GLSTM: A novel approach for prediction of real & synthetic PID diabetes data using GANs and LSTM classification model

Journal Title: International Journal of Experimental Research and Review - Year 2023, Vol 30, Issue 1

Abstract

Generative Adversarial Network (GAN) is a revolution in modern artificial systems. Deep learning-based Generative adversarial networks generate realistic synthetic tabular data. Synthetic data are used to enhance the size of a relatively small training dataset while ensuring the confidentiality of the original data. In this context, we implemented the GAN framework for generating diabetes data to help the health care professional in more clinical applications. GAN is used to validate the Pima Indian Diabetes (PID) Dataset. Various preprocessing techniques, such as handling missing values, outliers and data imbalance problems, enhance data quality. Some exploratory data analyses, such as heat maps, bar graphs and histograms, are used for data visualisation. We employed hypothesis testing to examine the resemblance between real data and GAN-generated synthetic data. In this study, we proposed a GAN-Long Short-Term Memory (GLSTM) system, in which GAN is used for data augmentation, and LSTM is used for diabetes classification. Additionally, various GAN models such as CTGAN, Vanilla GAN, Coupula GAN, Gaussian Coupula GAN, and TVAE GAN are used to generate the synthetic dataset. Experiments were conducted on real data, synthetic data, and by combining real and synthetic data. The model that used both real and synthetic data obtained a substantially better accuracy of 97% compared to 92% when only real data was used. We also observed that synthetic data could be used in place of real data, as the mean correlation between synthetic and real data is 0.93. Our study's findings outperformed when compared to state-of-the-art methodologies.

Authors and Affiliations

Sushma Jaiswal, Priyanka Gupta

Keywords

Related Articles

Some medicinal plants with anti -fertility potential used by the tribal people of the District Cooch Behar, West Bengal, India

The increase in population is becoming a comprehensive dilemma, causing much pressure alternative medicine for anti-fertility action. Ayurveda and other Indian literature mention the use of plants in various human ailmen...

Nutritional status and effect of physical activity on anthropmetric characteristics of Bengalee Muslim adolescents boys of North 24 Parganas, West Bengal, India

A cross-sectional study of 522 Bengalee Muslim boys aged 10-17 years of Deganga, North 24 Parganas, West Bengal, India, was undertaken to study their age differences in nutritional status and effect of physical activity...

Assessment of undernutrition among Santal children of Bolpur-Sriniketan block of Birbhum District, West Bengal, India

Present cross sectional study was undertaken to assess the nutritional status of 348 pre-primary and primary school going Santal children aged 4 to 10 years which includes 186 boys and 162 girls of Bolpur-Sriniketan Bloc...

Water bird diversity in Winter and Summer season of Motijheel lake, Murshidabad, West Bengal, India

Wetlands are the most preferred habitats for water birds. They support the birds by way of feeding, roosting, nesting and rearing young ones. Birds are essential animal group of an ecosystem and maintain a trophic level....

Popping balls papaya extract: Preparation of pediatric dosages in therapeutic formulations for therapeutic usage in dengue and malaria

Spherification is a cutting-edge molecular gastronomy method that has just emerged in the realm of food science and technology, and it may be used to produce foods with superior sensory qualities and a high level of cons...

Download PDF file
  • EP ID EP715428
  • DOI https://doi.org/10.52756/ijerr.2023.v30.004
  • Views 28
  • Downloads 0

How To Cite

Sushma Jaiswal, Priyanka Gupta (2023). GLSTM: A novel approach for prediction of real & synthetic PID diabetes data using GANs and LSTM classification model. International Journal of Experimental Research and Review, 30(1), -. https://europub.co.uk/articles/-A-715428