|
|
 |
| |
|
|
|
A Statistical Indexing and Sensitivity Analysis Framework for Green Filmmaking Using Fuzzy-AI |
|
|
|
PP: 763-779 |
|
|
doi:10.18576/jsap/140618
|
|
|
|
Author(s) |
|
|
|
Hamza Farhan Ahmad,
Suleiman Ibrahim Al-Hawary,
Yogeesh N.,
Mohammed El Khider,
A. Vasudevan,
Thirumalesha Babu T R,
Mohammad Faleh Hunitie,
|
|
|
|
Abstract |
|
|
| In the era of big data, this study takes on the line of sustainability in film and television production by integrating traditional methods such as fuzzy mathematics alongside innovative, AI-driven tools even under the conditions of small or uncertain data. Utilizing fuzzy sets, membership functions, and a Mamdani inference system we convert vague indicators (i.e., carbon footprint, energy consumption, distance travelled, disused portions, recycling rate) into a well-bolstered Sustainability Index (SI). AI modules fill in the gaps in missing or sparse data using techniques such as k-nearest neighbours imputation and anomaly detection, allowing cleaner input streams to feed into the fuzzy inference engine. Using comparative scenarios from conventional filmmaking to completely AI-optimized productions the framework highlights significant increases in resource efficiency and carbon footprint reduction. Sensitivity analyses further show that if we shift the membership functions of each crisp input ±10%, it would affect the ultimate SI rankings minimally, so the model is robust. Crisp threshold methods may miss subtle trade-offs, while the fuzzy approach is interpretable and flexible, enabling tailored rule sets to generate recommendations that reflect the nuances of real-world production workflows. The outcomes yield 50% decreases in carbon output and substantial energy savings in proposed advanced-AI scenarios, demonstrating that fuzzy mathematics–enhanced AI has the potential to function as a worthy decision-support mechanism for media stakeholders seeking cleaner media production pathways. |
|
|
|
|
|
|
|
