Table 2.

The characteristics of reviewed articles

Author	Country	Main approach	Type of sensor	Disease	Type of monitored vital sign	Function	Applied intelligent methods	Usage
Mohammed et al. (2020)	Malaysia	Proposing the design of system that has capability to detect the coronavirus automatically from the thermal image with less human interactions using smart helmet	Image processing module: smart helmet	COVID-19	The data of people’s face and temperature	Facial-recognition technology can also display the pedestrian’s personal information which can automatically take pedestrians’ temperatures. Optical camera and infrared thermal camera which provided information about the temperature at which the different focuses of interest were found	Cascade Classification algorithm + Viola–Jones algorithm	This helmet can help to people to screen infected persons; this allows persons with increased body temperature to be identified quickly and reliably, and to be isolated for more exact testing
Chung et al. (2020)	Taiwan	Providing the HEARThermo to continuously monitor body surface temperature and heart rate to trigger the reminders sent by chatbots	Watch-like wearable device	COVID-19	Body surface temperature and heart rate	Body temperature measurements once daily for healthcare workers and twice daily for people in isolation or quarantine are important measures to reduce the risk of cross infections	Not mentioned	The HEARThermo, as a wearable physiological monitor for remotely monitoring the health status of people under risk of infection, provides real-time data and decision support for healthcare providers and public health agencies
Hassan et al. (2018)	Malaysia	Proposing a conceptual IoT-based patient monitoring sensor for predicting and controlling dengue outbreak	Body area network: patient worn sensors	Dengue: mosquito-borne virus	Body temperature, heart-beat, blood pressure	The patient's vital signs and physiological information were monitored by 3 type of sensor These data received from sensors and then analyzed by analytical tools for better and effective decision making	Cloud computing algorithm: cloud machine learning platform	The analyzed data and proposed sensors will be used by the medical officer in healthcare organization for decision making. they can be visualized in dashboard to update the predictive factors and controlling the dengue outbreak. Also it can provide right medical support for predicting and controlling dengue
Lorence and Wu (2012)	USA	Proposing one promising model for using a combination of emerging systems-based technologies in multi sensor cartridges	Monitoring device worn as an arm cuff	Potential epidemics	Pulse, Blood pressure, or analyte detection	All data about users may be automatically gathered and stored at the remote server, those data may be used for elaboration of medical prognoses, epidemic trends, and/or risk calculations The server may include a computer program for data processing	Not mentioned	Where this system can be linked to multiple analyte measures and recorded continuously in real time, the integrated system can serve as an effective public health or clinical application, where there is need for immediate collection
Valsalan et al. (2019, 2020)	Oman	Designing and implementation of a smart patient health tracking system that uses sensors to track patient health	Body area network: patient worn sensors	Potential epidemics: rural areas	Pulse rate and body temperature	These sensors are connected to a control unit, calculates the values of the sensors. These values are then transmitted through a IoT cloud to the base station Based on the temperature and heart beat values, the doctor can decide the state of the patient and appropriate measures can be taken	Rule-based machine learning algorithm	A remote health monitoring system using IoT is proposed where the authorized personal can access these data stored using any IoT platform and based on these values received, the diseases are diagnosed accurately by the doctors from a distance
Radin et al. (2020)	USA	Proposing a predefined wearable sensor and evaluating the retrieved data to improve the ability to enact quick outbreak	A Fitbit wearable device	Respiratory infections: such as influenza	Total RHR (resting heart rate) and sleep measures	According to Fitbit, RHR is calculated as follows: periods of still activity during the day are identified by looking at the accelerometer signal provided by the device If inactivity is observed for a sufficiently long time, then it is assumed that the person is in a resting state, and their heart rate at that time is used to estimate their RHR	Mathematical model + association rule mining	By accessing these data, it could be possible to improve real-time and geographically refined influenza surveillance. This information could be vital to enact timely outbreak response measures to prevent further transmission of influenza cases effectively
De and Mukherjee (2015)	India	Taking proper action for curing the patient based on the health parameters’ values	Body area sensor network: patient worn sensors	Infectious diseases	Blood pressure, blood sugar level, respiration rate, body temperature, ECG	In this system health data of a user is captured by body sensor network and then sent to the user’s mobile device which is registered under a femtocell Using a database maintained at femtocell, captured health data are verified and if abnormality is detected, the data are sent to the cloud through the femtocell for storage	Markov chain model + Laplace estimation + Bayesian approach	Analyzing the health status of a number of patients affected by an infectious disease in a particular region, epidemic trends can be detected and then to aware people alert messages are sent over social networking sites
Edoh (2018)	Germany	To protect the population against emerging infectious diseases, request permanent crowd surveillance., particularly in high-risk regions	Optical sensor (fiber-optic sensors)	Ebola and infectious disease	Body temperature	The sense bio-signals using optical sensors of individuals within (ad-hoc) crowd with the objectives to monitor risks of emerging infectious diseases	Pedestrian detection method as a machine learning method to detect pedestrians	According to the results of the conducted experiment, the concept has the potential to improve the conventional epidemiological data collection. The measurement is reliable, and the recorded data are valid. The measurement error rates are about 8%
Sareen et al. (2018)	Guinea, Liberia and Sierra Leone	Proposing a model for remote monitoring of infected patients in real time using cloud computing	RFID	Ebola	Body temperature, blood pressure	Through RFID attached to the user’s body, the vital signs are captured through WBAN and is transmitted to the mobile phone via Bluetooth, from where the data is forwarded to the cloud server using WiFi 3G/4G in real time At the same time, users can enter their secondary and advanced symptoms through the interface provided by the mobile application	Cloud computing + decision tree-based algorithm (J48 decision tree) + SEIHR model	The vital body symptoms and social interactions are captured using WBAN and RFID respectively. The proposed model provided 94% accuracy for the classification and 92% of the resource utilization
Steinhubl et al. (2016)	Sierra Leone	Proposing a sensors based system for creating automated alerting of early changes in patient status	Wearable sensor	Ebola	Heart rate, heart rate variability, activity, respiratory rate, pulse transit time, uncalibrated skin temperature and posture	The researcher developed a modular wireless patient monitoring system (MWPMS) and conducted a proof of concept study in an Ebola treatment centre (ETC) The system was built around a wireless, multiparametric ‘band-aid’ patch sensor for continuous vital sign	Machine learning technology known as similarity-based modelling (SBM)	It can provide high-acuity monitoring with a continuous, objective measure of physiological status of all patients that is achievable in virtually any healthcare setting, anywhere in the world
Sood and Mahajan (2017)	India	Proposing fog based health monitoring system for real time monitoring and analysis of user’s health statistics and related events such as health data	Wearable IoT sensor	Chikungunya	Body temp, joint pain, headache, body pain, red eyes, rashes on the body, nausea, muscle pain and vomiting	Wearable IoT sensor layer collects data in real-time from various health sensors, location sensors, drug sensors, environmental sensors and meteorological sensors The acquired data is transmitted to the fog layer for real time processing and diagnosing possibly infected users from CHV. After diagnosing the CHV, fog layer immediately generates alerts to the user’s mobile	Fog computing	On the basis of health severity, emergency alerts are generated for delivering event information to user’s mobile on time through fog network. It will help uninfected residents to take immediate precautions to prevent the outbreak of these viruses and government healthcare agencies to control the problem effectively