Advertisement

Ambient context-based modeling for health risk assessment using deep neural network

  • Kyungyong Chung
  • Hyun Yoo
  • Do-Eun Choe
Original Research

Abstract

Context computing is a branch of ambient intelligence (AmI) research, which has been rapidly emerging in the support of intelligent smart health platform solution. To develop reliable ambient computing using the hybrid peer-to-peer network and Internet of Things, machine learning, deep learning, artificial intelligence, and context awareness have been applied. This study proposes an ambient context-based modeling for a health risk assessment using deep neural network. In the proposed method, we collected medical information from chronic disease patients such as EMR, PHR, and medical histories, as well as environmental data from a health platform. Subsequently, heterogeneous data are integrated through selecting, cleaning, modeling, and evaluating the collected raw data and then the context is created. The structured input data such as a sensor data are normalized by transforming the time domain data to the frequency domain information. Using a deep neural network, the normalized data are applied to create an ambient context. A deep neural network is composed of the following three layers: input layers with treated and untreated data; hidden layers where connection strength is trained as a weight; and output layers of trained results. In the deep neural network layers, the control of the weight of training data enables repeated learning to create an ambient context pattern. Using an ontology inference engine, unstructured/structured data, including individual health data and environmental information, and their context is presented as ontology metadata. In the knowledge base, hidden association relationships are discovered through mining. To inform the individual health conditions exposed to the individual environmental contexts, a health risk assessment model is developed with a set of the ambient context pattern learned with metadata and a deep neural network. The Minkowski distance formula, which defines a normalized geometrical distance between two nodes, is used to measure the similarity between the patients with chronical disease and the individual user based on the context. In the proposed model, the risk is represented as a similarity-based index. The risk assessment model can be implemented into the individual risk alert/prevention system. The model may significantly impact the healthcare industry as well as ambient intelligence research, thus contributing to improve the quality of human life of the future society.

Keywords

Ambient context Data mining Big data Deep learning Deep neural network Healthcare 

Notes

Acknowledgements

This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2018-0-01405) supervised by the IITP (Institute for Information & communications Technology Promotion).

References

  1. Adomavicius G, Tuzhilin A (2015) Context-aware recommender systems, recommender systems handbook. Springer, New York, pp 191–226CrossRefGoogle Scholar
  2. Agrawal R, Srikant R (1994) Fast algorithms for mining association rules. In: Proceedings of 20th international conference on very large data base, USA, pp 487–499Google Scholar
  3. Chaib A, Boussebough I, Chaoui A (2018) Adaptive service composition in an ambient environment with a multi-agent system. J Ambient Intell Hum Comput 9(2):367–380CrossRefGoogle Scholar
  4. Chen RC, Hsieh CF, Chang WL (2016) Using ambient intelligence to extend network lifetime in wireless sensor networks. J Ambient Intell Hum Comput 7(6):777–788CrossRefGoogle Scholar
  5. Chung KY, Lee JH (2004) User preference mining through hybrid collaborative filtering and content-based filtering in recommendation system. IEICE Trans Infor Syst E87-D(12):2781–2790MathSciNetGoogle Scholar
  6. Chung K, Park RC (2018) Chatbot-based healthcare service with a knowledge base for cloud computing. Cluster Comput.  https://doi.org/10.1007/s10586-018-2334-5 CrossRefGoogle Scholar
  7. Chung K, Kim JC, Park RC (2016) Knowledge-based health service considering user convenience using hybrid wi-fi P2P. Inf Technol Manag 17(1):67–80CrossRefGoogle Scholar
  8. HIRA (2018) Health insurance review and assessment service (online). http://opendata.hira.or.kr. Accessed 16 Apr 2018
  9. HL7 (2018) Health level seven international (online). http://www.hl7.org. Accessed 16 Apr 2018
  10. Jung H, Chung K (2015) Sequential pattern profiling based bio-detection for smart health service. Cluster Comput 18(1):209–219CrossRefGoogle Scholar
  11. Jung H, Chung K (2016a) Knowledge-based dietary nutrition recommendation for obese management. Inf Technol Manag 17(1):29–42CrossRefGoogle Scholar
  12. Jung H, Chung K (2016b) Life style improvement mobile service for high risk chronic disease based on PHR platform. Cluster Comput 19(2):967–977CrossRefGoogle Scholar
  13. Jung H, Yoo H, Chung K (2016) Associative context mining for ontology-driven hidden knowledge discovery. Cluster Comput 19(4):2261–2271CrossRefGoogle Scholar
  14. KCDCP (2015) 6th Korean National Health and Nutrition Examinations Survey (KNHANES VI-1). Korea Centers for Disease Control and Prevention, CheongjuGoogle Scholar
  15. KCDCP (2018) Korea Centers for Disease Control & Prevention (online). http://www.cdc.go.kr/CDC/eng. Accessed 16 Apr 2018
  16. Kim JH, Chung K (2014) Ontology-based healthcare context information model to implement ubiquitous environment. Multimed Tools Appl 71(2):873–888CrossRefGoogle Scholar
  17. Kim SH, Chung K (2016) Emergency situation monitoring service using context motion tracking of chronic disease patients. Cluster Comput 18(2):747–759CrossRefGoogle Scholar
  18. Kim JC, Chung K (2017) Emerging risk forecast system using associative index mining analysis. Cluster Comput 20(1):547–558CrossRefGoogle Scholar
  19. Kim JC, Chung K (2018) Mining health-risk factors using PHR similarity in a hybrid P2P network. Peer-to-Peer Netw Appl 11(6):1278–1287CrossRefGoogle Scholar
  20. KMA (2018) Korea Meteorological Administration (online). http://web.kma.go.kr/eng. Accessed 16 Apr 2018
  21. Mashal I, Alsaryrah O, Chung TY (2016) Testing and evaluating recommendation algorithms in internet of things. J Ambient Intell Hum Comput 7(6):889–900CrossRefGoogle Scholar
  22. OHDSI (2018) Observational Health Data Sciences and Informatics (online). https://www.ohdsi.org. Accessed 16 Apr 2018
  23. Rho MJ, Jan KS, Chung KY, Choi IY (2015) Comparison of knowledge, attitudes, and trust for the use of personal health information in clinical research. Multimedia Tools Appl 74(7):2391–2404CrossRefGoogle Scholar
  24. Rho MJ, Kim HS, Chung K, Choi IY (2016) Factors influencing the acceptance of telemedicine for diabetes management. Cluster Comput 18(1):321–331CrossRefGoogle Scholar
  25. Song CW, Jung H, Chung K (2017) Development of a medical big-data mining process using topic modeling. Cluster Comput.  https://doi.org/10.1007/s10586-017-0942-0 CrossRefGoogle Scholar
  26. Yoo H, Chung K (2018) Mining-based lifecare recommendation using peer-to-peer dataset and adaptive decision feedback. Peer-to-Peer Netw Appl 11(6):1309–1320CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  1. 1.Division of Computer Science and EngineeringKyonggi UniversitySuwon-siSouth Korea
  2. 2.Department of Computer Information EngineeringSangji UniversityWonju-siSouth Korea
  3. 3.Department of Civil and Environmental EngineeringPrairie View A&M UniversityPrairie ViewUSA

Personalised recommendations