Falls are a major health problem in the elderly population. Therefore, a dedicated monitoring system is highly desirable to improve independent living. This paper presents a video based fall detection system in an indoor environment using convolution neural network. Identifying human poses is important in detecting fall events as specific "change of pose" defines a fall. Knowledge of series of poses is a key to detecting fall or non-fall events. A lying pose which may be considered as an after-fall pose is different from other normal activities such as lying/sleeping on the sofa or crawling. This paper uses Convolutional Neural Networks (CNN) to recognise different poses. Using Kinect, the following image combinations are explored: RGB, Depth, RGB-D and background subtracted RGB-D. We have constructed our own dataset by recording different activities performed by different people in different indoor set-ups. Our results suggest that combining RGB background subtracted and Depth with CNN gives the best possible solution for monitoring indoor video based falls.
Dementia refers to a group of chronic conditions that cause the permanent and gradual cognitive decline. Therefore, a Person with Dementia (PwD) requires constant care from various classes of caregivers. The care costs of PwDs bear a tremendous burden on healthcare systems around the world. It is commonly accepted that utilising smart homes (SH), as an instance of ambient assisted living (AAL) technologies, can facilitate the care, and consequently improve the quality of PwDs wellbeing. Nevertheless, most of the existing platforms assume dementia care is a straight application of standard SH technology without accommodating the specific requirements of dementia care. A consequence of this approach is the inadequacy and unacceptability of generic SH systems in the context of dementia care. Contrary to most of the existing SH systems proposed for dementia care, this study considers the specific requirements of PwDs and their care circle in all development steps of an SH. In addition, it investigates how utilising novel design and computing approaches can enhance the quality of SHs for dementia care. To do so, the requirements of dementia care stakeholders are collected, analysed and reflected on in an SH system design. Extensions and adaptation of existing frameworks and technologies are proposed to implement a prototype based on the resulting design. Finally, thorough evaluations and validation of the prototype are carried out. The evaluations by a group of stakeholders show the suitability of the proposed methodology and consequently the resulting prototypes for reducing dementia care difficulties as well as its potential for deployment in the real-world environment.
Abstract-Cloud providers offer their IaaS services based on virtualization to enable multi-tenant and isolated environments for cloud users. Currently, each provider has its own proprietary virtual machine (VM) manager, called the hypervisor. This has resulted in tight coupling of VMs to their underlying hardware hindering live migration of VMs to different providers. A number of user-centric approaches have been proposed from both academia and industry to solve this issue. However, these approaches suffer limitations in terms of performance (migration downtime), flexibility (decoupling VMs from underlying hardware) and security (secure live migration). This paper proposes LivCloud to overcome such limitations. An open-source cloud orchestrator, a developed transport protocol, overlay network and secured migration channel are crucial parts of LivCloud to achieve effective live cloud migration. Moreover, an initial evaluation of LAN live migration in nested virtualization environment and between different hypervisors has been considered to show the migration impact on network throughput, network latency and CPU utilization. The evaluation has demonstrated the need for optimization within the LAN environment.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations鈥揷itations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright 漏 2024 scite LLC. All rights reserved.
Made with 馃挋 for researchers
Part of the Research Solutions Family.