Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2005 - 200912020 - 20211

Settings

Subject: search.filters.subject.Artificial neural network (ANN)

Search Results

Now showing 1 - 2 of 2
  • Article
    Citation - WoS: 13
    Citation - Scopus: 13
    Multi-Scale Benchtop 1h Nmr Spectroscopy for Milk Analysis
    (Academic Press, 2021) Söyler, Alper; Çıkrıkçı, Sevil; Çavdaroğlu, Çağrı; Bouillaud, Dylan; Farjon, Jonathan; Giraudeau, Patrick; Öztop, Mecit H.
    Benchtop NMR systems offers various advantages such as being easy to use, not requiring constant maintenance and being available at affordable prices. In this study, multiple aspects of benchtop NMR spectroscopy were explored to analyze milk in an industrial context, either regarding the quality of production or regarding the differentiation of the final product. The first part focuses on the production conditions of lactose hydrolysis in milk and quantitative online NMR spectroscopy was adapted to follow lactose hydrolysis in milk in continuous flow mode. The second part focuses on differentiating milk samples having different properties. 36 milk samples from France and Turkey were analysed and glycerol, fat and sugar contents were measured from the NMR spectra. Combination of spectroscopic data with a proposed Artificial Neural Network model enabled to classify milk of different origins and different properties. This study shows that benchtop NMR spectroscopy is a versatile non-destructive control method that can help controlling milk quality both during and after production. © 2020 Elsevier Ltd
  • Article
    Citation - WoS: 53
    Citation - Scopus: 63
    Artificial Neural Network (ann) Prediction of Compressive Strength of Vartm Processed Polymer Composites
    (Elsevier Ltd., 2005) Seyhan, Abdullah Tuğrul; Tayfur, Gökmen; Karakurt, Murat; Tanoğlu, Metin
    A three layer feed forward artificial neural network (ANN) model having three input neurons, one output neuron and two hidden neurons was developed to predict the ply-lay up compressive strength of VARTM processed E-glass/ polyester composites. The composites were manufactured using fabric preforms consolidated with 0, 3 and 6 wt.% of thermoplastic binder. The learning of ANN was accomplished by a backpropagation algorithm. A good agreement between the measured and the predicted values was obtained. Testing of the model was done within low average error levels of 3.28%. Furthermore, the predictions of ANN model were compared with those obtained from a multi-linear regression (MLR) model. It was found that ANN model has better predictions than MLR model for the experimental data. Also, the ANN model was subjected to a sensitivity analysis to obtain its response. As a result, the ANN model was found to have an ability to yield a desired level of ply-lay up compressive strength values for the composites processed with the addition of the thermoplastic binder.