Browsing by Author "Vimala Rani, M.V."

Filter results by typing the first few letters
Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    A machine learning algorithm for scheduling a burn-in oven problem
    (Inderscience Publishers, 2023) Mathirajan, M.; Reddy, S.; Vimala Rani, M.V.; Dhaval, P.
    This study applies artificial neural network (ANN) to achieve more accurate parameter estimations in calculating job-priority-data of jobs and the same is applied in a proposed dispatching rule-based greedy heuristic algorithm (DR-GHA) for efficiently scheduling a burn-in oven (BO) problem. The integration of ANN and DR-GHA is called as a hybrid neural network (HNN) algorithm. Accordingly, this study proposed eight variants of HNN algorithms by proposing eight variants of DR-GHA for scheduling a BO. The series of computational analyses (empirical and statistical) indicated that each of the variants of proposed HNN is significantly enhancing the performance of the respective proposed variants of DR-GHA for scheduling a BO. That is, more accurate parameter estimations in calculating job-priority-data for DR-GHA via back-propagation ANN leads to high-quality schedules w.r.t. total weighted tardiness. Further, proposed HNN variant: HNN-ODD is outperforming relatively with other HNN variants and provides very near optimal/estimated solution. © © 2023 Inderscience Enterprises Ltd.
  • No Thumbnail Available
    Item
    An experimental study of newly proposed initial basic feasible solution methods for a transportation problem
    (Springer, 2022) Mathirajan, M.; Reddy, S.; Vimala Rani, M.V.
    This study presents an extensive experimental study of heuristic methods or initial basic feasible solution (IBFS) methods, which is one of the main steps to achieve an optimal or accepted (near-optimal) solution, for a transportation problem (TP). In this study, we proposed 23 new IBFS methods (18 new IBFS methods, and 5 variants of existing IBFS methods) for a TP. We conducted a series of experimental analyses with 640 randomly generated problem instances to study the performance efficiency of the 23 newly proposed IBFS methods in comparison with (a) solutions obtained from 11 latest IBFS methods published in the literature, and (b) optimal solution obtained from linear programming approach. Our multiple performance analyses revealed that the first six ranking positions (with respect to the total transportation cost obtained from each of the 34 IBFS methods over 640 problem instances) are related to the newly proposed IBFS methods and the 7th to 10th ranking positions are related to the existing IBFS methods. Furthermore, the first two best performing newly proposed IBFS methods are yielding near to optimal solution (with 0% to 2% loss of optimality). So, these can be easily integrated as the sub-module to solve any complex decision-making problems such as Logistics/Supply Chain Management. © 2021, Operational Research Society of India.