Prediction of Demand for Red Blood Cells Using Artificial Intelligence Methods
نویسندگان
چکیده
Blood is a vital product with limited resources, available only from volunteers. For this reason, the blood components to be sent bank transfusion centers (hospitals) should accurately predicted. There are many variables that affect demand prediction. In study, fifteen different qualitative and quantitative were determined. Artificial intelligence (AI) methods used because prediction has nonlinear, complex uncertain relationships thus it also difficult mathematically express on relationship in between input output variables. AI have feature of predicting information not given or may occur future by learning past data. such as Decision Tree (DT), Support Vector Machine (SVM), Neural Network (ANN) Deep Learning (DL) applied providing supply public private hospitals operating four provinces. The data obtained results compared performance criteria (MAPE, MSE, MAE RMSE R2) values overprediction, underprediction, minimum maximum deviation. weekly average over predictions calculated 9.69, 5.29, 8.45, 15.65 underpredictions 17.57, 3.03, 3.94, 14.69 for DT, SVM, ANN, DL methods, respectively. SVM method was determined giving best values. Therefore, envisaged component can using method.
منابع مشابه
Developmental Trend of Artificial Blood ( Artificial Red Blood Cells )
Regarding research on artificial blood, the “Field of Artificial Blood Development” was inaugurated in 1997, supported by the Ministry of Health and Welfare Grant-in-Aid for Health Science Research, for intensive research activities in the three sub-fields, i.e., artificial red blood cells, artificial platelets, and artificial antibodies. Developed by molecular assembling technology, artificial...
متن کاملBayesian Prediction for Artificial Intelligence
This paper shows that the common method used for making predictions under uncertainty in AI and science is in error. This method is to use currently available data to select the best model from a given class of models-this process is called abduction-and then to use this model to make predictions about future data. The correct method requires averaging over all the models to make a prediction-w...
متن کاملArtificial Intelligence Methods for Ambient Intelligence
Ambient Intelligence (ISTAG (2001) Scenarios for Ambient Intelligence in 2010) is a vision that enables intelligent environments with pervasive technology. In this vision human users are at the cent re, but machine and human are seen as equal, collaborating, to improve both human being and machine performance. Ambient Intelligence offers many benefits. For example, by inst rumenting public and ...
متن کاملdevelopment of different optical methods for determination of glucose using cadmium telluride quantum dots and silver nanoparticles
a simple, rapid and low-cost scanner spectroscopy method for the glucose determination by utilizing glucose oxidase and cdte/tga quantum dots as chromoionophore has been described. the detection was based on the combination of the glucose enzymatic reaction and the quenching effect of h2o2 on the cdte quantum dots (qds) photoluminescence.in this study glucose was determined by utilizing glucose...
ذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Academic platform-Journal of engineering and science
سال: 2022
ISSN: ['2147-4575']
DOI: https://doi.org/10.21541/apjess.1078920