Adaptive neuro - Fuzzy Classifier Applied to Near Infrared Spectra of Raw Milk for Recognition of Bacterial Presence

Izdanje: Naučna konferencija Uniteh 2010

Oblast: Automation

Stranice: 538-542

Apstrakt:
Adaptive neuro - fuzzy classifier applied to near infrared spectra of raw milk for recognition of bacterial presence is presented in the paper. Healthy milk samples and milk samples contaminated with Staphylococе were used. Principal component analysis was used for spectral data processing to reduce the recognition features. First three components were used as a input data for the classifier. The output is one sample class contaminated or contaminated. The obtained average percent error for class contaminated samples is 3,88% and for class contaminated is 10,06%.
Ključne reči: milk, bacteria contamination, NIR spectroscopy, Neuro - Fuzzy, PCA
Priložene datoteke:
Kategorije objave: Radovi na konferenciji Unitech 2010, Gabrovo, Bugarska

Preuzimanje citata:

BibTeX format 
@article{article,
  author  = {P. Veleva Doneva, C. Draganova, S. Atanasova and V. Kukenska}, 
  title   = {Adaptive neuro - Fuzzy Classifier Applied to Near Infrared Spectra of Raw Milk for Recognition of Bacterial Presence},
  journal = {Naučna konferencija Uniteh 2010},
  year    = 2010,
  pages   = {538-542}}
RefWorks Tagged format 
RT Conference Proceedings
A1 Petja Veleva Doneva
A1 Cvetelina Draganova
A1 Stefka Atanasova
A1 Valentina Kukenska
T1 Adaptive neuro - Fuzzy Classifier Applied to Near Infrared Spectra of Raw Milk for Recognition of Bacterial Presence
AD Naučna konferencija Unitech, Gabrovo, Bugarska
YR 2010
Unapred formatirani prikaz citata
P. Veleva Doneva, C. Draganova, S. Atanasova and V. Kukenska, Adaptive neuro - Fuzzy Classifier Applied to Near Infrared Spectra of Raw Milk for Recognition of Bacterial Presence, Naučna konferencija Unitech, 2010