Search

Diabetes occurs among different age group populations due to insulin usage in the body. The pancreas produces insulin to convert the food into glucose, and it is observed by the blood cells to produce energy. In some people, the pancreas produces less insulin, and they are called type I diabetic patients. Hence, those people are suffering from type I diabetes and are advised to take insulin regularly through injection. But they don’t know the exact quantity of insulin to be taken on their day-to-day basis. The consumption level of insulin varies for every individual. The single individual consuming insulin also varies every day based on their regular activities, food, stress level, exercises, etc. Only through a regular blood test the patients may know the insulin level in their body. The patient needs the advice of physicians every day to change the consumption of insulin. It is difficult to get an appointment with the physicians to meet and know their blood glucose level and the quantity of insulin required for their bodies. Thus, there is a need for a computer-aided diagnosis system to solve this struggle among type I diabetic patients. By using the proposed system, hospitals could reduce the inpatients during critical times, while they visit the physicians only for testing the insulin level. The proposed IoT-based machine learning algorithm is suitable to efficiently handle the condition to predict the glucose level of the human body and suggest the quantity of insulin required for the diabetic patient. The patients are advised to access the system from anywhere without a physician’s help. The proposed technique is accurately predicting the required insulin level to assist diabetic patients. Insulin conception varies among the patients when they are fasting, after meals, and during sickness. First, patients should know their type of insulin. The patient must check the blood glucose level through the glucometer, and this has been recorded in the system to track the status. The noninvasive Dexcom G4 platinum sensor is used to update the patient’s glucose level reading every minute, and it will be displayed in an android device application. The patient’s glucose level is compared with the parameters in the dataset under different categories. In order to reliably predict the dosage of insulin needed for the patient on a specific day, the machine learning algorithm found an exact pattern-matching criterion. The graphical user interface collects the daily activities of the patients and analyzes their previous history of insulin consumption to make a wise decision on insulin calculation. The statistical results are projected through the graph which denotes the insulin dosage conceived by the patients on a particular period. This helps the physicians to suggest quick solutions during the time of admit due to any other illness in a hospital. The historical data enables the physicians and patients to act smoother in handling the diabetic disease. The proposed system improves the economy of the country by saving the life of diabetic patients.

The most prominent ophthalmic cause of blindness is Diabetic Retinopathy (DR). This retinal disease is characterized by variation in diameter of the retinal blood vessel and the new blood vessel growth inside the retina. A system to enhance the quality of the segmentation result over the pathological retinal images has been proposed. The proposed method uses Contrast Limited Adaptive Histogram Equalization (CLAHE) for preprocessing and Tandem Pulse Coupled Neural Network (TPCNN) model for automatic feature vectors generation then classification and extraction of the retinal blood vessels via Deep Learning Based Support Vector Machine (DLBSVM). The proposed approach is assessed over the standard public fundus image databases to evaluate the performance. The results render that these techniques improve the segmentation results with an average value of 74.45% sensitivity, 99.40% specificity, and 99.16% accuracy. The results evoke that the proposed method is a suitable alternative for supervised techniques.

Purpose: Accurate segmentation of retinal blood vessel is an important task in computer-aided diagnosis and surgery planning of diabetic retinopathy. Despite the high-resolution of photographs in fundus photography, the contrast between the blood vessels and the retinal background tends to be poor. Materials and Methods: In this proposed method, contrast-limited adaptive histogram equalization is used for noise cancellation and improving the local contrast of the image. By uniform distribution of gray values, it enhances the image and makes the hidden features more visible. The extraction of the retinal blood vessel depends on two levels of optimization. The first level is the extraction of blood vessels from the retinal image using Kirsch's templates. The second level is used to find the coarse vessels with the assistance of the unsupervised method of Fuzzy C-Means clustering. After segmentation, to remove the optic disc, the region-based active contour method is used. The proposed system is evaluated using DRIVE dataset with 40 images. Results: The performance of the proposed approach is comparable with state of the art techniques. The proposed technique outperforms the existing techniques by achieving an accuracy of 99.55%, sensitivity of 71.83%, and specificity of 99.86% in the experimental setup. Conclusion: The results show that this approach is a suitable alternative technique for the supervised method and it is support for similar fundus images dataset.

The aim of this paper to predict a student performance using traditional and machine learning techniques: Bayes algorithm, linear regression, logistic Regression, k-nn algorithm, decision tree. Naive based algorithm is the emerging field which compose the procedure of verified students details like semester marks, assignment, attendance, lab work which are used to improve students’ performance. This paper shows a model of students data prediction based on Bayes algorithm, linear regression, logistic Regression, k-nearest neighbor, decision tree and suggest the best algorithm among these algorithms based on performance details. Classification is an important area to predict and application in a variety of fields. In the view of full knowledge of the algorithm underlying probabilities, Bayes decision theory shows the optimal error rate. Decision tree algorithm is been used successfully in expert systems in capturing prediction. Mainly the decision tree classifiers are used to design and classify the student’s data with Boolean class labels. Linear regression is a linear approach to modeling the relationship between the details of students in scalar response.

Diabetic Retinopathy is one of the ophthalmic reasons for visual deficiency. The favored fixate of consideration is on the estimation of deviation in the breadth of the retinal veins and the new vessel development. To witness the progressions, segmentation has to be made primarily. A framework to improve the quality of the segmentation result over pathological retinal images is proposed. The proposed method uses adaptive histogram equalizer for preprocessing, pulse coupled neural Network model for automatic feature vector generation and extraction of the retinal blood vessels. The test result represents that the proposed method is enhanced than other retinal competitive methods. The evaluation of the proposed approach is executed over standard public DRIVE, STARE, REVIEW, HRF, and DRIONS fundus image datasets. The proposed technique improves the segmentation results in terms of sensitivity, specificity, and accuracy.

Diabetic Retinopathy (DR) occurs due to Type-II diabetes. It causes damages to the retinal blood vessels and reason for visual impairment. The predicted center is around the probability of variation in the estimation of retinal veins, and the crisp enrolls vessel development inside the retina. To witness the changes segmentation of retinal blood vessels has to be made. A framework to upgrade the quality of the segmentation results over morbid retinal images is proposed. This framework utilizes Contrast Limited Adaptive Histogram Equalization (CLAHE) for eliminating the background from the source image and enhances the foreground blood vessel pixels, Tandem Pulse Coupled Neural Network (TPCNN) model is endorsed for automatic feature vectors generation, and Deep Learning Based Support Vector Machine (DLBSVM) is proposed for classification and extraction of blood vessels. The DLBSVM parameters are fine-tuned via Firefly algorithm. The STARE, DRIVE, HRF, REVIEW, and DRIONS fundus image datasets are deliberated to assess the recommended techniques. The results render that the proposed technologies improve the segmentation with 80.61% Sensitivity, 99.54% Specificity, and 99.49% Accuracy.