Impact of Work Schedules on the Sleep Patterns of Railroad Workers using CHAID Neural Network and Ensemble Models of Machine Learning
Devyani Gupta1, Nikita Pande2, Jitendra Shreemali3, Prasun Chakrabarti4
1Devyani Gupta, Techno India NJR Institute of Technology, College, Biliya (Rajasthan), India.
2Nikita Pande, Techno India NJR Institute of Technology, College, Biliya (Rajasthan), India.
3Jitendra Shreemali, Techno India NJR Institute of Technology, College, Biliya (Rajasthan), India.
4Prasun Chakrabarti, Techno India NJR Institute of Technology, College, Biliya (Rajasthan), India.
Manuscript received on 15 March 2020 | Revised Manuscript received on 22 March 2020 | Manuscript Published on 30 March 2020 | PP: 12-16 | Volume-9 Issue-3S March 2020 | Retrieval Number: C10040393S20/20©BEIESP | DOI: 10.35940/ijeat.C1004.0393S20
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: The study examines the impact of work schedules on the sleep patterns of railroad workers in the USA. The study used the CHAID model, Neural Network and the Ensemble model to identify factors that have a greater impact on sleep patterns. Age, number of children / dependents are found to be key factors for sleep apnea as well as sleep disorders while job pressure and work hours are seen to be the third factor for sleep apnea and sleep disorder respectively. CHAID model provided the highest accuracy (92%) for sleep disorder while the ensemble model provided an accuracy of over 93% for sleep apnea.
Keywords: Neural Network, CHAID, Ensemble Model, Sleep Disorder, Sleep Apnea.
Scope of the Article: Machine Learning