Artificial Intelligence-Based System for Simulation of Predator
Sound as an Effective way of Reducing Frequency of Harmful
Birds’ Infestation in a Rice Farm

Nwonye Charles. A; Omeche. A. A; Esimike. H. C

doi:10.56201/ijemt.vol.11.no10.2025.pg205.220

📄 Download Paper

Artificial Intelligence-Based System for Simulation of Predator Sound as an Effective way of Reducing Frequency of Harmful Birds’ Infestation in a Rice Farm

Nwonye Charles. A, Omeche. A. A, Esimike. H. C

Abstract

This paper presents the simulation of predator sound as an effective way of reducing the frequency of rice harmful birds in a rice farm. In this research work, the harmful rice birds called sparrow birds were scared away using the sound of the predator (Squirrel) and also ordinary sound and the birds’ behaviours were observed over a period of two weeks. It was observed that at the initial instance while using the ordinary sound, the birds were scared away and they later returned to the farm. After subsequent scaring with this ordinary sound, the birds could not be scared away again by this ordinary sound since their cognitive abilities could not attach the sound to any previous ugly experience in the past. However, when the predator sound was used to scare away the birds, the birds were also scared away but it was noticed that the number of birds returning to the farm kept reducing until only very few birds could return to the farm. Due to the cognitive abilities of the birds, the harmful sparrow birds had to attach the predator sound to previous ugly experiences and recognise it as a threat and would fly far away from such rice farm. Hence, simulating the right predator sound in a rice farm would scare away harmful birds in a rice farm leaving the beneficial birds to do their insect pest control. In the course of this research work, a convolutional neural network model was designed and trained to recognize the sparrow birds in the rice farm while an algorithm was developed to simulate predator sound and ordinary sound for the scaring of the harmful sparrow birds. The developed convolutional neural network (CNN) model was developed from a pre-trained model called efficientnetb5 through a process of transfer intelligence. Then, the developed CNN model was trained with 2419 pre-processed images of the sparrow birds in google colab platform. The trained model was integrated with an algorithm that used the sound of the predator (squirrel) and ordina

Keywords

Artificial IntelligencePredator SoundHarmful birdsConvolutional neural networkRice farm and Ordinary Sound.

References

[1]. Sasu, D. D. (2023). Share of GDP by agricultural sector in Nigeria 2023. https://www.statista.com/aboutus/our-research-commitment/2683/doris-dokua-sasu Site visited 20/05/2024. [2]. Montràs-Janer, T., Knape, J., Nilsson, L., Tombre, I.., Pärt, T. and Månsson, J. (2019). Relating National Levels of Crop Damage to the Abundance of Large Grazing Birds: Implications for Management. [3]. Abdullahi, H.S ., Mahieddine, F. & Sheriff, R.E (2015). Technology Impact on Agricultural Productivity: A Review of Precision Agriculture using Unmanned Aerial Vehicles (UAVs). https//www.researchgate.net/publication/283641594. (20/12/2019). [4[. Ahmad, E., Hussain, I., Eds. (1990). Pakistan Agricultural Research Council. Islamabad, Pakistan: pp. 187–191. [5]. Alexander. M, Nicole .M and Daniel .T (2014). Prey Responses to Predator’s Sounds: A Review and Empirical Study. California, Los Angeles USA: Department of Ecology and Evolutionary Biology, University of California, Los Angeles. [6]. Andelt, W.F.; Woolley, T.P.; Hopper, S.N. (1997). Effectiveness of Barriers, Pyrotechnics, Flashing Lights, and Scarey Man for Deterring HeronPredation on Fish. Wildl. Soc. Bull. 25, 686–694. [7]. Bahr, J.; Erwin, R.; Green, J.; Buckingham, J.; Peel, H. (1992). A Laboratory Assessment of Bird Responses to an Experimental Strobe Light Deterrent. Sidney, BC, Canada: The Delta Environmental Management Group Ltd. and Southwest Research Institute. [8]. Blokpoel, H. (1980). Gull Problems in Ontario. Ottawa, ON, Canada: Canadian Wildlife Service. [9]. Swati, D., Swati, V.K., Shweta.S.G., Sayali, S.N. and Purva V.G (2015). Agricultural Drones for Spraying Fertilizers and Pesticides. International Journal of Advanced Research in Computer Science and Software Engineering. 5(2), 804-811. www.ijarcsse.com [10]. Hafeez, A., Husain, M. A., Singh, S. P., Chuaha, A., Khan, M. T., Kumar, N., Chuahan, A.Soni, S. K. (2023). Implementation of drone technology for farm monitoring and pesticide spraying: a review. Information Processing in Agriculture. 10 (2), 192-203. Doi:10.1016/j.inpa.2022.02.002 [11]. Deepak, M., Akanksha, G., Tasneem, A., & Dharmendra, S. (2017). Fusion of Drone and Satellite Data for Precision Agriculture Monitoring. Published in: 2016 11th International Conference on Industrial and Information Systems (ICIIS) Roorkee, India, Date of Conference: 3-4 Dec, 2016. DOI: 10.1109/ICIINFS.2016.8263068. [12]. Bongiovanni R, and Lowenberg-Deboer J. (2004). Precision Agriculture and Sustainability. Kluwer Academic Publishers. [13]. Oluwole, A., Adefemi, A. and Ade-Omowaye, J. (2020). Oluwole, A., Adefemi, A. and Ade-Omowaye, J. (2020). A Real Time Image Repellent System Using Raspberry pi. FUOYE Journal of Engineering and Technology, vol.5,Issue 2, September 2020. [14]. Ghosh, A., Sufian, A., Sultana, F., Chakrabarti, A. and De, D. (2020). Fundamental concepts of convolutional neural network. Recent Trends and Advances in Artificial Intelligence and Internet of Things doi: 10.1007/978-3-030-32644-9_36. [15]. Vakalopoulou, M., Christodoulidis, S., Burgos, N., Colliot, O. and Lepetit, V. (2023). Deep learning: basics and convolutional neural networks (CNN). Colliot, O. (Ed) Machine Learning for Brain Disorders, Springer, 2023: 77-115. doi: 10.1007/978-1- 0716-3195-9_3. hal-03957224v2[16]. Alexander. M, Nicole .M and Daniel .T (2014). Prey Responses to Predator’s Sounds: A Review and Empirical analysis. California, Los Angeles USA: Department of Ecology and Evolutionary Biology, University of California, Los Angeles. [17] Nwonye C.A, Akpado K.A and Amaefule D.O (2024).Development of a Specie-specific Bird Deterrent System using Birds Classifications by Convolutional Neural Network (CNN) Model. Published in International Journal of Engineering Research and sciences ISSN:2395-6992,Vol-10, Issue-5, May- 2024, Pages 07 – 18 published online in IJOER; DOI: https://dx.doi.org/10.5281/zenodo.11452990. [18] Nwonye C.A, Akpado K.A and Amaefule D.O (2024).A Convolutional Neural Network Model for Harmful Birds Recognition and Deterrent in a Dynamic Rice Farm Associated With Bird Migration And Climate Changes [Published in International Journal of Engineering Applied Sciences and technology Vol. 8, Issue 12, ISSN No. 2455-2143, Pages 371-379 Published Online April 2024 in IJEAST (http://www.ijeast.com)]. [19] Nwonye C.A, Akpado K.A, Alumona T.L, Oguejiofor O.S and Amaefule D.O (2024).Monitoring of Migration of Harmful Sparrow Birds in a Rice Farm Using Convolutional Neural Network (CNN) Model [Published in UNIZIK Journal of Engineering and Applied Sciences 3(2), September (2024) Pages 1144 - 1162. Journal homepage: https://journals.unizik.edu.ng/index.php/ujeas PRINT ISSN: 2992-4383 || ONLINE ISSN: 2992-4391].

Artificial Intelligence-Based System for Simulation of Predator Sound as an Effective way of Reducing Frequency of Harmful Birds’ Infestation in a Rice Farm

Abstract

Keywords

References

More Articles from INTERNATIONAL JOURNAL OF ENGINEERING AND MODERN TECHNOLOGY