Browsing by Author "Mwavu, Rogers"

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    An Overview of Data Science Innovations, Challenges and Limitations Towards Real-World Implementations in Global Health
    (Springer, Cham., 2020) Kimera, Richard; Kaggwa, Fred; Mwavu, Rogers; Mugonza, Robert; Tumuhimbise, Wilson; Munguci, Gloria; Kamuganga, Francis
    Health institutions are increasingly collecting vast amounts of patient data. However, mining data from those different institutions is not possible for various challenges. In this chapter, we will report on our experience on the trend of Data Science in Global Health in Uganda. The aim is to provide an insight into their challenges and limitations towards real-world implementation of a data science approach in global health.We also present a series of digital health projects that we implemented during the course of the project, and provide a critical assessment of the success and challenges of those implementations.
  • Thumbnail Image
    Item
    Tools, Architectures and Techniques for Monitoring Energy Efficiency in Computer Networks: State of the Art Survey
    (International Journal of Computer Applications, 2016) Mwavu, Rogers; Mugonza, Robert; Businge, John
    Energy efficiency in data center networks is increasingly becoming a gold standard for implementers. Energy costs are becoming high while performance is highly demanded. And while efforts are directed to the design of energy efficient networks, a number of open issues require addressing including: - scalability, fault tolerance, efficiency in performance though their presence does not outweigh the benefits of networks energy-aware. Truly, we observe that improvements in computer networks hardware performance comes with increasing energy consumption. To address these complementary challenges, this paper technically surveys existing, approaches and techniques (virtualization, energy-aware routing, among others), tools, and architectures employed in energy efficient computer networks. We have also provided a thorough review of data centre networks: server centric, switch centric and dual centric architectures with a view to inform developers and implementers of the overhead given architectural choice, identified challenges and opportunities. We conclude upon the survey that dual centric computer networks architectures have various nice properties for practical computer networks and provide flexible choices in designing of computer network architectures.
  • Thumbnail Image
    Item
    Unmasking biases and navigating pitfalls in the ophthalmic artificial intelligence lifecycle: A narrative review
    (Public Library of Science, 2024-10-08) Nakayama, Luis Filipe; Matos, João; Quion, Justin; Novaes, Frederico; Mitchell, William Greig; Mwavu, Rogers; Hung, Claudia Ju-Yi Ji; Santiago, Alvina Pauline Dy; Phanphruk, Warachaya; Cardoso, Jaime S; Celi, Leo Anthony
    Over the past 2 decades, exponential growth in data availability, computational power, and newly available modeling techniques has led to an expansion in interest, investment, and research in Artificial Intelligence (AI) applications. Ophthalmology is one of many fields that seek to benefit from AI given the advent of telemedicine screening programs and the use of ancillary imaging. However, before AI can be widely deployed, further work must be done to avoid the pitfalls within the AI lifecycle. This review article breaks down the AI lifecycle into seven steps—data collection; defining the model task; data preprocessing and labeling; model development; model evaluation and validation; deployment; and finally, post-deployment evaluation, monitoring, and system recalibration—and delves into the risks for harm at each step and strategies for mitigating them.