• Login
    View Item 
    •   USU-IR Home
    • Faculty of Engineering
    • Department of Electrical Engineering
    • Master Theses
    • View Item
    •   USU-IR Home
    • Faculty of Engineering
    • Department of Electrical Engineering
    • Master Theses
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Sistem Prakiraan Gas Beracun Karbon Monoksida Menggunakan Metode Ramalan Rata-Rata Bergerak Ganda

    View/Open
    fulltext (1.972Mb)
    Date
    2019
    Author
    Hasibuan, Eriansyah Saputra
    Advisor(s)
    Fahmi
    Hardi, Surya
    Metadata
    Show full item record
    Abstract
    Informasi kesehatan saat ini sangat perlu diperhatikan untuk menunjang keberlangsungan hidup manusia. Salah satu yang memberikan dampak terganggunya kesehatan pada manusia adalah polusi udara. Oleh karenanya dibutuhkan pengendalian inovatif untuk mengendalikan polusi udara. Pada penelitian ini disajikan sistem pemantauan gas polutan Karbon Monoksida (CO) yang dikalibrasikakan dengan sistem prediksi mengunakan metode rata – rata bergerak ganda (Double Moving Average). Prototipe untuk memantau gas CO menggunakan sensor MQ7, dihubungkan dengan mikrokontroler arduino dan modul GPRS. Pembacaan ditampilkan secara real time yang terkoneksi dengan webserver. Tahapan penelitian meliputi pengumpulan data dari prototipe gas CO, dianalisis dengan metode prediksi rata – rata bergerak ganda menggunakan pemrograman php, yang hasilnya di simpan ke database dan tampilkan ke webserver. Uji coba sistem prediksi gas CO dengan menganalisa nilai tingkat kesalahan prediksi pada Mean Absolute Persentage Error (MAPE), dan Mean Squared Error (MSE). Hasil pengujian dilakukan di wilayah KIM Belawan I, dengan mengukur menggunakan prototipe gas CO dan mengirim data secara real time ke webserver dalam inteval waktu 1 jam 13 menit. Dari hasil pengukuran data yang diterima dari prototipe gas CO sebanyak 44 data. Rentang waktu data prediksi dengan data real time gas CO rata-rata 4 menit. Hasil prediksi menggunakan metode rata – rata bergerak ganda memiliki MAPE maksimum dari 3,39% dan MAPE minimum 0,74%. Sedangkan MSE maksimum dari 5,84 dan MSE minimum 0,27. Berdasarkan hasil MAPE dan MSE, tingkat ketepatan sistem predeksi lebih 95%, sehingga sistem ini dapat di implementasikan baik di industri dan masyarakat.
     
    Health information at this time is very essential to support the continuity improvement of human life. One of the causes of problems to health in humans is the air pollution. It is necessary to have a monitoring system to provide information on air pollutio. In this research, a monitoring system for air pollutant gas, specifically Carbon Monoxide (CO) was developed and calibrated with a prediction system using the double moving average method. The prototype for monitoring CO gas used MQ7 sensor, connected with an Arduino microcontroller and GPRS module. Readings are displayed in real time connected to the web server. Stages of research include collecting data from CO gas prototypes, analyzed by predictive methods of multiple moving averages using php programming, the results of which are saved to the database and displayed to the web server. Test the CO gas prediction system by analyzing the value of the prediction error rate on the Mean Absolute Persentage Error (MAPE), and Mean Squared Error (MSE). The test results were carried out in the Belawan I KIM area, by measuring using CO gas prototypes and sending data in real time to the webserver within the interval of 1 hour 13 minutes. From the results of measurement of data received from CO gas prototypes as much as 44 data. The time range of predictive data with real time gas CO data is 4 minutes on average. The prediction results using the double moving average method have a maximum MAPE of 3.39% and a minimum MAPE of 0.74%. While the maximum MSE is 5.84 and MSE is a minimum of 0.27. Based on the results of MAPE and MSE, the accuracy of the prediction system is more than 95%, so this system can be implemented both in industry and society.

    URI
    http://repositori.usu.ac.id/handle/123456789/15172
    Collections
    • Master Theses [167]

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV
     

     

    Browse

    All of USU-IRCommunities & CollectionsBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit DateThis CollectionBy Issue DateTitlesAuthorsAdvisorsKeywordsTypesBy Submit Date

    My Account

    LoginRegister

    Repositori Institusi Universitas Sumatera Utara (RI-USU)
    Universitas Sumatera Utara | Perpustakaan | Resource Guide | Katalog Perpustakaan
    DSpace software copyright © 2002-2016  DuraSpace
    Contact Us | Send Feedback
    Theme by 
    Atmire NV