Medical Internet Of Things Enabled Intelligent Remote Patient Monitoring Using Wireless Sensor Network Technologies And Abnormality Detection Using Convolution Neural Network


  • Vignesh Ramamoorthy. H Associate Professor, Department of IT and Cognitive Systems, Sri Krishna Arts and Science College, Coimbatore-641 008, Tamil Nadu
  • S. Sridevi Assistant Professor, Department of Computer Science, KPR College of Arts Science and Research, Coimbatore -641407
  • Chandrashekhar B Banad Assistant Professor, Department of Automobile Engineering VNR Vignana Jyothi Institute of Engineering & Technology, Hyderabad
  • G. Siva Brindha Assistant Professor, Department of Information Technology, Hindusthan College of Arts & Science, Coimbatore- 641028


Medical Internet of Things, Patient health monitoring, GPS module, Wireless Sensor Network, Convolution Neural Network


Nowadays, people are exposed to various diseases due to lifestyle and climatic changes worldwide. Hence, it is considered essential to protect the health of human beings from multiple diseases and to increase the security of human beings from protecting from mortality. Effective patient monitoring becomes mandatory in the medical community to accomplish the proper life cycle of the patient. The department of the medical council establishes various schemes to preserve and protect the patient surviving multiple diseases. However, manual monitoring of patients is highly challenging. With the advancement of different sensor technologies, it is still easier to increase the efficiency of the automated monitoring model. The Internet of Things enabled distributed applications to provide an efficient solution. In this article, innovative medical Internet of Things allowed patient health and location tracking system using intelligent wireless sensors to be designed and experimented with using tiny, highly calibrated sensors. It is a distributed wireless model incorporating monitoring sensors, data collection units, transceivers, and base stations. The proposed wireless sensor network comprises a pressure sensor, blood glucose sensor, heartbeat sensor, temperature sensor, GPS module, and PIR sensor
that acquires the sensed data. It transforms it to the IOT server for further analysis. The temperature sensor senses the temperature of the patient, the PIR sensor senses the human movement in the specified region, the Blood glucose monitoring sensor measures blood glucose level, the blood pressure sensor measures the blood pressure of the patient, and the GPS module transmits the location information to the data collection unit or controller as aggregate information containing sensing data. The further controller transmits that aggregated information to the base station for the data server for data analytics operations. In this paradigm, the base station is implemented to control and manage the health and security of the patients on any critical event detection using deep learning architecture. Deep learning architecture employing a convolution neural network gathers the patient data from the base station and generates the feature from the convolution and pooling layers. The feature map generated will process in the softmax layer to identify the patient status. On the prediction of the abnormality, IoT enabled module generates the warning messages as a prerecorded voice
through the speaker or voice processor to alert the neighbor. A further warning message is transmitted to the doctor or hospital through a GPS module regarding the abnormality of the patient's health with their present location. Experimental analysis of the proposed modules is evaluated on their effectiveness and efficiency in managing the patient health in their location and preventing the patient health by timely treatment procedure.




How to Cite

Vignesh Ramamoorthy. H, S. Sridevi, Chandrashekhar B Banad, & G. Siva Brindha. (2023). Medical Internet Of Things Enabled Intelligent Remote Patient Monitoring Using Wireless Sensor Network Technologies And Abnormality Detection Using Convolution Neural Network. Chinese Journal of Computational Mechanics, (5), 75–80. Retrieved from