Jurnal Sistem Komputer
Not a member yet
    108 research outputs found

    Supervised Classification Karakter Morfologi Tanaman Keladi Tikus (Typhonium Flagelliforme) Menggunakan Database Management System

    Full text link
    Tanaman Keladi Tikus memiliki potensi medis tinggi dan bermanfaat dalam penyembuhan berbagai penyakit, seperti kanker payudara, kanker rahim dan leukemia. Tanaman keladi tikus memiliki keragaman genetik rendah karena pada umumnya tanaman ini diperbanyak melalui pemisahan bonggol secara vegetatif. Salah satu metode peningkatan keragaman genetik antara lain mutasi iradiasi sinar gamma. Uji coba peningkatan keragaman genetik ini menghasilkan data karakter morfologi dari tiap klon tanaman Keladi Tikus. Untuk menemukan pola dari data karakteristik morfologi tersebut, maka perlu dilakukan klasifikasi berdasarkan tingkat kesamaan dari data-data klon tersebut. Klasifikasi sebagai salah satu teknik data mining yang terukur, dapat dipercaya dan memenuhi suatu standar yang telah disepakati. CRISP-DM adalah standarisasi data mining yang digunakan pada penelitian ini. Untuk mengembangkan aplikasi klasifikasi data Mining tersebut digunakan bahasa pemrograman PHP dan Database Management System yaitu MySQ.. Berdasarkan penelitian dan setelah dilakukan pengujian, maka didapat perangkat lunak  yang dibuat dapat digunakan untuk melakukan perhitungan tingkat similaritas dan melakukan klasifikasi pada dataset morfologi tanaman Kelati Tikus. Tanaman Keladi Tikus memiliki potensi medis tinggi dan bermanfaat dalam penyembuhan berbagai penyakit, seperti kanker payudara, kanker rahim dan leukemia. Tanaman keladi tikus memiliki keragaman genetik rendah karena pada umumnya tanaman ini diperbanyak melalui pemisahan bonggol secara vegetatif. Salah satu metode peningkatan keragaman genetik antara lain mutasi iradiasi sinar gamma. Uji coba peningkatan keragaman genetik ini menghasilkan data karakter morfologi dari tiap klon tanaman Keladi Tikus. Untuk menemukan pola dari data karakteristik morfologi tersebut, maka perlu dilakukan klasifikasi berdasarkan tingkat kesamaan dari data-data klon tersebut. Klasifikasi sebagai salah satu teknik data mining yang terukur, dapat dipercaya dan memenuhi suatu standar yang telah disepakati. CRISP-DM adalah standarisasi data mining yang digunakan pada penelitian ini. Untuk mengembangkan aplikasi klasifikasi data Mining tersebut digunakan bahasa pemrograman PHP dan Database Management System yaitu MySQ.. Berdasarkan penelitian dan setelah dilakukan pengujian, maka didapat perangkat lunak  yang dibuat dapat digunakan untuk melakukan perhitungan tingkat similaritas dan melakukan klasifikasi pada dataset morfologi tanaman Kelati Tikus

    Ekualisasi Histogram untuk Peningkatan Kualitas Citra Telur Ayam secara Otomatis

    Full text link
    Citra digital yang diperoleh dari sistem akusisi yang berupa telepon pintar (smartphone) memiliki kualitas yang rendah. Selain kualitas, ukuran penyimpanan yang besar, citra yang diperoleh memiliki banyak noise. Begitu pula citra digital telur ayam yang digunakan dalam penelitian ini. Sehingga pra-pengolahan merupakan pilihan yang tepat untuk mengatasi kekurangan tersebut sebelum citra digital diolah lebih lanjut. Oleh karena itu perlu dikembangkan penelitian awal untuk meningkatkan kualitas citra telur ayam secara otomatis. Metode pra-pengolahan yang digunakan dalam penelitian ini diantaranya pengubahan jenis citra, ukuran citra, pengaturan kontras otomatis, cerah, filter median 3D, filter sharpen, serta ekualisasi histogram. Dari berbagai metode pra-pengolahan yang digunakan, ekualisasi histogram merupakan metode yang paling tepat untuk meningkatkan kualitas citra secara otomatis. Kata-kata kunci: citra telur ayam, pengaturan cerah, kontras, filter median, filter gaussian, ekualisasi histogra

    Editorial

    No full text

    Forecasting Sebagai Decision Support Systems Aplikasi dan Penerapannya Untuk Mendukung Proses Pengambilan Keputusan.

    Full text link
    Di dalam suatu perusahaan, pasti ada suatu kegiatan untuk mengetahui apa yang terjadi di masa mendatang dengan menggunakan data dari masa lampau dan sekarang. Forecasting juga adalah cara yang paling efektif dan efisien didalam lingkungan perusahaan untuk memprediksi dan membaca kondisi perusahaan saat ini dan memprediksi berdasar kondisi perusahaan saat ini. Sebagai contoh untuk mengetahui stok barang yang terdapat di gudang dan berapa banyak stok yang akan dijual untuk mendapatkan hasil penjualan yang optimal. Forecasting dapat diimplementasikan dengan bantuan teknologi informasi semisal datawarehouse, decision support system, data mining, machine learning dan teknologi komputasi inteligent lainnya, dengan tujuan untuk menggunakan data saat ini untuk kebutuhan prediksi kemungkinan-kemungkinan bisnis ke depan dalam rangka mendukung proses pengambilan keputusan. Forecasting dapat diimplementasikan dengan berbagai macam formula seperti Moving Average, Weighted Moving Average, Exponential smoothing, Mean Absolute Deviation dan Trend Moment. Penggunaan forecasting diimplementasikan pada berbagai macam ragam bisnis dalam mendukung proses-proses pengambilan keputusan guna meningkatkan profit perusahaan dengan memprediksi kemungkinan-kemungkinan yang akan terjadi berdasar kondisi perusahaan saat ini

    PERBANDINGAN PORTABILITY, REUSABILITY, DAN INTEROPERABILITY PADA E-COMMERCE BERBASIS OPEN SOURCE

    Full text link
    This paper will focus on comparison of portability, reusability, and interoperability values on open source-based e-commerce. The aim of comparing these three values is to find out which e-commerce has the best portability, reusability, and interoperability values. E-commerce software that will be tested are Magento 2.0, OpenCart 2.3.0.2, and WooCommerce 3.07. It has been chosen because this software are included in “The Top 10 Open Source e-Commerce Platforms” by CMS Critic website. Portability and reusability assessment is based on modularity, self-descriptive, and simplicity subfactor. The result obtained which e-commerce has the best value of the three factors tested is OpenCart with the best scores in the factor of portability and interoperability

    PENGEMBANGAN LEARNING CHARACTERISTIC RULE PADA ALGORITMA DATA MINING ATTRIBUTE ORIENTED INDUCTION

    No full text
    This paper shows the improvement of current characteristic rule learning in Attribute Oriented Induction (AOI) data mining technique. The proposed algorithm was applied with improvement upon current algorithm with 3 steps where the first step is elimination for checking condition if there is no higher level concept in concept hierarchy for attribute. The second step is elimination of attribute removal if fulfill for checking condition if there is no higher level concept. The third step is elimination of attributes in input dataset which no higher level concept in concept hierarchy. The development of these data mining algorithm applied Knowledge Data Discovery (KDD) methodology which consist 7 steps. Current and proposed AOI characteristic rule learning were implemented with server programming such as PHP Hypertext Preprocessor (PHP) and using 4 input datasets such as adult, breast cancer, census and IPUMS from University of California, Irvine (UCI) machine learning repository. The experiments showed that proposed AOI characteristic rule are better than current AOI characteristic rule, where experiments upon adult, breast cancer, census, IPUMS datasets have average 11, 3.8, 7.2, 7.2 respectively times better performance. The experiments were carried on AMD A10-7300(1.90 GHz) processor with 8.00 GB RA

    PENDEKATAN MODEL ANALITIS UNTUK BROADCAST PADA JARINGAN VANET

    No full text
    The broadcast storm problem in VANETs can be addressed by the use of single-hop and/or two-hop information in VANET’s broadcast decision. Most studies had been obtained from experiment and only few of them were from analytical analysis. This study attempts to approach analytically the one-hop information based broadcast. A combination of multiple broadcast schemes can also be analytically derived from the individual analysis. However, one must take a great care of using both speed and vehicular density at once, as analytically, the speed is linearly related to the vehicular density

    Rancang Bangun Robot Pengering Lantai Otomatis Menggunakan Metode Fuzzy

    Full text link
    The purpose of this research is to design and build a robot to dryer floor with automatic and moving regulary based on set of poin already control until can move like zig-zag. The robot is consist of mikrokontroler, motor shield as like driver motor, 2 sensor of ultrasonic, and motor of mop to dryer the floor. To control the movement use fuzzy logic with segeno method. Input from fuzzy logic and there are two kind of fuzzy logic, first is “error” and the second is “ ∆ error”. It’s from sensor of ultrasonic, after procure of data so the mikrokontroler will process it, and then the output it’s like value of PWM in order to moves and organize DC motor in order to be able to move straight, turn right, and turn left. After done testing and analysis, the level of success from motor of mop to moves with automatic as big as 80% because of effect the extent of the liquid found

    Perancangan Perangkat Elektronik Media Pembelajaran Iqra dalam Kode Braille

    No full text
    Iqra Learning is the first step in studying al-Qur’an, because al-Qur’an is a way of life for Muslims, no exception blind people. Limitations of learning device of al-Qur’an for the blind becomes an obstacle for the blind to learn Qur'an. This research describes the design of electronic learning device of Iqra Braille for blind people. This system consists of a computer that serves as an interface to manage Iqra braille to be read by the blind people, the mikrokontroler ATMega328P-PU which serves as a data processor of a computing device that can be translated in the braille code, and Braille Display devices which serves to show Braille codes from the data Iqra. Communication between computer and mikrokontroler used Bluetooth media. The results show that the system that has been made to run well. Braille Iqra data which entered by teachers can be displayed on a Braille Display

    PENGEMBANGAN SISTEM PENJADWALAN KULIAH MENGGUNAKAN ALGORITMA STEEPEST ASCENT HILL CLIMBING

    Full text link
    University of Technology Yogyakarta is a private university in Yogyakarta, it has several purposes, one of them is utilizing the maximum potential of technology to improve the effectiveness and efficiency of learning and dissemination of science and technology. One of the factors that can improve academic services are scheduling courses. Scheduling proses isn’t easy because they have to consider the possibility in scheduling, include subjects, times, lecturers, and lecture halls. Now, subject scheduling is still using Ms. Excel, the process is to input lecturer’s name one by one, to teach to the prescribed schedule and also to check whether the data is conflicting or not, so it takes long time. Therefore, we need a system that is able to perform scheduling more quickly, effectively and optimally. Subject scheduling system can be done by using the optimization system. For the case of optimization can be done using the steepest ascent hill climbing algorithm. Steepest ascent hill climbing algorithm is a search algorithm (heuristic), it is able to solve the problems of optimization with estimates to be produced in accordance with the desired criteria or rules. Subject scheduling process produces a schedule that takes less time compared to a system that is currently running. Although it is able to minimize the level of clashing schedules, its application needs to be re-checked on the level of conflicting schedules

    68

    full texts

    108

    metadata records
    Updated in last 30 days.
    Jurnal Sistem Komputer
    Access Repository Dashboard
    Do you manage Open Research Online? Become a CORE Member to access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard! 👇