Big data management with machine learning inscribed by domain knowledge for health care

Abstract

In this work, a framework that helps in the disease diagnosis process with big-data management and machine learning using rule based, instance based, statistical, neural network and support vector method is given. Concerning this, big-data that contains the details of various diseases are collected, preprocessed and managed for classification. Diagnosis is a day-to-day activity for the medical practitioners and is also a decision-making task that requires domain knowledge and expertise in the specific field. This framework suggests different machine learning methods to aid the practitioner to diagnose disease based on the best classifier that is identified in the health care system. The framework has three main segments like big-data management, machine learning and input/output details of the patient. It has been already proved in the literature that the computing methods do help in disease diagnosis, provided the data about that particular disease is available in the data center. Thus this framework will provide a source of confidence and satisfaction to the doctors, as the model generated is based on the accuracy of the classifier compared to other classifiers.

Spatial and temporal clustering analysis on chlorophyll-a data distribution

“…As all approach in data mining like in any other big data processing, should comprises data pre-processing [18], [10], we also start our study as shown in Fig.1. This study comprises three phases: the pre-processing data phase, the spatial and temporal analysis phase, and the clustering results visualization phase, as shown in Fig.…”

Sentimental analysis using recurrent neural network

“…RNN can keep the record of all the input values that are viewed by the network and also current input, which is value hidden at each layer network depend on all the previously seen inputs. Exhaustive training is to be done to this model and weights are to be adjusted so that higher accuracy is obtained [19]. Recurrent neural network in the scenario of sentimental analysis can also be modeled based on Sentiment Treebank [20].…”