This dataset allows comparison of the different strategies implemented by vehicle manufacturers being used to communicate with drivers. Spreadsheets were created in MS Excel to summarize data for each vehicle, and include page numbers in each vehicle owner's manual for reference. The photos taken of each vehicle control panel allow detailed inspection of the displays and controls.
The procedure followed while creating this data is summarized in Section II of Chen, Brian, et al. "Behavioral cloning in atari games using a combined variational autoencoder and predictor model." 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021. This data is not a result of a research but an intermediate product that is used in research.
This dataset is generated to train a behavioral cloning framework from gameplay screen captures and keystrokes of an "expert" player. The RL agent that is trained using "RL Baselines Zoo package" acts as the "expert" player, whose decision making process we desire to learn. In addition to behavioral cloning experiments, this dataset is further used to demonstrate the efficacy of a novel incremental tensor decomposition algorithm on image-based data streams.
Chen, Brian, et al. "Behavioral cloning in atari games using a combined variational autoencoder and predictor model." 2021 IEEE Congress on Evolutionary Computation (CEC). IEEE, 2021., Aksoy, Doruk, et al. "An Incremental Tensor Train Decomposition Algorithm." arXiv preprint arXiv:2211.12487 (2022)., and Chen, Brian, et al. "Low-Rank Tensor-Network Encodings for Video-to-Action Behavioral Cloning", forthcoming
Images of villages in Mali in which Tengou-Togo (Dogon family) is the primary language. Each file name contains important information about the photos, and are structured thus: LanguageFamily_Language_IdentificationNumber_GeographicCoordinate_Description_Date_InitialsOfThePhotographer
Moran, Steven & Forkel, Robert & Heath, Jeffrey (eds.) 2016. Dogon and Bangime Linguistics. Jena: Max Planck Institute for the Science of Human History. http://dogonlanguages.org
Hung, A., Enninful Adu, C., Moore, T.Y. (in review), SKOOTR: A SKating, Omni-Oriented, Tripedal Robot for dynamically stable indoor navigation. IEEE ICRA
Reconstructed CT slices for Right maxilla with M1/ and roots of P4/ of Plesiadapis gingerichi (University of Michigan Museum of Paleontology catalog number UMMP 68409) as a series of TIFF images. Raw projections are not included in this dataset. The reconstructed slice data from the scan are offered here as a series of unsigned 16-bit integer TIFF images. The upper left corner of the first image (*_0000.tif) is the XYZ origin.
Reconstructed CT slices for Incisor frag. of Plesiadapis gingerichi (University of Michigan Museum of Paleontology catalog number UMMP 68409) as a series of TIFF images. Raw projections are not included in this dataset. The reconstructed slice data from the scan are offered here as a series of unsigned 16-bit integer TIFF images. The upper left corner of the first image (*_0000.tif) is the XYZ origin.
Reconstructed CT slices for Right M3/ of Plesiadapis gingerichi (University of Michigan Museum of Paleontology catalog number UMMP 68409) as a series of TIFF images. Raw projections are not included in this dataset. The reconstructed slice data from the scan are offered here as a series of unsigned 16-bit integer TIFF images. The upper left corner of the first image (*_0000.tif) is the XYZ origin.
Reconstructed CT slices for Right M2/ of Plesiadapis gingerichi (University of Michigan Museum of Paleontology catalog number UMMP 68409) as a series of TIFF images. Raw projections are not included in this dataset. The reconstructed slice data from the scan are offered here as a series of unsigned 16-bit integer TIFF images. The upper left corner of the first image (*_0000.tif) is the XYZ origin.
Reconstructed CT slices for Left dentary with P/4-M/1, M/2 trigonid, P/3 roots of Plesiadapis gingerichi (University of Michigan Museum of Paleontology catalog number UMMP 68409) as a series of TIFF images. Raw projections are not included in this dataset. The reconstructed slice data from the scan are offered here as a series of unsigned 16-bit integer TIFF images. The upper left corner of the first image (*_0000.tif) is the XYZ origin.
Columns from left to right (omitting blanks) are:
Tiranige (transcription)
finder (English finder list, i.e. usually one-word glosses)
recherche (finder list in French)
English (full English gloss)
français (full French gloss)
code (for certain lexical categories: fauna, flora, body, kinship)
order/family (for flora-fauna terms)
species (for flora-fauna terms)
synonymy (alternative or former species binomials)
