Browsing by Author "Sanabria, Pablo"

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Deep Neural Networks on Mobile Healthcare Applications: Practical Recommendations
    (2018) Benedetto, Jose I.; Sanabria, Pablo; Neyem, Andres; Navon, Jaime; Poellabauer, Christian; Xia, Bryan (Ning)
    Deep learning has for a long time been recognized as a powerful tool in the field of medicine for making predictions or detecting abnormalities in a patient’s data. However, up until recently, hosting of these neural networks has been relegated to the domain of servers and powerful workstations due to the vast amount of resources they require. This trend has been steadily shifting in the recent years, and we are now beginning to see more and more mobile applications with similar capabilities. Deep neural networks hosted completely on mobile platforms are extremely valuable for providing healthcare services to remote areas without network connectivity. Yet despite this, there is very little information regarding the migration process of an existing server-based neural network to a mobile environment. In this work, we describe the various techniques and considerations that should be taken into account when developing a deep-learning enabled mobile application with offline support. We illustrate the above by providing a concrete example through our experience in migrating to mobile an in-house developed medical application for detecting early signs of traumatic brain injuries.
  • No Thumbnail Available
    Item
    New Heuristics for Scheduling and Distributing Jobs under Hybrid Dew Computing Environments
    (2021) Sanabria, Pablo; Tapia, Tomás Felipe; Neyem, Andres; Benedetto, Jose Ignacio; Hirsch, Matías; Mateos, Cristian; Zunino, Alejandro
    Mobile grid computing has been a popular topic for researchers due to mobile and IoT devices’ ubiquity and their evergrowing processing potential. While many scheduling algorithms for harnessing these resources exist in the literature for standard grid computing scenarios, surprisingly, there is little insight into this matter in the context of hybrid-powered computing resources, typically found in Dew and Edge computing environments. This paper proposes new algorithms aware of devices’ power source for scheduling tasks in hybrid environments, i.e., where the battery- and non-battery-powered devices cooperate. We simulated hybrid Dew/Edge environments by extending DewSim, a simulator that models battery-driven devices’ battery behavior using battery traces profiled from real mobile devices. We compared the throughput and job completion achieved by algorithms proposed in this paper using as a baseline a previously developed algorithm that considers computing resources but only from battery-dependent devices called Enhanced Simple Energy-Aware Schedule (E-SEAS). The obtained results in the simulation reveal that our proposed algorithms can obtain up to a 90% increment in overall throughput and around 95% of completed jobs in hybrid environments compared to E-SEAS. Finally, we show that incorporating these characteristics gives more awareness of the type of resources present and can enable the algorithms to manage resources more efficiently in more hybrid environments than other algorithms found in the literature.