Scopus İndeksli Yayınlar Koleksiyonu / Scopus Indexed Publications Collection
Permanent URI for this collectionhttps://hdl.handle.net/11147/7148
Browse
2 results
Search Results
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, BahtiyarThe 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: 1Citation - Scopus: 1Design and Comprehensive Analysis of a Solar-Biomass Hybrid System With Hydrogen Production and Storage: Towards Self-Sufficient Wastewater Treatment Plants(Pergamon-Elsevier Science Ltd, 2025) Tabriz, Zahra Hajimohammadi; Kasaeian, Alibakhsh; Mohammadpourfard, Mousa; Shariaty-Niassar, MojtabaThis paper comprehensively investigates a novel solar-biomass hybrid system designed to produce power, heating, hydrogen, methane, and digestate. The system's design is grounded in regional weather patterns and site-specific resource availability. A comprehensive thermodynamic and exergoeconomic analysis, based on the first and second laws of thermodynamics, is performed alongside parametric studies to evaluate the influence of key parameters on system performance. Multi-objective optimization employs a genetic algorithm facilitated by an artificial neural network to reduce computational time and balance exergy efficiency and total cost. The Pareto front is generated, and the TOPSIS method is employed to identify the optimal trade-off point. The system integrates an auxiliary boiler powered by stored hydrogen and methane to maintain consistent operation during periods of low solar irradiance. Key findings include a base-case overall energy efficiency of 78.67 % and exergy efficiency of 60.41 %. The base-case unit cost of hydrogen is determined to be $3.174/kg, demonstrating competitive viability. Integrating the biomass subsystem with the solar plant resulted in a 40 % increase in exergy efficiency and a 35 % improvement in the total unit cost of products compared to a stand-alone solar system. Optimized system parameters yielded an exergy efficiency of 55.52 % and a total cost rate of 14.98 M $/year. These results confirm the potential of this hybrid system as a promising sustainable solution for developing self-sufficient wastewater treatment plants.