Claim Missing Document
Check
Articles

Found 20 Documents
Search

PEMBUATAN APLIKASI JARINGAN SARAF TIRUAN Amriana, Amriana
SMARTek Vol 8, No 4 (2010)
Publisher : SMARTek

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (111.121 KB)

Abstract

Jaringan saraf tiruan bisa dibayangkan seperti otak buatan. Otak buatan ini dapat berpikir seperti manusia, dan juga sepandai manusia dalam menyimpulkan sesuatu dari potongan-potongan informasi yang diterima. Komputer diusahakan agar bisa berpikir sama seperti cara berpikir manusia dengan melakukan peniruan terhadap aktivitas-aktivitas yang terjadi di dalam sebuah jaringan saraf biologis
PENDETEKSIAN KERUSAKAN PRINTER MENGGUNAKAN METODE FORWARD CHAINING Amriana, Amriana; Dodu, Albrecht Yordanus Erwin; Mas, Pebri Ramadhan
ILKOM Jurnal Ilmiah Vol 12, No 1 (2020)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Univeristas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2852.449 KB) | DOI: 10.33096/ilkom.v12i1.523.47-57

Abstract

As technology advances, almost everyone has a printer in their home as a printing aid. but not a few printers that have small or big problems. with this technological advancement, almost all people have personal smarthpones. This research aims to build a moble based system where users can solve printer problems by using applications on their smartphones based on knowledge obtained from experts created by the Forward Chaining method. This expert system can detect nine different types of printers owned by Canon manufacturers with total of 26 Problem and 38 symptomps and has an 80 % of accuracy.
Rancang Bangun Sistem Presensi Menggunakan Sidik Jari (Studi Kasus Pada Lembaga Pemasyarakatan Klas II-A Palu) Amriana, Amriana; Hendra, Andi; Bakhtiar, Arfiah
ScientiCO : Computer Science and Informatics Journal Vol 1, No 1 (2018): Scientico : April
Publisher : Fakultas Teknik, Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Dermatoglyphic has been widely applied to recognize a person's identity, because people basically have something unique or characteristic possessed only by themselves. This raises the idea of making it a unique identity. This is useful for employees presence applications, especially at Lembaga Pemasyarakatan Klas IIA Palu which is still doing manual presence. This system provides the division of labor time and wereable to detect the fingerprints of employees using a fingerprint scanner. The system was made in several stages of the input fingerprint image, binarization fingerprint image, fingerprint image quality improvement, and matching fingerprint image. Improvements to the quality of the fingerprint image consists of the surgical process of mathematical morphology opening and erosion. The detection process of the fingerprint image used euclidean distance measurement points minutiae. The test results indicate that the presence system accuracy using euclidean distance measurement could detect the fingerprint image by 89% from 20 fingerprint data with 5 times testing for each data.
Penerapan Data Mining Untuk Pengelompokan Hasil Diagnosa Penyakit Pasien Pengguna BPJS Kesehatan (Studi Kasus Pada Rsud Undata Palu) Amriana, Amriana; Joefrie, Yuri Yudhaswana; Meidji, Farah Nabila
ScientiCO : Computer Science and Informatics Journal Vol 1, No 1 (2018): Scientico : April
Publisher : Fakultas Teknik, Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This research was conducted to process medical record data in RSUD Undata of central Sulawesi province, for some BPJS Kesehatan insurance member. Medical record contain information about identity and medical history by patient  in Hospital or community health center (Puskesmas). Medical records have disease information by patients encoded according to WHO standart. The code is called ICD (International Classification of Disease) and this research use C4.5 Algorithm as Classification method to process patient medical record which then uses address attributes, gender, age and disease diagnosis (ICD-10). Of the five attributes are groupings then processed into group of age, regional and icd. The result of this studi can find patterns of disease tendency that most suffered by people in a region.
Penentuan Harga Tandan Buah Segar (TBS) Kelapa Sawit Menggunakan Metode Fuzzy Logic Amriana, Amriana; Kasim, Anita Ahmad; Maghfirat, Maghfirat
ILKOM Jurnal Ilmiah Vol 12, No 3 (2020)
Publisher : Teknik Informatika Fakultas Ilmu Komputer Univeristas Muslim Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33096/ilkom.v12i3.619.236-244

Abstract

Tujuan penelitian ini adalah membuat sistem penentuan harga Tandan Buah Segar kelapa sawit menggunakan metode Fuzzy Logic. Perkebunan kelapa sawit adalah perkebunan yang memiliki sumber daya alam yang dapat menghasilkan keuntungan besar, karena digunakan sebagai minyak goreng dan masih banyak lagi. TBS kelapa sawit terdiri dari Crude Palm Oil (CPO) yaitu minyak daging buah dan Palm Kernel (PK) yaitu inti biji sawit. Penelitian ini membuat sistem menggunakan 5 variabel input yaitu harga CPO, harga IKS, Indeks K, Rendemen CPO dan Rendemen IKS, serta satu variabel output yaitu harga TBS kelapa sawit. Sistem ini menggunakan metode Fuzzy Logic karena dalam penelitian ini terdapat suatu fuzzy yang dapat ditentukan, yaitu harga TBS kelapas sawit. Sistem ini menggunakan 100 data untuk diuji menggunakan MAPE sehingga didapatkan  nilai persentase sebesar 85.75%. Sedangkan nilai rata-rata dari selisih antara data aktual dengan data hasil fuzzy mamdani adalah sebesar 17852 dengan rata-rata persentase kesalahan dari fuzzy mamdani adalah sebesar 14.25%. Hasil dari sistem ini adalah variabel output harga TBS kelapa sawit berdasarkan 5 variabel input. Metode Fuzzy Logic Mamdani menentukan hasil dari nilai yang tidak pasti. Proses fuzzy logic dimulai dari pembentukan himpunan fuzzy, kemudian aplikasi fungsi implikasi, lalu tahap komposisi aturan, setelah itu tahap deffuzifikasi.
STUDI KOMPARASI METODE WEIGHT PRODUCT DAN SIMPLE ADDITIVE WEIGHTING DALAM SISTEM PEMILIHAN ALAT KONTRASEPSI BERBASIS WEB Pangara, Takdir S; Anshori, Yusuf; Amriana, Amriana
ScientiCO : Computer Science and Informatics Journal Vol 4, No 1 (2021): Scientico : April
Publisher : Fakultas Teknik, Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Controlling birth is closely related to the use of contraceptives for their partners. However, the problem they often face is that they struggle to choose an effective contraceptive that suits their body condition. This is not only caused by the limited methods available but also because they do not know the requirements and safety of these contraceptive methods. This study aims to implement and analyze the comparison of the Weight Product (WP) method and the Simple Additive Weighting (SAW) method in a web-based contraceptive selection decision-making system. This system can work well in determining the right contraception for a married couple. In the time testing process, the implementation of the SAW method has an average execution time of 1.8784 s while the WP method has an average execution time of 0.3340 s. Based on the research results, the WP method is slightly faster than the SAW method in carrying out the calculation process in the decision support system for the selection of contraceptives. 
PENGENALAN KARAKTER ALFANUMERIK MENGGUNAKAN METODE BACKPROPAGARATION Amriana Amriana
JURNAL ILMIAH MATEMATIKA DAN TERAPAN Vol. 7 No. 2 (2010)
Publisher : Program Studi Matematika, Universitas Tadulako

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22487/2540766X.2010.v7.i2.136

Abstract

Jaringan saraf tiruan untuk aplikasi pengenalan karakter alfanumerik terdiri dari 3 lapisan yaitu lapisan input, sebuah lapisan tersembunyi dan sebuah lapisan output. Jaringan propagasi balik akan menerima input  biner  sehingga  data  harus  diatur  sebagai  sekumpulan  angka  (vektor).  Karakter  alfanumerik diterjemahkan kedalam bentuk matriks ukuran 5 x 7 yang melambangkan pixel-pixel. Data dimasukkan dalam bentuk biner, angka 1 menunjukkan pixel berisi citra, angka 0 menunjukkan kosong. Pengujian jaringan  dilakukan  dengan  menggunakan  program  aplikasi  MATLAB  yang  akan  mengenali  karakter alfanumerik.
Implementasi Algoritma Floyd Warshall Pada Pada Pencarian Lokasi Agen Bus, Tour And Travel, Dan Rental Mobil Di Kota Palu Berbasis Android Deny Wiria Nugraha; Amriana Amriana; Asri Arif
Sains, Aplikasi, Komputasi dan Teknologi Informasi Vol 2, No 2 (2020): Sains, Aplikasi, Komputasi dan Teknologi Informasi
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jsakti.v2i2.2400

Abstract

Penelitian ini bertujuan untuk membangun sebuah sistem yang dapat memberikan informasi lokasi agen bus, tour and travel, dan rental mobil yang ada di Kota Palu, dan sekaligus memberikan petunjuk jalur terpendek dengan menggunakan Algoritma Floyd warshall berbasis Android. Algoritma Floyd warshall adalah salah satu varian dari pemrograman dinamis, yaitu suatu metode yang melakukan pemecahan masalah dengan memandang solusi  yang akan diperoleh sebagai suatu keputusan yang saling terkait, algoritma ini menghitung bobot terkecil dari semua jalur yang menghubungkan sebuah pasangan titik, dan melakukannya sekaligus untuk semua pasangan titik. Perhitungan pencarian jalur terpendek menggunakan algoritma Floyd Warshall langkah pertama menentukan jalur yang akan dilalui dan nilai bobotnya dibuat ke dalam tabel atau matriks, lakukan perhitungan periterasi sampai dengan iterasi terakhir, lakukan berulang sebanyak vertexnya, dan menentukan jalur terpendek berlaku dari hasil iterasi terakhir. Proses perhitungan algoritma Floyd Warshall di implementasikan ke dalam sistem yang telah dibuat menggunakan aplikasi Delphi 10.3 CE dengan memanfaatkan prosedur algoritma Floyd Warshall, Penelitian ini menggunakan data sebanyak 120 lokasi agen bus, tour and travel dan rental mobil di kota Palu berbasis dengan mengimplementasikan algoritma Floyd Warshall untuk mencari jalur terpendek yang diterapkan pada Delphi 10.3 CE. Pada Delphi 10.3 CE peneliti merasakan kemudahan dan lebih ringan dalam pengerjaan  algoritma Floyd Warshall untuk pencarian jalur terpendek.
Implementation of simple additive weighting (SAW) in determining nutrition in toddlers Amriana, Amriana; Ardiansyah, R; Wirdayanti, Wirdayanti; Masykur, M
Applied Engineering and Technology Vol 2, No 1 (2023): April 2023
Publisher : ASCEE

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (337.252 KB) | DOI: 10.31763/aet.v2i1.685

Abstract

The stunting or malnutrition in toddlers are the main problems facing society today[1]. Also, the fact that these young children experience lack of adequate nourishment in Indonesia is quite indisputable. Handling nutritional problems is closely related to the strategy of a nation to create healthy, intelligent and productive human resources. Efforts to improve quality human resources begin with how to manage children's growth as part of a family with good nutrition and care For this reason, this study takes part in supporting the alleviation of cases of malnutrition by using the Simple Additive Weighting (SAW) Method which is used to find the optimal alternative from a number of alternative criteria. The basic concept of SAW is to find the weighted sum of the performance ratings for each alternative across all attributes[2]. The SAW method requires a decision matrix normalization process (X) to a scale that can be compared with all alternative ratings[3]. The SAW method recognizes 2 attributes, namely the benefit criteria and the cost criteria. The method used was Simple Additive Weighting (SAW) which consists of 2 criteria, namely Height (TB) and Weight (BW) according to age for toddlers. The calculation accuracy of this application is 90% of the tested data
Optimization of Herbal Plant Classification Using Hybrid Method Particle Swarm Optimization With Support Vector Machine Amriana, Amriana; Ilham, Amil Ahmad; Achmad, Andani; Yusran, Yusran
JOIV : International Journal on Informatics Visualization Vol 9, No 1 (2025)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.9.1.2576

Abstract

The classification process applied in this study helps identify the many kinds of herbal plants. Herbal plant leaf features are used based on color, shape, and texture. Particle Swarm Optimization and Support Vector Machine (PSO-SVM) hybridization are applied in the classification process to increase classification and identification accuracy. A well-liked metaheuristic approach for solving optimization issues is Particle Swarm Optimization (PSO). Particles look around the search area for the best responses.  A particle swarm is initially initialized randomly within the search area via the PSO algorithm. Every particle's mobility is determined by both its own experience and the experiences of the other particles in the swarm. Each particle keeps track of the best solution it has ever found and the swarm's most extraordinary remedy that has so far been discovered. The Hybrid approach concurrently selects features for the SVM and optimizes its parameters. The kernel function's gamma value non-linearly maps an input space to a high-dimensional feature space. At the same time, the C parameter determines the trade-off between fitting error minimization and model complexity. The Gaussian kernel parameter is set to determine the optimal parameter value of the RBF kernel function. Feature selection solves the issue by eliminating redundant, associated, and irrelevant features. A confusion matrix is utilized in the evaluation to gauge the system's performance. The results demonstrated an improvement in accuracy, with the hybrid PSO-SVM using test data achieving an accuracy of 98% compared to the SVM method, achieving a 91% accuracy.