Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Objectives”

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 127 records · Page 7

An Object-Oriented Interface to the CCSDS Ground Telecommand Services

The Telecommand Data Routing and Channel Services defined by the Consultative Committee for Space Data Systems (CCSDS) are flexible enough to support a myriad of commanding models. Because the standard is so broad, the traditional approach has been to implement only the portion of the standard needed by the particular spacecraft being tested/operated. Tasked with providing Telecommand Services for an entire class of spacecraft, where each spacecraft may choose any valid CCSDS commanding model, NASA Code 584 designed a common architecture capable of handling the full CCSDS protocol. The solution uses another CCSDS standard - the Standard Formatted Data Unit (SFDU) as the interface to the Telecommand Services. SFDUs provide a consistent way of labelling data objects, as well as allowing data objects to encapsulate other data objects. The resulting interface is: - Flexible: The full Data Routing and Channel Services are available via a single interface. The client (i.e. the command source) may enter commands at any layer within the protocol stack, specify any of the data aggregation or segmentation methods, and dynamically set any configuration parameter defined in the standard. - Object-oriented: Each object specifies both the data and the actions to be performed with the data. An object may contain other objects. - Expandable: New capabilities are added by defining new objects. Objects pass thru the protocol layers until they reach the applicable layer. The resulting design is: - Modular: The logic for each protocol layer is contained in a separate Application Program Interface (API). The objects used for the external interface are also used for communication between layers. - Distributable: The design can be split along any layer boundary for distribution across multiple machines. The objects ensure data consistency across platforms. This paper describes the SFDU-based interface and the resulting protocol implementation. The implementation is currently used by NASA (National Aeronautics and Space Administration) for integration & test of the microwave Anisotropy Probe (MAP) and Earth observer-I (EO-l) spacecraft. It will be used for post-launch operations of these spacecraft as well as the Imager for Magnetopause to Aurora Global Exploration (IMAGE) spacecraft.

Ray, Timothy Joseph↗

Using Machine Learning to Track Objects Across Cameras

Video surveillance is one of the most important technologies used by the International Atomic Energy Agency in international safeguards. At large, complicated facilities, multiple surveillance cameras are deployed to monitor the transfer of safeguards-relevant objects across the site. During inspections, all surveillance videos are reviewed to ensure the objects are not manipulated or diverted during transfer, a laborious, time-consuming task. This work describes using deep machine learning algorithms to track objects automatically across multiple cameras, greatly improving the efficiency of the review process. The fundamental problem in this object tracking task across multiple cameras is how to associate the same object, which may show extreme intra-class variations, such as viewpoints, occlusions, and various scales, in different and even non-overlapped cameras. Object re-identification (Re-ID) in nuclear facility video surveillance is even more challenging than classic person or vehicle Re-ID problems because different instances in the same category may display an identical appearance. One observation from nuclear facility surveillance videos is that all objects must be carted (e.g., via forklift) to move. Therefore, the spatial context information of an object, which provides the feature from the carrier, is critical for the object Re-ID task. This work proposes a two-stream convolutional neural networks model that takes features of objects and their surrounding regions into account. Moreover, the custom videos usually are gleaned from different scenes from the training data, which may have extreme variations in illumination changes and/or cluttered backgrounds. Directly applying the trained model to custom videos will dramatically decrease the performance. To tackle this problem, an advanced domain adaptation technique is proposed to mitigate the gap between the data taken from different scenes. The proposed framework will track objects of interest across a nuclear complex. The resulting tracks can be used in further analyses, such as event/activity recognition, anomaly detection, etc.

98 NUCLEAR DISARMAMENT, SAFEGUARDS, AND PHYSICAL P↗

Object sense and avoid system for autonomous vehicles

A system for determining a travel path for an autonomous vehicle (“AV”) to travel to a target while avoiding objects (i.e., obstacles) without the use of an imaging system is provided. An object sense and avoid (“OSA”) system detects objects in an object field that is adjacent to the AV and dynamically generates, as the AV travels, a travel path to the target to avoid the objects. The OSA system repeatedly uses sensors to collect sensor data of any objects in the object field. An object detection system then detects the objects and determines their locations based on triangulating ranges to an object as indicated by different sensors. The path planner system then plans a next travel direction for the AV to avoid the detected objects while seeking to minimize the distance traveled. The OSA system then instructs the AV to travel in the travel direction.

Beer, N. Reginald↗

Herbig-haro objects and mid-infrared outflows in the VELA C molecular cloud

We have performed a deep [S II] λλ6717/6731 wide field Herbig-Haro (HH) object survey toward the Vela C molecular cloud with a sky coverage of about 2 deg{sup 2}. In total, 18 new HH objects, HH 1090-1107, are discovered and the two previously known HH objects, HH 73-74, are also detected in our [S II] images. We also present an investigation of mid-infrared outflows in the Vela C molecular cloud using the Wide-field Infrared Survey Explorer images taken from AllWISE data release. Using the method suggested by Zhang and Wang, 11 extended green objects (EGOs) are identified to be the mid-infrared outflows, including 6 new mid-infrared outflows that have not been detected previously at other wavelengths and 5 mid-infrared counterparts of the HH objects detected in this work. Using the AllWISE Source Catalog and the source classification scheme suggested by Koenig et al., we have identified 56 young stellar object (YSO) candidates in the Vela C molecular cloud. The possible driving sources of the HH objects and EGOs are discussed based on the morphology of HH objects and EGOs and the locations of HH objects, EGOs and YSO candidates. Finally we associate 12 HH objects and 5 EGOs with 10 YSOs and YSO candidates. The median length of the outflows in Vela C is 0.35 pc and the outflows seem to be oriented randomly.

79 ASTRONOMY AND ASTROPHYSICS↗

Modeling Buried Object Brightness and Visibility for Ground Penetrating Radar

Comparing the observed brightness of various buried objects is a straightforward way to characterize the performance of a ground penetrating radar (GPR) system. However, a limitation arises. A simple comparison of buried object brightness values does not disentangle the effects of the GPR system itself from the system's operating environment and the objects being observed. Therefore, with brightness values exhibiting an unknown synthesis of systemic, environmental, and object factors, GPR system analysis becomes a convoluted affair. In this work, we use an experimentally collected dataset of over 25,000 object observations from five different multistatic radar arrays to develop models of buried object brightness and control for these various effects. Additionally, our modeling efforts provide a means for quantifying the relative brightness of GPR systems, the objects they detect, and the physical properties of those objects that influence observed brightness. To evaluate the models' performance on new object observations, we repeatedly simulate fitting them to half the dataset and predicting the observed brightness values of the unseen half. In addition, we introduce a method for estimating the probability that individual observations constitute a visible object, which aids in failure analysis, performance characterization, and dataset cleaning.

97 MATHEMATICS AND COMPUTING↗

SLOAN DIGITAL SKY SURVEY OBSERVATIONS OF KUIPER BELT OBJECTS: COLORS AND VARIABILITY

Colors of trans-Neptunian objects (TNOs) are used to study the evolutionary processes of bodies in the outskirts of the solar system and to test theories regarding their origin. Here I describe a search for serendipitous Sloan Digital Sky Survey (SDSS) observations of known TNOs and Centaurs. I present a catalog of SDSS photometry, colors, and astrometry of 388 measurements of 42 outer solar system objects. I find weak evidence, at the Almost-Equal-To 2{sigma} level (per trial), for a correlation between the g - r color and inclination of scattered disk objects and hot classical Kuiper Belt objects. I find a correlation between the g - r color and the angular momentum in the z direction of all the objects in this sample. These findings should be verified using larger samples of TNOs. Light curves as a function of phase angle are constructed for 13 objects. The steepness of the slopes of these light curves suggests that the coherent backscatter mechanism plays a major role in the reflectivity of outer solar system small objects at small phase angles. I find weak evidence for an anticorrelation, significant at the 2{sigma} confidence level (per trial), between the g-band phase-angle slope parameter and the semimajor axis, as well as the aphelion distance, of these objects (i.e., they show a more prominent 'opposition effect' at smaller distances from the Sun). However, this plausible correlation should be verified using a larger sample. I discuss the origin of this possible correlation and argue that if this correlation is real it probably indicates that 'Sedna'-like objects have a different origin than other classes of TNOs. Finally, I identify several objects with large variability amplitudes.

79 ASTRONOMY AND ASTROPHYSICS↗

Impact of Data Placement on Resilience in Large-Scale Object Storage Systems

Distributed object storage architectures have become the de facto standard for high-performance storage in big data, cloud, and HPC computing. Object storage deployments using commodity hardware to reduce costs often employ object replication as a method to achieve data resilience. Repairing object replicas after failure is a daunting task for systems with thousands of servers and billions of objects, however, and it is increasingly difficult to evaluate such scenarios at scale on realworld systems. Resilience and availability are both compromised if objects are not repaired in a timely manner. In this work we leverage a high-fidelity discrete-event simulation model to investigate replica reconstruction on large-scale object storage systems with thousands of servers, billions of objects, and petabytes of data. We evaluate the behavior of CRUSH, a well-known object placement algorithm, and identify configuration scenarios in which aggregate rebuild performance is constrained by object placement policies. After determining the root cause of this bottleneck, we then propose enhancements to CRUSH and the usage policies atop it to enable scalable replica reconstruction. We use these methods to demonstrate a simulated aggregate rebuild rate of 410 GiB/s (within 5% of projected ideal linear scaling) on a 1,024-node commodity storage system. We also uncover an unexpected phenomenon in rebuild performance based on the characteristics of the data stored on the system.

Carns, Philip↗

Faint Object Detection in Multi-Epoch Observations via Catalog Data Fusion

Astronomy in the time-domain era faces several new challenges. One of them is the efficient use of observations obtained at multiple epochs. The work presented here addresses faint object detection and describes an incremental strategy for separating real objects from artifacts in ongoing surveys. The idea is to produce low-threshold single-epoch catalogs and to accumulate information across epochs. This is in contrast to more conventional strategies based on co-added or stacked images. We adopt a Bayesian approach, addressing object detection by calculating the marginal likelihoods for hypotheses asserting that there is no object or one object in a small image patch containing at most one cataloged source at each epoch. The object-present hypothesis interprets the sources in a patch at different epochs as arising from a genuine object; the no-object hypothesis interprets candidate sources as spurious, arising from noise peaks. We study the detection probability for constant-flux objects in a Gaussian noise setting, comparing results based on single and stacked exposures to results based on a series of single-epoch catalog summaries. Our procedure amounts to generalized cross-matching: it is the product of a factor accounting for the matching of the estimated fluxes of the candidate sources and a factor accounting for the matching of their estimated directions. We find that probabilistic fusion of multi-epoch catalogs can detect sources with similar sensitivity and selectivity compared to stacking. The probabilistic cross-matching framework underlying our approach plays an important role in maintaining detection sensitivity and points toward generalizations that could accommodate variability and complex object structure.

79 ASTRONOMY AND ASTROPHYSICS↗

Optical and radio properties of X-ray selected BL Lacertae objects

The eight BL Lac objects from the HEAO 1 A-2 all-sky survey and from the Einstein medium-sensitivity survey (MSS) form a flux-limited complete X-ray selected sample. The optical and radio properties of the MSS BL Lac objects are presented and compared with those of the HEAO 1 A-2 sample and with those of radio-selected BL Lac objects. The X-ray selected BL Lac objects possess smaller polarized fractions and less violent optical variability than radio-selected BL Lac objects. These properties are consistent with the substantial starlight fraction seen in the optical spectra of a majority of these objects. This starlight allows a determination of definite redshifts for two of four MSS BL Lac objects and a probable redshift for a third. These redshifts are 0.2, 0.3, and 0.6. Despite the differences in characteristics between the X-ray selected and radio-selected samples, it is concluded that these eight objects possess most of the basic qualities of BL Lac objects and should be considered members of that class. Moreover, as a class, these X-ray selected objects have the largest ratio of X-ray to optical flux of any active galactic nuclei yet discovered.

Stocke, J. T.↗

Robot Acting on Moving Bodies (RAMBO): Interaction with tumbling objects

Interaction with tumbling objects will become more common as human activities in space expand. Attempting to interact with a large complex object translating and rotating in space, a human operator using only his visual and mental capacities may not be able to estimate the object motion, plan actions or control those actions. A robot system (RAMBO) equipped with a camera, which, given a sequence of simple tasks, can perform these tasks on a tumbling object, is being developed. RAMBO is given a complete geometric model of the object. A low level vision module extracts and groups characteristic features in images of the object. The positions of the object are determined in a sequence of images, and a motion estimate of the object is obtained. This motion estimate is used to plan trajectories of the robot tool to relative locations rearby the object sufficient for achieving the tasks. More specifically, low level vision uses parallel algorithms for image enhancement by symmetric nearest neighbor filtering, edge detection by local gradient operators, and corner extraction by sector filtering. The object pose estimation is a Hough transform method accumulating position hypotheses obtained by matching triples of image features (corners) to triples of model features. To maximize computing speed, the estimate of the position in space of a triple of features is obtained by decomposing its perspective view into a product of rotations and a scaled orthographic projection. This allows use of 2-D lookup tables at each stage of the decomposition. The position hypotheses for each possible match of model feature triples and image feature triples are calculated in parallel. Trajectory planning combines heuristic and dynamic programming techniques. Then trajectories are created using dynamic interpolations between initial and goal trajectories. All the parallel algorithms run on a Connection Machine CM-2 with 16K processors.

Davis, Larry S.↗

Formation and Migration of Trans-Neptunian Objects

We consider that trans-Neptunian objects (TNOs) with diameter d greater than 100 kilometers moving now in not very eccentric orbits could be formed directly by the compression of large rarefied dust condensations (with a greater than 30 AU), but not by the accretion of smaller solid planetesimals. Probably, some planetesimals with d approximately 100- 1000 kilometers in the feeding zone of the giant planets and even large main-belt asteroids also could be formed directly by such compression. Some smaller objects (TNOs, planetesimals, asteroids) could be debris of larger objects, and other such objects could be formed directly by compression of condensations. A small portion of planetesimals from the feeding zone of the giant planets that entered into the trans-Neptunian region could left in eccentrical orbits beyond Neptune and became so called "scattered objects". Our computer runs in which gravitational interactions of bodies were taken into account with the use of the spheres method, showed that the embryos of Uranus and Neptune could increase their semimajor axes from less than 10 AU to their present values, moving permanently in orbits with small eccentricities, due to gravitational interactions with the migrating planetesimals. Later on, Thommes et al. considered a similar model using direct numerical integration. The total amount of water delivered to the Earth during the formation of the giant, planets was about the mass of water in the Earth oceans. The end of such bombardment could be caused mainly by the planetesimals that became scattered objects. For the present mass of the trans-Neptunian belt, the collisional lifetime of 1-kilometer TNO is about the age of the Solar system, but only a small portion (less than 1%) of 100-km TNOs could be destroyed during this age. The probability of destruction of a typical TNO (with 30 less than a,less than 50 AU) by scattered objects can be of the same order of magnitude as that by typical TNOs. TNOs could be even more often destroyed during planet formation than during last 4 Gyr. The analysis of the results of the orbital evolution of Jupiter-crossing objects (JCOs) and TNOs showed that, in principle, the trans-Neptunian belt can provide up to 100% of Earth-crossing objects, but, of course, some of them came from the main asteroid belt. Most of the collisions of former JCOs with the Earth were from orbits with aphelia inside Jupiter's orbit and belonged to a small portion of objects which moved in such orbits for a long time. About 1 of 300 JCOs collided with the Sun. The ratio of the total mass of icy planetesimals that migrated from the feeding zone of the giant planets and collided with the planet to the mass of this planet was greater (by a factor of 3 in our runs) for Mars than that for Earth and Venus.

Ipatov, S. I.↗

Adaptive Morphological Feature-Based Object Classifier for a Color Imaging System

Utilizing a Compact Color Microscope Imaging System (CCMIS), a unique algorithm has been developed that combines human intelligence along with machine vision techniques to produce an autonomous microscope tool for biomedical, industrial, and space applications. This technique is based on an adaptive, morphological, feature-based mapping function comprising 24 mutually inclusive feature metrics that are used to determine the metrics for complex cell/objects derived from color image analysis. Some of the features include: Area (total numbers of non-background pixels inside and including the perimeter), Bounding Box (smallest rectangle that bounds and object), centerX (x-coordinate of intensity-weighted, center-of-mass of an entire object or multi-object blob), centerY (y-coordinate of intensity-weighted, center-of-mass, of an entire object or multi-object blob), Circumference (a measure of circumference that takes into account whether neighboring pixels are diagonal, which is a longer distance than horizontally or vertically joined pixels), . Elongation (measure of particle elongation given as a number between 0 and 1. If equal to 1, the particle bounding box is square. As the elongation decreases from 1, the particle becomes more elongated), . Ext_vector (extremal vector), . Major Axis (the length of a major axis of a smallest ellipse encompassing an object), . Minor Axis (the length of a minor axis of a smallest ellipse encompassing an object), . Partial (indicates if the particle extends beyond the field of view), . Perimeter Points (points that make up a particle perimeter), . Roundness [(4(pi) x area)/perimeter(squared)) the result is a measure of object roundness, or compactness, given as a value between 0 and 1. The greater the ratio, the rounder the object.], . Thin in center (determines if an object becomes thin in the center, (figure-eight-shaped), . Theta (orientation of the major axis), . Smoothness and color metrics for each component (red, green, blue) the minimum, maximum, average, and standard deviation within the particle are tracked. These metrics can be used for autonomous analysis of color images from a microscope, video camera, or digital, still image. It can also automatically identify tumor morphology of stained images and has been used to detect stained cell phenomena (see figure).

McDowell, Mark↗

An Upper Bound on Orbital Debris Collision Probability When Only One Object has Position Uncertainty Information

Upper bounds on high speed satellite collision probability, P (sub c), have been investigated. Previous methods assume an individual position error covariance matrix is available for each object. The two matrices being combined into a single, relative position error covariance matrix. Components of the combined error covariance are then varied to obtain a maximum P (sub c). If error covariance information for only one of the two objects was available, either some default shape has been used or nothing could be done. An alternative is presented that uses the known covariance information along with a critical value of the missing covariance to obtain an approximate but useful P (sub c) upper bound. There are various avenues along which an upper bound on the high speed satellite collision probability has been pursued. Typically, for the collision plane representation of the high speed collision probability problem, the predicted miss position in the collision plane is assumed fixed. Then the shape (aspect ratio of ellipse), the size (scaling of standard deviations) or the orientation (rotation of ellipse principal axes) of the combined position error ellipse is varied to obtain a maximum P (sub c). Regardless as to the exact details of the approach, previously presented methods all assume that an individual position error covariance matrix is available for each object and the two are combined into a single, relative position error covariance matrix. This combined position error covariance matrix is then modified according to the chosen scheme to arrive at a maximum P (sub c). But what if error covariance information for one of the two objects is not available? When error covariance information for one of the objects is not available the analyst has commonly defaulted to the situation in which only the relative miss position and velocity are known without any corresponding state error covariance information. The various usual methods of finding a maximum P (sub c) do no good because the analyst defaults to no knowledge of the combined, relative position error covariance matrix. It is reasonable to think, given an assumption of no covariance information, an analyst might still attempt to determine the error covariance matrix that results in an upper bound on the P (sub c). Without some guidance on limits to the shape, size and orientation of the unknown covariance matrix, the limiting case is a degenerate ellipse lying along the relative miss vector in the collision plane. Unless the miss position is exceptionally large or the at-risk object is exceptionally small, this method results in a maximum P (sub c) too large to be of practical use. For example, assuming that the miss distance is equal to the current ISS alert volume along-track (+ or -) distance of 25 kilometers and that the at-risk area has a 70 meter radius. The maximum (degenerate ellipse) P (sub c) is about 0.00136. At 40 kilometers, the maximum P (sub c) would be 0.00085 which is still almost an order of magnitude larger than the ISS maneuver threshold of 0.0001. In fact, a miss distance of almost 340 kilometers is necessary to reduce the maximum P (sub c) associated with this degenerate ellipse to the ISS maneuver threshold value. Such a result is frequently of no practical value to the analyst. Some improvement may be made with respect to this problem by realizing that while the position error covariance matrix of one of the objects (usually the debris object) may not be known the position error covariance matrix of the other object (usually the asset) is almost always available. Making use of the position error covariance information for the one object provides an improvement in finding a maximum P (sub c) which, in some cases, may offer real utility. The equations to be used are presented and their use discussed.

Frisbee, Joseph H., Jr.↗

Data object classification using feature generation through crowdsourcing

In a computing device that implements a data object classification tool, a method for classifying data may include detecting change in spatial coordinates for each of at least two of a set of data objects within a canvas space. Each of the data objects may be associated with a vector of features. A rule set may be generated based on the vector of features associated with each of the at least two data objects. The rule set may use feature(s) that explain the changed spatial coordinates. The data objects may be selectively rearranged within the canvas space by applying the generated rule set to any remaining data objects among the set of data objects so as to assign spatial coordinates to the remaining objects. For each of the data objects, the spatial coordinates may be stored as new semantic feature(s) within the vector of features for that data object.

97 MATHEMATICS AND COMPUTING↗

System and method for adaptive object-oriented sensor fusion for environmental mapping

The present disclosure relates to a mapping system adapted for detecting objects in an environmental scene, by scanning an environmental scene with propagating energy, and receiving reflected energy back from objects present in the environmental scene, in a prioritized manner, for later use. The system may comprise an imaging subsystem which includes a detection and ranging subsystem for initially identifying primitive objects in the environmental scene. The imaging subsystem may also include an identification and mapping subsystem for prioritizing the primitive objects for further scanning and analysis, to ultimately identify one or more of the primitive objects as one or more abstract objects. An environmental model, updated in real time, is used to maintain a map of the primitive objects and the known abstract objects within the environmental scene, as new primitive objects and new abstract objects are obtained with repeated scans of the environmental scene.

Panas, Robert Matthew↗

Casimir potential of a compact object enclosed by a spherical cavity

We study the electromagnetic Casimir interaction of a compact object contained inside a closed cavity of another compact object. We express the interaction energy in terms of the objects' scattering matrices and translation matrices that relate the coordinate systems appropriate to each object. When the enclosing object is an otherwise empty metallic spherical shell, much larger than the internal object, and the two are sufficiently separated, the Casimir force can be expressed in terms of the static electric and magnetic multipole polarizabilities of the internal object, which is analogous to the Casimir-Polder result. Although it is not a simple power law, the dependence of the force on the separation of the object from the containing sphere is a universal function of its displacement from the center of the sphere, independent of other details of the object's electromagnetic response. Furthermore, we compute the exact Casimir force between two metallic spheres contained one inside the other at arbitrary separations. Finally, we combine our results with earlier work on the Casimir force between two spheres to obtain data on the leading-order correction to the proximity force approximation for two metallic spheres both outside and within one another.

71 CLASSICAL AND QUANTUM MECHANICS, GENERAL PHYSIC↗

srMO-BO-3GP: A sequential regularized multi-objective Bayesian optimization for constrained design applications using an uncertain Pareto classifier

Bayesian optimization (BO) is an efficient and flexible global optimization framework that is applicable to a very wide range of engineering applications. To leverage the capability of the classical BO, many extensions, including multi-objective, multi-fidelity, parallelization, and latent-variable modeling, have been proposed to address the limitations of the classical BO framework. In this work, we propose a novel multi-objective BO formalism, called srMO-BO-3GP, to solve multi-objective optimization problems in a sequential setting. Three different Gaussian processes (GPs) are stacked together, where each of the GPs is assigned with a different task. The first GP is used to approximate a single-objective computed from the multi-objective definition, the second GP is used to learn the unknown constraints, and the third one is used to learn the uncertain Pareto frontier. At each iteration, a multi-objective augmented Tchebycheff function is adopted to convert multi-objective to single-objective, where the regularization with a regularized ridge term is also introduced to smooth the single-objective function. Finally, we couple the third GP along with the classical BO framework to explore the convergence and diversity of the Pareto frontier by the acquisition function for exploitation and exploration. The proposed framework is demonstrated using several numerical benchmark functions, as well as a thermomechanical finite element model for flip-chip package design optimization.

42 ENGINEERING↗

SU-F-R-46: Predicting Distant Failure in Lung SBRT Using Multi-Objective Radiomics Model

Purpose: To predict distant failure in lung stereotactic body radiation therapy (SBRT) in early stage non-small cell lung cancer (NSCLC) by using a new multi-objective radiomics model. Methods: Currently, most available radiomics models use the overall accuracy as the objective function. However, due to data imbalance, a single object may not reflect the performance of a predictive model. Therefore, we developed a multi-objective radiomics model which considers both sensitivity and specificity as the objective functions simultaneously. The new model is used to predict distant failure in lung SBRT using 52 patients treated at our institute. Quantitative imaging features of PET and CT as well as clinical parameters are utilized to build the predictive model. Image features include intensity features (9), textural features (12) and geometric features (8). Clinical parameters for each patient include demographic parameters (4), tumor characteristics (8), treatment faction schemes (4) and pretreatment medicines (6). The modelling procedure consists of two steps: extracting features from segmented tumors in PET and CT; and selecting features and training model parameters based on multi-objective. Support Vector Machine (SVM) is used as the predictive model, while a nondominated sorting-based multi-objective evolutionary computation algorithm II (NSGA-II) is used for solving the multi-objective optimization. Results: The accuracy for PET, clinical, CT, PET+clinical, PET+CT, CT+clinical, PET+CT+clinical are 71.15%, 84.62%, 84.62%, 85.54%, 82.69%, 84.62%, 86.54%, respectively. The sensitivities for the above seven combinations are 41.76%, 58.33%, 50.00%, 50.00%, 41.67%, 41.67%, 58.33%, while the specificities are 80.00%, 92.50%, 90.00%, 97.50%, 92.50%, 97.50%, 97.50%. Conclusion: A new multi-objective radiomics model for predicting distant failure in NSCLC treated with SBRT was developed. The experimental results show that the best performance can be obtained by combining all features.

60 APPLIED LIFE SCIENCES↗