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.

      Inferensi Hasil Karakterisasi UV-Vis Kadar Hemoglobin Darah Manusia Menggunakan Artificial Neural Network (ANN)

      Thumbnail
      View/Open
      Cover (607.2Kb)
      Fullteks (2.637Mb)
      Lampiran (1.257Mb)
      Date
      2022
      Author
      Meilani, Nida Mustika
      Alatas, Husin
      Irzaman
      Metadata
      Show full item record
      Abstract
      Pengukuran kadar hemoglobin darah sampai saat ini kebanyakan masih menggunakan metode invasif tetapi sudah banyak peneliti yang mengembangkan pengukuran secara noninvasif. Dari kedua metode ini pengukuran kadar Hb secara noninvasif dianggap lebih akurat, data lebih cepat diperoleh, serta data yang diperoleh kontinyu. Sehingga penelitian ini bertujuan menguji metode Artificial Neural Network (ANN) untuk menduga kadar hemoglobin darah tanpa menggunakan reagen serta menguji performa metode pendekatan pola dengan variabel perhitungan akurasi berupa Root Mean Square Error (RMSE), sensitivitas, spesifisitas, diagnosis akurasi, Number Needed to Diagnose (NND), serta menentukan korelasi antara serapan panjang gelombang kadar hemoglobin darah dengan akurasi pendugaan. Hasil penelitian ini diperoleh kandidat panjang gelombang dengan rentang 300 nm-500 nm dan nilai akurasinya mencapai 90%. Sedangkan untuk nilai pearson terbaik terdapat pada panjang gelombang 590 nm sebesar 0,52
       
      The measurement of blood hemoglobin levels today is mostly using invasive methods, but many researchers have developed non-invasive measurements. From these two methods, non-invasive measurement of Hb levels is considered more accurate, the data obtained faster and continuously. With that result this study aim to test method Artificial Neural Network (ANN) to estimate blood hemoglobin levels without using reagents and to test the performance of the pattern approach method with the calculation variables of accuracy such as Root Mean Square Error (RMSE), sensitivity, specificity, diagnosis accuracy, Number Needed to Diagnose (NND), and to determine correlation between absorption wavelength blood hemoglobin level with estimation accuracy. From this research obtained the result that the percentage of candidates with wavelengths a range of 300 nm-500 nm and its accuracy value can reach until 90%. While for the best Pearson value is found at a wavelength 590 nm of 0.52.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/110771
      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