Bangalore Rajshekar Kavya
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bangalore Rajshekar Kavya has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- A. S. Shrikanth
Department of Mathematics, Adichunchanagiri Institute of Technology Chikkamagaluru, Chikkamagaluru, India
2 shared publications - Avant Srinivas Shrikanth
Department of Mathematics, Adichunchanagiri Institute of Technology, affiliated to Visvesvaraya Technological University Chikkamagaluru - 577102, India
2 shared publications - Balluru Thammannagowda Ashwini1 shared publication
- Deekshitha K V
Department of Mathematics, Malnad College of Engineering, affiliated to Visvesvaraya Technological University Hassan – 573202, India
1 shared publication - H. S. Suresh Chandra
Department of Civil Engineering, PES College of Engineering, Mandya, India
1 shared publication - Marilinge Rame Gowda1 shared publication
Latest Publications
- Open Access
- 24 June 2026
- Published by Tulpar Academic Publishing in Challenge Journal of Concrete Research Letters
- Vol. 17 (2) , 122
Performance assessment of polypropylene fiber-reinforced engineered cementitious composites using experimental investigation and ANN modeling
The use of engineered cementitious composites (ECC) in structural repair and rehabilitation is becoming more and more common because of their strain-hardening behavior, controlled cracking, and better durability. Polypropylene fiber-reinforced ECC has even more benefits like being resistant to corrosion and saving money, however its mechanical performance is very much affected by the changes in mix composition and the amount of fiber used in the mix. The traditional approaches in mix design are mostly based on either carrying out large-scale experimental trials or using complex micromechanics-based formulations, which are both time-consuming and not very applicable in practice. On the other hand, although the use of Artificial Neural Networks (ANNs) for modeling the behavior of different cement-based materials has been successful, its use in the case of polypropylene fiber-reinforced ECC is still limited. The present study aims to develop an ANN-based predictive framework to predict compressive and flexural strength of polypropylene fiber-reinforced ECC by using the parameters of the mix design. A detailed experimental program with compressive strength and three-point bending tests was performed with different polypropylene fiber contents to study the ECC mixtures. ECC mixtures containing 0–2.0% PP fibers were experimentally tested at curing ages of 14, 28, and 56 days. The results indicate that an optimum PP fiber content of 1.5% yielded the highest mechanical performance, achieving compressive strengths of 31.95 MPa, 47.95 MPa, and 50.61 MPa, and corresponding flexural strengths of 13.41 MPa, 17.50 MPa, and 24.12 MPa at 14, 28, and 56 days, respectively. For making the model more robust and generally applicable, the experimental results were merged with the data from published literature that was carefully selected for ANN training and validation. An ANN model trained using 105 datasets (experimental and literature-based) demonstrated strong predictive capability, with coefficients of determination (R²) of 0.955 and 0.963 for compressive and flexural strength during training, and 0.953 and 0.975 during testing, respectively. The mean absolute percentage error remained below 8.2% for both strength parameters. The proposed model shows a very strong agreement between the values of strength predicted and those measured in the experiments, as it is able to capture the non-linear relationship between the composition of ECC and its mechanical performance. The framework that has been developed is a practical tool for the optimization of ECC mixes and assessment of their performance, particularly for applications involving the rehabilitation of buildings where accurate predictions and efficient design of materials are of utmost importance.
- 24 June 2026
- Published by Tulpar Academic Publishing in Challenge Journal of Concrete Research Letters
- Vol. 17 (2) , 122
Open AccessPerformance assessment of polypropylene fiber-reinforced engineered cementitious composites using experimental investigation and ANN modeling
The use of engineered cementitious composites (ECC) in structural repair and rehabilitation is becoming more and more common because of their strain-hardening behavior, controlled cracking, and better durability. Polypropylene fiber-reinforced ECC has even more benefits like being resistant to corrosion and saving money, however its mechanical performance is very much affected by the changes in mix composition and the amount of fiber used in the mix. The traditional approaches in mix design are mostly based on either carrying out large-scale experimental trials or using complex micromechanics-based formulations, which are both time-consuming and not very applicable in practice. On the other hand, although the use of Artificial Neural Networks (ANNs) for modeling the behavior of different cement-based materials has been successful, its use in the case of polypropylene fiber-reinforced ECC is still limited. The present study aims to develop an ANN-based predictive framework to predict compressive and flexural strength of polypropylene fiber-reinforced ECC by using the parameters of the mix design. A detailed experimental program with compressive strength and three-point bending tests was performed with different polypropylene fiber contents to study the ECC mixtures. ECC mixtures containing 0–2.0% PP fibers were experimentally tested at curing ages of 14, 28, and 56 days. The results indicate that an optimum PP fiber content of 1.5% yielded the highest mechanical performance, achieving compressive strengths of 31.95 MPa, 47.95 MPa, and 50.61 MPa, and corresponding flexural strengths of 13.41 MPa, 17.50 MPa, and 24.12 MPa at 14, 28, and 56 days, respectively. For making the model more robust and generally applicable, the experimental results were merged with the data from published literature that was carefully selected for ANN training and validation. An ANN model trained using 105 datasets (experimental and literature-based) demonstrated strong predictive capability, with coefficients of determination (R²) of 0.955 and 0.963 for compressive and flexural strength during training, and 0.953 and 0.975 during testing, respectively. The mean absolute percentage error remained below 8.2% for both strength parameters. The proposed model shows a very strong agreement between the values of strength predicted and those measured in the experiments, as it is able to capture the non-linear relationship between the composition of ECC and its mechanical performance. The framework that has been developed is a practical tool for the optimization of ECC mixes and assessment of their performance, particularly for applications involving the rehabilitation of buildings where accurate predictions and efficient design of materials are of utmost importance.
- Open Access
- 15 June 2026
- Published by AMG Transcend Association in Biointerface Research in Applied Chemistry
- Vol. 16 (3)
M-Polynomial Driven QSPR Modeling for Mechanical Characteristics of Single-Layer Borophene Nanosheets
Borophene, with its outstanding mechanical and electronic properties, is a promising material for advanced technological applications. This work applies concepts from chemical graph theory to examine five single-layered borophene nanosheets by deriving their M-polynomials and computing various Degree-based Topological Indices (DBTI). These indices are correlated with key mechanical properties - Young’s modulus, Poisson’s ratio, strain at ultimate tensile strength, and ultimate tensile strength. Further linear, quadratic, cubic, exponential, and logarithmic regression models were examined, and based on the coefficient of determination (R2) value, the most appropriate model was identified. Thus, the study demonstrates that M-polynomial–based descriptors offer an efficient and reliable framework for predicting the mechanical behavior of borophene nanosheets.
- 15 June 2026
- Published by AMG Transcend Association in Biointerface Research in Applied Chemistry
- Vol. 16 (3)
Open AccessM-Polynomial Driven QSPR Modeling for Mechanical Characteristics of Single-Layer Borophene Nanosheets
Borophene, with its outstanding mechanical and electronic properties, is a promising material for advanced technological applications. This work applies concepts from chemical graph theory to examine five single-layered borophene nanosheets by deriving their M-polynomials and computing various Degree-based Topological Indices (DBTI). These indices are correlated with key mechanical properties - Young’s modulus, Poisson’s ratio, strain at ultimate tensile strength, and ultimate tensile strength. Further linear, quadratic, cubic, exponential, and logarithmic regression models were examined, and based on the coefficient of determination (R2) value, the most appropriate model was identified. Thus, the study demonstrates that M-polynomial–based descriptors offer an efficient and reliable framework for predicting the mechanical behavior of borophene nanosheets.
- 20 May 2025
- Published by Springer Nature in Asian Journal of Civil Engineering
- Vol. 26 (8) , 3233-3244
Comparative study on the mechanical properties of geopolymer concrete containing GGBS and fly ash using experimental analysis and artificial neural network
- 20 May 2025
- Published by Springer Nature in Asian Journal of Civil Engineering
- Vol. 26 (8) , 3233-3244
Comparative study on the mechanical properties of geopolymer concrete containing GGBS and fly ash using experimental analysis and artificial neural network
- 3 June 2022
- Published by Springer Nature in Asian Journal of Civil Engineering
- Vol. 23 (6) , 877-886
Prediction of mechanical properties of glass and basalt fiber reinforced concrete using ANN
- 3 June 2022
- Published by Springer Nature in Asian Journal of Civil Engineering
- Vol. 23 (6) , 877-886
Prediction of mechanical properties of glass and basalt fiber reinforced concrete using ANN