMATICS AND COMPUTING↗

State-of-the-art on research and applications of machine learning in the building life cycle

Fueled by big data, powerful and affordable computing resources, and advanced algorithms, machine learning has been explored and applied to buildings research for the past decades and has demonstrated its potential to enhance building performance. This study systematically surveyed how machine learning has been applied at different stages of building life cycle. By conducting a literature search on the Web of Knowledge platform, we found 9579 papers in this field and selected 153 papers for an in-depth review. The number of published papers is increasing year by year, with a focus on building design, operation, and control. However, no study was found using machine learning in building commissioning. There are successful pilot studies on fault detection and diagnosis of HVAC equipment and systems, load prediction, energy baseline estimate, load shape clustering, occupancy prediction, and learning occupant behaviors and energy use patterns. None of the existing studies were adopted broadly by the building industry, due to common challenges including (1) lack of large scale labeled data to train and validate the model, (2) lack of model transferability, which limits a model trained with one data-rich building to be used in another building with limited data, (3) lack of strong justification of costs and benefits of deploying machine learning, and (4) the performance might not be reliable and robust for the stated goals, as the method might work for some buildings but could not be generalized to others. Finally, findings from the study can inform future machine learning research to improve occupant comfort, energy efficiency, demand flexibility, and resilience of buildings, as well as to inspire young researchers in the field to explore multidisciplinary approaches that integrate building science, computing science, data science, and social science.

32 ENERGY CONSERVATION, CONSUMPTION, AND UTILIZATI↗

Towards operational atmospheric correction of airborne hyperspectral imaging spectroscopy: Algorithm evaluation, key parameter analysis, and machine learning emulators

Atmospheric correction of airborne hyperspectral imaging spectroscopy (AHIS) to obtain high-quality surface reflectance is the prerequisite for remote sensing applications. Over the last decades, different atmospheric correction methods have been developed based on radiative transfer models (RTMs), however, the relative performances of different algorithms are unclear. Automated operational atmospheric correction methods to process large-volume AHIS data in a high-accurate and high-throughput manner are still lacking. Therefore, this study proposed an operational atmospheric correction pipeline for deriving surface reflectance from AHIS data. To ensure the accuracy and efficiency of the pipeline, we focused on three specific aspects: (1) selecting a suitable RTM for the development of atmospheric lookup tables (LUTs) by comparing the commercial MODerate resolution atmospheric TRANsmission (MODTRAN) and open-sourced Library for Radiative TRANsfer (LibRadTRAN) models, where the widely-used software, Atmospheric/Topographic Correction for Airborne Imagery (ATCOR), was used as benchmarks; (2) identifying key atmospheric correction parameters and determining suitable sources for parameter retrievals including AHIS, Moderate Resolution Imaging Spectroradiometer (MODIS), and AErosol RObotic NETwork (AERONET); and (3) testing the performance of using machine learning emulators to speed up the RTM-based atmospheric correction. Results indicate that (1) atmospheric correction based on MODTRAN LUTs can produce surface reflectance accurately with mean absolute errors < 0.05 and cosine similarities > 0.98 compared to field measurements, which is comparable to the software ATCOR and slightly outperforms the LibRadTRAN LUTs; (2) sobol global sensitivity analysis demonstrates that in the atmospheric correction, visibility and water vapor are two key parameters that can be accurately derived from AHIS in contrast to MODIS or AERONET data; and (3) Random Forest emulators can produce accurate estimations of surface reflectance with mean absolute errors < 0.03 and cosine similarities > 0.98 for higher processing efficiency and determine a suitable set of wavelengths for retrieving atmospheric visibility and water vapor. In conclusion, the proposed atmospheric correction pipeline also improved the four-stream radiative transfer theory for airborne applications by considering adjacent effects from airborne surrounding pixels and can also be applied for atmospheric correction of hyperspectral data from spaceborne missions.

47 OTHER INSTRUMENTATION↗

Analysis of plasma-modes of a gated bilayer system in high electron mobility transistors

We present rigorous analytical and computational models to study the plasma-waves in a gated-bilayer system present in a double-channel high electron mobility transistor. By analytically deriving the dispersion relations, we have identified the optical and acoustic modes in such systems. We find that the presence of the metal gate selectively modifies the optical plasmons of an ungated-bilayer, while the acoustic plasmons remain largely unchanged. Analysis shows that these modified optical plasmons could be advantageous for resonant and non-resonant plasma-wave devices. The paper further serves to verify our analytical formulae using a full-wave hydrodynamic numerical solver, based on finite difference time domain algorithm. Using the solver, we examine these modes in the gated/ungated bilayers under a plane wave excitation. We observe that, most incident power couples to the optical mode for such an excitation. Nevertheless, acoustic modes can also be excited, if the discontinuity dimensions are optimized accordingly. These observations are also explained using 2D field-plots for the first time, thus providing intuitive understanding of the plasmon excitation in the bilayers.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

SU-E-J-114: A Practical Hybrid Method for Improving the Quality of CT-CBCT Deformable Image Registration for Head and Neck Radiotherapy

Purpose: Accurate deformable image registration (DIR) between CT and CBCT in H&N is challenging. In this study, we propose a practical hybrid method that uses not only the pixel intensities but also organ physical properties, structure volume of interest (VOI), and interactive local registrations. Methods: Five oropharyngeal cancer patients were selected retrospectively. For each patient, the planning CT was registered to the last fraction CBCT, where the anatomy difference was largest. A three step registration strategy was tested; Step1) DIR using pixel intensity only, Step2) DIR with additional use of structure VOI and rigidity penalty, and Step3) interactive local correction. For Step1, a public-domain open-source DIR algorithm was used (cubic B-spline, mutual information, steepest gradient optimization, and 4-level multi-resolution). For Step2, rigidity penalty was applied on bony anatomies and brain, and a structure VOI was used to handle the body truncation such as the shoulder cut-off on CBCT. Finally, in Step3, the registrations were reviewed on our in-house developed software and the erroneous areas were corrected via a local registration using level-set motion algorithm. Results: After Step1, there were considerable amount of registration errors in soft tissues and unrealistic stretching in the posterior to the neck and near the shoulder due to body truncation. The brain was also found deformed to a measurable extent near the superior border of CBCT. Such errors could be effectively removed by using a structure VOI and rigidity penalty. The rest of the local soft tissue error could be corrected using the interactive software tool. The estimated interactive correction time was approximately 5 minutes. Conclusion: The DIR using only the image pixel intensity was vulnerable to noise and body truncation. A corrective action was inevitable to achieve good quality of registrations. We found the proposed three-step hybrid method efficient and practical for CT/CBCT registrations in H&N. My department receives grant support from Industrial partners: (a) Varian Medical Systems, Palo Alto, CA, and (b) Philips HealthCare, Best, Netherlands.

60 APPLIED LIFE SCIENCES↗

SU-E-T-513: Investigating Dose of Internal Target Volume After Correcting for Tissue Heterogeneity in SBRT Lung Plans with Homogeneity Calculation

Purpose It was recommended to use the prescription of 54 Gy/3 with heterogeneity corrections for previously established dose scheme of 60 Gy/3 with homogeneity calculation. This study is to investigate dose coverage for the internal target volume (ITV) with and without heterogeneity correction. Methods Thirty patients who received stereotactic body radiotherapy (SBRT) to a dose of 60 Gy in 3 fractions with homogeneous planning for early stage non-small-cell lung cancer (NSCLC) were selected. ITV was created either from 4DCT scans or a fusion of multi-phase respiratory scans. Planning target volume (PTV) was a 5 mm expansion of the ITV. For this study, we recalculated homogeneous clinical plans using heterogeneity corrections with monitor units set as clinically delivered. All plans were calculated with 3 mm dose grids and collapsed cone convolution algorithm. To account for uncertainties from tumor delineation and image-guided radiotherapy, a structure ITV2mm was created by expanding ITV with 2 mm margins. Dose coverage to the PTV, ITV and ITV2mm were compared with a student paired t-test. Results With heterogeneity corrections, the PTV V60Gy decreased by 10.1% ± 18.4% (p<0.01) while the maximum dose to the PTV increased by 3.7 ± 4.3% (p<0.01). With and without corrections, D99% was 65.8 ± 4.0 Gy and 66.7 ± 4.8 Gy (p=0.15) for the ITV, and 63.9 ± 3.4 Gy and 62.9 ± 4.6 Gy for the ITV2mm (p=0.22), respectively. The mean dose to the ITV and ITV2mm increased 3.6% ± 4.7% (p<0.01) and 2.3% ± 5.2% (p=0.01) with heterogeneity corrections. Conclusion After heterogeneity correction, the peripheral coverage of the PTV decreased to approximately 54 Gy, but D99% of the ITV and ITV2mm was unchanged and the mean dose to the ITV and ITV2mm was increased. Clinical implication of these results requires more investigation.

60 APPLIED LIFE SCIENCES↗

MarmotViz

MarmotViz is an illustrative visualization plug-in for ParaView. It enables users to identify and track time-varying features in simulation datasets. It permits the application of illustrative visualization effects to these features including: selective visualization, feature coloring, boundary smoothing, haloing, silhouette outlining, speedlines, and strobe silhouettes. These techniques serve to assist in exploration and interpretation of simulation data and can be used to generate enhanced renderings for presentation. The MarmotViz plug-in is developed as a flexible framework, and can be easily extended to incorporate new region-of-interest (ROI) identification algorithms, feature matching and tracking algorithms, and illustrative visualization effects.

Rattner, Alexander↗

Differentially Private Map Matching (DPMM) v1.0

Human mobility trajectories provide valuable information for developing mobility applications, as they contain diverse and rich information about the users. User mobility data is valuable for various applications such as intelligent transportation systems (ITS), commercial business models, and disease-spread models. However, such spatio-temporal traces may pose a threat to user privacy. GPS trajectories in their raw form are not suitable for transportation studies, as they require matching locations with nearest road links — a process called map-matching. This software implements a differential privacy (DP)-based map-matching algorithm, called DPMM, that generates link-level location trajectories in a privacy-preserving manner to protect users' origin destinations (OD) and travel paths. OD privacy is achieved by injecting Planar Laplace noise to the user OD GPS points. Travel-path privacy is provided with randomized travel path construction using exponential DP mechanism. The injected noise level is selected adaptively, by considering the link density of the location and the functional category of the localized links. For path privacy, our mechanism samples waypoints and selects candidate paths between waypoints. DPMM provides privacy effectively with respect to link density instead of other trajectory samples in the database compared to other privacy mechanisms. Compared to the different baseline models our DP-based privacy model offers closer query responses to the raw data in terms of individual and aggregate trajectory-level statistics with an average at absolute deviation from the baseline for individual statistics on ϵ = 1.0. Beyond individual trajectory statistics, the DPMM outperforms the other benchmark DP-based mechanisms on different aggregate statistics with up to 8x improvement in utility.

Peisert, Sean [Lawrence Berkeley National Laborato↗

Flexible silicon photonic architecture for accelerating distributed deep learning

The increasing size and complexity of deep learning (DL) models have led to the wide adoption of distributed training methods in datacenters (DCs) and high-performance computing (HPC) systems. However, communication among distributed computing units (CUs) has emerged as a major bottleneck in the training process. In this study, we propose Flex-SiPAC, a flexible silicon photonic accelerated compute cluster designed to accelerate multi-tenant distributed DL training workloads. Flex-SiPAC takes a co-design approach that combines a silicon photonic hardware platform with a tailored collective algorithm, optimized to leverage the unique physical properties of the architecture. The hardware platform integrates a novel wavelength-reconfigurable transceiver design and a micro-resonator-based wavelength-reconfigurable switch, enabling the system to achieve flexible bandwidth steering in the wavelength domain. The collective algorithm is designed to support reconfigurable topologies, enabling efficient all-reduce communications that are commonly used in DL training. The feasibility of the Flex-SiPAC architecture is demonstrated through two testbed experiments. First, an optical testbed experiment demonstrates the flexible routing of wavelengths by shuffling an array of input wavelengths using a custom-designed spatial-wavelength selective switch. Second, a four-GPU testbed running two DL workloads shows a 23% improvement in job completion time compared to a similarly sized leaf-spine topology. We further evaluate Flex-SiPAC using large-scale simulations, which show that Flex-SiPAC is able to reduce the communication time by 26% to 29% compared to state-of-the-art compute clusters under representative collective operations.

Wu, Zhenguo (ORCID:0000000322847985)↗

SITCOMTN-162: Testing the implementation of Metadetection and Cell-Based Coadds on Abell 360 LSSTComCam data

The purpose of this technote is to test the technical quality of LSSTComCam commissioning data, specifically the Rubin_SV_38_7 field, by utilizing cell-based coadds and Metadetection by measuring the tangential and cross weak lensing shear profiles of the massive cluster Abell 360 (called A360 throughout the technote). The process entails generating the cell-based coadds for Metadetection to run on, identifying and removing cluster member galaxies, applying quality cuts, calibrating the shear measurements, and validation. Cell-based coadds and Metadetection are both currently in the process of being implemented within the LSST Science Pipelines at the time of this technote. There is substantial technical value in attempting a difficult measurement prior to full implementation. Measuring the tangential shear around A360 will showcase the current abilities of these algorithms, as well as highlight where work is still needed. As seen from the resulting shear profile of A360, the cell-based coadds and Metadetection are able to work in tandem to produce a shear catalog and resulting reduced shear profile. This technote is one part of a series studying A360 in order to both stress test the commissioning camera and demonstrate the technical capabilities of the Vera Rubin Observatory. We study the quality of the PSF modeling and impact it can have on cluster WL in [Combet et al., 2025], implementation of cell-based coadds and subsequent use for Metadetect [Sheldon et al., 2023] in this technote, photometric calibration in (in prep), source selection and photometric redshifts in [Adari et al., 2025], use of Anacal [Li et al., 2024] to produce a cluster shear profile in [Li et al., 2025], and background subtraction in this field and Fornax in [Zhou et al., 2025].

79 ASTRONOMY AND ASTROPHYSICS↗

MO-F-CAMPUS-J-02: Automatic Recognition of Patient Treatment Site in Portal Images Using Machine Learning

Purpose: To investigate the method to automatically recognize the treatment site in the X-Ray portal images. It could be useful to detect potential treatment errors, and to provide guidance to sequential tasks, e.g. automatically verify the patient daily setup. Methods: The portal images were exported from MOSAIQ as DICOM files, and were 1) processed with a threshold based intensity transformation algorithm to enhance contrast, and 2) where then down-sampled (from 1024×768 to 128×96) by using bi-cubic interpolation algorithm. An appearance-based vector space model (VSM) was used to rearrange the images into vectors. A principal component analysis (PCA) method was used to reduce the vector dimensions. A multi-class support vector machine (SVM), with radial basis function kernel, was used to build the treatment site recognition models. These models were then used to recognize the treatment sites in the portal image. Portal images of 120 patients were included in the study. The images were selected to cover six treatment sites: brain, head and neck, breast, lung, abdomen and pelvis. Each site had images of the twenty patients. Cross-validation experiments were performed to evaluate the performance. Results: MATLAB image processing Toolbox and scikit-learn (a machine learning library in python) were used to implement the proposed method. The average accuracies using the AP and RT images separately were 95% and 94% respectively. The average accuracy using AP and RT images together was 98%. Computation time was ∼0.16 seconds per patient with AP or RT image, ∼0.33 seconds per patient with both of AP and RT images. Conclusion: The proposed method of treatment site recognition is efficient and accurate. It is not sensitive to the differences of image intensity, size and positions of patients in the portal images. It could be useful for the patient safety assurance. The work was partially supported by a research grant from Varian Medical System.

60 APPLIED LIFE SCIENCES↗