Browsing by Author "SP17-BCS-029 , SP17-BCS-101 , SP17-BCS-080"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Mvitals - An Intelligent Edge Computing Based Wireless Mobile Healthcare System
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Noor Jaffri , Muhammad Irtiza , Hafsa Khan; SP17-BCS-029 , SP17-BCS-101 , SP17-BCS-080; Imran Raza
    Internet of Things (IoT) made it possible to interconnect millions of different “Things” to create huge networks. IoT based applications include but not limited to smart homes, automated parking systems, fitness bands and health monitoring systems, etc. IoT made it possible to build autonomous and effective real-time health care monitoring systems. It allows these systems to be equipped with sensors that collect the patient’s data regarding vital signs and reduce human error. The existing systems use cloud computing technology where the collected data is stored, processed and analysed on cloud servers. As the human population has been increasing exponentially, the public healthcare sector is focusing on advanced wearable devices rather than traditional monitoring systems. Due to a lack of continuous monitoring, many patients have been suffering in hospitals as well as in homes. To overcome this problem, technical experts are discovering new and viable approaches based on various technologies e.g., cloud, edge and fog computing. The proposed intelligent system i.e., mVitals, is based on edge computing and targets such patients who require real-time healthcare monitoring. This system will be highly portable and easy to use. The key objective of mVitals is to monitor the patients’ vital signs such as heart rate, electrocardiogram (ECG), body temperature, etc. in real-time. The communication of the system will be wireless, so the patient wearing it will not feel tangled with wires. mVitals will be designed using Arduino UNO and various sensors such as ECG, heart rate, body temperature, oxygen saturation level, blood pressure and body posture. The patient’s data will be acquired via sensors and transferred to an edge server to reduce latency and bandwidth utilization. Edge server will transfer the real-time data to the AI server, where machine learning algorithms will be applied on acquired data for noise reduction, analytics, predictions, and alert generation. Medical history and reports of the patients will be stored in a real-time database which will further help doctors to assess the patient’s condition and suggest treatment plans.