Hassan Nawazish Rasool
, Muhammad Zeb
The spectrometer, a powerful analytical instrument, plays a vital role in the fields of Chemistry, Material Sciences, Biochemistry, and Physics by allowing researchers to test, discover, and measure the spectral content of various fluids. This paper details the development of a portable, lightweight, cost-effective spectrometer device, which incorporates artificial intelligence for fluid classification. In a practical application, milk is used as the test fluid, with different qualities achieved by introducing controlled impurities. The spectrometer collected spectral data using a camera sensor, and the dataset is subsequently randomized and divided into training and testing data. Employing a range of machine learning algorithms and neural networks, the device accurately predicts the class of the fluid. The integration of optical components and microcontrollers facilitated model deployment. Notably, this device provides real-time fluid classification and displays results on an Organic LED. Beyond milk, its versatility allows for quality analysis of various fluids containing impurities, such as gasoline, human blood, and saliva. Remarkably compact at 70 x 70 x 50 mm and lightweight at 0.2 kilograms, the device had achieved an impressive average accuracy of 93.45 percent. It stands out for its ease of use, recharge ability, accuracy, and cost effectiveness compared to traditional spectrophotometers, positioning it as a valuable tool in the realm of scientific research and quality assessment.
Hassan Nawazish Rasool Muhammad Zeb “Neural Network based Portable Spectrometer for Fluid Classification” Internation Vol. 13 Issue 01 PP. 01-06 January 2026. https://doi.org/10.5281/zenodo.18183364.
[1] Mettler Toledo GmbH, “UV / VIS Spectrophotometry,” Mettler-Toledo Int., no. September 2015, p. 56, 2021, [Online]. Available: https://www.mt.com/es/es/home/library/guides/laboratory- division/1/uvvis-spectrophotometry-guide-applications fundamentals.html
[2] F. Sánchez Rojas, C. Bosch Ojeda, and J. M. Cano Pavón, “Spectrophotometry | biochemical applications,” Encycl. Anal. Sci., no. April, pp. 205–213, 2019, doi: 10.1016/B978-0-12-409547- 2.00501-1.
[3] P. Carpentier, A. Royant, J. Ohana, and D. Bourgeois, “Advances in spectroscopic methods for biological crystals. 2. Raman spectroscopy,” J. Appl. Crystallogr., vol. 40, no. 6, pp. 1113–1122, 2007, doi: 10.1107/S0021889807044202.
[4] R. A. Ahmadi, F. Hasanvand, G. Bruno, H. A. Rudbari, and S. Amani, “Synthesis, spectroscopy, and magnetic characterization of copper(II) and cobalt(II) complexes with 2-amino-5-bromopyridine as ligand,” Russ. J. Coord. Chem. Khimiya, vol. 39, no. 12, pp. 867–871, 2013, doi: 10.1134/S1070328413110018.
[5] K. Laganovska et al., “Portable low-cost open-source wireless spectrophotometer for fast and reliable measurements,” HardwareX, vol. 7, p. e00108, 2020, doi: 10.1016/j.ohx.2020.e00108.
[6] J. Riu, G. Gorla, D. Chakif, R. Boqué, and B. Giussani, “Rapid analysis of milk using low-cost pocket-size NIR spectrometers and multivariate analysis,” Foods, vol. 9, no. 8, 2020, doi: 10.3390/foods9081090.
[7] J. A. Diaz-Olivares, I. Adriaens, E. Stevens, W. Saeys, and B. Aernouts, “Online milk composition analysis with an on-farm near-infrared sensor,” Comput. Electron. Agric., vol. 178, no. September, p. 105734, 2020, doi: 10.1016/j.compag.2020.105734.
[8] L. L. Monteiro, P. Zoio, B. B. Carvalho, L. P. Fonseca, and C. R. C. Calado, “Quality Monitoring of Biodiesel and Diesel/Biodiesel Blends: A Comparison between Benchtop FT-NIR versus a Portable Miniaturized NIR Spectroscopic Analysis,” Processes, vol. 11, no. 4, 2023, doi: 10.3390/pr11041071.
[9] R. M. Correia et al., “Portable near infrared spectroscopy applied to fuel quality control,” Talanta, vol. 176, no. August 2017, pp. 26–33, 2018, doi: 10.1016/j.talanta.2017.07.094.
F. D. Santos et al., “Discrimination of oils and fuels using a portable NIR spectrometer,” Fuel, vol. 283, no. August 2020, p. 118854, 2021, doi: 10.1016/j.fuel.2020.118854.
