Yazar "Wassan, Niaz" seçeneğine göre listele

Listeleniyor 1 - 4 / 4
  • Küçük Resim
    Öğe
    A framework for robust glaucoma detection: A confidence-aware deep uncertainty quantification approach with a comprehensive assessment for enhanced clinical decision-making
    (Elsevier ltd, 2025) Zarean, Javad; Tajally, AmirReza; Tavakkoli-Moghaddam, Reza; Sajadi, Seyed Mojtaba; Wassan, Niaz
    Glaucoma poses a significant threat to public health worldwide, as it can result in irreversible vision loss. Timely identification is vital for halting the progression of visual field deterioration. In recent years, deep neural networks (DNNs) have become increasingly popular in medical imaging due to their ability to identify patterns. As a result, this study introduces a new computer-aided diagnosis (CAD) system based on deep learning (DL) algorithms for glaucoma detection that extracts meaningful features from retinal fundus images (RFIs) and employs uncertainty quantification (UQ) models, including Monte Carlo dropout (MCD), ensemble Bayesian, and ensemble Monte Carlo dropout (EMCD), to generate both point estimates and confidence values for the outputs, thereby capturing the uncertainty associated with the classifications. The proposed framework is validated using well-known clinical datasets, and the reliability of the outputs is evaluated using comprehensive performance metrics such as expected calibration error (ECE), entropy analysis, and a multi-criteria UQ assessment. Experimental results demonstrate the superiority of the ensemble model, with uncertainty accuracies registering at 97.64%, 97.26%, and 98.97% for the "ACRIMA", "RIM-ONE-DL", and "ORIGA" datasets, respectively. Moreover, the proposed algorithms can alert users to the majority of erroneous diagnoses by assigning uncertainty labels, providing valuable insights for clinicians in glaucoma detection. Such tools can assist healthcare professionals in reducing the probability of misdiagnosis and ensuring that patients receive timely and appropriate treatment.
  • Küçük Resim Yok
    Öğe
    A hybrid machine learning model based on ensemble methods for devices fault prediction in the wood industry
    (Pergamon-Elsevier Science Ltd, 2024) Dahesh, Arezoo; Tavakkoli-Moghaddam, Reza; Wassan, Niaz; Tajally, AmirReza; Daneshi, Zahra; Erfani-Jazi, Aseman
    In manufacturing industries, including the wood industry, devices, and equipment are considered the basic elements and the main capital for production. That is why managers are trying to maintain and use these devices and equipment optimally. On the other hand, repurchasing device parts or repairing equipment in case of major damage can cause more damage than planned costs. Therefore, a model that can determine the fault class based on the signs seen in the equipment would prevent major damage to the device and save on repair costs. In this regard, using the registered features for equipment and with the help of machine learning algorithms, a model can be created that can classify devices in the appropriate class based on their observed features. The present study uses nine machine learning algorithms to make this model, trains each model on three sets of selected features, and finally compares them. It is worth mentioning that after evaluating the models, based on the features selected from the embedded techniques, permutation feature importance methods, and genetic algorithm, the best models are considered as categorical boosting with the training and testing accuracy of 0.895 and 0.909, random forest with the training and testing accuracy of 0.905 and 0.893, and extreme gradient boosting with the training and testing accuracy of 0.884 and 0.885.
  • Küçük Resim
    Öğe
    Lagrangian relaxation method for solving a new time-dependent production - distribution planning model
    (Pergamon-elsevier science, 2024) Rezaali, Zahra; Ghodratnama, Ali; Amiri-Aref, Mehdi; Tavakkoli-Moghaddam, Reza; Wassan, Niaz
    In today 's competitive business environment, organizations must decide how to handle the processing of their logistics equipment economically. One of the vital logistical concerns is distribution planning that is especially crucial depending on the facilities and goods being used. When it comes to perishable goods, this problem assumes double the significance. The position of the warehouse and the route of the vehicles make up the distribution planning problem. These two problems are considered concurrently and solved in the location-routing mathematical model. This paper aims to provide a production and distribution strategy to serve clients and consumers better. This research attempts to produce as efficiently as possible while providing prompt customer service, which is crucial in today 's corporate environment. This study uses three-level supply chains for perishable goods to create a supply chain network that minimizes costs. In this case, time-dependent demands refer to requests that may be made when the vehicle will arrive. Places and routes in this area are designed to meet all needs. In general, it is desirable to have factories and distribution centers in known locations, know the service 's opening and closing hours, and know how to manage the flow of materials and goods as they are stored in distribution centers and for retailers (clients). Additionally, it is desirable to route vehicle that connects the various levels of the supply chain and ensures that vehicles travel on schedule overall. First, the supply chain model represented as non-linear programming is transformed into linear programming to solve it using the CPLEX solver of GAMS commercial software and the Lagrangian relaxation (LR) method. Then, this model is verified using numerical examples and related parameters to see how it impacts the variables and the objective function 's result. The results show the capability of the LR method.
  • Küçük Resim Yok
    Öğe
    Optimizing COVID-19 medical waste management using goal and robust possibilistic programming
    (Pergamon-Elsevier Science Ltd, 2024) Karimi, Hamed; Wassan, Niaz; Ehsani, Behdad; Tavakkoli-Moghaddam, Reza; Ghodratnama, Ali
    During the global Coronavirus Disease (COVID-19) pandemic, the exponential rise in Hazardous Medical Waste (HMW) due to increased demand for personal protective equipment and heightened medical requirements posed significant threats to public health. This study proposes an innovative approach using a reverse logistics supply chain network that comprehensively integrates sustainability factors (e.g., cost, working conditions, exposure risks, and environmental impact) to manage the risks associated with medical waste effectively amid the pandemic. This research focuses on employing a guideline -based allocation of medical waste to specific technologies, leveraging the Torabi-Hassini (TH), Lp-metric (Lebesgue metric), and Goal Attainment (GA) approaches and robust possibilistic programming to address uncertainties. A real -case study validates the proposed model, demonstrating its ability to balance multiple objectives by optimizing the flow among treatment centers and introducing new Temporary Treatment Centers (TTCs). Also, we analyze broad sensitivity through weights assigned to the objective functions to obtain Pareto solutions. The convexity of the Pareto front confirms the conflict among the objective functions. The Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) approach specifies that the Lp-metric approach outperforms the others, and the TH approach is regarded as the second rank. The study's findings highlight the model's efficacy and provide crucial managerial insights for health organization administrators in efficiently managing the HMW supply chain network.