Abstract

This paper presents a model of personal wellness prediction of Hellenic seafarers, based on mechanical learning with classification using the Exhaustive CHAID, ID3 algorithms and neural networks. The research is asked to answer the following research questions: "Is there a possibility of creating a model of personal wellness prediction through supervised mechanical learning? To what extent is this model acceptable and reliable? "And" can the binary classification with maximum information gain be applied? ". Training data was drawn from 900 samples of Hellenic naval engineers and captains completing training at the Navy Training Center (KESEN). The results of the research are that using Exhaustive CHAID with split-validation, Exhaustive CHAID with Crossvalidation, ID3 in Matlab environment and MLP with neural network methods, it is possible to create such a prediction model in which the sleep issues parameter is the determining factor for the existence or not of personal wellness.

References

• Simon, H.A (1981). The Sciences of Artificial. MIT Press
• Forsythe R. & Rada R. (1986). Machine Learning: Applications in Expert Systems and Information Retrieval. E. Horwood
• Carbonell & Langley, 1983. Machine Learning in S. Shaphiro: Encyclopedia of A.I., Wiley.
• Michalski, Carbonell and Mitchell 1983. Machine Learning: An Artificial Intelligence Approach, Vol 1, Tioga Publishing
• Nikolaou G.,Advanced Systems Control Topics, Teaching notes of the postgraduate curriculum, Piraeus 2017
• Diamantaras K.,Artificial Neural Networks, Kleidarithmos Publications, Athens 2007
• Goldberg, David E.; Holland, John H. (1988). «Genetic algorithms and machine learning». Machine Learning 3
• Michie, D.Spiegelhalter, D. J..Taylor, C. C. (1994). Machine Learning, Neural and Statistical Classification. Ellis Horwood.
• Mehryar Mohri, Afshin Rostamizadeh, Ameet Talwalkar (2012) Foundations of Machine Learning, MIT Press
• EthemAlpaydin "Introduction to Machine Learning The MIT Press, 2010
• Simon Haykin, “Neural networks and learning machines 3rd ed.”, Prentice Hall, 2009
• John Slavio, “Deep Learning and Artificial Intelligence: A Beginners’ Guide to Neural Networks and Deep Learning”, Abhishek Kumar, 2018
• Stuart Russell, “Artificial Intelligence: A Modern Approach Paperback”, Pearson Prentice Hall, 2015.
• Ajay Agrawal, Joshua Gans, Avi Goldfarb, “Prediction Machines: The Simple Economics of Artificial Intelligence”, Pearson Prentice Hall, 2018
• Pao,Yoh-Han, “Adaptive Pattern Recognition and Neural Networks”, Wokingham, USA: Addison-Wesley, 1989.
• Russel, S. J. ,& Norvig, P., “Artificial Intelligence-A Modern Approach (2η edition)”, Upper Saddle River, New Jersey: Pearson Prentice Hall, 2003.
• Vlaxavas I., Kefalas P., Vasiliadis N., Refanidis I., Kokkoras F. & Sakellariou, "Artificial Intelligence (3rd Edition)", Thessaloniki: University of Macedonia Publishing, 2011.
• Mitchell, T.M., “Machine Learning”, Η.Β.:McGraw-Hill International Editions, 1997.
• Barr, A. and Feigenbaum, E. A. 1981. The Handbook of artificial intelligence, volume 1, Stanford, Calif.: Heuris Tech Press ; Los Altos, Calif. : William Kaufmann
• Vlachavas I., Notes to Artificial Intelligence. Introduction to Artificial Intelligence. Thessaloniki, 2013
• Forsythe R. & Rada R. (1986). Machine Learning: Applications in Expert Systems and Information Retrieval. E. Horwood
• Michalski, Carbonell and Mitchell 1983. Machine Learning: An Artificial Intelligence Approach, Vol 1, Tioga Publishing
• Jepsen J., R., Zhao Z. and Leeuwen W., M.A, 2015. Seafarer fatigue: a review of risk factors, consequences for seafarers’ health and safety and options for mitigation. IntMarit Health, 66, 2: 106–117, Via Medica.
• Witten, I.H., Frank, E. (2000), Data Mining: Practical Machine Learning Tools and Techniques with Java Implementations Morgan Kaufmann, San Mateo, CA, 2000.
• Kambourlazos V. and Papakostas G., 2015. Introduction to Computational Intelligence. Greek Academic Electronic Signs and Assistive, ISBN: 978-960-603-078-9
• Anderson, J. A. and Rosenfeld,E., 1988. Neurocomputing: Foundations of Research, MIT Press, Cambridge.
• Widrow, B., and Lehr, M. A, 1990. ‘’30 years of adaptive NN: Perceptron, Madaline and Backpropagation’’, Proc. Of the IEEE, vol. 23.
• Lippmann. R. P. 1987. ‘An introduction to Computing with NN’, IEEE ASSP Magazine, vol. 5
• Kohonen, T., 1984. Self – Organization and Associative Memory, Springer Verlag, Berlin.
• Selye H., 1956. The stress of life. New York, McGraw Hill Book Company (2nd ed, 1978)
• Byrne M.J., Thompson LF. Key concepts for the study and practice of nursing, 2nd ed. Saint Louis, CV Mosby Company.
• Dohrenwend, B. p., Shrout, P. E., Egri, G. and Mendelson, F. S. (1980). What pshychiatric screening scales measure in the general population: II. The components of demoralization by contrast with other dimensions of psychopathology. Archives of General Psychiatry, 37.
• Benson, H. (Ed.). (2000). Foreword: Twenty-fifth anniversary update. In The relaxation response (pp. 1-45). New York: Harper Torch.
• Elo A. L., 1985. Health and stress of seafarers. Scandinavian Journal of Work, Environment & Health 11, 427-432.
• Farber Barry A., (1983). Stress and Burnout in the Human Service Professions. New York: Pergamum Press.
• Moghaddum K.M. et al.(2013). Guidelines to Reducing Fatigue in Seafarers. Science explorer Publications.
• European Commission (2017). Seafarers: New measures to improve working conditions.
• Carotenuto A., Molino I., Fasanaro A., M. and Amenta F., 2012. Psychological stress in seafarers: a review. IntMarit Health 2012; 63, 4: 188–194, Via Medica
• Campbell, A., Converse, P., Rodgers, W. L. (1976). The quality of American life: Perceptions, evaluation and satisfactions. New York: Russell Sage Foundation.