casa 20(21): e4

Research Article

Prediction of Pineapple Sweetness from Images Using Convolutional Neural Network

Download190 downloads
  • @ARTICLE{10.4108/eai.13-7-2018.165518,
        author={Adisak Sangsongfa and Nopadol Am-Dee and Payung Meesad},
        title={Prediction of Pineapple Sweetness from Images Using Convolutional Neural Network},
        journal={EAI Endorsed Transactions on Context-aware Systems and Applications},
        volume={7},
        number={21},
        publisher={EAI},
        journal_a={CASA},
        year={2020},
        month={7},
        keywords={CNN, prediction, sweetness measurement},
        doi={10.4108/eai.13-7-2018.165518}
    }
    
  • Adisak Sangsongfa
    Nopadol Am-Dee
    Payung Meesad
    Year: 2020
    Prediction of Pineapple Sweetness from Images Using Convolutional Neural Network
    CASA
    EAI
    DOI: 10.4108/eai.13-7-2018.165518
Adisak Sangsongfa1, Nopadol Am-Dee2, Payung Meesad3,*
  • 1: Department of Computer Science, Rajabhat Mu-Ban Chombueng University, Thailand
  • 2: Department of Industrial Technology Management, Rajabhat Mu-Ban Chombueng University, Thailand
  • 3: Department of Information Technology Management, King Mongkut’s University of Technology North Bangkok
*Contact email: adisak.s@mcru.mail.go.th

Abstract

The objective of this research is to propose a deep learning based-prediction model for pineapple sweetness. In this research, we use a Convolutional Neural Network (CNN) to predict sweetness of pineapples from images. The dataset contains 4,860 pineapple images for training. Based on the CNN designed it is found that the best image size is 300 × 300 pixels resized to 30 × 30 pixels. The classification accuracy of training and testing are 72.38% and 78.50%, respectively. In addition, the root mean square error values for training and testing are 0.1362 and 0.1156, respectively. When developed as a mobile application, the accuracy of the application is 80.15%, the root mean square error value is 0.0156 and the reliability is 95.00%.