Monitoring the osmotic dehydration process of quince by the novel fusion modular neural networks - fuzzy logic (Fmnn-Fl)

摘要: This paper presents a novel approach to monitor food process based on Modular Neural Networks (MNNs) and fuzzy inference system. The proposed MNN consists of three separate modules, each using different image features as input including: edge detection, wavelet transform, Hough transform. sugeno system was used combine the outputs from these modules classify images quince during osmotic dehydration process. To test method, for classification, database made 108 samples’ (12 classes). In experiments, developed architecture achieved 91.6% recognition accuracy. Next step, solid gain, water loss moisture content samples were considered MNNs outputs, whereas time classified inputs. minimum %MRE (18.153) with 89% prediction ability (WL) obtained when applying two hidden layers 6 neurons per layers. lowest (35.5335) 93% gain (SG) 8 first second layer, respectively. And finally at least (7.4759) 96% (MC) by 5 results show that this model could be commendably implemented quantitative modeling monitoring quality changes