Ines Bula Bunjaku
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ines Bula Bunjaku has a total of 3 co-authors. Here are the top co-authors by number of shared publications:
- Edin Bula
E&I Mechatronic, 10000 Prishtina, Kosovo
3 shared publications - Alush Mexhuani1 shared publication
- Edmond Muhaxheri
Department of Computing and Information Technologies, Rochester Institute of Technology Kosovo (RIT Kosovo), 10000 Prishtina, Kosovo
1 shared publication
Latest Publications
- Open Access
- 25 August 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (9) , 713
Hierarchical Modeling of AI-Supported Mathematical Problem Solving, Student Diagnostic Reasoning, and Mathematics Achievement
This study develops and empirically evaluates a multilevel analytical framework linking AI-generated mathematical reasoning, students’ diagnostic reasoning, and mathematics achievement in AI-supported mathematical problem solving. A classroom intervention with 76 undergraduate Calculus A students generated 380 repeated student–problem observations across five mathematical tasks and three instructional formulations. Students evaluated AI-generated solutions for final-answer correctness, methodological correctness, and procedural completeness, identified mathematical errors, and proposed corrections before completing an individual posttest. Hierarchical mixed-effects models and student-level achievement analyses were used to examine successive stages of the learning process. Instructional formulation was not significantly associated with the quality of AI-generated mathematical reasoning. Final-answer correctness, methodological correctness, and procedural completeness showed substantial task-specific variation. Instructional formulation was significantly associated with students’ error detection, with higher detection performance under Instruction Types B and C than under Type A, while AI-generated response quality remained comparable across instructional formulations. Baseline mathematical proficiency was the strongest predictor of posttest performance. Students’ Mean Error-Detection Event Rate was positively associated with posttest achievement. No robust overall independent association between instructional formulation and posttest achievement was identified after baseline adjustment. Students’ diagnostic engagement with AI-generated mathematical reasoning was associated with subsequent mathematics achievement, supporting the analysis of diagnostic reasoning as a distinct component of AI-supported mathematics learning.
- 25 August 2026
- Published by MDPI AG in Algorithms
- Vol. 19 (9) , 713
Open AccessHierarchical Modeling of AI-Supported Mathematical Problem Solving, Student Diagnostic Reasoning, and Mathematics Achievement
This study develops and empirically evaluates a multilevel analytical framework linking AI-generated mathematical reasoning, students’ diagnostic reasoning, and mathematics achievement in AI-supported mathematical problem solving. A classroom intervention with 76 undergraduate Calculus A students generated 380 repeated student–problem observations across five mathematical tasks and three instructional formulations. Students evaluated AI-generated solutions for final-answer correctness, methodological correctness, and procedural completeness, identified mathematical errors, and proposed corrections before completing an individual posttest. Hierarchical mixed-effects models and student-level achievement analyses were used to examine successive stages of the learning process. Instructional formulation was not significantly associated with the quality of AI-generated mathematical reasoning. Final-answer correctness, methodological correctness, and procedural completeness showed substantial task-specific variation. Instructional formulation was significantly associated with students’ error detection, with higher detection performance under Instruction Types B and C than under Type A, while AI-generated response quality remained comparable across instructional formulations. Baseline mathematical proficiency was the strongest predictor of posttest performance. Students’ Mean Error-Detection Event Rate was positively associated with posttest achievement. No robust overall independent association between instructional formulation and posttest achievement was identified after baseline adjustment. Students’ diagnostic engagement with AI-generated mathematical reasoning was associated with subsequent mathematics achievement, supporting the analysis of diagnostic reasoning as a distinct component of AI-supported mathematics learning.
- Open Access
- 30 June 2026
- Published by Instytut Gospodarki Surowcami Mineralnymi i Energia Polskiej Akademii Nauk in Polityka Energetyczna – Energy Policy Journal
- Vol. 29 (2) , 213-248
Optimization of wind power generation in Kosovo based on GIS modelling and terrain data (GWA, SRTM, CORINE)
The study analyses the wind energy potential of Kosovo using geographic information systems (GIS), integrating environmental and infrastructural factors. The methodology involves modelling wind speeds from the Global Wind Atlas, assessing terrain characteristics through the Shuttle Radar...
- 30 June 2026
- Published by Instytut Gospodarki Surowcami Mineralnymi i Energia Polskiej Akademii Nauk in Polityka Energetyczna – Energy Policy Journal
- Vol. 29 (2) , 213-248
Open AccessOptimization of wind power generation in Kosovo based on GIS modelling and terrain data (GWA, SRTM, CORINE)
The study analyses the wind energy potential of Kosovo using geographic information systems (GIS), integrating environmental and infrastructural factors. The methodology involves modelling wind speeds from the Global Wind Atlas, assessing terrain characteristics through the Shuttle Radar...
- Open Access
- 1 March 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (1) , 223-237
Efficiency of squirrel-cage induction motors with copper and aluminum rotors
This study presents a method for estimating efficiency in three-phase squirrel-cage induction motors with copper and aluminum rotor cages. A detailed two-dimensional transient finite-element model of a 1.25 kW motor was created and analyzed under rated conditions (500 V, 50 Hz, 990 rpm, 75 °C) to determine torque, slip, losses, and efficiency. Finite-element results confirmed the copper rotor's advantage, with 11.0% higher efficiency (85.1% compared to 76.7%) and 37.5% lower rotor-cage losses (80 W compared to 128 W) compared to aluminum. For rapid efficiency prediction, both Mamdani-type fuzzy inference system (FIS) and adaptive neuro-fuzzy inference system (ANFIS) models were developed using simulation data. The fuzzy system showed a maximum deviation of 0.8% for the copper rotor, while the neuro-fuzzy approach achieved effective nonlinear mapping for both rotor types with R² = 0.872 against finite-element benchmarks. Sensitivity tests with ±0.3% slip and ±15 W loss variations maintained estimation errors below 2.5%. This combined simulation and intelligent system methodology enables practical efficiency evaluation and rotor material comparison for motor condition assessment and industrial energy management.
- 1 March 2026
- Published by Institute of Advanced Engineering and Science in International Journal of Power Electronics and Drive Systems (IJPEDS)
- Vol. 17 (1) , 223-237
Open AccessEfficiency of squirrel-cage induction motors with copper and aluminum rotors
This study presents a method for estimating efficiency in three-phase squirrel-cage induction motors with copper and aluminum rotor cages. A detailed two-dimensional transient finite-element model of a 1.25 kW motor was created and analyzed under rated conditions (500 V, 50 Hz, 990 rpm, 75 °C) to determine torque, slip, losses, and efficiency. Finite-element results confirmed the copper rotor's advantage, with 11.0% higher efficiency (85.1% compared to 76.7%) and 37.5% lower rotor-cage losses (80 W compared to 128 W) compared to aluminum. For rapid efficiency prediction, both Mamdani-type fuzzy inference system (FIS) and adaptive neuro-fuzzy inference system (ANFIS) models were developed using simulation data. The fuzzy system showed a maximum deviation of 0.8% for the copper rotor, while the neuro-fuzzy approach achieved effective nonlinear mapping for both rotor types with R² = 0.872 against finite-element benchmarks. Sensitivity tests with ±0.3% slip and ±15 W loss variations maintained estimation errors below 2.5%. This combined simulation and intelligent system methodology enables practical efficiency evaluation and rotor material comparison for motor condition assessment and industrial energy management.