Leveraging Artificial Intelligence in Blockchain-Based E-Health for Safer Decision Making Framework

Machine learning-based (ML) systems are becoming the primary means of achieving the highest levels of productivity and effectiveness. Incorporating other advanced technologies, such as the Internet of Things (IoT), or e-Health systems, has made ML the first choice to help automate systems and predict future events. The execution environment of ML is always presenting contrasting types of threats, such as adversarial poisoning of training datasets or model parameters manipulation. Blockchain technology is known as a decentralized network of blocks that symbolizes means of protecting block content integrity and ensuring secure execution of operations.Existing studies partially incorporated Blockchain into the learning process. This paper proposes a more extensive secure way to protect the decision process of the learning model. Using smart contracts, this study executed the model's decision by the reversal engineering of the learning model's decision function from the extracted learning parameters. We deploy Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP) classifiers decision functions on-chain for more comprehensive integration of Blockchain. The effectiveness of this proposed approach is measured by applying a case study of medical records. In a safe environment, SVM prediction scores were found to be higher than MLP. However, MLP had higher time efficiency.

Integrated Bayesian and association-rules methods for autonomously orienting COVID-19 patients.

The coronavirus infection continues to spread rapidly worldwide, having a devastating impact on the health of the global population. To fight against COVID-19, we propose a novel autonomous decision-making process which combines two modules in order to support the decision-maker: (1) Bayesian Networks method-based data-analysis module, which is used to specify the severity of coronavirus symptoms and classify cases as mild, moderate, and severe, and (2) autonomous decision-making module-based association rules mining method. This method allows the autonomous generation of the adequate decision based on the FP-growth algorithm and the distance between objects. To build the Bayesian Network model, we propose a novel data-based method that enables to effectively learn the network's structure, namely, MIGT-SL algorithm. The experimentations are performed over pre-processed discrete dataset. The proposed algorithm allows to correctly generate 74%, 87.5%, and 100% of the original structure of ALARM, ASIA, and CANCER networks. The proposed Bayesian model performs well in terms of accuracy with 96.15% and 94.77%, respectively, for binary and multi-class classification. The developed decision-making model is evaluated according to its utility in solving the decisional problem, and its accuracy of proposing the adequate decision is about 97.80%.

THE INTERNET OF THINGS SECURITY: A SURVEY ENCOMPASSING UNEXPLORED AREAS AND NEW INSIGHTS

The cosmic evolution of the Internet of things (IoTs) in par with its realization in all spheres of life undertakings, mandates continuous research pursuits in IoT and its associated components. While the rapid evolution of IoTs has facilitated monumental opportunities for humanity, it has also acted as a catalyst precipitating diverse security issues. Cybercrimes have been on the rise as criminals and hackers continue to take advantage of IoT's security loopholes and vulnerabilities. The enormity of the attacks has not only been damaging to the quality of life, but it poses a disservice and an unquantifiable risk to human safety. Thus, a timely and comprehensive review, analysis and investigation of the security of IoTs is crucial. Through a systematic literature review of over 200 articles, we set out the latest findings and trends to provide new insights into the security of IoTs, taking cognizant of its social, economic, technical and legal implications, which will be beneficial to researchers, manufacturers, individuals, organizations, and governments. Although many studies reviewing the state of IoT exist in the literature, no studies shape the area of its security well. Hence, there is currently no study that provides an in-depth survey of the emerging security concerns of IoT from diverse perspectives and in tandem with the current condition of the global world today. Compared to other related reviews on the security of IoTs, this survey encompasses much more technical angles to the security of IoT. It begins with the review of the concept of IoTs, the assessments of its industrial development trends, revolutionary paradigms and updated security of the IoT. Key challenges in the security of blockchain technology, a recent spike in distributed denial of service (DDoS) attacks due to the COVID-19 pandemic are sensitive areas that have remained untouched by previous review works. Additionally, politics and security of electoral votes, forensic issues in the IoT era and much more are some of the new depths missing in the literature of IoT security. Thus, a huge divide in the total adoption and actualization of IoT in diverse areas of human endeavour. This review formalizes the IoT concept, illuminating deep insights into possible solutions to the heterogeneous nature of IoT's security challenges, emerging issues, gaps, opportunities, foresight, and recommendations.

COVID-CGAN: Efficient Deep Learning Approach for COVID-19 Detection Based on CXR Images Using Conditional GANs

COVID-19, a novel coronavirus infectious disease, has spread around the world, resulting in a large number of deaths. Due to a lack of physicians, emergency facilities, and equipment, medical systems have been unable to treat all patients in many countries. Deep learning is a promising approach for providing solutions to COVID-19 based on patients’ medical images. As COVID-19 is a new disease, its related dataset is still being collected and published. Small COVID-19 datasets may not be sufficient to build powerful deep learning detection models. Such models are often over-fitted, and their prediction results cannot be generalized. To fill this gap, we propose a deep learning approach for accurately detecting COVID-19 cases based on chest X-ray (CXR) images. For the proposed approach, named COVID-CGAN, we first generated a larger dataset using generative adversarial networks (GANs). Specifically, a customized conditional GAN (CGAN) was designed to generate the target COVID-19 CXR images. The expanded dataset, which contains 84.8% generated images and 15.2% original images, was then used for training five deep detection models: InceptionResNetV2, Xception, SqueezeNet, VGG16, and AlexNet. The results show that the use of the synthetic CXR images, which were generated by the customized CGAN, helped all deep learning models to achieve high detection accuracies. In particular, the highest accuracy was achieved by the InceptionResNetV2 model, which was 99.72% accurate with only ten epochs. All five models achieved kappa coefficients between 0.81 and 1, which is interpreted as an almost perfect agreement between the actual labels and the detected labels. Furthermore, the experiment showed that some models were faster yet smaller compared to the others but could still achieve high accuracy. For instance, SqueezeNet, which is a small network, required only three minutes and achieved comparable accuracy to larger networks such as InceptionResNetV2, which needed about 143 min. Our proposed approach can be applied to other fields with scarce datasets.