1. Elastic Scheduling of Parallel Real-Time Tasks with Discrete Utilizations

Authors: James Orr, Johnny Condori Uribe, Christopher David Gill, Sanjoy Baruah, Kunal Agrawal, Shirley J Dyke, Arun Prakash, Iain J Bate, Christpher Wong, Sabina Adhikari
Publisher: Association for Computer Machinery, New York, NY, United States
Conference: RTNS 2020: 28th International Conference on Real-Time Networks and Systems
Published: 12 June 2020
doi: https://doi.org/10.1145/3394810.3394824
Elastic scheduling allows for online adaptation of real-time tasks’ utilizations (via manipulation of each task’s computational workload or period) in order to maintain system schedulability in case the utilization demand of one or more tasks changes. This is done currently by assigning each task a utilization (and therefore period or workload) from within a continuous range of acceptable values. While this works well for anytime tasks whose quality of service improves with duration or for tasks that can run at any rate within a given range, many computationally-elastic tasks have a specific workload for each distinct mode of operation and therefore cannot perform arbitrary amounts of work. Similarly, some period-elastic tasks must run at specific (e.g. harmonic) rates. Therefore, a discrete set of candidate utilizations per task must be accommodated in such cases.

This paper provides a new elastic task model in which each task has a discrete set of possible utilizations (instead of a continuous range). This allows users to specify only relevant candidate periods and workloads for each task. The discrete nature of this model also allows each task to modify its workload and/or its period when changing its mode of operation, instead of adapting in only one dimension of task utilization. Elastic tasks thus can exploit both period elasticity and computational elasticity. This greatly increases both the diversity of adaptations available to each task and the kinds of real-time tasks relevant to elastic scheduling.

We use the real-world example of real-time hybrid simulation as a motivating application domain with discretely computationally- elastic, period-elastic, and combined-elastic parallel real-time tasks under the Federated Scheduling paradigm. We prove the scheduling of these tasks to be NP-hard, and provide a pseudo-polynomial time scheduling algorithm. We then use this scheduling algorithm to implement the first virtual real-time hybrid simulation experiment in which discrete elastic adaptation of platform resource utilizations enables adaptive switching between controllers with differing computational demands. We also study the effects of scheduling tasks with discretized vs. continuous candidate utilizations.

2. FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices: An updated 2022 landscape

Authors: Geeta Joshi, Aditi Jain, Sabina Adhikari, Harshit Garg, Mukund Bhandari
doi: https://doi.org/10.1101/2022.12.07.22283216
As artificial intelligence (AI) has been highly advancing in the last decade, machine learning (ML) based medical devices are increasingly used in healthcare. In this article, we did an extensive search on FDA database and performed analysis of FDA approved Artificial Intelligence and Machine Learning (AI/ML)-Enabled Medical Devices. We have presented all the listed AI/ML-Enabled Medical Devices according to the date of approval, medical specialty, implementation modality of Medical Devices, and anatomical site of use. Our summary includes the current landscape of FDA approved AI/ML-Enabled Medical Devices till date and different FDA approval pathways for medical devices which will help understand the overview of AI/ML-Enabled Medical Devices, and its overall trends.

3. Genome and transcriptome dynamics of Amaranth species

Authors: Sabina Adhikari, Dinesh Adhikary, Upama Khatri-Chhetri