View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Physics
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - Faculty of Mathematics and Natural Sciences
      • UT - Physics
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Penggunaan Fast Artificial Neural Network dalam Menganalisis Hasil Pengukuran Kadar Hemoglobin Darah dengan Metode Spektrofotometri

      Thumbnail
      View/Open
      Cover (263.5Kb)
      Full text (844.9Kb)
      Lampiran (1016.Kb)
      Date
      2022
      Author
      Desmulyani, Witri
      Irzaman
      Widayanti, Tika
      Metadata
      Show full item record
      Abstract
      Seiring bekembangnya teknologi maka dalam pengukuran kadar hemoglobin diperlukan alat yang dapat memberikan informasi secara cepat dan akurat. Penelitian ini bertujuan untuk mengembangkan, menguji performa metode pengukuran kadar hemoglobin dengan menggunakan metode kecerdasan buatan atau Fast Artificial Neural Network serta memberikan informasi mengenai kandidat lampu yang layak dalam pengukuran kadar hemoglobin darah melalui metode akurasi yang meliputi analisis Root Mean Square Error (RMSE). Selain itu juga menggunakan metode uji diagnostik berupa sensitivitas, spesifisitas, diagnosis akurasi dan analisis Number Needed to Diagnose (NND). Kandidat lampu yang memiliki nilai Root Mean Square Error yang baik yaitu pada rentang panjang gelombang 410 nm dan 420 nm dengan rata-rata absorbansi 0,598 serta nilai standar deviasi sebesar 0,176. Sedangkan kandidat lampu yang memiliki nilai terbaik berdasarkan uji diagnostik berada pada rentang panjang gelombang 580 nm sampai 800 nm dengan nilai spesifisitas 89%, diagnosis akurasi 95%, number needed to diagnose 1,1 kali pengulangan. Nilai sensitivitas pada penelitian sudah mencapai keakuratan maksimal 100%. Nilai pearson terbaik terdapat pada panjang gelombang 430 nm sebesar 0,94.
       
      As technology develops, measuring hemoglobin level requires a new method that can provide information quickly and accurately. The study aims to develop and test the performance of the hemoglobin level measurement using an artificial intelligence method or Fast Artificial Neural Network and provide information about suitable lamp candidates in measuring blood hemoglobin levels through an accuracy method that includes Root Mean Square Error (RMSE). It also used diagnostic test method in the form of sensitivity, specificity, accuracy of diagnosis and analysis of Number Needed to Diagnose (NND). Lamp candidates that have good Root Mean Square Error are in the wavelength range of 410 nm and 420 nm with an average absorbance of 0,598 and a standart deviation is 0,176. Meanwhile, the lamp candidate that have based on diagnostic tests are in the wavelength range 680 nm to 800 nm with a specificity value 89%, diagnostic accuracy of 95%, number needed to diagnose is 1,1 repetitions. Sensitivity value in this study has reached a maximum accuracy of 100%. Pearson value was found at a wavelength of 430 nm of 0,94
       
      URI
      http://repository.ipb.ac.id/handle/123456789/114977
      Collections
      • UT - Physics [1236]

      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