An interior design method based on the coupling of I-GWO and self-updating neural network under the background of green interaction

In the context of verdant interplay, interior design is progressively compelled to appraise the equilibrium between ecological sustainability and user experientiality. To this end, this manuscript postulates a novel interior design algorithm rooted in the interaction grey wolf algorithm (I-GWO) conjoined with a self-updating neural network. Initially, a tailored I-GWO is harnessed to fine-tune the interior design proposal, wherein the design quandary is transformed into an optimisation conundrum, thereby deploying the I-GWO to navigate the realm of optimal solutions. Subsequently, a bespoke self-updating neural network is architected, amalgamating convolutional neural networks (CNN) and long-short-term memory (LSTM), thereby refining the design blueprint even further. This contrived neural network evinces the innate capacity to autonomously assimilate and update weights and biases. The nomenclature and precepts of interior design are thereby assimilated through the synergy of the I-GWO and self-updating neural network. Finally, empirical attestations evince the algorithm's meritorious aptitude in optimising interior design schemes while adeptly incorporating considerations of environmental sustainability. The outcomes evince a noteworthy 42.5% enhancement in temporal efficiency when compared to extant state-of-the-art algorithms. Furthermore, the proposed method attains the zenith in convergence efficacy when juxtaposed with six other state-of-the-art algorithms.