| Autor: |
Kumbi, Arun A., Birje, Mahantesh N. |
| Předmět: |
|
| Zdroj: |
Wireless Personal Communications; Jan2022, Vol. 122 Issue 2, p1221-1246, 26p |
| Abstrakt: |
The innovative services of Internet-of-Things (IoT) led to the design of sophisticated systems using heterogeneous technologies. IoT poses integrating networks to offer smooth services to humans. Irrigation plays a trending role in sustainable sugarcane crop production in areas that suffer from water scarcity. The effective usage of water is a major constraint in agriculture due to the increasing demand for water and excessive requirement to enhance productivity. This paper proposes Sun-flower Atom Optimization-based Deep convolution neural network (SFAO-DeepCNN) algorithm for providing optimal water control in sugarcane crops. Initially, the data collection is performed in the IoT network using the Artificial Bee Colony (ABC) algorithm. Then, the push-based algorithm and log transformation are employed for making data suitable for processing. In addition, the Apriori algorithm is employed for selecting an effective feature from a massive set of features adapting a feature score. The Apriori algorithm helps to increase the accuracy of the classifier. The feature score is newly devised to identify proficient features for computing the watering quantity. The water controlling phase is performed using DeepCNN, which is trained with the proposed Sunflower Atom Optimization (SFAO) algorithm. The proposed SFAO-deep CNN outperformed other methods with maximal accuracy of 92%, specificity of 91.2% and sensitivity of 94.1%, respectively. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink