• ANITA SACHIN MAHAJAN

Now days from health care industries large volume of data is generating. It is necessary to collect, store and process this data to discover knowledge from it and utilize it to take significant decisions. Diabetic Mellitus (DM) is from the Non-Communicable Diseases (NCD), and lots of people are suffering from it. Now days, for developing countries such as India, DM has become a big health issue. The DM is one of the critical diseases which has long term complications associated with it and also follows with various health problems. Diabetes is one of the threatening diseases to the entire mankind, though it is not fatal. Irrespective of the presence of several existing approaches for diabetes prediction, big data based diabetes prediction is quite rare. The applicability of the proposed work is wider because, medical records from different sources are extracted and the necessary attributes meant for predicting diabetes alone are processed. The goal of this work is attained by different phases such as data collection, preprocessing, attribute selection and prediction. The diabetes prediction is carried out by Extreme Learning Machine (ELM) classifier. The performance of the proposed approach is analyzed by varying the classifiers and the existing approaches in terms of disease prediction accuracy, precision, recall and time consumption. From the experimental results, the efficiency of the work is proven. Diabetes Mellitus (DM) is a metabolic diseases group where the person will have high blood sugar due to the pancreas unable to produce sufficient insulin or the cell’s which are not responding to the insulin produced. Diabetes is a chronic disease and a major public health challenge worldwide. The main drawback is that there is lack of awareness of the people on eating habits. In our country, diabetes patient counts have increased steadily due to this reason. Diabetes is a metabolic disease affecting a multitude of people worldwide. Its incidence rates are increasing alarmingly every year. If untreated, diabetes-related complications in many vital organs of the body may turn fatal. Early detection of diabetes is very important for timely treatment which can stop the disease progressing to such complications. RR-interval signals known as heart rate variability (HRV) signals (derived from electrocardiogram (ECG) signals) can be effectively used for the non-invasive detection of diabetes. This research paper presents a methodology for classification of diabetic and normal HRV signals using deep learning mechanism. We employ long short-term memory (LSTM), convolutional neural network (CNN) and its combinations for extracting complex temporal dynamic features of the input HRV data. These features are passed into support vector machine (SVM) for classification. We have obtained the performance improvement of 0.03% and 0.06% in CNN and CNN-LSTM architecture respectively compared to our earlier work without using SVM. The classification system proposed can help the clinicians to diagnose diabetes using ECG signals with a very high accuracy of 95.7%.

Deep learning, Diabetes, ECG, CNN, Hadoop, MapReduce, Predictive Analysis

"Medical Diagnosis of Diabetes Using Deep Learning Techniques and Big data Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.7, Issue 4, page no.1490-1497, April-2020, Available :http://www.jetir.org/papers/JETIR2004402.pdf

"Medical Diagnosis of Diabetes Using Deep Learning Techniques and Big data Analytics", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.7, Issue 4, page no. pp1490-1497, April-2020, Available at : http://www.jetir.org/papers/JETIR2004402.pdf