Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network

Ashiquzzaman, Akm; Tushar, Abdul Kawsar; Islam, Rashedul; Shon, Dongkoo; Im, Ki Chun; Park, Jeong-Ho; Lim, Dong-Sun; Kim, Jong‐Myon

doi:10.1007/978-981-10-6451-7_5

Cited by 78 publications

(41 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The prominent attribute of the deep learning is that deep embedded layers recognize the features and cascade them into the final output prediction to cast classification. This is the attribute that has contributed to deep learning method being used in problems in image recognition and disease prediction [16], among others. In our proposed model, the CNN layers have been increased in number from the model used by [5].…”

Section: Resultsmentioning

confidence: 99%

Handwritten Arabic numeral recognition using deep learning neural networks

Ashiquzzaman

Tushar

2017

2017 IEEE International Conference on Imaging, Vision &Amp; Pattern Recognition (icIVPR)

Self Cite

115

View full text Add to dashboard Cite

Handwritten character recognition has been the center of research and a benchmark problem in the sector of pattern recognition and artificial intelligence, and it continues to be a challenging research topic. Due to its enormous application many works have been done in this field focusing on different languages. Arabic, being a diversified language has a huge scope of research with potential challenges. A convolutional neural network model for recognizing handwritten numerals in Arabic language is proposed in this paper, where the dataset is subject to various augmentation in order to add robustness needed for deep learning approach. The proposed method is empowered by the presence of dropout regularization to do away with the problem of data overfitting. Moreover, suitable change is introduced in activation function to overcome the problem of vanishing gradient. With these modifications, the proposed system achieves an accuracy of 99.4% which performs better than every previous work on the dataset.

show abstract

Section: Resultsmentioning

confidence: 99%

Handwritten Arabic numeral recognition using deep learning neural networks

Ashiquzzaman

Tushar

2017

2017 IEEE International Conference on Imaging, Vision &Amp; Pattern Recognition (icIVPR)

Self Cite

115

View full text Add to dashboard Cite

show abstract

“…As a future work, the non-used classifiers can be applied to other datasets in a combined model to enhance further the accuracy of predicting the Diabetes disease. [20] 768 8 [21] 102,538 49 [22] 768 8 [23] 768 8 [24] 392 8 [25] 768 8 [7] 768 8 [45] 768 8…”

Section: Discussionmentioning

confidence: 99%

“…Also, Ashiquzzaman et al [7] used a Deep Neural Network (DNN). The architecture of the DNN composed of Multilayer Perceptron (MLP), General Regression Neural Network (GRNN), and Radial Basis Function (RBF).…”

Section: Related Work Using Deep Learningmentioning

confidence: 99%

Current Techniques for Diabetes Prediction: Review and Case Study

et al. 2019

View full text Add to dashboard Cite

Diabetes is one of the most common diseases worldwide. Many Machine Learning (ML) techniques have been utilized in predicting diabetes in the last couple of years. The increasing complexity of this problem has inspired researchers to explore the robust set of Deep Learning (DL) algorithms. The highest accuracy achieved so far was 95.1% by a combined model CNN-LSTM. Even though numerous ML algorithms were used in solving this problem, there are a set of classifiers that are rarely used or even not used at all in this problem, so it is of interest to determine the performance of these classifiers in predicting diabetes. Moreover, there is no recent survey that has reviewed and compared the performance of all the proposed ML and DL techniques in addition to combined models. This article surveyed all the ML and DL techniques-based diabetes predictions published in the last six years. In addition, one study was developed that aimed to implement those rarely and not used ML classifiers on the Pima Indian Dataset to analyze their performance. The classifiers obtained an accuracy of 68%–74%. The recommendation is to use these classifiers in diabetes prediction and enhance them by developing combined models.

show abstract

“…It can handle the massive amount of data and have the capability to decode a complex problem in an easy way. Recently, various machine learning techniques [9,10] and bio-inspired computing technique [11] as well as deep learning techniques [14,18] are used in several medical prognoses. To predict diabetes mellitus, we have used deep neural network which is recently very popular method in machine learning.…”

Section: Introductionmentioning

confidence: 99%

“…Ashiquzzaman et al [14] proposed a prediction framework for the diabetes mellitus using deep learning approach where the overfitting is diminished by using the dropout method. There are two fully connected layers each trailed by a dropout layer.…”

Section: Introductionmentioning

confidence: 99%

Diabetes Prediction: A Deep Learning Approach

Ayon¹,

Islam²

2019

IJIEEB

137

View full text Add to dashboard Cite

Nowadays, Diabetes is one of the most common and severe diseases in Bangladesh as well as all over the world. It is not only harmful to the blood but also causes different kinds of diseases like blindness, renal disease, kidney problem, heart diseases etc. that causes a lot of death per year. So, it badly needs to develop a system that can effectively diagnose the diabetes patients using medical details. We propose a strategy for the diagnosis of diabetes using deep neural network by training its attributes in five-fold and tenfold crossvalidation fashion. The Pima Indian Diabetes (PID) data set is retrieved from the UCI machine learning repository database. The results on PID dataset demonstrate that deep learning approach design an auspicious system for the prediction of diabetes with prediction accuracy of 98.35%, F1 score of 98, and MCC of 97 for five-fold cross-validation. Additionally, accuracy of 97.11%, sensitivity of 96.25%, and specificity of 98.80% are obtained for tenfold cross-validation. The experimental results exhibit that the proposed system provides promising results in case of five-fold cross-validation.

show abstract

Reduction of Overfitting in Diabetes Prediction Using Deep Learning Neural Network

Cited by 78 publications

References 16 publications

Handwritten Arabic numeral recognition using deep learning neural networks

Handwritten Arabic numeral recognition using deep learning neural networks

Current Techniques for Diabetes Prediction: Review and Case Study

Diabetes Prediction: A Deep Learning Approach

Contact Info

Product

Resources

About