cover
Contact Name
Phie Chyan
Contact Email
chyan_id@yahoo.com
Phone
+62411871038
Journal Mail Official
tematika@fti.uajm.ac.id
Editorial Address
Fakultas Teknologi Informasi Universitas Atma Jaya Makassar Jl. Tanjung Alang No. 23 Makassar 90134
Location
Kota makassar,
Sulawesi selatan
INDONESIA
TEMATIKA: Jurnal Penelitian Teknik Informatika dan Sistem Informasi
ISSN : 23033878     EISSN : 23388641     DOI : -
Core Subject : Science,
TEMATIKA (ISSN: 2303-3878, e-ISSN: 2338-8641) is an interdisciplinary journal of original research and writing in the wide areas of informatics and Information Systems.
Arjuna Subject : -
Articles 5 Documents
Search results for , issue "Vol 5, No 1 (2017)" : 5 Documents clear
Analisa Perbandingan Metode Mahalanobis Distance Dan Euclidean Distance Pada Sistem Pengenalan Wajah Nasir, Arnold
TEMATIKA, Journal of Informatics and Information Systems Vol 5, No 1 (2017)
Publisher : Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar

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

Abstract

Dalam kurun waktu 20 tahun terakhir teknologi dibidang pengenalan citra mengalami peningkatan yang signfikan. Berbagai metode pencocokan kedekatan citra seperti Euclidean distance merupakan salah satu metode yang paling umum digunakan pada sebuah sistem pengenalan wajah. Akan tetapi metode tersebut memiliki beberapa kelemahan, seperti hasil pencocokan yang kurang akurat serta proses pencocokan data dengan dataset yang membutuhkan waktu yang lama. Guna mengatasi masalah tersebut maka penelitian ini mencoba untuk menerapkan metode Mahalanobis Distance terhadap sistem pengenalan wajah. Kegiatan penelitian ini berfokus untuk membandingkan tingkat akurasi dan lamanya waktu yang dibutuhkan oleh kedua metode tersebut dengan dataset pengujian yang bervariasi, seperti wajah yang tertutup sebagian maupun jarak antara pengguna dengan kamera. Hasil pengujianini menunjukkan bahwa Mahalanobis Distance mampu meningkatkan keakuratan sistem untuk mengenali wajah seseorang sebesar 42%.Keywords: Sistem pengenalan wajah, Eigenface, Mahalanobis Distance, Euclidean distance, Principal Component Analysis
Sistem Otomasi Rumah Berbasis Logika Fuzzy Menggunakan Arduino Uno R3 Untuk Mengoptimalkan Penggunaan Listrik Antony, Heriyanto; Sumarta, Sean Coonery
TEMATIKA, Journal of Informatics and Information Systems Vol 5, No 1 (2017)
Publisher : Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar

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

Abstract

This research focuses on the manufacture of home automation systems to optimize the use of electricity. Home automation system has four features, namely automatic control, manual control, control based on the habits and customs control based on fuzzy logic and method Tsukamoto. Fuzzy logic Tsukamoto will calculate the temperature that should be spent by the AC, using input from sensors LM35 that are indoors and outdoors, so that the temperature of the issued AC was not too hot and too cold home automation system features 3 sensors which PIR sensor, sensor LM35 and LDR sensor that will be used as input data on the system. Home automation system will control electrical equipment, namely air conditioning and lighting optimally.Keywords: Arduino Uno R3, Controlling, Home Automation, Fuzzy Logic  
Analisa Penerapan Model Algoritma Fuzzy Evolusi (Studi Kasus: Penentuan Menu Makanan Diabetes Melitus) Yosry, Farlin; Lisangan, Erick Alfons
TEMATIKA, Journal of Informatics and Information Systems Vol 5, No 1 (2017)
Publisher : Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar

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

Abstract

Adaptive fuzzy evolutionary algorithm control genetic parameters based on population diversity to avoid premature convergence. However, population diversity isn’t guaranteed achieving optimum global solution. This research aims to model adaptive fuzzy with fitness goals and analyze influence of genetic parameters, fuzzy, crossover and mutation technique towards case study DM food menu determination that has fitness goal as calorie needs. This research results show that adaptive fuzzy with fitness goals is able to produce solution that has fitness with good degree of accuracy. Crossover relies on fuzzy and mutation while fuzzy adaptive, chromosome mutation and larger population can produce better fitness.Keywords: Adaptive fuzzy genetic algorithm, Diabetes mellitus, Food menu, Fuzzy evolutionary, Xu model
Perancangan Model Sistem Penelusuran Dwelling Time Terminal Peti Kemas Makassar PT. Pelabuhan Indonesia IV (PERSERO) Fadli, Andi Muhammad; Syarif, Adi Chandra
TEMATIKA, Journal of Informatics and Information Systems Vol 5, No 1 (2017)
Publisher : Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar

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

Abstract

This research are focused on designing systems that can perform data collection and the search report container.PT Pelabuhan Indonesa IV (Persero) Container Terminal Unit is a service company that is engaged in loading and unloading activities include stevedoring, cargodoring, and receiving / delivery.One of the causes of his old dwelling time at PT Pelabuhan Indonesa IV (Persero) Unit Container Terminal is inaccurate planning laying containers. This research uses a method of designing Rapid Application Development (RAD). Result of the research is a model system that can provide transparent information on the placement of the container in order to tracking the dwelling time.Keywords: container, dwelling time, PT Pelabuhan Indonesa IV (Persero), RAD, TPM.
Analisa Perbandingan Algoritma Pelatihan Propagasi Balik Dan Algoritma Pelatihan Levenberg-Marquardt (Studi Kasus: Prediksi Cuaca Kota Makassar) Lisye, Lisye; Bara'langi, Stefany Yunita
TEMATIKA, Journal of Informatics and Information Systems Vol 5, No 1 (2017)
Publisher : Fakultas Teknologi Informasi, Universitas Atma Jaya Makassar

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

Abstract

Artificial Neural Network can solve a problem based on its experience and training. The purpose of this research is analyzing the comparison of two training that is Backpropagation Training (BP) and Levenberg-Marquardt (LM) Training to determine the speed and accuracy of each training. The case that be used is the weather prediction at Makassar City which is obtained from BMKG. The advantage of BP is the runtime execution to get SSE’s value faster than LM that has difference 410.48974 ms. The advantage of LM is can obtain the smallest SSE’s value on training process than BP, that is 0.0264.Keywords: Artificial Neural Network, Levenberg-Marquardt, weather prediction, Backpropagation

Page 1 of 1 | Total Record : 5