Deep Reinforcement Learning Model for Blood Bank Vehicle Routing Multi-Objective Optimization

作     者：Meteb M.Altaf Ahmed Samir Roshdy Hatoon S.AlSagri 

作者机构：Director of Advanced Manufacturing and Industry 4.0 CenterKing Abdul-Aziz City for Science and Technology RiyadhSaudi Arabia Data Science and AI Senior Manager VodafoneCairoEgypt Information System DepartmentAl Imam Mohammad Ibn Saud Islamic UniversityRiyadhSaudi Arabia 

出 版 物：《Computers, Materials & Continua》 (计算机、材料和连续体（英文）)

年 卷 期：2022年第70卷第2期

页      面：3955-3967页

核心收录：

学科分类：07[理学] 0701[理学-数学] 070101[理学-基础数学] 

主　　题：Optimization blood bank deep neural network reinforcement learning blood centers multi-objective optimization 

摘      要：The overall healthcare system has been prioritized within development top lists *** many national populations are aging,combined with the availability of sophisticated medical treatments,healthcare expenditures are rapidly *** banks are a major component of any healthcare system,which store and provide the blood products needed for organ transplants,emergency medical treatments,and routine *** delivery of blood products is vital,especially in emergency ***,blood delivery process parameters such as safety and speed have received attention in the literature,as well as other parameters such as delivery *** this paper,delivery time and cost are modeled mathematically and marked as objective functions requiring simultaneous optimization.A solution is proposed based on Deep Reinforcement Learning(DRL)to address the formulated delivery functions as Multi-objective Optimization Problems(MOPs).The basic concept of the solution is to decompose the MOP into a scalar optimization sub-problems set,where each one of these sub-problems is modeled as a separate Neural Network(NN).The overall model parameters for each sub-problem are optimized based on a neighborhood parameter transfer and DRL training *** optimization step for the subproblems is undertaken collaboratively to optimize the overall *** solutions can be directly obtained using the trained ***,the multi-objective blood bank delivery problem is addressed in this *** technical advantage of this approach is that once the trainedmodel is available,it can be scaled without the need formodel *** scoring can be obtained directly using a straightforward computation of the NN layers in a limited *** proposed technique provides a set of technical strength points such as the ability to generalize and solve rapidly compared to othermulti-objective *** model was trained and tested on 5 major hospi