Search

Studies involving colourising images has been garnering researchers' keen attention over time, assisted by significant advances in various Machine Learning techniques and compute power availability. Traditionally, colourising images have been an intricate task that gave a substantial degree of freedom during the assignment of chromatic information. In our proposed method, we attempt to colourise images using Vision Transformer - Inception - Generative Adversarial Network (ViT-I-GAN), which has an Inception-v3 fusion embedding in the generator. For a stable and robust network, we have used Vision Transformer (ViT) as the discriminator. We trained the model on the Unsplash and the COCO dataset for demonstrating the improvement made by the Inception-v3 embedding. We have compared the results between ViT-GANs with and without Inception-v3 embedding., Comment: 12 pages

An important aspect of AI design and ethics is to create systems that reflect aggregate preferences of the society. To this end, the techniques of social choice theory are often utilized. We propose a new social choice function motivated by the PageRank algorithm. The function ranks voting options based on the Condorcet graph of pairwise comparisons. To this end, we transform the Condorcet graph into a Markov chain whose stationary distribution provides the scores of the options. We show how the values in the stationary distribution can be interpreted as quantified aggregate support for the voting options, to which the community of voters converges through an imaginary sequence of negotiating steps. Because of that, we suggest the name "convergence voting" for the new voting scheme, and "negotiated community support" for the resulting stationary allocation of scores. Our social choice function can be viewed as a consensus voting method, sitting somewhere between Copeland and Borda. On the one hand, it does not necessarily choose the Condorcet winner, as strong support from a part of the society can outweigh mediocre uniform support. On the other hand, the influence of unpopular candidates on the outcome is smaller than in the primary technique of consensus voting, i.e., the Borda count. We achieve that without having to introduce an ad hoc weighting that some other methods do.

Existing prognostic tools mainly focus on predicting the risk of mortality among patients with coronavirus disease 2019. However, clinical evidence suggests that COVID-19 can result in non-mortal complications that affect patient prognosis. To support patient risk stratification, we aimed to develop a prognostic system that predicts complications common to COVID-19. In this retrospective study, we used data collected from 3,352 COVID-19 patient encounters admitted to 18 facilities between April 1 and April 30, 2020, in Abu Dhabi (AD), UAE. The hospitals were split based on geographical proximity to assess for our proposed system's learning generalizability, AD Middle region and AD Western & Eastern regions, A and B, respectively. Using data collected during the first 24 hours of admission, the machine learning-based prognostic system predicts the risk of developing any of seven complications during the hospital stay. The complications include secondary bacterial infection, AKI, ARDS, and elevated biomarkers linked to increased patient severity, including d-dimer, interleukin-6, aminotransferases, and troponin. During training, the system applies an exclusion criteria, hyperparameter tuning, and model selection for each complication-specific model. The system achieves good accuracy across all complications and both regions. In test set A (587 patient encounters), the system achieves 0.91 AUROC for AKI and >0.80 AUROC for most of the other complications. In test set B (225 patient encounters), the respective system achieves 0.90 AUROC for AKI, elevated troponin, and elevated interleukin-6, and >0.80 AUROC for most of the other complications. The best performing models, as selected by our system, were mainly gradient boosting models and logistic regression. Our results show that a data-driven approach using machine learning can predict the risk of such complications with high accuracy., Comment: 19 pages, 5 figures

Massive MIMO is seen as a main enabler for low latency communications, thanks to its high spatial degrees of freedom. The channel hardening and favorable propagation properties of Massive MIMO are particularly important for multiplexing several URLLC devices. However, the actual utility of channel hardening and spatial multiplexing is dependent critically on the accuracy of channel knowledge. When several low latency devices are multiplexed, the cost for acquiring accurate knowledge becomes critical, and it is not evident how many devices can be served with a latency-reliability requirement and how many pilot symbols should be allocated. This paper investigates the trade-off between achieving high spectral efficiency and high reliability in the downlink, by employing various power allocation strategies, for maximum ratio and minimum mean square error precoders. The results show that using max-min SINR power allocation achieves the best reliability, at the expense of lower sum spectral efficiency., Comment: Presented in Asilomar 2019

In-plane compressively strained $\alpha$-Sn films have been theoretically predicted and experimentally proven to possess non-trivial electronic states of a 3D topological Dirac semimetal. The robustness of these states typically strongly depends on purity, homogeneity and stability of the grown material itself. By developing a reliable fabrication process, we were able to grow pure strained $\alpha$-Sn films on InSb(100), without heating of the substrate during growth, nor using any dopants. The $\alpha$-Sn films were grown by molecular beam epitaxy, followed by experimental verification of the achieved chemical purity and structural properties of the film's surface. Local insight into the surface morphology was provided by scanning tunneling microscopy. We detected the existence of compressive strain using M\"ossbauer spectroscopy and we observed a remarkable robustness of the grown samples against ambient conditions. The topological character of the samples was confirmed by angle-resolved photoemission spectroscopy, revealing the Dirac cone of the topological surface state. Scanning tunneling spectroscopy, moreover, allowed obtaining an improved insight into the electronic structure of the 3D topological Dirac semimetal $\alpha$-Sn above the Fermi level., Comment: APM19-AR-01221R