Search NASA⌕ Search

SEARCH · Search NASA

Results for “Shapley values”

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.

5 records
All sourcesNASA NTRSDOE OSTI
NASA NTRS2024

Generating Dominating Sets Using Locally Defined Centrality Measures

The dominating set problem has many practical applications but is well-known to be NP-hard. Therefore, there is a need for efficient heuristic algorithms, especially in applications such as ad hoc wireless networks. Most distributed algorithms proposed in the literature assume that each node has knowledge of the network structure. We propose a distributed heuristic algorithm that uses two rounds of communication, and where each node has only local information, both in terms of network structure and dominating set assignment. First, each node calculates a local centrality measure to determine whether it is part of the dominating set D. The second round guarantees D is a dominating set by adding any non-dominated nodes. We compare several centrality measures and show that the Shapley centrality, derived from the Shapley value in game theory, is theoretically motivated and performs well in practice on several synthetic and real-world networks.

Network↗
NASA NTRSDate not supplied

Off-Nominal Event Analysis in Autonomous Flights Based on Explainable Artificial Intelligence

A key objective in the Urban Air Mobility program at NASA is to intelligently perform an autonomous flight in a complex urban environment under all weather conditions with guaranteed levels of safety. To accomplish this, the mission manager (central decision-making module) of the vehicle needs to make informed decisions between various Courses of Action (CoA) based on its' interpretation of the inputs it receives. If an off-nominal event is detected either based on the amalgamation of sensor data or the use of machine learning models, the mission manager may greatly benefit from identification of the input features that most likely contributed to that specific event. Such an understanding is usually not possible to obtain from the classical machine learning models (deep learning) due to the inherent black box like structure. However, this understanding is achieved using eXplainable Artificial Intelligence (XAI) models that provide a human interpretable rationale for the predictions made. This work presents a game theory inspired XAI model for the off-nominal assessment of autonomous flights. The proposed approach based on Shapley values is model agnostic, provides local as well as global explanation and satisfies the four axioms (efficiency, symmetry, dummy, additivity) to achieve fair contribution. The versatility of the approach is first demonstrated on a simulated dataset in which the significance of each input to flight phase prediction is clearly identified. Subsequently, data from simulated flight trajectories are fed into the model which reveal the input features that most likely contributed to a rotor failure event thereby empowering the mission manager to take the appropriate CoA.

autonomy↗
NASA NTRSDate not supplied

Off-Nominal Event Analysis in Autonomous Flights Based on Explainable Artificial Intelligence

A key objective in the Urban Air Mobility program at NASA is to intelligently perform an autonomous flight in a complex urban environment under all weather conditions with guaranteed levels of safety. To accomplish this, the mission manager (central decision-making module) of the vehicle needs to make informed decisions between various Courses of Action (CoA) based on its' interpretation of the inputs it receives. If an off-nominal event is detected either based on the amalgamation of sensor data or the use of machine learning models, the mission manager may greatly benefit from identification of the input features that most likely contributed to that specific event. Such an understanding is usually not possible to obtain from the classical machine learning models (deep learning) due to the inherent black box like structure. However, this understanding is achieved using eXplainable Artificial Intelligence (XAI) models that provide a human interpretable rationale for the predictions made. This work presents a game theory inspired XAI model for the off-nominal assessment of autonomous flights. The proposed approach based on Shapley values is model agnostic, provides local as well as global explanation and satisfies the four axioms (efficiency, symmetry, dummy, additivity) to achieve fair contribution. The versatility of the approach is first demonstrated on a simulated dataset in which the significance of each input to flight phase prediction is clearly identified. Subsequently, data from simulated flight trajectories are fed into the model which reveal the input features that most likely contributed to a rotor failure event thereby empowering the mission manager to take the appropriate CoA.

autonomy↗
NASA NTRS1993

The structure of the nearby universe traced by theIRAS galaxies

One of the most important discoveries of the Infrared Astronomical Satellite (IRAS) has been the detection of about 20,000 galaxies with 60 microns fluxes above 0.5 Jy. From the observational point of view, the IRAS galaxies are ideal tracers of density, since they are homogeneously detected over most of the sky, and their fluxes are unaffected by galactic extinction. The nearby universe was mapped by the IRAS galaxies to a distance of approximately 200 h(exp -1) Mpc for the absolute value of b less than 5 deg. The ability to map down to such low galactic latitudes has proven to be particularly imporant, since some of the most important nearby large-scale structures, such as the Great Attractor, the Perseus-Pisces region, and the Shapley concentration, all lie there. Two major results of the U.S. IRAS redshift survey are discussed.

Yahil, Amos↗
NASA NTRS1991

The small-scale clustering properties of dwarf galaxies

Two results on the small-scale clustering properties of dwarf galaxies are reported, which were identified in the vicinity of early-type Shapley-Ames galaxies on high-resolution photographic plates. The first result indicates that dwarf galaxies display the same trend of stronger clustering toward earlier morphological type on small scales as their giant counterparts on larger scales. It is suggested that early-type dwarfs can be used as dynamical probes of dark halos around early-type giant galaxies and as tracers of the dynamical evolution of such halos in dense environments. The second result pertains to the trend of increasing early-type dwarf frequency per early-type giant with environment richness previously established for rich groups. It is found that a minimum value of isolated early-type galaxies is approximately 0.25, as compared to a maximum of approximately 8 in rich environments like the Virgo Cluster.

Vader, J. P.↗