Modified Efficient Protection of Palm Disaster from RPW Larvae using WSNs
Veeraprathap V1, Ramya B K2, Narendra Kumar G3

1Veeraprathap V , Dept. of Electronics & Communication, UVCE, Bangalore University, Bangalore, Karnataka, India.
2Ramya B K, Dept. of Electronics & Communication, UVCE, Bangalore University, Bangalore, Karnataka, India.
3Narendra Kumar G, Dept. of Electronics & Communication, UVCE, Bangalore University, Bangalore, Karnataka, India.
Manuscript received on January 02, 2020. | Revised Manuscript received on January 15, 2020. | Manuscript published on January 30, 2020. | PP: 245-251 | Volume-8 Issue-5, January 2020. | Retrieval Number: D8158118419/2020©BEIESP | DOI: 10.35940/ijrte.D8158.018520

Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)

Abstract: Red Palm Weevil (Rhynchophorus ferrugineus) is the most dangerous and deadly pest to date for coconut, date, sago, oil, and other palms. Because of the dissemble nature of feeding, RPW infestation is detected in the last stage. RPW larvae acoustic activity consists of crawling, chewing, emission and quick oscillating sound. Network of wireless sensor are used to record the sound produced by the Weevil larvae and early stage detection of larvae infestation to coconut tree is conducted using Acoustic techniques. Coconut palm tree is fixed with wireless sensors to receive the sound wave produced by RPW larvae to transmit to server via access points which is capturing the signals from six tree arranged in hexagonal form to process using the Mat lab tools and fundamental frequency of received may also comprise of environment noise. Mel scale in frequency which is nonlinear for spectrum of log power to cosine transform of linear for power spectrum of short term to represent the cepstrum of Mel frequency for processing of received sound. Featured extraction is performed using the Mel Frequency Cepstral. Mel frequency for feature extraction is most used method for feature extraction in frequency domain. Algorithm model of back propagation with neural network of Feed forward are used to enhance the recognize performance. The adopted method is less expensive than current methods of RPW larvae detection. The results in simulation are stimulated in early stage larvae detection and before the damage affect the economic threshold helping the farmers to follow the control measures.
Keywords: MFCC, Neural Network, Ad-hoc Network (MANET), Acoustic activity.
Scope of the Article: Mobile Adhoc Network.