Blood type classification using computer vision and machine learning

Ferraz, Ana; Brito, José Henrique Silveira de; Carvalho, Vı́tor; Machado, José

doi:10.1007/s00521-015-2151-1

Cited by 15 publications

(14 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results obtained with the introduction of Machine Learning algorithms were promising making the efficiency much higher [40]. After the classification of the occurrence or lack of agglutination was used the ABO and Rh classification algorithm [40]. The ABO and Rh result is classified in accordance with the principle of interpretation presented in the test reference of the plate test.…”

Section: Software Application Interfacementioning

confidence: 99%

“…For each type of classifier four sets of classifiers were trained, one for each of the features (standard deviation, histogram, HoG, and FFT). The results obtained with the introduction of Machine Learning algorithms were promising making the efficiency much higher [40]. After the classification of the occurrence or lack of agglutination was used the ABO and Rh classification algorithm [40].…”

Section: Software Application Interfacementioning

confidence: 99%

“…Previously, some Machine Learning algorithms were used to detect the occurrence or lack of agglutination as well; at the same time deterministic algorithm were developed to classify the ABO and Rh result [40]. Decision Trees and Support Vector Machines (SVM) were used to classify the occurrence of agglutination with a dataset to build the model (training data) and to evaluate the model (test data).…”

Section: Software Application Interfacementioning

confidence: 99%

“…Several prototypes were developed in order to satisfy the defined specifications, step by step [36][37][38][39][40][41]. The final prototype -basis prototype for industrial production -is described in next sub-section.…”

Section: Prototype Specificationsmentioning

confidence: 99%

See 3 more Smart Citations

Mechatronic system for performing blood pre-transfusion tests

Ferraz

Carvalho

Machado

et al. 2016

Sensors and Actuators A: Physical

Self Cite

View full text Add to dashboard Cite

Section: Software Application Interfacementioning

confidence: 99%

Section: Software Application Interfacementioning

confidence: 99%

Section: Software Application Interfacementioning

confidence: 99%

Section: Prototype Specificationsmentioning

confidence: 99%

See 2 more Smart Citations

Mechatronic system for performing blood pre-transfusion tests

Ferraz

Carvalho

Machado

et al. 2016

Sensors and Actuators A: Physical

Self Cite

View full text Add to dashboard Cite

“…Particularly, it should be noted, that ANN allows solving problems after the training by empiric data [7]. Moreover, a row of recent publications in the field of solving multidisciplinary problems is available [8,9,10].…”

Section: Introductionmentioning

confidence: 99%

Parameter Identification of Hydro-Mechanical Processes Using Artificial Intelligence Systems

2019

IJOMAM

View full text Add to dashboard Cite

The article is aimed at developing the comprehensive approach of parameter identification of complicated hydro-mechanical system by means of artificial intelligence systems (AIS) using artificial neural networks (ANN) and genetic algorithms (GA). The scientific novelty of the proposed method is inconsequent implementation of numerical analysis approach (e. g., FEM and CFD simulations), mathematical modeling of hydro-mechanical processes using the quasilinear regression procedure (QLRP), and artificial intelligence systems. Algorithms and related design schemes for implementation of the abovementioned technique are proposed for solving the interdisciplinary problems of aero-elastic interaction of gas-dispersed flow with the previously deformed flexible plates in a separation channel, static calculations of fixtures for parts manufacturing, as well as dynamic analysis of centrifugal compressors' rotors. All the presented has a significant advantage in comparison with the direct solving of the abovementioned problems. This advantage is in the ability of the comprehensive sequence "FEM / CFD-ANN / GA-QLRP" to predict the solutions of highly nonlinear mathematical models describing hydro-mechanical processes with uncertainties. As a result, unknown parameters of the mathematical models describing the complicated hydro-mechanical interactions are refined under an incompleteness of the initial data.

show abstract