TY - GEN
T1 - Evaluate the next nanobubble movement with artificial intelligence
AU - Eduardo, Huarote Zegarra Raúl
AU - Flores, Jhonny Wilfredo Valverde
AU - Yensi, Vega Luján
AU - Aradiel, Castañeda Hilario
AU - José, Flores Masías Edward
AU - Cesar, Larios Franco Alfredo
AU - Huaman, Jhonatan Isaac Vargas
N1 - Publisher Copyright:
© 2021 Latin American and Caribbean Consortium of Engineering Institutions. All rights reserved.
PY - 2021
Y1 - 2021
N2 - This research supports solving the problem of how to know the next movement of the nanobubble, for this purpose, two methods will be used to represent the behavior of air nanobubbles in liquids, such as the correlation of data expressed in an equation and the backpropagation in learning your route. To obtain the positions of the movements of the air nanobubbles at a scale of 10-9 m in diameter, algorithms based on computer vision, using high-power cameras. The correlation of data was identified to generate the equation and the neural network to learn its movements. In conclusion, the behavior of nanobubbles in water was identified, generating a specific movement pattern of y = 9E-06x3 - 0.0034x2 + 1.6831x + 299.25; with a correlation of: R2 = 0.9976 managing to obtain a 98.94% certainty, and it was possible to learn these movements by generating the appropriate synaptic weights with a 99.6% certainty in prediction their route or next path.
AB - This research supports solving the problem of how to know the next movement of the nanobubble, for this purpose, two methods will be used to represent the behavior of air nanobubbles in liquids, such as the correlation of data expressed in an equation and the backpropagation in learning your route. To obtain the positions of the movements of the air nanobubbles at a scale of 10-9 m in diameter, algorithms based on computer vision, using high-power cameras. The correlation of data was identified to generate the equation and the neural network to learn its movements. In conclusion, the behavior of nanobubbles in water was identified, generating a specific movement pattern of y = 9E-06x3 - 0.0034x2 + 1.6831x + 299.25; with a correlation of: R2 = 0.9976 managing to obtain a 98.94% certainty, and it was possible to learn these movements by generating the appropriate synaptic weights with a 99.6% certainty in prediction their route or next path.
KW - Air nanobubbles
KW - Backpropagation
KW - Digital image processing
KW - Path
KW - Predict
UR - http://www.scopus.com/inward/record.url?scp=85122035552&partnerID=8YFLogxK
U2 - 10.18687/LACCEI2021.1.1.362
DO - 10.18687/LACCEI2021.1.1.362
M3 - Conference contribution
AN - SCOPUS:85122035552
T3 - Proceedings of the LACCEI international Multi-conference for Engineering, Education and Technology
BT - 19th LACCEI International Multi-Conference for Engineering, Education Caribbean Conference for Engineering and Technology
A2 - Larrondo Petrie, Maria M.
A2 - Zapata Rivera, Luis Felipe
A2 - Aranzazu-Suescun, Catalina
T2 - 19th LACCEI International Multi-Conference for Engineering, Education Caribbean Conference for Engineering and Technology: "Prospective and Trends in Technology and Skills for Sustainable Social Development" and "Leveraging Emerging Technologies to Construct the Future", LACCEI 2021
Y2 - 19 July 2021 through 23 July 2021
ER -