A5039040767- Multi-Criteria Decision Making
- Optimization and Mathematical Programming
- Neural Networks and Applications
- Fuzzy Logic and Control Systems
- Vehicle Routing Optimization Methods
- Fuzzy and Soft Set Theory
- Fuzzy Systems and Optimization
- Advanced Multi-Objective Optimization Algorithms
- Evolutionary Algorithms and Applications
- Optimal Power Flow Distribution
- Electric Power System Optimization
- Metaheuristic Optimization Algorithms Research
- Advanced Algebra and Logic
- EEG and Brain-Computer Interfaces
- Energy Load and Power Forecasting
- Machine Learning and ELM
- Image and Signal Denoising Methods
- Transportation Planning and Optimization
- Face and Expression Recognition
- Optimization and Packing Problems
- Optical Imaging and Spectroscopy Techniques
- Non-Invasive Vital Sign Monitoring
- Blind Source Separation Techniques
- Visual and Cognitive Learning Processes
- Scheduling and Timetabling Solutions
National Institute of Technology Durgapur
2016-2025
Indian Statistical Institute
2002-2003
This article proposes an efficient meta-heuristic approach, namely, oppositional grey wolf optimization (OGWO) algorithm for resolving the optimal operating strategy of economic load dispatch (ELD) problem. The proposed combines two basic concepts. Firstly, hunting behavior and social hierarchy wolves are used to search solutions secondly, concept is integrated with (GWO) accelerate convergence rate conventional GWO algorithm. To show performance algorithm, it applied on small, medium large...
Economic load dispatch (ELD) is the process of allocating committed units such that constraints imposed are satisfied and production cost minimized. This paper presents a novel heuristic algorithm for solving complex ELD problem, by employing comparatively new method named krill herd (OKHA). KHA nature-inspired metaheuristics which mimics herding behaviour ocean individuals. In this article, combined with opposition based learning (OBL) to improve convergence speed accuracy basic algorithm....
The shortest path problem (SPP) is one of the most important combinatorial optimization problems in graph theory due to its various applications. uncertainty existing real world makes it difficult determine arc lengths exactly. fuzzy set popular tools represent and handle information incompleteness or inexactness. In cases, SPP graph, called (FSPP) uses type-1 (T1FS) as length. Uncertainty evaluation membership degrees inexactness human perception not considered T1FS. An interval type-2...
We propose a new archive-based steady-state micro genetic algorithm (ASMiGA). In this context, archive maintenance strategy is proposed, which maintains set of nondominated solutions in the unless size falls below minimum allowable size. It makes adaptive and dynamic. have proposed environmental selection mating strategy. The reduces exploration less probable objective spaces. increases searching more search regions by enhancing exploitation existing solutions. A crossover DE-3 here. ASMiGA...
The weights of a multilayer perceptron (MLP) may be altered by multiplicative and/or additive noises if it is implemented in hardware. Moreover, an MLP using analog circuits, prone to stuck-at 0 faults, i.e., link failures. In this paper, we have proposed methodology for making robust with respect failures, noise, and noise. This achieved penalizing the system error three regularizing terms. To train use weighted sum following four terms: 1) mean squared (MSE); 2) l <sup...
Shortest path problem is one of the most fundamental and well-known optimization problems in graph theory due to its various real-world applications. Fuzzy set can manage uncertainty, associated with information a problem, where conventional mathematical models may fail reveal satisfactory result. In cases, shortest fuzzy graph, called uses type-1 as arc length. The uncertainty linguistic description not represented properly by inexactness human perception evaluation membership degrees...
In most real life investment situations future security returns are represented mainly based on expert's judgments due to the occurrence of unexpected incidents in economic and social changes or lack historical data. order tackle such uncertainties, securities evalua ted by experts instead this study, a multi-objective uncertain portfolio selection model has been proposed defining average return as expected value, risk variance divergence among cross-entropy where considered variables. The...
This article proposes an algorithmic approach for group decision making (GDM) problems using neutrosophic soft matrix (NSM) and relative weights of experts. NSM is the representation sets (NSSs), where NSS combination set set. We propose a new idea assigning to experts based on cardinalities NSSs. The weight assigned each their preferred attributes opinions, which reduces chance unfairness in process. Firstly we introduce choice combined sets. Multiplying matrices with individual NSMs, this...
In real world, most of the combinatorial optimization problems are multi-objective and it is difficult to optimize them simultaneously. literature, some individual algorithms (ACO, GA, etc.) available solve such discrete (MOOPs), particularly trav elling salesman (TSPs). Here a hybrid algorithm combining ACO GA with diversity developed TSPs named MOACOGAD. Generally in TSP, routes for travel not considered as lengths remain unaltered. life, there may be several from one destination another...
The immunity of multilayer perceptron (MLP) is less effective toward input noise. In this article, we have focused on the robustness MLP with respect to noise where can be additive or multiplicative. Here, proposed a DropConnect-based regularized reduce coadaptation among neurons hidden layer. At first, empirically and statistically shown that by reducing neurons, an achieve better immunity. We also injection <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML"...
This paper presents a self-organized genetic algorithm-based rule generation (SOGARG) method for fuzzy logic controllers. It is three-stage hierarchical scheme that does not require any expert knowledge and input-output data. The first stage selects rules required to control the system in vicinity of set point. second extends this entire input space, giving rulebase can bring its point from almost all initial states. third refines reduces number rules. two stages use same fitness function...
Abstract This paper investigates the uncertain maximum flow of a network whose capacities are random fuzzy variables. We have developed expected value model (EVM) and chance‐constrained (CCM) for problem (MFP) under environment formulated their crisp equivalent models. To solve these models, we proposed varying population genetic algorithm with indeterminate crossover (VPGAwIC). In VPGAwIC, selection chromosome depends on its lifetime. An improved lifetime allocation strategy (iLAS) has also...