Artificial intelligence-enabled Internet of Things-based system for COVID-19 screening using aerial thermal imaging

Innovative IoT-enabled mask detection system: A hybrid deep learning approach for public health applications

The integration of IoT and deep learning has revolutionized real-time monitoring systems, particularly in public health applications such as face mask detection. With increasing public reliance on these technologies, robust and efficient frameworks are critical for ensuring compliance with health measures. Existing models, on the other hand, often have problems, such as being slow to compute, not being able to work well in a wide range of environments, and not being able to adapt well to IoT devices with limited resources. These shortcomings highlight the need for an optimized and scalable solution. To address these issues, this study utilizes three datasets: the Kaggle Face Mask Dataset, the Public Places Dataset, and the Public Videos Dataset, encompassing varied environmental conditions and use cases. The proposed framework integrates ResNet50 and MobileNetV2 architectures, optimized using the Adaptive Flame-Sailfish Optimization (AFSO) algorithm. This hybrid approach enhances detection accuracy and computational efficiency, making it suitable for real-time deployment. The novelty of the paper lies in combining AFSO with a hybrid deep learning architecture for parameter optimization and improved scalability. Performance metrics such as accuracy, sensitivity, precision, and F1-score were used to evaluate the model. The proposed framework achieved an accuracy of 97.8 % on the Kaggle dataset, significantly outperforming baseline models and demonstrating its robustness and efficiency for IoT-enabled face mask detection systems.•The article introduces a novel hybrid framework that combines ResNet50 and MobileNetV2 architectures optimized with Adaptive Flame-Sailfish Optimization (AFSO).•The system demonstrates superior performance, achieving 97.8 % accuracy on the Kaggle dataset, with improved efficiency for IoT-based real-time applications.•Validates the framework's robustness and scalability across diverse datasets, addressing computational and environmental challenges.

The Use of Hybrid CNN-RNN Deep Learning Models to Discriminate Tumor Tissue in Dynamic Breast Thermography

Breast cancer is one of the leading causes of death for women worldwide, and early detection can help reduce the death rate. Infrared thermography has gained popularity as a non-invasive and rapid method for detecting this pathology and can be further enhanced by applying neural networks to extract spatial and even temporal data derived from breast thermographic images if they are acquired sequentially. In this study, we evaluated hybrid convolutional-recurrent neural network (CNN-RNN) models based on five state-of-the-art pre-trained CNN architectures coupled with three RNNs to discern tumor abnormalities in dynamic breast thermographic images. The hybrid architecture that achieved the best performance for detecting breast cancer was VGG16-LSTM, which showed accuracy (ACC), sensitivity (SENS), and specificity (SPEC) of 95.72%, 92.76%, and 98.68%, respectively, with a CPU runtime of 3.9 s. However, the hybrid architecture that showed the fastest CPU runtime was AlexNet-RNN with 0.61 s, although with lower performance (ACC: 80.59%, SENS: 68.52%, SPEC: 92.76%), but still superior to AlexNet (ACC: 69.41%, SENS: 52.63%, SPEC: 86.18%) with 0.44 s. Our findings show that hybrid CNN-RNN models outperform stand-alone CNN models, indicating that temporal data recovery from dynamic breast thermographs is possible without significantly compromising classifier runtime.

Unmanned aerial vehicles and pre-hospital emergency medicine

Unmanned aerial vehicles (UAVs) are used in many industrial and commercial roles and have an increasing number of medical applications. This article reviews the characteristics of UAVs and their current applications in pre-hospital emergency medicine. The key roles are transport of equipment and medications and potentially passengers to or from a scene and the use of cameras to observe or communicate with remote scenes. The potential hazards of UAVs both deliberate or accidental are also discussed.

Hybrid deep learning model based smart IOT based monitoring system for Covid-19

Recently, COVID-19 becomes a hot topic and explicitly made people follow social distancing and quarantine practices all over the world. Meanwhile, it is arduous to visit medical professionals intermittently by the patients for fear of spreading the disease. This IoT-based healthcare monitoring system is utilized by many professionals, can be accessed remotely, and provides treatment accordingly. In context with this, we designed an IoT-based healthcare monitoring system that sophisticatedly measures and monitors the parameters of patients such as oxygen level, blood pressure, temperature, and heart rate. This system can be widely used in rural areas that are linked to the nearest city hospitals to monitor the patients. The collected data from the monitoring system are stored in the cloud-based data storage and for the classification our approach proposes an innovative Recurrent Convolutional Neural Network (RCNN) based Puzzle optimization algorithm (PO). Based on the outcome further treatments are made with the assistance of physicians. Experimental analyses are made and analyzed the performance with state-of-art works. The availability of more data storage capacity in the cloud can make physicians access the previous data effortlessly.

Optical Biosensors for the Diagnosis of COVID-19 and Other Viruses-A Review

The sudden outbreak of the COVID-19 pandemic led to a huge concern globally because of the astounding increase in mortality rates worldwide. The medical imaging computed tomography technique, whole-genome sequencing, and electron microscopy are the methods generally used for the screening and identification of the SARS-CoV-2 virus. The main aim of this review is to emphasize the capabilities of various optical techniques to facilitate not only the timely and effective diagnosis of the virus but also to apply its potential toward therapy in the field of virology. This review paper categorizes the potential optical biosensors into the three main categories, spectroscopic-, nanomaterial-, and interferometry-based approaches, used for detecting various types of viruses, including SARS-CoV-2. Various classifications of spectroscopic techniques such as Raman spectroscopy, near-infrared spectroscopy, and fluorescence spectroscopy are discussed in the first part. The second aspect highlights advances related to nanomaterial-based optical biosensors, while the third part describes various optical interferometric biosensors used for the detection of viruses. The tremendous progress made by lab-on-a-chip technology in conjunction with smartphones for improving the point-of-care and portability features of the optical biosensors is also discussed. Finally, the review discusses the emergence of artificial intelligence and its applications in the field of bio-photonics and medical imaging for the diagnosis of COVID-19. The review concludes by providing insights into the future perspectives of optical techniques in the effective diagnosis of viruses.

Nighttime light perspective in urban resilience assessment and spatiotemporal impact of COVID-19 from January to June 2022 in mainland China

The outbreak of the coronavirus disease 2019 (COVID-19) epidemic has resulted in large threats and damage to society and the economy. In this study, we evaluate and verify the comprehensive resilience and spatiotemporal impact of the COVID-19 epidemic from January to June 2022 in mainland China based on multisource data. First, we adopt a combination of the mandatory determination method and the coefficient of variation method to determine the weight of the urban resilience assessment index. Furthermore, Beijing, Shanghai, and Tianjin were selected to verify the feasibility and accuracy of the resilience assessment results based on the nighttime light data. Finally, the epidemic situation was dynamically monitored and verified with population migration data. The results show that urban comprehensive resilience of mainland China is shown in the distribution pattern of higher resilience in the middle east and south and lower resilience in the northwest and northeast. Moreover, the average light intensity index is inversely proportional to the number of newly confirmed and treated cases of COVID-19 in the local area. This study provides a scientific reference to improve the comprehensive resilience of cities to achieve the goals of sustainable development (SDGs 11): make cities and human settlements resilient and sustainable.

Elevating Healthcare: Rapid Literature Review on Drone Applications for Streamlining Disaster Management and Prehospital Care in Saudi Arabia

Saudi Arabia's health sector faces pressing challenges in disaster and prehospital care delivery, such as prolonged response times, limited access to remote areas, and strained medical resources. Integrating drone technology has emerged as an innovative approach to address these challenges and revolutionize healthcare delivery. Drones can significantly enhance response times, increase access to underserved areas, and reduce the burden on existing medical infrastructure. A detailed analysis of global case studies demonstrates the successful use of drones in healthcare delivery, emphasizing the importance of regulatory frameworks and public-private partnerships. These examples provide valuable insights into Saudi Arabia's health sector transformation. The potential benefits of integrating drone technology include improved patient outcomes, increased efficiency, and cost savings. To ensure the successful implementation of this transformative approach, it is crucial to establish clear regulatory guidelines, invest in research and development, and foster collaboration between the government, private sector, and healthcare stakeholders. The aim of this study is to explore the potential of drone technology in transforming healthcare delivery in Saudi Arabia, particularly within disaster response and prehospital care services.

Computer-aided methods for combating Covid-19 in prevention, detection, and service provision approaches

The infectious disease Covid-19 has been causing severe social, economic, and human suffering across the globe since 2019. The countries have utilized different strategies in the last few years to combat Covid-19 based on their capabilities, technological infrastructure, and investments. A massive epidemic like this cannot be controlled without an intelligent and automatic health care system. The first reaction to the disease outbreak was lockdown, and researchers focused more on developing methods to diagnose the disease and recognize its behavior. However, as the new lifestyle becomes more normalized, research has shifted to utilizing computer-aided methods to monitor, track, detect, and treat individuals and provide services to citizens. Thus, the Internet of things, based on fog-cloud computing, using artificial intelligence approaches such as machine learning, and deep learning are practical concepts. This article aims to survey computer-based approaches to combat Covid-19 based on prevention, detection, and service provision. Technically and statistically, this article analyzes current methods, categorizes them, presents a technical taxonomy, and explores future and open issues.

A survey of COVID-19 detection and prediction approaches using mobile devices, AI, and telemedicine

Since 2019, the COVID-19 pandemic has had an extremely high impact on all facets of the society and will potentially have an everlasting impact for years to come. In response to this, over the past years, there have been a significant number of research efforts on exploring approaches to combat COVID-19. In this paper, we present a survey of the current research efforts on using mobile Internet of Thing (IoT) devices, Artificial Intelligence (AI), and telemedicine for COVID-19 detection and prediction. We first present the background and then present current research in this field. Specifically, we present the research on COVID-19 monitoring and detection, contact tracing, machine learning based approaches, telemedicine, and security. We finally discuss the challenges and the future work that lay ahead in this field before concluding this paper.

A centralized contact-tracing protocol for the COVID-19 pandemic

Digital contact tracing (DCT) is one of the weapons to be used against the COVID-19 pandemic, especially in a post-lockdown phase, to prevent or block foci of infection. As DCT systems can handle highly private information about people, great care must be taken to prevent misuse of the system and actions detrimental to people's privacy, up to mass surveillance. This paper presents a new centralized DCT protocol, called ZE2-P3T (Zero Ephemeral Exchanging Privacy-Preserving Proximity Protocol), which relies on smartphone localization but does not give any information about the user's location and identity to the server. Importantly, the fact that no exchange of ephemeral identities among users is required is the basis of the strong security of the protocol, which is proven to be more secure than the state-of-the-art protocol DP-3T/GAEN.

Integration of cloud computing with the Internet of things for the treatment and management of the COVID-19 pandemic

The globe is now fighting the COVID-19 epidemic, and a cost-effective method to battle the outbreak is urgently required. In this era, the Internet of Things (IoT) offers healthcare systems or checks and discovers patients in epidemics to prevent the virus from spreading. In order to tackle the current COVID-19 pandemic, intelligent health care based on IoT is becoming increasingly vital in better digital technologies. This technology allows gadgets to link hospitals and other predefined sites to tackle this dilemma. The cognitive Internet of Medical Things (IoMT) is a potential technology for quick analysis, dynamic monitoring and control, improved therapy and management, and prevention of viral transmission. This technology can send a message to the hospital immediately in an emergency. Due to the importance of this subject, the influence of IoT-centered innovations in the management of COVID-19 is examined in this article. The three main areas, including early detection, viral prevention, and patient care, are considered in this paper. The results showed that using IoT, such as drones and robots, has been fruitful in reducing contact with patients and identifying disease symptoms. Also, they showed that the IoT wearable gadgets and the cloud platform to store the patient’s information have helped doctors track the patient’s condition.

Data mining methodology for obtaining epidemiological data in the context of road transport systems

Millions of people use public transport systems daily, hence their interest for the epidemiology of respiratory infectious diseases, both from a scientific and a health control point of view. This article presents a methodology for obtaining epidemiological information on these types of diseases in the context of a public road transport system. This epidemiological information is based on an estimation of interactions with risk of infection between users of the public transport system. The methodology is novel in its aim since, to the best of our knowledge, there is no previous study in the context of epidemiology and public transport systems that addresses this challenge. The information is obtained by mining the data generated from trips made by transport users who use contactless cards as a means of payment. Data mining therefore underpins the methodology. One achievement of the methodology is that it is a comprehensive approach, since, starting from a formalisation of the problem based on epidemiological concepts and the transport activity itself, all the necessary steps to obtain the required epidemiological knowledge are described and implemented. This includes the estimation of data that are generally unknown in the context of public transport systems, but that are required to generate the desired results. The outcome is useful epidemiological data based on a complete and reliable description of all estimated potentially infectious interactions between users of the transport system. The methodology can be implemented using a variety of initial specifications: epidemiological, temporal, geographic, inter alia. Another feature of the methodology is that with the information it provides, epidemiological studies can be carried out involving a large number of people, producing large samples of interactions obtained over long periods of time, thereby making it possible to carry out comparative studies. Moreover, a real use case is described, in which the methodology is applied to a road transport system that annually moves around 20 million passengers, in a period that predates the COVID-19 pandemic. The results have made it possible to identify the group of users most exposed to infection, although they are not the largest group. Finally, it is estimated that the application of a seat allocation strategy that minimises the risk of infection reduces the risk by 50%.

Analysis of factors influencing public attention to masks during the COVID-19 epidemic-Data from Sina Weibo

As we all know, vaccination still does not protect people from novel coronavirus infections, and wearing masks remains essential. Research on mask attention is helpful to understand the public's cognition and willingness to wear masks, but there are few studies on mask attention in the existing literature. The health belief model used to study disease prevention behaviors is rarely applied to the research on mask attention, and the research on health belief models basically entails the use of a questionnaire survey. This study was purposed to establish a health belief model affecting mask attention to explore the relationship between perceived susceptibility, perceived severity, self-efficacy, perceived impairment, action cues and mask attention. On the basis of the establishment of the hypothesis model, the Baidu index of epidemic and mask attention, the number of likes and comments on Weibo, and the historical weather temperature data were retrieved by using software. Keyword extraction and manual screening were carried out for Weibo comments, and then the independent variables and dependent variables were coded. Finally, through binomial logistic regression analysis, it was concluded that perceived susceptibility, perceived severity and action cues have significant influences on mask attention, and that the accuracy rate for predicting low attention is 93.4%, and the global accuracy is 84.3%. These conclusions can also help suppliers make production decisions.

AI-enabled radiologist in the loop: novel AI-based framework to augment radiologist performance for COVID-19 chest CT medical image annotation and classification from pneumonia

A SARS-CoV-2 virus-specific reverse transcriptase-polymerase chain reaction (RT-PCR) test is usually used to diagnose COVID-19. However, this test requires up to 2 days for completion. Moreover, to avoid false-negative outcomes, serial testing may be essential. The availability of RT-PCR test kits is currently limited, highlighting the need for alternative approaches for the precise and rapid diagnosis of COVID-19. Patients suspected to be infected with SARS-CoV-2 can be assessed using chest CT scan images. However, CT images alone cannot be used for ruling out SARS-CoV-2 infection because individual patients may exhibit normal radiological results in the primary phases of the disease. A machine learning (ML)-based recognition and segmentation system was developed to spontaneously discover and compute infection areas in CT scans of COVID-19 patients. The computable assessment exhibited suitable performance for automatic infection region allocation. The ML models developed were suitable for the direct detection of COVID-19 (+). ML was confirmed to be a complementary diagnostic technique for diagnosing COVID-19(+) by forefront medical specialists. The complete manual delineation of COVID-19 often requires up to 225.5 min; however, the proposed RILML method decreases the delineation time to 7 min after four iterations of model updating.

A novel explainable COVID-19 diagnosis method by integration of feature selection with random forest

Several Artificial Intelligence-based models have been developed for COVID-19 disease diagnosis. In spite of the promise of artificial intelligence, there are very few models which bridge the gap between traditional human-centered diagnosis and the potential future of machine-centered disease diagnosis. Under the concept of human-computer interaction design, this study proposes a new explainable artificial intelligence method that exploits graph analysis for feature visualization and optimization for the purpose of COVID-19 diagnosis from blood test samples. In this developed model, an explainable decision forest classifier is employed to COVID-19 classification based on routinely available patient blood test data. The approach enables the clinician to use the decision tree and feature visualization to guide the explainability and interpretability of the prediction model. By utilizing this novel feature selection phase, the proposed diagnosis model will not only improve diagnosis accuracy but decrease the execution time as well.

Comprehensive Survey of IoT, Machine Learning, and Blockchain for Health Care Applications: A Topical Assessment for Pandemic Preparedness, Challenges, and Solutions

Internet of Things (IoT) communication technologies have brought immense revolutions in various domains, especially in health monitoring systems. Machine learning techniques coupled with advanced artificial intelligence techniques detect patterns associated with diseases and health conditions. Presently, the scientific community is focused on enhancing IoT-enabled applications by integrating blockchain technology with machine learning models to benefit medical report management, drug traceability, tracking infectious diseases, etc. To date, contemporary state-of-the-art techniques have presented various efforts on the adaptability of blockchain and machine learning in IoT applications; however, there exist various essential aspects that must also be incorporated to achieve more robust performance. This study presents a comprehensive survey of emerging IoT technologies, machine learning, and blockchain for healthcare applications. The reviewed articles comprise a plethora of research articles published in the web of science. The analysis is focused on research articles related to keywords such as ‘machine learning’, blockchain, ‘Internet of Things or IoT’, and keywords conjoined with ‘healthcare’ and ‘health application’ in six famous publisher databases, namely IEEEXplore, Nature, ScienceDirect, MDPI, SpringerLink, and Google Scholar. We selected and reviewed 263 articles in total. The topical survey of the contemporary IoT-based models is presented in healthcare domains in three steps. Firstly, a detailed analysis of healthcare applications of IoT, blockchain, and machine learning demonstrates the importance of the discussed fields. Secondly, the adaptation mechanism of machine learning and blockchain in IoT for healthcare applications are discussed to delineate the scope of the mentioned techniques in IoT domains. Finally, the challenges and issues of healthcare applications based on machine learning, blockchain, and IoT are discussed. The presented future directions in this domain can significantly help the scholarly community determine research gaps to address.

A CNN-based scheme for COVID-19 detection with emergency services provisions using an optimal path planning

Unmanned Air Vehicles (UAVs) are becoming popular in real-world scenarios due to current advances in sensor technology and hardware platform development. The applications of UAVs in the medical field are broad and may be shared worldwide. With the recent outbreak of COVID-19, fast diagnostic testing has become one of the challenges due to the lack of test kits. UAVs can help in tackling the COVID-19 by delivering medication to the hospital on time. In this paper, to detect the number of COVID-19 cases in a hospital, we propose a deep convolution neural architecture using transfer learning, classifying the patient into three categories as COVID-19 (positive) and normal (negative), and pneumonia based on given X-ray images. The proposed deep-learning architecture is compared with state-of-the-art models. The results show that the proposed model provides an accuracy of 94.92%. Further to offer time-bounded services to COVID-19 patients, we have proposed a scheme for delivering emergency kits to the hospitals in need using an optimal path planning approach for UAVs in the network.