View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Vocational School
      • UT - Computer Engineering Tehcnology
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Vocational School
      • UT - Computer Engineering Tehcnology
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Deteksi Suara Burung Pipit Menggunakan Algoritma Random Forest pada Sistem Pengendalian Hama Berbasis IoT

      Thumbnail
      View/Open
      Cover (620.8Kb)
      Fulltext (1.740Mb)
      Lampiran (140.7Kb)
      Date
      2025
      Author
      Haniyah, Wanda
      Sukoco, Heru
      Metadata
      Show full item record
      Abstract
      Penelitian ini bertujuan mengembangkan sistem pengendalian hama burung pipit berbasis Internet of Things (IoT) dengan pendekatan deteksi suara. Sistem ini menggunakan sensor suara dan algoritma Random Forest untuk membedakan suara burung pipit dari suara lain secara akurat. Total 10.000 data suara (5.000 suara pipit dan 5.000 suara non-pipit) dikumpulkan pada Januari hingga Maret 2025, lalu dibagi menjadi 70% data latih, 15% data validasi, dan 15% data uji. Model menghasilkan akurasi validasi sebesar 96% dan akurasi uji sebesar 95%, dengan precision 95,83%, recall 95,07%, dan F1-score 95,45%. Ketika suara pipit terdeteksi, sistem akan mengaktifkan servo dan memutar suara burung predator melalui speaker untuk mengusir burung pipit. Data hasil deteksi dikirimkan secara real-time ke Firebase dan ditampilkan pada web dashboard, memungkinkan pengguna untuk memantau kondisi sawah dari jarak jauh. Hasil implementasi menunjukkan bahwa sistem mampu mengenali suara burung pipit dengan baik dan memberikan respons otomatis secara efektif.
       
      This study aims to develop an Internet of Things (IoT)-based sparrow pest control system using a sound detection approach. The system employs a sound sensor and the Random Forest algorithm to accurately distinguish sparrow sounds from other noises. A total of 10,000 sound samples (5,000 sparrow sounds and 5,000 non-sparrow sounds) were collected between January and March 2025, and then divided into 70% training data, 15% validation data, and 15% testing data. The model achieved a validation accuracy of 96% and a test accuracy of 95%, with a precision of 95.83%, recall of 95.07%, and F1-score of 95.45%. When a sparrow sound is detected, the system responds by activating a servo motor and playing a predator bird sound through a speaker to drive the sparrows away. The detection results are sent in real time to Firebase and displayed on a web dashboard, allowing users to remotely monitor the condition of the rice field. The implementation results demonstrate that the system can effectively recognize sparrow sounds and provide an automatic and efficient response.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/168516
      Collections
      • UT - Computer Engineering Tehcnology [172]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository