Healthcare 4.0 paradigm aims at realization of data-driven and patient-centric health systems wherein advanced sensors can be deployed to provide personalized assistance. Hence, extreme mentally affected patients from diseases like Alzheimer can be assisted using sophisticated algorithms and enabling technologies. Motivated from this fact, in this paper, DeTrAs: Deep Learning-based Internet of Health Framework for the Assistance of Alzheimer Patients is proposed. DeTrAs works in three phases: (1) A recurrent neural network-based Alzheimer prediction scheme is proposed which uses sensory movement data, (2) an ensemble approach for abnormality tracking for Alzheimer patients is designed which comprises two parts: (a) convolutional neural network-based emotion detection scheme and (b) timestamp window-based natural language processing scheme, and (3) an IoT-based assistance mechanism for the Alzheimer patients is also presented. The evaluation of DeTrAs depicts almost 10–20% improvement in terms of accuracy in contrast to the different existing machine learning algorithms.

No abstract

No abstract

The next generation vehicular networks would be expected to support a wide array of cutting edge applications concerning intelligent transportation system (ITS). Due to this reason, the scale and complexity of ITS-based compute-intensive tasks has exhibited a phenomenal increase and will continue to grow in future. Thus, a large quantity of data requiring different levels of processing is generated, that necessities the need of in-vehicle computational resources as well as collaboration from technologies like, cloud and edge computing. This has led to the development of paradigms such as vewehicular cloud computing (VCC) and vehicular edge computing (VEC). Although VCC provides rich computing resources of the cloud servers to process tasks but it is affected due to long latency and instability of connections. In contrast, VEC provides compute resources closer to the data source to offset the relatively higher latency but the task requester should be able to perceive the computing and communication environment so as to allocate tasks effectively. Thus, it is essential to utilize both edge and cloud capabilities to create a collaborative cloud edge network that can cater to the demand of vehicular networks. A distributed task orchestration framework (DTOF) supporting a Vehicle-to-Vehicle based task orchestration scheme has been proposed that utilizes the vehicular movements along urban roads for creation of vehicular edges. The edge creation process utilizes an innovative light weight string processing algorithm based on hashing technique. The performance of DTOF has been evaluated based on extensive simulation by considering Chandigarh city road maps and the obtained results exhibit the satisfactory performance of DTOF for task orchestration.

No abstract