ABSTRACT
A Cloudlet federation can be beneficial to overcome the latency and resource scarcity challenges in a cloudlet deployment altogether, as a task can run on a cloudlet within the federation, sharing resources of member cloudlets. Nonetheless, the cloudlet federation is not context-aware in terms of latency, so to perform federated learning in cloudlet federation, the selection of a resource-efficient deep learning model is challenging. Additionally, the accuracy of a deep learning model can be affected if end-user devices are unreliable and provide incorrect data for training deep learning models at the cloudlets. Thus, resource and context-aware federated learning solutions are required for accurate and latency-critical applications such as COVID-19 detection using X-ray images. This paper presents a novel context-aware cloudlet federated learning solution for COVID-19 detection that monitors the resources of a cloudlet using a broker thereby minimizing latency without any impact on the accuracy of the deep learning model. Results show that the proposed model reduces the latency by 5% and increases the accuracy by 5% as compared to the state-of-the-art conventional federated learning approach.
ABSTRACT
Objective: NA Background: We present 3 clinically important, treatment-responsive COVID-19 related neurological cases. Diagnosis and treatment can be challenging but neurological sequelae may be treatable, and recovery can occur. Design/Methods: NA Case 1: An 81-year-old gentleman was admitted with a one-week history of incoherent speech, deteriorating mobility, and poor appetite. While admitted, he developed cyclical apnoeic spells during sleep. Neurological examination revealed profound spasticity, hyper-reflexia, myoclonus and startle response to loud noise. Clinically, he was treated as a case of progressive encephalopathy rigidity and myoclonus (PERM) and responded well to intravenous immunoglobulin with improvement in his cognition and mobility. To our knowledge, this is the first case report of post-Covid PERM. Case 2: A 76-year-old lady, recovered from COVID-19 infection, continued to deteriorate neurologically with cognitive slowing, aphasia, and dyskinesia. Cranial MRI was unremarkable and CSF was sterile. Encephalopathic changes were noted on scalp EEG. Autoimmune encephalitis was suspected, a 3-day course of methyl prednisolone yielded significant improvement and complete recovery ensued over 3 months. Case 3: A 44-year-old man admitted with COVID-19 pneumonitis developed sudden onset left arm weakness and sensory loss, treated as COVID-related ischemic stroke. Extensive white and grey matter hyper-intensity with punctate hemorrhage on MRI raised radiological suspicion of hemorrhagic encephalitis or vasculitis. There was no beading on a subsequent MR angiogram. He was treated with a course of intravenous methyl prednisolone and a weaning regime of oral prednisolone. At 4-month follow up, he had made a good functional recovery. Conclusions: We report three cases of neurological complications temporally associated with COVID-19 infection. Improvement occurred following immunosuppression, which supports hypotheses of virus-induced autoimmunity.