Yazar "Ali, Sadia Samar" seçeneğine göre listele

Listeleniyor 1 - 7 / 7
  • Küçük Resim
    Öğe
    Breast tumor localization and segmentation using machine learning techniques: overview of datasets, findings, and methods
    (Elsevier, 2023) Ranjbarzadeh, Ramin; Dorosti, Shadi; Jafarzadeh Ghoushchi, Saeid; Caputo, Annalina; Tirkolaee, Erfan Babaee; Ali, Sadia Samar; Arshadi, Zahra; Bendechache, Malika
    The Global Cancer Statistics 2020 reported breast cancer (BC) as the most common diagnosis of cancer type. Therefore, early detection of such type of cancer would reduce the risk of death from it. Breast imaging techniques are one of the most frequently used techniques to detect the position of cancerous cells or suspicious lesions. Computer-aided diagnosis (CAD) is a particular generation of computer systems that assist experts in detecting medical image abnormalities. In the last decades, CAD has applied deep learning (DL) and machine learning approaches to perform complex medical tasks in the computer vision area and improve the ability to make decisions for doctors and radiologists. The most popular and widely used technique of image processing in CAD systems is segmentation which consists of extracting the region of interest (ROI) through various techniques. This research provides a detailed description of the main categories of segmentation procedures which are classified into three classes: supervised, unsupervised, and DL. The main aim of this work is to provide an overview of each of these techniques and discuss their pros and cons. This will help researchers better understand these techniques and assist them in choosing the appropriate method for a given use case. © 2022 Elsevier Ltd
  • Küçük Resim Yok
    Öğe
    Circular Economy Practices in the Context of Emerging Economies
    (Mdpi, 2024) Ali, Sadia Samar; Weber, Gerhard-Wilhelm; Tirkolaee, Erfan Babaee; Goli, Alireza
    [Abstract Not Available]
  • Küçük Resim Yok
    Öğe
    Designing a reliable-sustainable supply chain network: adaptive m-objective ?-constraint method
    (Springer, 2024) Sepehri, Arash; Tirkolaee, Erfan Babaee; Simic, Vladimir; Ali, Sadia Samar
    In the current era emphasizing sustainability and circularity, supply chain network design is a critical challenge for making reliable decisions. The optimization of facility location-allocation inventory problems (FLAIPs) holds the key to achieving dependable product delivery with reduced costs and carbon emissions. Despite the importance of these challenges, a substantial research gap exists regarding economic, reliability, and sustainability criteria for FLAIPs. This paper aims to fill this gap by introducing a multi-objective mixed-integer linear programming model, focusing on configuring a reliable sustainable supply chain network. The model addresses three key objectives: minimizing costs, minimizing emissions, and maximizing reliability. A notable contribution of this research lies in elaborating on five levels of a supply chain network catering to the delivery of multiple products across various periods. Another novelty is the simultaneous incorporation of economic, environmental, and reliability objectives in the network design-a facet rarely addressed in prior research. Results highlight that varying demand levels for each facility lead to altered trade-offs between objectives, empowering practitioners to make diverse decisions in facility location allocation. The proposed mathematical model undergoes validation through numerical examples and sensitivity analysis of parameters. The paper concludes by presenting theoretical and managerial implications, contributing valuable insights to the field of sustainable supply chains.
  • Küçük Resim Yok
    Öğe
    Innovative supply chain network design with two-step authentication and environmentally-friendly blockchain technology
    (Springer, 2024) Babaei, Ardavan; Tirkolaee, Erfan Babaee; Ali, Sadia Samar
    Blockchain Technology (BT) has the potential to revolutionize supply chain management by providing transparency, but it also poses significant environmental and security challenges. BT consumes energy and emits carbon gases, affecting its adoption in Supply Chains (SCs). The substantial energy demand of blockchain networks contributes to carbon emissions and sustainability risks. Moreover, for secure and reliable transactions, mutual authentication needs to be established to address security concerns raised by SC managers. This paper proposes a tri-objective optimization model for the simultaneous design of the SC-BT network, considering a two-step authentication process. The model considers transparency caused by BT members, emissions of BT, and costs related to BT and SC design. It also takes into account uncertainty conditions for participating BT members in the SC and the range of transparency, cost, and emission targets. To solve the model, a Branch and Efficiency (B&E) algorithm equipped with BT-related criteria is developed. The algorithm is implemented in a three-level SC and produces cost-effective and environmentally friendly outcomes. However, the adoption of BT in the SC can be costly and harmful to the environment under uncertain conditions. It is worth mentioning that implementing the proposed algorithm from our article in a three-level SC case study can result in a significant cost reduction of over 16% and an emission reduction of over 13%. The iterative nature of this algorithm plays a vital role in achieving these positive outcomes.
  • Küçük Resim Yok
    Öğe
    ME-CCNN: Multi-encoded images and a cascade convolutional neural network for breast tumor segmentation and recognition
    (Springer, 2023) Ranjbarzadeh, Ramin; Jafarzadeh Ghoushchi, Saeid; Tataei Sarshar, Nazanin; Tirkolaee, Erfan Babaee; Ali, Sadia Samar; Kumar, Teerath; Bendechache, Malika
    Breast tumor segmentation and recognition from mammograms play a key role in healthcare and treatment services. As different tumors in mammography have dissimilar densities, shapes, sizes, and edges, the interpretation of mammograms can be time-consuming and prone to interpretation variability even for a highly trained radiologist or expert. In this study, several encoding approaches are first proposed to achieve an effective breast cancer recognition system as well as create new images from the input image. Each encoded image represents some unique features that are crucial for detecting the target texture properly. Subsequently, pectoral muscle is eliminated using obtained features from these encoded images. Moreover, 11 distinct images are then applied to a shallow and efficient cascade Convolutional Neural Network (CNN) for classifying each pixel inside the image. This network accepts 11 local patches as the input from 11 obtained encoded images. Next, all extracted features are concatenated to a vertical vector to apply to the fully connected layers. Using different representations of the input mammogram images, the suggested model is able to analyze the input texture more effectively without using a deep CNN model. Finally, comprehensive experiments are then conducted on two public datasets which then demonstrate that the proposed framework successfully is able to gain competitive outcomes compared to a number of baselines.
  • Küçük Resim
    Öğe
    A parallel hybrid PSO-GA algorithm for the flexible flow-shop scheduling with transportation
    (Elsevier Ltd, 2022) Amirteimoori, Arash; Mahdavi, Iraj; Solimanpur, Maghsud; Ali, Sadia Samar; Tirkolaee, Erfan Babaee
    In this paper, a Mixed-Integer Linear Programming (MILP) model to simultaneously schedule jobs and transporters in a flexible flow shop system is suggested. Wherein multiple jobs, finite transporters, and stages with parallel unrelated machines are considered. In addition to the mentioned technicalities, the jobs are able to omit one or more stages, and may not be executable by all the machines, and similarly, transportable by all the transporters. To the best of our knowledge, no study in the literature has featured efficacy of the parallel computing in simultaneous scheduling of jobs and transporters in the flexible flow shop system which remarkably shortens run time if the solution approaches are designed accordingly. To this end, we employ Gurobi solver, Parallel Genetic Algorithm (PGA), Parallel Particle Swarm Optimization (PPSO) and hybrid Parallel PSO-GA Algorithm (PPSOGA) to deal with the problem instances. Furthermore, a parallel version of Ant Colony Optimization (ACO) algorithm adapted from the state-of-the-art literature is developed to verify the performance of our suggested solution methods. Using 60 problem instances generated via uniform distribution, the suggested solution approaches are compared against one another. After assessing the results of the computational experiments, it is deduced that PPSOGA algorithm outperforms PGA, PPSO, Parallel Ant Colony Optimization (PACO) and Gurobi solver in terms of the quality of the solutions. The efficiency and run time of the suggested approaches are then assessed through two prominent statistical tests (i.e., Wald and Analysis of Variance (ANOVA)). Eventually, it comes to spotlight that PPSOGA algorithm is computationally rewarding and dependable.
  • Küçük Resim Yok
    Öğe
    A robust optimization model to design an IoT-based sustainable supply chain network with flexibility
    (Springer, 2023) Goli, Alireza; Tirkolaee, Erfan Babaee; Golmohammadi, Amir-Mohammad; Atan, Zumbul; Weber, Gerhard-Wilhelm; Ali, Sadia Samar
    Supply chain network design is one of the most important issues in today's competitive environment. Moreover, the ratio of transportation costs to the income of manufacturing companies has increased significantly. In this regard, strategic decisions, as well as tactical decisions making, are of concern for supply chain network design. In this research, a flexible, sustainable, multi-product, multi-period, and Internet-of-Things (IoT)-based supply chain network with an integrated forward/reverse logistics system is configured where the actors are suppliers, producers, distribution centers, first- and second-stage customers, repair/disassembly centers, recycling centers, and disposal centers. In order to create flexibility in this supply chain, it is possible to dispatch directly to customers from distribution centers or manufacturing plants. For direct shipping, the application IoT system is taken into account in the transportation system to make them able to manage direct and indirect delivery at the same time. The options and considerations are then incorporated into a Multi-Objective Mixed-Integer Linear Programming model to formulate the problem which is then converted into a single-objective model using Goal Programming (GP) method. Moreover, in order to deal with uncertainty in the demand parameter, robust optimization approach is applied. The obtained results from a numerical example reveal that the proposed model is able to optimally design the supply chain network whose robustness is highly dependent on the budgets of uncertainty whereas up to 213.528% increase in the GP objective function is observed.