Research Application of Integrating Small Habitat Genetic Algorithm in Ecological Landscape Design

Abstract

Environmental landscaping involves designing, planning, and managing landscapes that benefit both humans and the environment. Landscape design incorporates both landscaping and environmental considerations to address complicated issues holistically. Humans have a significant impact on the ecology by seeding native species and removing alien species.In this study, Research Application of Integrating Small Habitat Genetic Algorithm in Ecological Landscape Design(ISHGA-ELD-HOTNN) are proposed. Initially, the data gathered from Deep Globe Land cover classification dataset. To execute this input data is pre-processed using Multimodal Hierarchical Graph Collaborative Filtering (MHGCF). It is used to clean and normalize the data. Then, the pre-processed data are fed to Feature extraction segment using Newton Time Extracting Wavelet Transform (NTEWT), visual feature such as colour, texture and shape are extracted. In general, Higher-Order Topological Neural Networks (HOTNN) generates the landscape design. Hence, proposed utilize Harbor Seal Whiskers Optimization Algorithm (HSWOA) enhance Higher-Order Topological Neural Networks accurately generate the landscape design. Then, the Research Application of Integrating Small Habitat Genetic Algorithm in Ecological Landscape Design ISHGA-ELD-HOTNN is implemented to Python and the performance metrics such as, Accuracy, precision, Recall, F1-score, mean square error and error rate. Finally, the performance of ISHGA-ELD-HOTNN method provides 19.67%, 22.57% and 33.15% high accuracy, 23.17%, 26.62% and 28.68% higher Precision and 23.37%, 27.57% and 27.23% low error while compared with existing Mapping human perception of urban landscape from street-view images: A deep-learning approach (MHP-ULSVI-CNN) , Rural landscape design strategy based on deep learning model (RLDS-ELM) and Environmental landscape design and planning system based on computer vision and deep learning (ELD-PS-CV-DNN),  respectively.