Premium
Clustered ANFIS weighing models for sweet lime ( Citrus limetta ) using computer vision system
Author(s) -
Phate Vikas R.,
Malmathanraj Ramanathan,
Palanisamy Ponnusamy
Publication year - 2019
Publication title -
journal of food process engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.507
H-Index - 45
eISSN - 1745-4530
pISSN - 0145-8876
DOI - 10.1111/jfpe.13160
Subject(s) - adaptive neuro fuzzy inference system , artificial neural network , artificial intelligence , machine learning , computer science , fuzzy logic , robustness (evolution) , cluster analysis , data mining , mathematics , fuzzy control system , biochemistry , chemistry , gene
In the present research work, a clustered adaptive neuro‐fuzzy inference system (ANFIS) is used to develop the model of relationship between the weight with 1D and 2D features of the Indian sweet lime fruit extracted through the developed computer vision system. Initially, three clustering methods are used to classify the input data into a homogeneous group. Then, the self‐learning proficiency of an artificial neural network and the ability of fuzzy theory to deal with the uncertainty and nonlinearity are utilized by developing the ANFIS model. Finally, the clustered data is combined with the ANFIS models trained by two different learning methods are analyzed. The goodness‐of‐fit indicators close to unity and the lower values of the error performance metrics implies the adequacy, robustness, and superiority of the proposed method. Moreover, the lower value of Theil's coefficient for uncertainty (UII) signifies the credibility of the model to predict the weight of a sweet lime fruit. Practical applications The presented improved approach of clustered ANFIS modeling for weighing sweet lime fruit will be fruitful to the researchers, farmers, and engineers. In order to, design and develop the real time weight‐based grading, sorting, and packaging machine's knowledge about the fruit weight‐size relation is a basic requirement. Use of this proposed approach (computer vision linked with the clustered ANFIS model) will greatly reduce the handling of the fruit as well as the workload that are responsible for the qualitative and quantitative losses of fruits on bulk industrial scale. Also, this weighing model using 1D and 2D features will be more beneficial, faster, and economically viable substitute to the on‐field manual method used in agriculture specially during the sorting, grading, and packaging of sweet lime.