IPB University Logo

SCIENTIFIC REPOSITORY

IPB University Scientific Repository collects, disseminates, and provides persistent and reliable access to the research and scholarship of faculty, staff, and students at IPB University

AI Repository
 
Building and Categories


      View Item 
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      •   IPB Repository
      • Final Assignments
      • Undergraduate Final Assignments
      • UF - School of Data Science, Mathematic and Informatics
      • UF - Computer Science
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Optimasi dan Efisiensi Komputasi Sistem Rekomendasi Makanan Berbasis Algoritma Genetika pada Server dengan Sumber Daya Terbatas

      Thumbnail
      Date
      2026
      Jenis/Type
      Skripsi
      Subtype
      Undergraduate Theses
      Author
      Rahmah, Syifa Izzatul
      Priandana, Karlisa
      Seminar, Kudang Boro
      Metadata
      Show full item record
      Abstract
      Sistem rekomendasi makanan berbasis Genetic Algorithm (GA) yang dikembangkan untuk lingkungan restoran sebelumnya diimplementasikan pada layanan cloud serverless. Ketergantungan pada infrastruktur cloud menimbulkan biaya operasional yang tinggi sehingga muncul kebutuhan untuk menjalankan sistem pada server lokal restoran yang lebih ekonomis. Namun, implementasi GA yang belum dioptimasi menyebabkan waktu respons yang tinggi pada server dengan sumber daya terbatas. Analisis terhadap kode implementasi mengidentifikasi tiga bottleneck utama, yaitu akses data Pandas yang berulang, tidak adanya mekanisme caching hasil komputasi, dan filter DataFrame berulang pada data yang tidak berubah. Penelitian ini mengoptimalkan efisiensi komputasi GA melalui tiga strategi implementasi yang menyasar ketiga bottleneck tersebut: konversi struktur data ke NumPy array, precomputation indeks kategori menu, dan mekanisme caching hasil komputasi total nutrisi. Seluruh optimasi dilakukan pada tingkat implementasi kode tanpa mengubah logika algoritma, formula perhitungan kebutuhan gizi, antarmuka pengguna, maupun layanan backend. Hasil pengujian menunjukkan rata-rata waktu respons berkurang dari 67,26 detik menjadi 0,939 detik. Sebaran nilai fitness pada 10 paket menu rekomendasi pada kedua versi berada pada rentang yang sebanding, mengindikasikan kualitas rekomendasi tidak menurun. Dengan demikian, sistem rekomendasi makanan berbasis GA dapat dijalankan pada server lokal restoran.
       
      A food recommendation system based on Genetic Algorithm (GA) developed for restaurant environments were previously implemented on cloud serverless services. Dependence on cloud infrastructure resulted in high operational costs, creating a need to run the system on more economical local restaurant servers. However, the unoptimized GA implementation caused high response times on servers with limited resources. Analysis of the implementation code identified three main bottlenecks: repeated Pandas data access, absence of a caching mechanism for computation results, and repeated DataFrame filtering on unchanged data. This research optimizes GA computational efficiency through three implementation strategies targeting these bottlenecks: converting data structures to NumPy arrays, precomputing menu category indices, and caching total nutrition computation results. All optimizations were performed at the code implementation level without modifying the algorithm logic, nutritional requirement calculation formulas, user interface, or backend services. Testing results show that the average response time decreased from 67.26 seconds to 0.939 seconds. The fitness value distributions across the 10 recommended menu packages in both versions fall within comparable ranges, indicating that recommendation quality did not decline. Thus, the GA-based food recommendation system can be operated on local restaurant servers.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/178655
      Collections
      • UF - Computer Science [180]

      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