Modified Barnacles Mating Optimization with Deep Learning Based Weed Detection Model for Smart Agriculture

Weed control is a significant means to enhance crop production. Weeds are accountable for 45% of the agriculture sector’s losses, which primarily occur because competition with crops. Accurate and rapid weed detection in agricultural fields was difficult task presence wide range species at various densities growth phases. Presently, several smart tasks, such as detection, plant disease identification, water soil conservation, yield prediction, can be realized by using technology. In this article, we propose Modified Barnacles Mating Optimization Deep Learning based (MBMODL-WD) technique. The MBMODL-WD technique aims automatically identify weeds field. Primarily, presented uses Gabor filtering (GF) noise removal process. For automated DenseNet-121 model feature extraction MBMO algorithm hyperparameter optimization. design involves integration self-population-based initialization standard BMO algorithm. At last, Elman Neural Network (ENN) method applied classification To demonstrate enhanced performance approach, series simulation analyses were performed. A comprehensive set simulations highlighted methodology over other DL models maximum accuracy 98.99%.