The Internet of Medical Things (IoMT). Группа авторов

The Internet of Medical Things (IoMT) - Группа авторов


Скачать книгу
Logistic Regression. Also, the identification performance was higher than the state-of-the-art algorithm.

      Techniques to reach the clouds have proposed a number of data, continuing to develop techniques that provide tools. This same performance development on cloud software simulated cloud computing environment. Typical cloud environmental simulation test was performed by taking the final test matches result. The damaged devices provided for tolerance and efficiency to meet the environmental consequences of fake cloud workflow software that comes as a scientific and social networking sites [1, 12, 13] are continued to develop a method to obtain a higher amount and take advantage of security capabilities. Co-processor is called cryptographic. This increases cost and increases functionality data protection in a distributed computing [9].

      PaaS (as a protection of data services): The award has become user safety standards. Data protection, data security, and proposals provide data authentication and data protection for administrators, out of some malicious software though. Hindrance single-cloud platform is beneficial for protecting large amounts of application users.

      One fuzzy nearest neighbor technology is the proposed framework for decision rule fuzzy prototype; there are three strategies that determine the membership value of the training samples, helping for more blur results by providing input sample vector with unknown neighbor grade classification. When it is believed to be more than two neighbors, likely, this is why neighbors are between large numbers of parts of the tie, that it, Kashmir nearest neighbor residue groups.

      A cloud technology to avoid data duplication currently uses computing decks, and efferent and convergence remain important management strategy to secure de-duplication. Insured reduction strategy unnecessary data is widely applied to cloud storage despite the mass convergence encryption. The distribution of security is implemented for a major concern. Convergence works as encryption here. Large amounts of key are required to maintain power. At the same time, it is a difficult task.

      Research shows that some areas employ classification of public data to share data in private and technology and to protect personal data. One such classification technology is the k-nearest neighbor algorithm. It is a machine learning to know the types of technology classified as personal data and public data. Personal data is encrypted and sent using RSA technology cloud server.

      A clinical decision support system (CDSS) is an application that analyzes data to help healthcare providers make decisions, and improve patient care. A CDSS focuses on using knowledge management to get clinical advice based on multiple factors of patient-related data. Clinical decision support systems enable integrated workflows, provide assistance at the time of care, and offer care plan recommendations. Physicians use a CDSS to diagnose and improve care by eliminating unnecessary testing, enhancing patient safety, and avoiding potentially dangerous and costly complications. The applications of big data in healthcare include, cost reduction in medical treatments, eliminate the risk factors associated with diseases, prediction of diseases, improves preventive care, analyzing drug efficiency. Some challenging tasks for the healthcare industry are:

      1 (i) How to decide the most effective treatment for a particular disease?

      2 (ii) How certain policies impact the outlay and behavior?

      3 (iii) How does the healthcare cost likely to rise for different aspects of the future?

      4 (iv) How the claimed fraudulently can be identified?

      5 (v) Does the healthcare outlay vary geographically?

      1. Smith, Rawat, P.S., Saroha, G.P., Bartwal, V., Evaluating SaaSModeler (small mega) Running on the Virtual Cloud Computing Environment using CloudSim. Int. J. Comput. Appl. (0975-8887), 5, 13, 2012c of September. London, A247, 529–551, April 1955.

      2. Whitney, A. and Dwyer, II, S.J., the performance and implementation of the K-nearest neibbor decision rule with no training samples correctly identified, in: Proc. 4 Ann. Allerton Conf. On the Circuit System Band Theory, 1966.

      3. Dasarathy, B.V., Nosing aroung the environment: A new structure and a system of classification rules for recognition in the most affected. IEEE Trans. Pattern Anal. Mach. Intell., PAMI- 2, 67–71, 1980.

      4. Keller, J.M., Gray, M.R., Givens, Jr, J.A., A Fussy-K-Nearest Neighbor algorithm. IEEE Trans. Syst. Man Cybern., SMC-15, 4, 580–585, July/August 1985.

      5. Bauer, E. and Kohavi, R., A comparison of voting classification algorithms impirical: Bagging, Improve and variants. Mach. Learn., 36.1, 36105–139, 1999.

      6. Khan, M., Ding, Q., Perrizo, W., K-Nearest Neighbor Classification on Spatial Data Streams Using P-Trees1, 2. PAKDD 2002 LNAI, vol. 2336, pp. 517–528, 2002.

      7. Catteddu, D. and Hogben, G., Cloud Computing: Benefits, risks and recommendations for information security, ENISA, Berlin, Heidelberg, 2009.

      8. Phyu, T.N., Survey on Data Mining Classification Techniques. Proceedings of the International MultiConference of Engineers and Computer Scientists 2009, March 18-2009, vol. I, IMECS, 2009.

      9. Ram, C.P. and Sreenivaasan, G., Security as a Service (SASS): Securing of user data by the coprocessor and distributing data. Trendz Information and Computing Sciences (TISC2010), December 2010, pp.152–155.

      10. Yau, S.S. and Ho, G., Privacy protection in cloud computing sytems. Int. J. Software Inform., 4, 4, 351–365, December 2010.

      11. Mishra, A., An Authentication Mechanism Based on Client-Server Architecture for Accessing Cloud Computing, International Journal of Emerging Technology Advanced Engineering, 2, 7, 95–99, July 2012.

      12. Huang, S.-C. and Chen, B.-H., Highly accurate moving object detection in variable bit rate video-based traffic monitoring systems. IEEE Transactions on Neural Networks and Learning Systems, 24.12, 1920–1931, 2013.


Скачать книгу