Joint Workshop KO2PI and The 1st International Conference on Advance & Scientific Innovation

Research Article

Soft Neuro Computing GUI-based Diabetes Mellitus

Download75 downloads
  • @INPROCEEDINGS{10.4108/eai.23-4-2018.2277601,
        author={Agus Rusgiyono and Hasbi Yasin and Abdul Hoyyi and Rezzy Eko Caraka},
        title={Soft Neuro Computing GUI-based Diabetes Mellitus},
        proceedings={Joint Workshop KO2PI and The 1st International Conference on Advance \& Scientific Innovation},
        publisher={EAI},
        proceedings_a={ICASI},
        year={2018},
        month={7},
        keywords={soft computing; ffnn; diabetes mellitus; classification},
        doi={10.4108/eai.23-4-2018.2277601}
    }
    
  • Agus Rusgiyono
    Hasbi Yasin
    Abdul Hoyyi
    Rezzy Eko Caraka
    Year: 2018
    Soft Neuro Computing GUI-based Diabetes Mellitus
    ICASI
    EAI
    DOI: 10.4108/eai.23-4-2018.2277601
Agus Rusgiyono1,*, Hasbi Yasin1, Abdul Hoyyi1, Rezzy Eko Caraka2
  • 1: Departement of Statistics, Diponegoro University, Semarang, Indonesia
  • 2: School of Mathematical Sciences, The National University of Malaysia, Bangi, Malaysia
*Contact email: agus.rusgi@gmail.com

Abstract

Health is a vital aspect of life. According to this, we need to improve public health due to an unhealthy lifestyle which may lead to the occurrence of various kinds of diseases. Diabetes Mellitus (DM) is one negative impacts left by an unhealthy lifestyle which is caused by high blood sugar levels. Numbers of diabetes patients get late treatments due to delayed identification on them. In fact, if a diagnosis report conducted earlier, the treatment can be given earlier as well, and bad conditions may be avoided. Therefore, a system identifying diabetes is needed so that the disease can be detected as fast, accurate, and early as possible. To tackle this issue, we aimed to design soft computing system for early detection of diabetes mellitus by using neural network and binary sigmoid activation function. In a nutshell, The accuracy level of the DM detection was 92.44%.