An integrated deep learning and stochastic optimization approach for resource management in team-based healthcare systems

Olya, Mohammad Hessam; Badri, Hossein; Teimoori, Sadaf; Yang, Kai

doi:10.1016/j.eswa.2021.115924

Cited by 23 publications

(10 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, this algorithm is one of the first artificial neural networks that have been used. 6 We make use of this machine learning method to handle big data of large number of criteria and sub-criteria. A configuration of perceptron machine learning is depicted in Figure 3.…”

Section: Machine Learning (Big Data Weighing Process)mentioning

confidence: 99%

“…The key issue in a supply chain is the coordinated management and control of all these activities 5 . In fact, supply chain management is an integrated process in which a number of business agents such as suppliers, manufacturers, distributors, and retailers work together to extract raw materials and transform these materials into final products to deliver the products to the customers 6 …”

Section: Introductionmentioning

confidence: 99%

“…5 In fact, supply chain management is an integrated process in which a number of business agents such as suppliers, manufacturers, distributors, and retailers work together to extract raw materials and transform these materials into final products to deliver the products to the customers. 6 In general, the selection of suppliers is done in two ways; in the first case, which is known as "single source", one supplier alone is able to meet all the needs of the buyer and the buyer should only choose the best supplier in his decision making process. In the second case, which is more general and is known as the "multi-source" case, no supplier is able to supply all the buyer's orders and it is necessary to decide on the selection of several suppliers.…”

mentioning

confidence: 99%

See 2 more Smart Citations

Rough DT²R²ML for renewable energy supplier selection in the presence of big data

Fazlollahtabar

2023

Concurrency and Computation

View full text Add to dashboard Cite

SummarySupplier selection is a substantial problem in supply chain management due to concurrent decision on key performance indicators on multi‐dimension data. Recently, more studies investigated the supplier section problem with respect to variety of criteria within the contexts of applied cases. The problem is more significant when industries with high amount of investment explore appropriate suppliers such as renewable energy. This article concerns with developing a new method encompass all indices effective on supplier selection. The proposed algorithm first group by decision tree (DT) indices to criteria and sub‐criteria; then, to include large amount of uncertain data, rough comparisons and weighing are fulfilled using a machine learning (RML). Further, transformation (T) to crisp value and ranking (R) of suppliers are delivered. The new method is implemented for a renewable energy supplier selection problem as a case study. The outputs show the effectiveness of the proposed method in practice since it can handle big data through a machine learning technique. Managerial implications as decision supports are discussed.

show abstract

Section: Machine Learning (Big Data Weighing Process)mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

Rough DT²R²ML for renewable energy supplier selection in the presence of big data

Fazlollahtabar

2023

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

“…Each algorithm has its advantages and drawbacks, but in all stages, no technique could be considered superior [9]. In recent times, deep learning (DL) networks have accomplished considered interesting because of their strong abstract representation learning and capability to extract features automatically [10]. Similar to the ML algorithm, this model depends on learning from the data, but rather than utilizing handengineered features, which is a time-consuming and very difficult task, the DL technique provides various benefits like the exclusion of clumsy feature extraction methods and development in the performance of the training dataset.…”

Section: Introductionmentioning

confidence: 99%

Leveraging Retinal Fundus Images with Deep Learning for Diabetic Retinopathy Grading and Classification

Yamin¹,

Basahel²,

Bajaba³

et al. 2023

Computer Systems Science and Engineering

View full text Add to dashboard Cite

Recently, there has been a considerable rise in the number of diabetic patients suffering from diabetic retinopathy (DR). DR is one of the most chronic diseases and makes the key cause of vision loss in middle-aged people in the developed world. Initial detection of DR becomes necessary for decreasing the disease severity by making use of retinal fundus images. This article introduces a Deep Learning Enabled Large Scale Healthcare Decision Making for Diabetic Retinopathy (DLLSHDM-DR) on Retinal Fundus Images. The proposed DLLSHDM-DR technique intends to assist physicians with the DR decision-making method. In the DLLSHDM-DR technique, image preprocessing is initially performed to improve the quality of the fundus image. Besides, the DLLSHDM-DR applies HybridNet for producing a collection of feature vectors. For retinal image classification, the DLLSHDM-DR technique exploits the Emperor Penguin Optimizer (EPO) with a Deep Recurrent Neural Network (DRNN). The application of the EPO algorithm assists in the optimal adjustment of the hyperparameters related to the DRNN model for DR detection showing the novelty of our work. To assuring the improved performance of the DLLSHDM-DR model, a wide range of experiments was tested on the EyePACS dataset. The comparison outcomes assured the better performance of the DLLSHDM-DR approach over other DL models.

show abstract

“…e solution-derived results for the numerical instances indicated that the model performed appropriately. Olya et al [18] proposed a stochastic mathematical model for resources management and inventory problem in the healthcare system, where the patient demand was uncertain and was satisfied using simulation. ey pursued the goal to allocate the nurses to the patients and minimize the service costs.…”

Section: Introductionmentioning

confidence: 99%

Presenting a Multi‐Echelon and Multi‐Product Model for Inventory Control considering Shortages Using a Heuristic Algorithm

Ara

Toofani

Kaveh

et al. 2022

Discrete Dynamics in Nature and Society

View full text Add to dashboard Cite

In the present study, a mathematical model is provided for inventory management in a three-level supply chain including a supplier, a manufacturer, and a distributor, taking into account the potential for product deficiency. Significant parameters such as the optimal order size for raw materials, optimal production rate, optimal allowed deficiencies at each supply chain level, the of the vehicles and the number of times the products are delivered between the supply chain components have been provided aiming at minimizing inventory management costs in the supply chain. The problem was solved using a heuristic algorithm. The proposed model is implemented for 20 different numerical examples. According to the results, the difference between the solutions obtained from the algorithm and the solutions obtained from the optimal values with the real variables is an average of 1.52%.

show abstract

An integrated deep learning and stochastic optimization approach for resource management in team-based healthcare systems

Cited by 23 publications

References 31 publications

Rough DT²R²ML for renewable energy supplier selection in the presence of big data

Rough DT²R²ML for renewable energy supplier selection in the presence of big data

Leveraging Retinal Fundus Images with Deep Learning for Diabetic Retinopathy Grading and Classification

Presenting a Multi‐Echelon and Multi‐Product Model for Inventory Control considering Shortages Using a Heuristic Algorithm

Contact Info

Product

Resources

About

An integrated deep learning and stochastic optimization approach for resource management in team-based healthcare systems

Cited by 23 publications

References 31 publications

Rough DT2R2ML for renewable energy supplier selection in the presence of big data

Rough DT2R2ML for renewable energy supplier selection in the presence of big data

Leveraging Retinal Fundus Images with Deep Learning for Diabetic Retinopathy Grading and Classification

Presenting a Multi‐Echelon and Multi‐Product Model for Inventory Control considering Shortages Using a Heuristic Algorithm

Contact Info

Product

Resources

About

Rough DT²R²ML for renewable energy supplier selection in the presence of big data

Rough DT²R²ML for renewable energy supplier selection in the presence of big data