Hybrid leader based optimization with deep learning driven weed detection on internet of things enabled smart agriculture environment. (December 2022)

• Record Type: Journal Article
• Authors: Alrowais, Fadwa; Asiri, Mashael M; Alabdan, Rana; Marzouk, Radwa; Hilal, Anwer Mustafa; alkhayyat, Ahmed; Gupta, Deepak
• Is Part Of: Computers & electrical engineering. Volume 104:Part A(2022)
• Publication Date: 2022-12
• Subjects: Internet of Things -- Smart farming -- Deep learning -- Agriculture -- Parameter optimization -- Computer vision -- Object detection -- Metaheuristics; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2022.108411
• Languages: English
• ISSNs: 0045-7906

Abstract

Highlights: Develop an IoT assisted optimal deep learning-driven weed detection model. Employ hybrid leader optimizer with YOLO-v5 model for detection process. Present KELM model for classification of weeds and crops. Validate the performance on benchmark dataset and achieves 98.87% accuracy. Abstract: Recent technological advancements of Cloud Computing (CC), Internet of Things (IoT), Artificial Intelligence (AI), computer vision, etc. enable the transformation of traditional agricultural practices into smart agricultural practices. In this background, the current article introduces a novel Hybrid Leader-based Optimization with DL-driven Weed Detection in IoT-enabled Smart Agriculture (HLBODL-WDSA) model. The prime aim of the proposed HLBODL-WDSA model is to collect the images using IoT devices and recognize the weeds automatically. Initially, the HLBODL-WDSA model enables the IoT devices to capture the farm images and transmits the images to the cloud server for examination. Next, the HLBODL-WDSA model applies YOLO-v5-based weed detection process in which HLBO algorithm is exploited as a hyperparameter optimizer. Finally, the Kernel Extreme Learning Machine (KELM) model is applied for effective classification of the weeds. The proposed HLBODL-WDSA model was experimentally validated and the outcomes established the better performance of the proposed HLBODL-WDSA model over recent approaches. Graphical abstract: Image, graphical abstract