Comparison of Coronary Heart Disease Prediction models using various Machine Learning Algorithms

In the health sector, Data Analytics and Machine Learning (ML) methods are taking over role of skill and experience of a doctor especially in diagnosing diseases and preventive health measures. The health care industry is collecting very large amount of data related to patients, his medical history for preventive medication and diagnosing disease well in time and more accurately. In this paper, a comparison of five classification machine learning methods viz. Decision Tree, Random Forests, Support Vector Machine, Artificial Neural Network and Fuzzy Logic based soft computing method is done for heart disease diagnosis on the basis of data available on public domain. Out of 76 parameters collected for a patient, only 15 medical parameters such as blood pressure, sex, age, obesity and cholesterol level are used for predicting heart disease of patients.

Prediction by Soft Computing, Planning, and Strategy Building of Aquatic Catch: Chilika Lagoon, Odisha, India

Introduction: The Chilika lagoon in south Odisha, India was ecologically degraded from 1985 onwards by reduction of its aquatic (fish + prawn + shrimp) catches along with reduction in salinity, hydraulic regime, water exchange, aquatic weeds invasion, and sediment influx. The aquatic catch was 8669MT in year 1985-1986 gradually reduced to 1274MT during 1995-1996 from Odisha Fisheries Dept. records which resulted in poor economic condition of ≈0,2million fishermen and they migrated to adopt other livelihood. One direct tidal inlet dredged (Sipakuda) and Naraj barrage in the apex of South Mahanadi Delta were the major hydraulic interventions made to regain hydraulic regime. After the hydraulic interventions, the eco system restored, and the aquatic catch surged but it was insufficient to livelihood sustenance for the fishermen community of the Chilika, so that they are forced for alternate occupation and migration. Methodologies: Fish catch data collected for 30 years and soft computing models linear regression, Multi Linear Perception (ANN), SMOorg (SVM) and the Random Forest algorithms (Weka Software) are used to predict the fish catch data of the lagoon for coming decade from 2020 to 2030. The effects of major hydraulic interventions are analyzed and the soft computing method of the fish and shrimp catch prediction of the Chilika has been attempted for the first time except some statistical approaches. Results: The Random Forest is found to be the preferred algorithm followed by the MLP model. The amount of catch remained around 12-13TMT if the variables and the present status of the lagoon is maintained. The combined effect of the Sipakuda Tidal inlet and the effective operation of the Naraj barrage have maintained the sustainable aqua catch. The present study shall be an immense help for the lake users and policy makers to augment aquatic catch, and alternate livelihood fishers community of the Chilika lagoon.

Determination of attributes affecting price-performance using fuzzy rule-based systems: online ratings of hotels by travel 2.0 users

Purpose Fuzzy rule-based system (FRBS), a soft computing method used for big data analysis, is used to determine which single hotel attribute or interrelated hotel attributes used in Travel 2.0 data play a role on price–performance (PP). Design/methodology/approach FRBS, based on fuzzy set theory, is used using the data set of four- and five-star hotels in the Alanya destination in Turkey collected from HolidayCheck.de website for the period between 2009 and 2016. Findings Single attributes do not have an impact on PP. At least two or more attributes are necessary to have an impact on PP. Compensations among attributes that are observed to be leading to PP not to change from their current level. Instead of assuming a linear relationship between hotel attributes and PP, non-linearity should often be assumed. In addition, some hotel attributes do not have an impact on PP until some other attribute reaches a certain level. Research limitations/implications The limitations of this research can be grouped under two topics. While the first is related to data, which is German-speaking tourists staying at four- and five-star hotels between 2009 and 2016, the second is the limitation on generalizability. By implementing other types of data related to hotel attributes, new insights can be generated to shed light on different aspects of the relationship between hotel attributes and PP or other measures such as overall evaluation. Originality/value A data-driven model called FRBS is constructed using original verbal statements. Novel insights pertinent to relations between hotel attributes and PP have been extracted.