Solving Task Scheduling Problem in the Cloud Using a Hybrid Particle Swarm Optimization Approach

Synergistic confluence of pervasive sensing, computing, and networking is generating heterogeneous data at unprecedented scale and complexity. Cloud computing has emergered in the last two decades as a unique storage and computing resource to support a diverse assortment of applications. Numerous organizations are migrating to the cloud to store and process their information. When the cloud infrastructures and resources are insufficient to satisfy end-users requests, scheduling mechanisms are required. Task scheduling, especially in a distributed and heterogeneous system is an NP-hard problem since various task parameters must be considered for an appropriate scheduling. In this paper we propose a hybrid PSO and extremal optimization-based approach to resolve task scheduling in the cloud. The algorithm optimizes makespan which is an important criterion to schedule a number of tasks on different Virtual Machines. Experiments on synthetic and real-life workloads show the capability of the method to successfully schedule task and outperforms many known methods of the state of the art.

Stability and Variability of Indoor Room Transitions and Mild Cognitive Impairment in Older Adults

Indoor room transition is an underexplored real-world activity outcome. We estimated the stability and variability of indoor room transitions and their associations with mild cognitive impairment (MCI) in older adults. Older adults living-alone (n=159, age=78.3±8.8 years, 14% MCI) from the Oregon Center for Aging & Technology (ORCATECH) and the Minority Aging Research Study (MARS) were included. Room transitions were detected using passive infrared motion sensors in bathroom, bedroom, kitchen, and living room. The hourly number of room transitions was used to calculate the interdaily stability and intradaily variability of room transitions. MCI was operationalized by the Clinical Dementia Rating equaled 0.5. Generalized estimating equations models adjusted for demographics, health, and environmental factors revealed that older adults with MCI had a lower interdaily stability of room transitions than cognitive healthy peers (z=-2.06,p=0.03). A pervasive-sensing system deployed in homes can obtrusively measure room transition activities to inform cognitive health in older adults.