A systematic review may provide technical and practical literature for a specific topic (50). A systematic review requires a proper collection of papers on the subject. Preparing a dataset is one of the main steps in determining review work quality (50). According to the P.R.I.S.M.A. guidelines, the present study has collected the most relevant studies from W.O.S. and Scopus libraries (51). There are four steps for preparing the database using the P.R.I.S.M.A. guidelines, including (52): (1) identification, (2) screening, (3) eligibility, and (4) inclusion. In the identification step, we employed the frequently used keywords, including COVID-19, pandemic, diagnosis, detection, Prediction, Monitoring, Classification, Identification, IoT, and Machine learning to search within the article title abstract and keywords. In the first step, about 109 articles have been identified and selected from the Thomson Reuters Web-of-Science (WoS) and Elsevier Scopus. In the Screening step, the duplicate articles have been removed. Twenty-five articles (about 23%) have been removed from the dataset. Thirty nine articles (about 36%) have been eliminated due to the lack of details on the methods, datasets, full text, etc. A total of 45 cases (about 41%) have been included in the screening step. In the eligibility step, the authors team surveyed the full text of the papers, and marked the relevant articles during monitoring eligibility. In this phase, 23 cases (about 22%) have been selected for investigating the evaluation criteria and including in the dataset.

IoT is an interconnected set of computing tools from simple to complex that can be used in conjunction with mechanical or digital machines in the presence of humans, animals, or objects. IoT technology can easily transfer data from the source to the destination through the network without the operator's presence. This technology can be considered a special tool in human-human interaction or human-computer interaction (53, 54). An IoT platform includes the minimum equipment required, such as smart devices equipped with the web (55). These systems consist of processors, sensors, and communication hardware to collect, send, control, manage, and convert data into accessible data (55, 56). These systems connect to an IoT port used to send data to the cloud so that data can be analyzed and shared (57). These devices can operate by connecting to other related systems based on their information (58). These tools perform many of their tasks without human intervention.

Today, IoT technology in health and treatment is growing rapidly (59). The main applications of IoT in the process of treatment and intelligent health can include identification, digitization of medical information, patient transfer to the hospital, use of vital signs sensors, use of smartphones in communication, and digitization of medical processes (60, 61). Furthermore, IoT has become more popular and important due to the COVID-19 pandemic (62). Because this virus is highly contagious and has a high risk to human health, and has caused many problems for the medical staff, using non-contact methods to diagnose as soon as possible, control patients, monitor the condition of patients with acute illness, as well as maintain social distance, can be an important factor in breaking off part of the virus infection cycle (63, 64). In non-contact methods, the IoT is a leader and can solve many problems in this field (65). Figure 1 presents the main applications of the IoT in COVID-19 era.

Table 2 presents the highlighted studies for applying IoT-based techniques to tackle COVID-19. This table represents the studies based on the main four columns. First, the objective briefly describes the main objective of each study. Methodology/proposed algorithm presents the main algorithm and procedure employed by each study. Keyword indicates the main points and concentration of the study and finally, the application section presents the field of the application of each method.

Figure 2 presents the contribution of different applications which are performed by IoT techniques to track COVID-19 related fields.

Figure 2 is generated based on Table 2 to present the main applications and their portions by studies for handling IoT in the COVID-19 pandemic. Monitoring, detection, and diagnosis are the main application of IoT-based techniques in tackling the COVID-19 pandemic. Monitoring can be performed in different ways. Accordingly, Roy et al. employed IoT as a real-time solution for monitoring COVID-19 outbreaks (66). Also, Otoom et al. employed IoT to provide monitoring and detection data using a real-time system to feed to the machine learning algorithms for further applications or handling (69). Singh et al. and Vedaei et al. used IoT as a tool for monitoring COVID-19 patients and their health condition in cooperating with an interconnected network (70, 71). Ashraf et al. proposed a smart edge surveillance system to monitor wearable smart gadgets which are operated according to IoT-based technology (72). Karmore et al. developed a Medical Diagnosis Humanoid to provide a complete diagnostic system for COVID-19 using IoT-based technology (74). De Vito et al. presented the outputs of a high-resolution A.Q. monitoring system based on an IoT-based technique (80).

Baskaran et al. used a non-contact infrared sensor to examine the body temperature to detect the patients with COVID-19 (73). Wang et al. exploited the social relationships in the platform of Social IoT to solve controlling issues of the COVID-19 epidemic by sharing the limited protective resources (77). Kumar et al. investigated an IoT based platform to prevent the spreading of COVID-19 (78). Kolhar et al. developed a platform of a decentralized IoT-based biometric based on a face detection platform for handling COVID-19 outbreaks (79). Aman et al. developed an architecture of IoT based framework for medical applications with respect to combat COVID-19 (38). Manalu et al. investigated the information technology to respond COVID-19 pandemic trend in accordance with the IoT technology (81).

Figure 3 presents the main contribution of these papers. According to the reviewed studies, the COVID-19 dataset can be imported from three main sources, including Radiography, statistics of health centers, and Sensors for prediction, monitoring, identification, detection, diagnosis, and classification purposes. The output of the techniques needs to be evaluated to confirm the approach performance and accuracy values. The frequently used parameters for performance analysis include Accuracy, Precision, Recall, R.M.S.E., Correlation coefficient and mean absolute percentage error. This can be considered a brief explanation of the main contribution of the present study. This study successfully presents the advantages and disadvantages of each technique for a specific task in handling the COVID-19 dataset and proposes the future perspectives. Also, this study can detect the main challenges and limitations.

There is a need to categorize the main applications of IoT and the relevance technique following COVID-19. Table 3 presents the study's main contributions to the application of IoT and integrated IoT-ML-based techniques. Based on Table 3, the exact application of each of the methods used can be extracted. It is also possible to find out which methodology is still available for which application can be considered a research opportunity for the future. Also, by carefully examining the different reasons for the tendency of each method to the fields shown in independent research, which can be considered necessary research and planning opportunities for policymakers in this field.

As shown in Table 3, IoT-based technology requires ML-based techniques to complete the task. Figure 4 presents the share of each methodology in the applications by percentage.

As shown in Figure 4, IoT has been used more than other applications to monitor and detect COVID-19 cases. However, it has been less popular in the identification at the same time.

Utilizing the ML platform led to reducing the adverse effects of the disease and accelerating the healing process (62). The combination of A.I. and ML has led to advances in treatment, medication, screening, prognosis, contact tracking, and the drug/vaccine development process and reduced human intervention in medical performance (82). ML is also used as a tool for managing virtual queues to prevent crowds in physical waiting rooms or long queues. In addition, it is used to predict waiting times and implement calls in a privacy manner in conjunction with the cell phone platform (83).

The ML method is widely used in data analysis by intelligently producing an analytical model. This method is a subset of artificial intelligence that analyzes data and produces a model for estimating, categorizing, optimizing, predicting, identifying problems, and decision-making (84, 85).

New computing technologies have made the problems assessed by ML-based techniques today a little different from the way they are analyzed based on past technologies (86). These techniques began to evolve from pattern recognition to a comprehensive theory of the ability of computers to perform specific tasks without the need for special planning (87, 88).

In the field of medicine and treatment, ML is known as one of the most practical tools for analyzing medical data, identifying, predicting, and even treating different situations. With the advancement of medical science in today's world and the production of large volumes of medical data, there is an urgent need to analyze this data (89). Figure 5 presents the main applications of ML-based techniques for medical science to tackle the COVID-19 pandemic. Identifying the prevalence, effective parameters in the eradication of the virus, identifying patients in the early stages, patients' pattern behaviors, and predicting outbreak and mortality rates can be considered practical and effective areas of ML-based techniques (90, 91).

Table 4 presents the highlighted studies for the application of ML-based techniques for handling COVID-19. Similar to Tables 3, 4 discuss them in four columns. The objective column briefly describes the main objective of each study. Methodology/proposed algorithm presents the main algorithm and procedure employed by each study. Keyword indicates the main points and concentration of the study and finally, application section presents the field of the application of each method.

According to Table 4, ML-based techniques are employed for detection, identification, monitoring, diagnosis, prediction, and classification purposes in the presence of the COVID-19 dataset. Figure 6 presents the summary of each application separately. Singh and Kaur employed an ML-based platform using hybrid random forest, Gaussian Naïve Bayes, and Generative adversarial network as a healthcare application to detect COVID-19 cases (93). Vinod et al. developed a pre-trained CNN method as an ML-based technique integrated using C.T. scan and chest x-ray images to identify, detect, and predict the positive infected patients (94). Ardakani et al. developed an ML-based technique (ResNet) for fast diagnosis of COVID-19 cases compared to radiology data (96). Polsinelli et al. developed a study to detect COVID-19 promptly using CNN as a frequently used DL-based architecture (97). Nour et al. proposed an intelligence computer-aided model based on CNN with SVM classifier architecture on chest X-rays to support daily clinical applications (98). Chowdhury et al. investigated the utility of A.I. in the rapid and accurate detection of COVID-19 in the presence of chest X-ray images (102). Sethi et al. employed Logistic Regression (L.R.), Multinomial Naïve Bayes, Decision Tree (D.T.), Random Forest (R.F.), SVM, and XGBoost classifiers to analyze the emotions expressed by people using social media to monitor and detect sentiment behind COVID-19 (110). Ardabili et al. developed ML-based techniques for the prediction of COVID-19 outbreaks (91). In another study, Ardabili et al. also employed a hybrid ML-based technique (Multilayered perceptron integrated by gray wolf optimizer) for the global prediction of COVID-19 cases (90). In addition, Loey et al. employed the DL-based ResNet method in the presence of an SVM-based classifier to detect a masked face (92).

According to Figure 6, detection, diagnosis, and prediction can be considered as the main categories of the application of ML-based methods in COVID-19. In general, one of the main sections of analyzing IoT-based and ML-Based techniques applied for a specific field is their evaluation in terms of accuracy, error, or in other word performance of the model. Table 5 presents the evaluation criteria employed for each model.

According to Table 5, accuracy, followed by the recall and precision parameters has owned the highest portion of the evaluation criteria employed for analyzing COVID-19 based dataset using IoT and ML-based techniques. In the following, Table 6 is generated from Table 4 for indicating the share of each ML-based technique for each application and their main contributions. According to Table 6, ResNet as an architecture of deep learning methods followed by CNN, XGBoost, SVM, D.T., and L.R. has been used more often to tackle work with COVID-19 related data.

Figure 7 presents the share of different ML methods for different tasks to tackle the COVID-19 pandemic. As is clearly indicated in this figure, ResNet, followed by CNN, is the most common application of ML in this field. This can be due to the model's nature for handling different applications like monitoring, detection, identification, classification, and diagnosis. In comparison, other methods can do a limited number of applications.

Models developed using ML and IoT-ML require an evaluation step for recognizing their performance and accuracy values. According to the studies reviewed, the most effective and frequently used evaluation criteria are including Accuracy, Recall, Precision, Root mean square error (R.M.S.E.), Correlation coefficient and Mean absolute percentage error (M.A.P.E.). These criteria compare the models' output and actual values and provide a comparison score (90, 91). In the present study, we employed the criteria values reported by each study for evaluating and comparing the models. Table 7 presents the main criteria for evaluation.

This section presents the main findings of IoT based techniques (Table 8) and ML-based techniques (Table 9). Each table includes two main columns called findings and pros. and cons.

According to Table 8, most of these studies lack numerical analysis for the method's performance. One of the main reasons can be the nature of the IoT technique, which goes through a practical process and shows its performance in practical applications and does not need to provide numerical statistics. In all these applications, IoT could successfully cope with the task. IoT provided a fast and efficient approach to tracking the disease spread (66). On the other hand, it can be employed as a real-time framework to minimize the impact of communicable diseases through the early detection of cases (67). In the study by Singh et al. IoT technology successfully increased patient satisfaction and reduced the readmission rate in the hospital (70). However, there is a need to integrate IoT platforms with ML-based techniques for detection purposes. In the study by Rahman et al. DL applications with IoT platforms provided promising findings to detect A.E. attacks. However, there is a need for further research, attention, and implementation of appropriate defense mechanisms, safeguards, and controls (67). Kolhar et al. employed Multi-task Cascaded Convolutional Network architecture (M.C.C.N.N.), and findings claimed that the efficiently integrated by Raspberry Pi increased the robustness of detection and recognition (79).

According to the findings given in Table 9, the most share of studies developed by ML-based techniques for handling COVID-19 based datasets provided performance criteria. The most share of the performance criteria, according to Figure 8 is related to the accuracy factor. Accuracy factor is a general and normalized factor. Therefore, it can be employed for comparing the ML-based methods with different datasets. Figure 9 presents the accuracy values for each model for comparing their performance in handling the COVID-19 dataset.

Figure 9 indicates CNN with SVM classifier, Genetic CNN, and pre-trained CNN followed by ResNet, provided highest accuracy values. On the other hand, the lowest accuracy was related to single CNN followed by XGboost and K.N.N. techniques.

Nowadays, when the world is struggling with COVID-19 disease, every innovation and technology is used to fight this disease. Like many other areas, healthcare requires the support of new technologies such as IoT, and ML. Exploring the disease-related dataset, data preparation, prevention, and control of infectious diseases has become one of the main purposes of A.I. IoT and ML have a vital personality in better understanding, dealing with the COVID-19 crisis, and discovering the COVID-19 vaccine. ML-based technology allows computers to predict the pattern and speed of disease transmission with their intelligence and by mimicking large amounts of data. A.I. uses information from people with coronary heart disease, and improved and dead people as tracking data.

To combat the spread of the corona virus, IoT-based methods of communicating with patients provide transparency and a better understanding of how the virus is spread and strengthen the treatment and research process. ML is one of the new technologies for tracking the spread of the virus and finding effective parameters in it. The ML method can successfully identify high-risk patients and predict the necessary measures to deal with possible infections to reduce the point of the effect of the disease. In addition, ML-based methods can estimate the risk of patient mortality through previous analysis. This technique improves patients' planning, treatment, and reduction and is a complementary medical tool that works with data and evidence. On the other hand, this technology improves decision-making and reduces the cost of treatment and diagnosis. At the same time, in medical imaging, ML tools help to recognize the patterns in the images and strengthen the ability of radiologists to diagnose the possibility of disease and early diagnosis of the disease.

One of the main limitations of IoT, and ML-based techniques for applications in COVID-19 is the lack of a complete dataset. This can be due to the unique development of models by limited data for a specific application within the same data field. The purpose of using IoT, A.I., or ML-based techniques is to solve a specific problem in the real world with a real application that requires the use of special hardware and equipment. There are limitations in the cost and availability of developing and equipping communication hardware in therapeutic, diagnostic, estimation, and forecasting applications for IoT technology or ML-based techniques. Also, there are limited best practices available for IoT developers. The lack of IoT edge authentication and licensing standards has led to restrictions on the application and enactment of laws, regulations, and policies in the use of this technology, and this has led to the absence of IoT-based incident response activities as the best methods. All of these limitations mean that there is still no focus on identifying ways to gain situational awareness of the security of IoT assets in a medical complex.