AI-POWERED DECISION SCIENCE
Dance classification using pretrained deep learning models integrated with the circular Fermatean fuzzy MARCOS method
This study presents a hybrid framework for identifying and classifying dance styles using pretrained deep learning models, evaluated under multiple performance criteria. To address the inherent uncertainty and complexity in selecting the best-performing models, a novel circular Fermatean fuzzy measurement of alternatives and ranking based on the compromise solution (CFF-MARCOS) approach is proposed. Unlike existing methods, the integration of circular Fermatean fuzzy sets (CFFS) into the MARCOS framework enables more refined handling of hesitation and ambiguity in expert evaluations.
Executive Impact Overview
The integration of advanced deep learning with multi-criteria decision-making (MCDM) offers a robust solution for complex classification tasks, particularly in creative domains like dance.
0
Improved Decision Reliability
0
Enhanced Uncertainty Handling
0
Robust Model Selection
0
Computational Efficiency Gains
Deep Analysis & Enterprise Applications
Select a topic to dive deeper, then explore the specific findings from the research, rebuilt as interactive, enterprise-focused modules.
The Power of CFF-MARCOS
The study introduces a novel integration of Circular Fermatean Fuzzy Sets (CFFS) with the MARCOS (Measurement Alternatives and Ranking According to Compromise Solution) method. This innovative approach allows for more refined handling of hesitation and ambiguity in expert evaluations compared to traditional linear fuzzy methods. CFFS provides a three-dimensional representation of uncertainty, making it highly suitable for multi-dimensional decision-making problems like dance classification. This advanced framework ensures robust and interpretable rankings, addressing a significant gap in existing AI-based classification techniques.
Unpacking the CFF-MARCOS Framework
The CFF-MARCOS methodology systematically evaluates and ranks alternatives based on a compromise solution, explicitly designed to handle complex fuzzy information. It begins by collecting linguistic evaluations from decision-makers, converting them into CFFVs, and aggregating them into a decision matrix. Subsequent steps involve determining optimal solutions, calculating distance measures, deriving criteria weights, constructing weighted normalized matrices, and finally, computing utility degrees and functions to establish a clear ranking. This structured approach ensures a comprehensive and robust evaluation process.
Automated Dance Classification & Beyond
The CFF-MARCOS framework was applied to a case study involving the classification of dance styles using pretrained deep learning models. By considering multiple criteria such as accuracy, precision, training time, and generalization capability, the method successfully identified the most suitable models, with **DenseNet121 (A5)** emerging as the top performer. This not only enhances automated dance classification but also provides a scalable, computationally efficient, and interpretable decision-making tool applicable to other complex AI-driven tasks in fields like healthcare, automation, and finance where expert judgment and uncertainty are paramount.
Enterprise Process Flow: CFF-MARCOS Methodology
Train Deep Learning Model
→
Evaluate DL Models
→
Select Evaluation Criteria
→
Construct CFF Decision Matrix
→
Compute Distance Measures
→
Derive Criteria Weights
→
Normalize the Decision Matrix
→
Construct Weighted Normalized Matrix
→
Calculate Utility Degrees and Functions
→
Rank the Alternatives
A5
Highest-Ranked Deep Learning Model for Dance Classification
Model A5 (DenseNet121) consistently demonstrated superior performance in accuracy, precision, F1-score, generalization, and computational efficiency, securing the top rank in the CFF-MARCOS evaluation for dance classification.
| Feature | CFF-MARCOS | WASPAS | VIKOR | EDAS | COCOSO | TOPSIS |
|---|---|---|---|---|---|---|
| Handling Uncertainty | High | Medium | Medium | Low | Medium | Low |
| Incorporation of CFFS | High | Low | Low | Low | Low | Low |
| Result Stability Across Scenarios | High | Medium | Medium | Low | Medium | Medium |
| Sensitivity to Criteria Weights | High | Medium | High | High | Medium | High |
| Computational Complexity | High | Medium | Medium | Medium | High | Medium |
| Ease of Implementation | High | High | Medium | High | Medium | High |
| Interpretability of Results | High | Medium | Medium | High | Medium | Medium |
| Multi-Expert Integration | High | Medium | Medium | Low | Medium | Low |
| Adaptability to Fuzzy Environments | High | Medium | Medium | Low | Medium | Low |
Case Study: Automated Dance Classification Using CFF-MARCOS
This study showcased the practical application of CFF-MARCOS in a complex AI scenario, providing a robust solution for model selection.
Problem: Selecting the most suitable pretrained deep learning model for dance classification is complex due to conflicting performance criteria (accuracy, training time, complexity) and expert uncertainty.
Solution: The CFF-MARCOS framework integrates Circular Fermatean Fuzzy Sets (CFFS) with the MARCOS method to evaluate ten pretrained deep learning models across seven criteria, incorporating expert judgments to provide robust rankings.
Outcome: The method successfully identified DenseNet121 (A5) as the top-performing model, demonstrating improved decision reliability and clarity, even with trade-offs in different performance metrics, ensuring a nuanced selection aligned with real-world needs.
Calculate Your Potential AI ROI
Estimate the annual savings and efficiency gains your organization could achieve by implementing an AI solution tailored to your needs.
Estimated Annual Savings
$0
Annual Hours Reclaimed
0
Your AI Implementation Roadmap
A typical enterprise AI project journey, from initial consultation to full-scale deployment and optimization.
Discovery & Strategy
In-depth analysis of current operations, identification of AI opportunities, and development of a tailored AI strategy and roadmap aligned with business objectives.
Solution Design & Prototyping
Detailed design of the AI solution, including model selection, architecture, data pipeline, and rapid prototyping to validate concepts and refine requirements.
Development & Integration
Full-scale development of the AI models, seamless integration with existing enterprise systems, and rigorous testing for performance, security, and scalability.
Deployment & Optimization
Controlled deployment of the AI solution, continuous monitoring of performance, and iterative optimization based on real-world data and user feedback to maximize ROI.
Ready to Transform Your Enterprise with AI?
Book a free, no-obligation consultation with our AI specialists to explore how these insights can be applied to your unique business challenges.
Ready to Get Started?
Book Your Free Consultation.
Let's Discuss Your AI Strategy!
Lets Discuss Your Needs
Select a Date
Sun
Mon
Tue
Wed
Thu
Fri
Sat