Optimization of Backpropagation for Early Detection of Diabetes Mellitu

Abstract

Diabetes mellitus is one of the urgent health problems in the world. Diabetes is a condition primarily defined by the level of hyperglycemia giving rise to risk of micro vascular damage. Those who suffer from this disease generally do not realize and tend to overlook the early symptoms. Late recognition of these early symptoms may drive the disease to a more concerning level. One solution to solve this problem is to create an application that may perform early detection of diabetes mellitus so that it does not grow larger. In this article, a new method in performing early detection of diabetes mellitus is suggested. This method is backpropagation with three optimization namely early initialization with Nguyen-Widrow algorithm, learning rate adaptive determination, and determination of weight change by applying momentum coefficient. The observation is conducted by collecting 150 data consisting of 79 diabetes mellitus patient and 71 non diabetes mellitus patient data. The result of this study is the suggested algorithm succeeds in detecting diabetes mellitus with accuracy rate of 99.33%. Optimized backpropagation algorithm may allow the training process goes 12.4 times faster than standard backpropagation.

Improving self-organizing map with nguyen-widrow initialization lgorithm

“…A reduction of an average of 7.39% on the number of iterations was recorded using improved SOM as compared to traditional SOM thus improving the training time. This was because Nguyen-Widrow initialization is known to accelerate the training process in a neural network [14][15][16]. Thus, the improved SOM yields a better quality of cluster results and speeds up the training speed which led to improved processing time.…”

“…This speeds up the training process by setting the initial weights of the first layer so that each node is assigned its own interval at the start of the training [13][14]. When applied to optimize the backpropagation algorithm, the Nguyen-Widrow was able to produce the best accuracy level and accelerate the training process [15]. Optimal performance was achieved at the backward process by adapting the learning rate parameter capable of affecting the value of the weighting and reduced the number epoch [16].…”

Identifikasi Penderita COVID-19 Berdasarkan Chest X-Ray Menggunakan Algoritma Jaringan Syaraf Tiruan Backpropagation

“…Kata kunci: COVID-19, Chest X-Ray, Backpropagation, Pandemi, Algoritma. [2], memprediksi dan pengenalan pola [3] dan juga mendeteksi dugaan penyakit paru berdasarkan gejala [4]. Selain itu, algoritma jaringan syaraft tiruan Bacpropagation juga sering digunakan dalam pengklasifikasian dan identifikasi citra.…”

“…Algoritma 1 merupakan proses dalam pre processing. for i = 1 to line do for j = 1 to column do grayco[0](tone(i,j),tone(i,j+1))+1 grayco[1](tone(i,j),tone(i-1,j+1))+1 grayco [2](tone(i,j),tone(i-1,j))+1 grayco [3](tone(i,j),tone(i-1,j-1))+1 end for end for symmetric=grayco+transpose(grayco) Normalisasi=glcmNorm(symmetric) Correlation: getCorrelation(Normalisasi) Energy: getEnergy(Normalisasi) Contrast: getContrast(Normalisasi) Homogenity: getHomogenity(Normalisasi)…”

A proposed model for diabetes mellitus classification using coyote optimization algorithm and least squares support vector machine

“…Diabetes is one of the main reasons for the increase in the number of deaths in the world, especially the Type-II-DM, which is the most common [4]. Many serious health disorders occur when neglected and not treated, such as heart attack, myocardial infarction, stroke, renal failure, blindness, neuropathy, gangrene, micro vascular damage and increased susceptibility to infection [5], [6]. With its spread, places a great strain on the public health system [7], [8].…”