Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection

Permanent URI for this collectionhttps://hdl.handle.net/11147/7148

Browse

Filters

2025 - 20263

Settings

Author: search.filters.author.Deliismail, OzgunScopus Q: search.filters.scopusQuartile.Q1

Search Results

Now showing 1 - 3 of 3
  • Article
    Knowledge-Based Training of Learning Architectures Under Input Sensitivity Constraints for Improved Explainability
    (Pergamon-Elsevier Science Ltd, 2026) Sildir, Hasan; Erturk, Emrullah; Edizer, Deniz Tuna; Deliismail, Ozgun; Durna, Yusuf Muhammed; Hamit, Bahtiyar
    The traditional machine learning (ML) training problem is unconstrained and lacks an explicit formulation of the underlying driving phenomena. Such a formulation, based solely on experimental data, does not ensure the delivery of qualitative knowledge among variables due to many theoretical issues in the optimization task. This study further tightens Artificial Neural Networks (ANNs) training by including input sensitivities as additional constraints and applies to regression and classification tasks based on literature data. In theory, such sensitivity represents the change direction of the target variable per change in measurements from indicators. The resulting nonlinear optimization problem is solved th rough a rigorous solver and includes the sensitivity expressions through algorithmic differentiation. Compared to traditional methods, with an acceptable decrease in the prediction capability, the proposed model delivers more intuitive, explainable, and experimentally verifiable predictions under input variable variations, under robustness to overfitting, while serving robust identification tasks. A classification case study includes a patient-oriented clinical decision support system development based on the impact of cancer-indicating variables. A competitive test prediction accuracy is obtained compared to commonly used algorithms despite 10 % decrease in the training. The regression case is built upon the energy load estimation to account for prominent considerations to obtain desired sensitivity patterns and proposed methodology delivers significant accuracy drop compared to some formulations to address knowledge patterns. The approach delivers a compatible pattern with practitioner expertise and is compared to widely used machine learning algorithms, whose performances are evaluated through common statistics in addition to multi-variable response graphs.
  • Article
    Citation - WoS: 1
    Citation - Scopus: 1
    Dynamic and Stochastic Optimization of Algae Cultivation Process
    (Pergamon-elsevier Science Ltd, 2025) Kivanc, Sercan; Beykal, Burcu; Deliismail, Ozgun; Sildir, Hasan
    This study offers a realistic representation of system dynamics which accounts for light intensity, biomass, substrate, and nitrogen concentration, by employing stochastic programming techniques to account for spatial and temporal variations for algae growth. The optimization task focuses on lipid productivity and selectivity, which are crucial factors in the context of algal biofuel production. Different scenarios from likely and unlikely cases of model parameters were evaluated. Optimal initial conditions for key variables such as nitrogen, substrate, light, biomass, lipid, and surface light intensity are calculated, considering the uncertainty of the parameters as well as other governing equations. The results show that a remarkable 11.18% increase in lipid productivity compared to a reference scenario. Furthermore, in the stochastic case, our results highlight that uncertainty has a disproportionately large effect on biomass in comparison to lipid concentration, providing valuable insights into the behavior of the system under varying conditions. This provides a comprehensive exploration of the parameter uncertainty on lipid productivity and algal growth.
  • Article
    Citation - WoS: 5
    Citation - Scopus: 5
    Automated Deep Learning Model Development Based on Weight Sensitivity and Model Selection Statistics
    (Pergamon-elsevier Science Ltd, 2025) Yalcin, Damla; Deliismail, Ozgun; Tuncer, Basak; Boy, Onur Can; Bayar, Ibrahim; Kayar, Gizem; Sildir, Hasan
    Current sustainable production and consumption processes call for technological integration with the realm of computational modeling especially in the form of sophisticated data-driven architectures. Advanced mathematical formulations are essential for deep learning approach to account for revealing patterns under nonlinear and complex interactions to enable better prediction capabilities for subsequent optimization and control tasks. Bayesian Information Criterion and Akaike Information Criterion are introduced as additional constraints to a mixed-integer training problem which employs a parameter sensitivity related objective function, unlike traditional methods which minimize the training error under fixed architecture. The resulting comprehensive optimization formulation is flexible as a simultaneous approach is introduced through algorithmic differentiation to benefit from advanced solvers to handle computational challenges and theoretical issues. Proposed formulation delivers 40% reduction, in architecture with high accuracy. The performance of the approach is compared to fully connected traditional methods on two different case studies from large scale chemical plants.