Hieu Le, Dieu-thu Le, Verena Weber, Chris Church, Kay Rottmann, Melanie Bradford, Peter Chin. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track. 2022.
Over the past decades, progress in deployable autonomous flight systems has slowly stagnated. This is reflected in today's production air-crafts, where pilots only enable simple physics-based systems such as autopilot for takeoff, landing, navigation, and terrain/traffic avoidance. Evidently, autonomy has not gained the trust of the community where higher problem complexity and cognitive workload are required. To address trust, we must revisit the process for developing autonomous capabilities: modeling and simulation. Given the prohibitive costs for live tests, we need to prototype and evaluate autonomous aerial agents in a high fidelity flight simulator with autonomous learning capabilities applicable to flight systems: such a open-source development platform is not available. As a result, we have developed GymFG: GymFG couples and extends a high fidelity, open-source flight simulator and a robust agent learning framework to facilitate learning of more complex tasks. Furthermore, we have demonstrated the use of GymFG to train an autonomous aerial agent using Imitation Learning. With GymFG, we can now deploy innovative ideas to address complex problems and build the trust necessary to move prototypes to the real-world.
FIFor The Alzheimer’s Disease Neuroimaging Initiative
For The Alzheimer’s Disease Neuroimaging Initiative
+4
Background: Generative adversarial networks (GAN) can generate images of improved quality but their ability to augment image-based classification tasks is not fully explored. Purpose: We evaluated if a modified GAN can learn from MRI scans of multiple magnetic field strength to enhance Alzheimer’s disease (AD) classification performance. Materials and methods: T1-weighted brain MRI scans from 151 participants of the Alzheimer’s Disease Neuroimaging Initiative (ADNI), who underwent both 1.5 Tesla (1.5T) and 3 Tesla imaging at the same time were selected to construct a GAN model. This model was trained along with a three-dimensional fully convolutional network (FCN) using the generated images (1.5T*) as inputs to predict AD status. Quality of the generated images was evaluated using signal to noise ratio (SNR), Blind/Referenceless Image Spatial Quality Evaluator (BRISQUE) and Natural Image Quality Evaluator (NIQE). Data from the Australian Imaging, Biomarker & Lifestyle Flagship Study of Ageing (AIBL, n=107), and the National Alzheimer’s Coordinating Center (NACC, n=565) was used for model validation. Results: The mean quality of the generated (1.5T*) images was consistently higher than the 1.5T images, as measured using SNR, BRISQUE and NIQE on the validation datasets. The 1.5T*-based FCN classifier performed better than the FCN model trained using the 1.5T scans. Specifically, the mean area under curve increased from 0.907 to 0.932, from 0.934 to 0.940 and from 0.870 to 0.907 on the ADNI test, AIBL and NACC datasets, respectively. Conclusion: This study demonstrates that GAN frameworks can be constructed to simultaneously improve image quality and augment classification performance. Key points: Our proposed generative adversarial network used 1.5 and 3 Tesla MR scans of the brain to generate images of improved quality, as estimated using no-reference image quality algorithms. Classification models of Alzheimer’s disease risk developed using the generated images had higher classification performance than the models developed using the original 1.5 Tesla scans.