Spectral signature for quality assessment of anchovy fish meal (Engraulis Ringens) using Partial Least Squares



Fish meal, Spectral signature, Hyperspectral image


Fishmeal is one of the most important foods for the aquaculture, livestock and poultry sectors in Latin America and the world. However, one of the constraints in the fishing industry is to measure online the physicochemical composition of this product and ensure its quality. In this study, the spectral signature of anchovy fish meal (Engraulis Ringens) has been obtained in wavelengths from 400 to 900 nm and has been related to its values of Protein, Ash, Moisture, Fat, Free Fatty Acids (FFA), total volatile basic nitrogen (TVB-N), sand, histamine and antioxidant remnant (REM.A/O). To analyze these relationships has been used the regression of Partial Least Squares (PLS) finding the best results to determine the Protein, Fat, Moisture and with some accuracy TBVN and Histamine. In addition, the most important spectral ranges have been identified for the calculation of the estimates. With these results we have a model to determine the physicochemical composition of anchovy fish meal based on the spectral signature that could be implemented in automatic systems for process control.


Download data is not yet available.

Author Biographies

Juan Soto, Universidad de Piura, Laboratory of Automatic Control Systems, Piura, Peru.

Juan Soto is Mechanical Electrical Engineer from the University of Piura, in 2013; he has completed a Master with mention in Energy Efficiency at the University of Piura, 2014. He is currently a researcher at the University of Piura; author of papers on Embedded Systems, Automatic Control of Industrial Processes, Image Processing, Development of models based on Machine Learning and Deep Learning, Algorithms for parameter estimation based on hyperspectral images and their spectral signature. Participates in I + D + i projects with funds from INNOVATE PERÚ and CONCYTEC programs; has intellectual property registers (Copyright and Invention Patent).

Gerson La Rosa, Universidad de Piura, Laboratory of Automatic Control Systems, Piura, Peru.

Gerson La Rosa is an industrial and systems engineer from the University of Piura (UDEP) with an M.Sc in Data Analysis Engineering, Process Improvement and Decision Making from the Department of Statistics of the Polytechnic University of Valencia (UPV).
He currently works in the Research Department of the UDEP and supports the laboratory of Automatic and Control Systems (SAC) of the same university. He is currently pursuing a PhD in Engineering with mention in Automation, Control and Process Optimization at UDEP. His areas of interest are the identification and validation of models based on statistical and Machine Learning techniques to estimate characteristic parameters in fishing, agricultural and hydrological processes.

Ernesto Paiva, Universidad de Piura, Laboratory of Automatic Control Systems, Piura, Peru.

Ernesto Paiva received the degree of Mechanical-Electrical Engineer from the University of Piura, Peru, in 2013; he has completed a Master's degree in Mechanical-Electrical Engineering with mention in Automatics and Optimization at the University of Piura funded by CONCYTEC 2016. He is currently a research assistant at the Department of Technology and Innovation (DTI) - SUPSI, in charge of the development of Deep Learning algorithms ANN, CNN, LSTM, Conv LSTM.

William Ipanaque, niversidad de Piura, Laboratory of Automatic Control Systems, Piura, Peru.

William Ipanaqué Ph.D. in Computer and Automatic Engineering from the Polytechnic of Milan (Italy). His research fields are automatic control, optimization and automation of emerging processes and technologies. Founder and director of the Mechanical Electrical Master with mention in Automation and Optimization from UDEP. He has worked as a member of the Advisory Council of the Congress of the Republic of the commission of Science, Innovation and Technology. For his work in technological research, in 2015 he was recognized with the order of merit Santiago Antúnez de Mayolo Gamero and in 2014 he received recognition from Concytec for the working group of automatic control systems that he directs at the UDEP.


R. L. Olsen and M. R. Hasan, “A limited supply of fishmeal: Impact on future increases in global aquaculture production,” Trends Food Sci. Technol., vol. 27, no. 2, pp. 120–128, 2012, doi:10.1016/j.tifs.2012.06.003.

A. G. J. Tacon and M. Metian, “Global overview on the use of fish meal and fish oil in industrially compounded aquafeeds: Trends and future prospects,” Aquaculture, vol. 285, no. 1–4, pp. 146–158, 2008, doi:10.1016/j.aquaculture.2008.08.015.

L. M. Potter, W. J. Pudelkiewics, L. Webster, and L. D. Matterson, “Metabolizable Energy and Digestibility Evaluation of Fish Meal for Chickens,” Poult. Sci., vol. 41, no. 6, pp. 1745–1752, 1961, doi:10.3382/ps.0411745.

S. W. Kim and R. A. Easter, “Nutritional value of fish meals in the diet for young pigs,” J. Anim. Sci., vol. 79, no. 7, pp. 1829–1839, 2001, doi:10.2527/2001.7971829x.

J. D. Berrocoso, M. P. Serrano, L. Cámara, P. G. Rebollar, and G. G. Mateos, “Influence of diet complexity on productive performance and nutrient digestibility of weanling pigs,” Anim. Feed Sci. Technol., vol. 171, no. 2–4, pp. 214–222, 2012, doi:10.1016/j.anifeedsci.2011.10.013.

S. M. Sinn, W. R. Gibbons, M. L. Brown, J. M. Derouchey, and C. L. Levesque, “Evaluation of microbially enhanced soybean meal as an alternative to fishmeal in weaned pig diets,” Animal, vol. 11, no. 5, pp. 784–793, 2017, doi:10.1017/S1751731116002020.

M. Hasan and M. Halwart, “Fish as feed inputs for aquaculture: Practices, sustainability and implications: a global synthesis,” in Fish as feed inputs for aquaculture: practices, sustainability and implications, 518th ed., no. 518, Rome: FAO Fisheries and Aquaculture Technical Paper, pp. 1–61, 2009.

R. W. Hardy, “Utilization of plant proteins in fish diets: Effects of global demand and supplies of fishmeal,” Aquac. Res., vol. 41, no. 5, pp. 770–776, 2010, doi:10.1111/j.1365-2109.2009.02349.x.

International Trade Center, “Trade Map - Estadísticas del comercio para el desarrolo internacional de las empresas.” [Online]. Available: https://www.trademap.org/Index.aspx, 2018.

Sociedad Nacional de Pesquería, “Harina de pescado / Fishmeal - Sociedad Nacional de Pesquería.” [Online]. Available: https://www.snp.org.pe/oferta_exportable/harina-de-pescado/, 2018.

J. M. Prats, Control Estad¡stico de Procesos mediante Análisis Multivariante de Imágenes. Valencia: Universidad Politécnica de Valencia, 2005.

M. Lin, M. Mousavi, M. Al-Holy, A. G. Cavinato, and B. A. Rasco, “Rapid near infrared spectroscopic method for the detection of spoilage in rainbow trout (Oncorhynchus mykiss) fillet,” J. Food Sci., vol. 71, no. 1,2006), doi:10.1111/j.1365-2621.2006.tb12400.x.

B. Gümüş and M. O. Balaban, “Prediction of the weight of aquacultured rainbow trout (Oncorhynchus mykiss) by image analysis,” J. Aquat. Food Prod. Technol., vol. 19, no. 3–4, pp. 227–237, 2010, doi:10.1080/10498850.2010.508869.

A. Folkestad et al., “Rapid and non-invasive measurements of fat and pigment concentrations in live and slaughtered Atlantic salmon (Salmo salar L.),” Aquaculture, vol. 280, no. 1–4, pp. 129–135, 2008, doi:10.1016/j.aquaculture.2008.04.037.

P. Katikou, S. I. Hughes, and D. H. F. Robb, “Lipid distribution within atlantic salmon (Salmo salar) fillets,” Aquaculture, vol. 202, no. 1–2, pp. 89–99, 2001, doi:10.1016/S0044-8486(01)00562-2.

J. P. Wold and T. Isaksson, “Non-destructive determination of fat and moisture in whole Atlantic salmon by near-infrared diffuse spectroscopy,” J. Food Sci., vol. 62, no. 4, pp. 734–736, 1997, doi:10.1111/j.1365-2621.1997.tb15446.x.

J. F. Wold et al., “Non-contact transflectance near infrared imaging for representative on-line sampling of dried salted coalfish (bacalao),” J. Near Infrared Spectrosc., vol. 14, no. 1, pp. 59–66, 2006, doi:10.1255/jnirs.587.

H.-J. He, D. Wu, and D.-W. Sun, “Nondestructive Spectroscopic and Imaging Techniques for Quality Evaluation and Assessment of Fish and Fish Products,” Crit. Rev. Food Sci. Nutr., vol. 55, no. 6, pp. 864–886, 2015, doi:10.1080/10408398.2012.746638.

Y. Zhang, L.-H. Tan, F. Cao, and Y. He, “Study on brand discrimination of fish oil based on multiple spectroscopy techniques,” Mod. Food Sci. Technol., vol. 30, no. 10, pp. 263–267, 2014, doi:10.13982/j.mfst.1673-9078.2014.10.044.

J. H. Cheng and D. W. Sun, “Partial Least Squares Regression (PLSR) Applied to NIR and HSI Spectral Data Modeling to Predict Chemical Properties of Fish Muscle,” Food Eng. Rev., vol. 9, no. 1, pp. 36–49, 2017, doi:10.1007/s12393-016-9147-1.

T. Isaksson, G. Tøgersen, A. Iversen, and K. I. Hildrum, “Non‐destructive determination of fat, moisture and protein in salmon fillets by use of near‐infrared diffuse spectroscopy,” J. Sci. Food Agric., vol. 69, no. 1, pp. 95–100, 1995, doi:10.1002/jsfa.2740690115.

D. Wu and D. W. Sun, “Colour measurements by computer vision for food quality control - A review,” Trends Food Sci. Technol., vol. 29, no. 1, pp. 5–20, 2013, doi:10.1016/j.tifs.2012.08.004.

Y. Huang and A. Cavinato, “Nondestructive Determination of Moisture and Sodium Chloride in Cured Atlantic Salmon (Salmo salar)(Teijin) Using Short-wavelength Near-infrared Spectroscopy (SW-NIR),” J. Food Sci., vol. 68, no. 2, 2003, doi:10.1111/j.1365-2621.2003.tb05698.x.

G. Viera-maza, “Aplicación de procesamiento de imágenes para clasificación de granos de cacao según su color interno,” Universidad de Piura, Piura, 2018.

A. Höskuldsson, “PLS regression methods” Journal of Chemometrics, vol. 2, no. 3, pp. 211–228, 1988, doi:10.1002/cem.1180020306.

R. Kohavi, “A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection A Study of Cross-Validation and Bootstrap for Accuracy Estimation and Model Selection,” Int. Jt. Conf. Artif. Intell., no. March 2001, pp. 1137–1143, 2016.

L. Ståhle and S. Wold, “Partial Least Squares Analysis with Cross-Validation for the Two-Class Problem: A Monte Carlo Study,” J. Chemom., vol. 1, no. 3, pp. 185–196, 1987, doi:10.1002/cem.1180010306.

T. Mehmood, K. H. Liland, L. Snipen, and S. Sæbø, “A review of variable selection methods in Partial Least Squares Regression,” Chemom. Intell. Lab. Syst., vol. 118, pp. 62–69, 2012, doi:10.1016/j.chemolab.2012.07.010.

Ruiz, J., Soto, J., Ipanaque, W. Evaluation of spectral relation indexes of the Peruvian's cocoa beans during fermentation process. IEEE Latin America Transactions 14(6), 2862 – 2867, 2016, doi:10.1109 / TLA.2016.7555266.

Soto, J., Ruiz, J., Ipanaque, W., Chinguel, C. Nuevo índice hiperespectral para determinar el estado de fermentación en el análisis no destructivo del cacao violeta orgánico. Transacciones IEEE América Latina, 16 (9), 2435-2440, 2018, doi:10.1109 / TLA.2018.8789565.

Soto, J., Prieto, F., Ipanaque, W., Machacuay, J. Evaluación de la calidad del grano de cacao mediante el uso de imágenes hiperespectrales y técnicas de lógica difusa. Proc. SPIE 9534, Duodécima Conferencia Internacional sobre Control de Calidad por Visión Artificial 2015, 95340M, 2015, doi:10.1117/12.2182598.



How to Cite

Soto, J., La Rosa, G., Paiva, E., & Ipanaque, W. (2022). Spectral signature for quality assessment of anchovy fish meal (Engraulis Ringens) using Partial Least Squares. IEEE Latin America Transactions, 21(2), 200–206. Retrieved from https://latamt.ieeer9.org/index.php/transactions/article/view/6701

Most read articles by the same author(s)