Abstract: Diabetes Mellitus (DM)  is one the most dreaded life style disease condition which is spreading as an epidemic across the globe. Diabetes is a group of metabolic diseases characterized by hyperglycemia or hypoglycemia resulting from defects in insulin secretion, insulin action, or both. Chronic hyperglycemia is associated with long-term damage, dysfunction, and failure of different organs, especially the eyes, kidneys, nerves, heart, and blood vessels. In our assignment, we consider the effect of Diabetes Mellitus on the healing of foot ulcers, internal bleeding due to false postures and many more. So, there is a need for monitoring foot pressure and treating these conditions effectively. But each person’s feet and walking pattern are different and unique. In this paper, we present a versatile and any-size-fit in-shoe sensor which is capable of capturing data as you walk in real-time; vivid and easy to understand graphics obtained, will let the subject and the doctor see what happens while walking. The graphics are displayed on the Smartphones using an Android application developed by us. It is wireless, portable and user friendly technology and also records the data or history for gait analysis by a podiatrist. The user friendly application will display the foot strikes dynamically as a movie, frame by frame. A podiatrist or the subject can use side by side comparisons of graphics before and after treatment to evaluate effectiveness or suggest correction. The acquired data consists of many pressure points values which directly or indirectly affect the fitness of the diabetic foot. Data pre-processing helps to format the data into useful form by removing redundancy and noise, eliminating missing and non-numerical values, and also by normalization. Data analysis and visualization are carried out to improve the statistical analysis of given data. Logistic regression is carried out on the data since it contains lot of columns with categorical values. Accuracy, precision, and f1 score of the model have been measured. Various conclusions can be drawn from this interdependent data set and can be stored as historical data for future analysis.
Keywords: Diabetes Mellitus (DM), hyperglycemia, hypoglycemia Machine Learning, Data pre-processing
| DOI: 10.17148/IJARCCE.2020.9208