In the present digital world, Information and Communication Technology along with the Internet of Things are considered as the backbone for the smart city evolution. IoT is concentrated more nowadays, due to the convergence of images on Information Technology and human behavior known as Operation Technology. It is in the progressing stage with the notion of the cyber-physical world, where things are facilitated to satisfy feasible needs. Similarly, the Internet of Medical Things is gaining attention due to the current COVID-19 situation. It has gifted numerous sensors and devices with the increased accuracy, productivity, and reliability to the healthcare industry. Increasing the sensor devices in smart cities results in the handling of a large amount of data. Therefore, big data is focused due to its characteristics such as volume, variety, velocity, and veracity. Extraction of hidden correlations and insights from data is performed through big data analytics or a big data value chain. Such concepts are integrated with Artificial Intelligence and Machine Learning technologies which are more important in collecting real-time data collection and helps in gaining knowledge on how smart cities and their applications in the health sector evolve to adapt to the conditions. The main advantage of Big Data Analytics is that it helps in commonality along with heterogeneity principles. Even though cities are digitalized, urban health is still limited to IoT devices that fetch sensor data, eliminating the inclusion of human anatomy and biological data. Integration of these two data forms will help in attaining the target of Big Data and leads to contextualized, sustainable, and resilient smart cities which renders more living factors. This chapter will focus on the role of Big Data in smart health applications which plays a vital role in safeguarding human lives.
Improvement in Healthcare
Big Data analytics in the medical sector can assist medical professionals to facilitate improvement in healthcare. With the help of data analysis, clinical images of patients can be used to detect certain medical conditions. In the COVID-19 pandemic, many integrated technologies are being used to remodel the healthcare systems. The management of an integrated healthcare solution necessitates the need for the security of medical data. Here proposed a security framework based on the Logistic equation, Hyperchaotic equation, and Deoxyribonucleic Acid (DNA) encoding.
Subsequently, a Lossless Computational Secret Image Sharing (CSIS) method is used to convert the encrypted secret image into shares for distributed storage in cloud-based servers. Hyperchaotic and DNA encryption is performed to improve the overall security of the system. Furthermore, Pseudorandom Numbers (PRN) generated by the logistic equation are XORed with the image sequence in two phases by changing the parameters slightly. Finally, the application of Secret Sharing (SS) generates completely noise-like cipher images that enhance the security of the cloud-based cryptosystem. The generated shares are small in size and require fewer resources like storage capacity and transmission bandwidth which is highly desirable in IoT-based systems. It is verified that the cryptosystem is highly secure against attacks as well as interferences and has a very strong key sensitivity.
This proposes an image encryption scheme using Quasigroup and Fibonacci Q-transformation. The proposed scheme is based on substitution–permutation structure, which can handle images of any size, i.e., square as well as non-square. The Quasigroup of order 256 and Fibonacci Q-transformation are used as primitives for substitution and diffusion of image pixels, respectively. The encryption method is designed to have the secret keys applied with specific orders such that correct decryption is only possible when correct keys and correct orders are supplied together. The proposed scheme has good efficiency, an extensively huge keyspace, and the ability to resist all common attacks. The feasibility and performance of the proposed scheme are examined by conducting various experimental results. The robustness of the proposed scheme is validated by analyzing it against statistical and cryptanalytical attacks. Further, the superiority of the proposed scheme is confirmed by comparing it with the related works.
Smart healthcare framework for ambient assisted living using IoMT and big data analytics techniques
IoMT interconnects wearable sensors, patients, healthcare providers, and caregivers via software and ICT (Information and Communication Technology). AAL (Ambient Assisted Living) enables the integration of new technologies to be part of our daily life activities. Here provided a novel smart healthcare framework for AAL to monitor the physical activities of elderly people using IoMT and intelligent machine learning algorithms for faster analysis, decision making, and better treatment recommendations. Data is collected from multiple wearable sensors placed on the subject’s left ankle, right arm, and chest is transmitted through IoMT devices to the integrated cloud and data analytics layer. To process huge amounts of data in parallel, Hadoop MapReduce techniques are used. Multinomial Naïve Bayes classifier, which fits into the MapReduce paradigm, is utilized to recognize the motion experienced by different body parts and provides higher scalability and better performance with parallel processing when compared to the serial processors. The proposed framework predicts 12 physical activities with an overall accuracy of 97.1%.
This can be considered as an optimal solution for recognizing physical activities to remotely monitor the health conditions of elderly generations.