In this extended abstract we present our approach to marshal digital tools in the fight against malaria. We describe our scalable infrastructure which leverages abstractions to support effective deployment of existing computational models and their associated data.
In this work, our aim is to identify whether the choice of virtualization strategy influences the performance of simulations in robotics. Performance is quantified in the error between a reference trajectory and the actual trajectory for the ball mov
ing along the surface of a smooth plate. The two-sample Kolmogorov-Smirnov test is used to assess significance of variations in performance under the different experimental settings. Our results show that the selection of virtualization technology does have a significant effect on simulation, and moreover this effect can be amplified by the use of some operating systems. While these results are a strong cause for caution, they also provide reason for optimism for those considering repeatable robotics research using virtualization.
Applying state of the art deep learning models to novel real world datasets gives a practical evaluation of the generalizability of these models. Of importance in this process is how sensitive the hyper parameters of such models are to novel datasets
as this would affect the reproducibility of a model. We present work to characterize the hyper parameter space of an LSTM for language modeling on a code-mixed corpus. We observe that the evaluated model shows minimal sensitivity to our novel dataset bar a few hyper parameters.
The task of decision-making under uncertainty is daunting, especially for problems which have significant complexity. Healthcare policy makers across the globe are facing problems under challenging constraints, with limited tools to help them make da
ta driven decisions. In this work we frame the process of finding an optimal malaria policy as a stochastic multi-armed bandit problem, and implement three agent based strategies to explore the policy space. We apply a Gaussian Process regression to the findings of each agent, both for comparison and to account for stochastic results from simulating the spread of malaria in a fixed population. The generated policy spaces are compared with published results to give a direct reference with human expert decisions for the same simulated population. Our novel approach provides a powerful resource for policy makers, and a platform which can be readily extended to capture future more nuanced policy spaces.
This paper presents a novel application of Genetic Algorithms(GAs) to quantify the performance of Platform as a Service (PaaS), a cloud service model that plays a critical role in both industry and academia. While Cloud benchmarks are not new, in thi
s novel concept, the authors use a GA to take advantage of the elasticity in Cloud services in a graceful manner that was not previously possible. Using Google App Engine, Heroku, and Python Anywhere with three distinct classes of client computers running our GA codebase, we quantified the completion time for application of the GA to search for the parameters of controllers for dynamical systems. Our results show statistically significant differences in PaaS performance by vendor, and also that the performance of the PaaS performance is dependent upon the client that uses it. Results also show the effectiveness of our GA in determining the level of service of PaaS providers, and for determining if the level of service of one PaaS vendor is repeatable with another. Such a concept could then increase the appeal of PaaS Cloud services by making them more financially appealing.
Modern robotics often involves the use of web technologies as a means to cope with the complexity of design and operation. Many of these technologies have been formalized into standards, which are often avoided by those in robotics and controls becau
se of a sometimes warranted fear that the web is too slow, or too uncertain for meaningful control applications. In this work we argue that while web technologies may not be applicable for all control, they should not be dismissed outright because they can provide critical help with system integration. Web technologies have also advanced significantly over the past decade. We present the details of an application of a web server to perform open and close-loop control (between 3Hz and 1kHz) over a variety of different network topologies. In our study we also consider the impact of a web browser to implement the control of the plant. Our results confirm that meaningful control can be performed using web technologies, and also highlight design choices that can limit their applicability.
