The Internet of Medical Things (IoMT). Группа авторов
Concepts used to assess the quality of research are reliability and validity. They show how well something is measured through a method, methodology, or test.
Data Resolution: is a leading global provider of hosted technology solutions for businesses of all sizes. SaaS, managed virtual environments, business continuity solutions, cloud computing and advanced data center services.
Auditability: A data audit refers to the auditing of data to assess its quality or utility for a specific purpose. Auditing data, unlike auditing finances, involves looking at key metrics, other than quantity, to create conclusions about the properties of a data set.
2.4.3 Storage
Data retention policies can be applied based on the lack of applicable criteria diversity.
Storage Encryption: is the use of encryption for data both in transit and on storage media. Data is encrypted while it passes to storage devices, such as individual hard disks, tape drives, or the libraries and arrays that contain them.
K-communication encryption: Leakage and data from the system or eavesdropping risk. A sensitive and data communication must be provided in encryption items.
Problems Integrity: Data integrity is handled by critical issues and has a hash algorithm such as MD5 and SHA. This also applies to the security level of the data essential element.
Policy Access Control: It’s aims to ensure that, by having the appropriate access controls in place, the right information is accessible by the right people at the right time and that access to information, in all forms, is appropriately managed and periodically audited.
Backup and Recovery Plan: A backup plan is required for disaster recovery storage purposes. Data must be connected to base backup scheme. There are separate standards for authenticating user data as required by data quality standards for classification data.
2.4.4 Soft Computing Techniques for Data Classification
Soft computing techniques are collection of soft computing techniques methodology.
• Exploit the tolerance for imperfection and uncertainty.
• Provide capability to handle real-life ambiguous situations.
• Try to achieve robustness against imperfection.
One of the most popular soft computing-based classification techniques is fuzzy classification. Fuzzy classes can better represent transitional areas than hard classification, as class membership is not binary but instead one location can belong to a few classes. In fuzzy set-based systems, membership values of data items range between 0 and 1, where 1 indicates full membership and 0 indicates no membership. Figure 2.3 shows a block diagram of fuzzy classification technique.
This section explains the various layers of analysis framework. Analytical framework is divided into user interface layer and processing layer. User interface layer is responsible for taking input from the user and processing. Processing layer is responsible for classification and comparison. Data access layer is responsible for connecting applications to databases for storing data. Figure 2.4 shows the system architecture and the interaction between the various components. Each layer is implemented use the class file that will implement the interface and data processing.
Figure 2.3 Fuzzy classification block diagram.
Figure 2.4 illustrates that the analytical framework consists of two layers where first layer provide user interface that allows users to select the desired dataset and algorithms and second layer provide processing component to selected algorithm.
Figure 2.4 Analysis framework architecture.
2.5 Related Work
The authors [1] analyzed health data using safety management and proposals of Blockchain. However, Blockchain are computationally expensive, demand for high bandwidth and additional computing, and not fully suitable for limited resources because it was built for smart city of IoT devices. In this work, they use the device—IoT Blockchain—that tries to solve the above problems. The authors proposed novel device structure— IoT Blockchain—a model suitable for additional privacy and is considered to be property, other than the conservation property and their network. In our model, this additional privacy and security properties based on sophisticated cryptographic priority. The solution here is more secure and anonymous transactions to IoT applications and data-based Blockchain networks.
Whitney and Dwyer [2] introduced in the medical field the advantage of the Blockchain approach and proposed the technology blockchain personal health record (PHR), data can be handled well if it is properly classified, for example, we can classify different medical data like BMI of a person as lean, normal, fat and obese. Some of the important applications of data mining techniques in the field of medicine include health informatics, medical data management, patient monitoring systems, analysis of medical images for unknown information extraction and automatic identification of diseases.
In the paper [3], the authors proposed a novel EHR sharing, including the decentralization structure of the mobile cloud distribution platform Blockchain. In particular, they are designed to be the system for achieving public safety EHRs between various patients and medical providers using a reliable access control smart contract. They provide a prototype implementation using real-data Ethereum Blockchain shared scenarios on mobile applications with Amazon cloud computing. Empirical results suggest that the proposal provides an effective solution for reliable data exchange to maintain sensitive medical information about the potential threats to the mobile cloud. Evaluation models of security systems and share analysis also enhance lighting, design, performance improvement in high security standards, and lowest network latency control with data confidentiality compared with existing data.
The authors [4] proposed a system for detecting lung cancer while using the neural network and genetic algorithm Backpropagation. In this paper, classification was performed using Neural Network Backpropagation which would classify as normal or abnormal the digital X-ray, CT images, MRIs, and so forth. The normal condition is that which is characteristic of a healthy patient. For the study of the feature, the abnormal image will be considered further. The genetic algorithm can be used for adaptive analysis to extract and assign characteristics based on the fitness of the extracted factors. The features selected would be further classified as cancerous or noncancerous for images previously classified as abnormal. This method would then help to make an informed judgment on the status of the patient.
The authors [5] proposed segmentation techniques to improve tumor detection efficiency and computational efficiency; the GA is used for automated tumor stage classification. The choice in the classification stage shall be based on the extraction of the relevant features and the calculation of the area. The comparative approach is developed to compare four watersheds, FCM, DCT, and BWT-based segmentation techniques, and the highest is chosen by evaluating the segmentation score. The practical products of the proposed approach are evaluated and validated based on the segmentation ranking, accuracy, sensitivity, specificity, and dice similarity index coefficient for development and quality evaluation on MRI brain images.
In [6],