A research paper comparing multilayer perceptron neural networks to logistic regression for optimizing steel structure design. The study evaluates different ANN configurations to find effective arrangements for reducing weight, costs, and environmental impact. The work was authored by Amirhossein Ostovar and published on figshare under a CC-BY-4.0 license.
Use Cases
- Benchmarking neural network performance against logistic regression based on the described comparison.
- Optimizing steel structure weight and cost based on the described design process.
- Investigating ANN configurations for structural design based on the study of hidden layers and neurons.
- Analyzing the impact of early-stage design on energy and material consumption as described.
Strengths
- The research provides a direct comparison of MLP networks and logistic regression.
- The dataset is openly available under a CC-BY-4.0 license.
- The description details a specific application in steel structure design optimization.
Limitations
- The dataset consists of PDF and DOCX files totaling 909.2 KB, indicating a limited scope.
- Row count and column-level documentation are absent; data structure must be inferred.
- The description metadata is limited; actual data quality requires manual inspection after download.
Provenance
- Source
- figshare
- Freshness
- Last updated 2026-05-05 12:12:28; freshness should be verified.