Articles

Found 36 Documents
Search

PROGRAM APLIKASI KEAMANAN CITRA DENGAN ALGORITMA DES DAN TRANSFORMASI WAVELET DISKRIT Solichin, Zaki; Bayu, Surarso; Sarwoko, Eko Adi
MATEMATIKA Vol 15, No 1 (2012): JURNAL MATEMATIKA
Publisher : MATEMATIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (344.998 KB)

Abstract

Application program security image using DES cryptographic algorithm and discrete wavelet transform is an application program that is used to secure image transmission through the Internet. Manufacturing processes are as follows, first is to make the program application for image encryption ciphertext is a program that is used to transform the initial image into the form of a compressed image using advanced discrete wavelet transform (DWT) and the Haar filter, then encrypt image transformation results with using the DES encryption algorithm specified by the encryption key, the encrypted form of information in the form of ciphertext. The second process is the process for making an application program to restore the initial image into the form ciphertext, the ciphertext decrypt the encrypted image and the particular key (the key with encryption) using DES decryption algorithm, the decrypted image, then decrypted form of the image is brought back into form initial image using inverse discrete wavelet transformation (IDWT) and reconstruction program.
IMPLEMENTASI DAN STUDI PERBANDINGAN STEGANOGRAFI PADA FILE AUDIO WAVE MENGGUNAKAN TEKNIK LOW-BIT ENCODING DENGAN TEKNIK END OF FILE Kurniawan, Isa; Sarwoko, Eko Adi; Riyanto, Djalal Er
Journal of Informatics and Technology Vol 2, No 3 (2013): Wisuda Agustus 2013
Publisher : Jurusan Ilmu Komputer / Informatika, FMIPA UNDIP, Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (245.125 KB)

Abstract

Menjaga keamanan informasi/data yang bersifat pribadi/rahasia dari pihak yang tidak berkepentingan terhadap data tersebut dapat dilakukan dengan berbagai cara, diantaranya dengan steganografi. Steganografi adalah ilmu yang menyembunyikan data di dalam media penampung sehingga keberadaan data tersebut tidak dapat diketahui. Untuk penerapannya dapat digunakan Teknik Low-Bit Encoding dan Teknik End Of File. Pada tugas akhir ini diimplementasikan steganografi menggunakan kedua teknik tersebut dengan file audio WAV sebagai media penampung dan data yang disembunyikan berupa sebuah file. Di dalam implementasi diperlukan juga data lainnya untuk disisipkan, yaitu mark (5 byte), nama file (32 byte), ekstensi file (4 byte), panjang file (4 byte), dan MD5Password (32 byte). Hasil perbandingan yang diperoleh, ukuran data (dalam byte) yang dapat disisipkan menggunakan Teknik Low-Bit Encoding bergantung pada file WAV (tidak dapat melebihi jumlah sampel audio file WAV yang telah dibagi delapan), sedangkan untuk Teknik End Of File ukuran data yang disisipkan dapat melebihi ukuran file WAV. Untuk ukuran file WAV setelah disisipkan data pada Teknik Low-Bit Encoding tidak mengalami perubahan, sedangkan untuk Teknik End Of File ukuran file WAV mengalami perubahan, yaitu bertambah dengan ukuran data
AKURASI MODEL PREDIKSI METODE BACKPROPAGATION MENGGUNAKAN KOMBINASI HIDDEN NEURON DENGAN ALPHA Widodo, Aris Puji; Suhartono, Suhartono; Sarwoko, Eko Adi; Firdaus, Zulfia
MATEMATIKA Vol 20, No 2 (2017): JURNAL MATEMATIKA
Publisher : MATEMATIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (726.685 KB)

Abstract

Permasalahan yang banyak terjadi pada Perusahaan Daerah Air Minum (PDAM) adalah mengenai ketersediaan produksi air bersih untuk dapat memenuhi kebutuhan pelanggan secara baik. Permasalahan ini terjadi diantaranya diakibatkan dengan adanya peningkatan jumlah pelanggan yang mengakibatkan permintaan akan air bersih juga  meningkat, dan faktor kehilangan air, sehingga pendistribusian air tidak berjalan dengan baik. Oleh karena itu diperlukan sebuah kajian sebagai pertimbangan untuk memberikan solusi mengenai prediksi produksi air bersih di PDAM. Studi kasus yang digunakan pada penelitian adalah PDAM Purwa Tirta Dharma Kabupaten Grobogan. Penelitian ini menggunakan metode Jaringan Syaraf Tiruan Backpropagation. Data PDAM yang digunakan adalah  meliputi data faktor-faktor yang mempengaruhi pada produksi air bersih, diantaranya jumlah pelanggan, jumlah air terjual, jumlah kehilangan air dan jumlah debit sumber air. Penelitian ini menggunakan data laporan bulanan 5 tahun terakhir (Januari 2011 s/d Desember 2015). Data yang digunakan dibagi menjadi 2, yaitu 70% untuk pelatihan dan 30% untuk pengujian. Jaringan terbaik diambil dari nilai Mean Square Error (MSE) pelatihan dan pengujian yang terkecil. Eksperimen yang dilakukan pada penelitian ini menggunakan scenario dengan cara melakukan kombinasi antara hidden neuron dengan alpha. Hasil eksperimen yang telah dilakukan, maka diperoleh nilai MSE pelatihan rata-rata sebesar 0,009538, MSE pengujian rata-rata sebesar 0,050373, dan nilai akurasinya sebesar 95,93%.
PEMBANGUNAN SISTEM INFORMASI ALUMNI BERBASIS WEB PADA PROGRAM STUDI TEKNIK INFORMATIKA UNIVERSITAS DIPONEGORO Binarso, Yusi Ardi; Sarwoko, Eko Adi; Bahtiar, Nurdin
Journal of Informatics and Technology Volume 1, Nomor 1, Tahun 2012
Publisher : Jurusan Ilmu Komputer / Informatika, FMIPA UNDIP, Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (610.976 KB)

Abstract

Informatics Engineering Major of Diponegoro University in Faculty of Sains and Math is a course that have graduated many students who have competency at information technology. However, the communicator unavailability between alumnus, make other alumnus information obtaining or information sharing, such as job vacancies, difficult. With the utilization of internet technology, a Web-Based Alumnus Information System can be used as a communicator between the alumnus and make information distribution become quickly and easily. The Web-Based Alumnus Information System at Informatics Engineering Major of Diponegoro University was built using Waterfall model, PHP as programming language, and MySQL as database management system. The Web-Based Alumnus Information System can help the Informatics Engineering Program on alumnus data management, report making, and facilitate the alumnus to obtain information about other alumnus, news about campus, job vacancies, and scholarship.
ALGORITMA BACK PROPAGATION NEURAL NETWORK UNTUK PENGENALAN POLA KARAKTER HURUF JAWA Nurmila, Nazla; Sugiharto, Aris; Sarwoko, Eko Adi
JURNAL MASYARAKAT INFORMATIKA Vol 1, No 1 (2010): Jurnal Masyarakat Informatika
Publisher : Jurusan Ilmu Komputer/Informatika UNDIP

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (385.588 KB) | DOI: 10.14710/jmasif.1.1.

Abstract

Back Propagation Neural Network (BPNN) is a type of algorithm in Neural Network that can be use for Javanese alphabets character recognition. Matlab 7.1 has been used as a software to support the program. The main purpose of this research is order to find out BPNN?s training characteristic from each samples. On the other hand, this research also gives BPNN?s accurancy value in Javanese alphabets character recognition. The result of research shows that each part of the samples having different BPNN?s characteristic based on the best training.   Keywords : NN, BPNN
FUZZY MODEL BASED SOLVING NONLINEAR SYSTEMS WITH CASE STUDY OF TRUCK-TRAILER SYSTEM sasongko, priyo Sidik; indriyati, Indriyati; sarwoko, Eko adi
MATEMATIKA Vol 12, No 2 (2009): JURNAL MATEMATIKA
Publisher : MATEMATIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (6.365 KB)

Abstract

 In this paper, we consider the fuzzy controller problem for nonlinear system using fuzzy models. The controller is constructed using a design model of the dynamical process to be controlled. The design model obtained from the truth model using a fuzzy modeling approach. The Takagi-Sugeno fuzzy model is adopted for fuzzy modeling of the nonlinear system. The truth model represents a detailed description of the process dynamic. The model is used in a simulation to evaluate the performance of the controller design. Stabilization of the closed-loop discrete Takagi-Sugeno systems using the well-known PDC (Paralel Distributed Compensation) technique is investigated. The design procedure we adopt is to convert the design of the controller to a Linear Matrix Inequality (LMI) problem so that the stability of the whole system can be assured.  
ANALISIS PENGARUH KARAKTERISTIK WILAYAH (KELURAHAN) TERHADAP BANYAKNYA KASUS DEMAM BERDARAH DENGUE (DBD) DI KOTA SEMARANG Rahmawati, Rita; Kartono, Kartono; Sulistyo, Robertus Heri; Noranita, Betha; Sarwoko, Eko Adi; Wardaya, Asep Yoyo
MEDIA STATISTIKA Vol 5, No 2 (2012): Media Statistika
Publisher : Department of Statistics, Faculty of Science and Mathematics, Universitas Diponegoro

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (251.452 KB) | DOI: 10.14710/medstat.5.2.87-93

Abstract

DBD still become one of the major problems of public health in Indonesia because the death rate tended sufferers to increase from year to year. Incredible happening (KLB) of DBD which was initially occurring every five years, now it?s getting often happens. In the city of Semarang, during 2009 occurring 165 times KLB in urban village, 35 times KLB in the level of community health centers and 15 times KLB at the district level. Though the number of DBD cases in 2009 from 2008 was declining, but in this year also noted that the number of deaths resulting from DBD increased to 43 people from 18 people in 2008. This research aims to analyze the characteristics of the neighborhood (whose data is always updated by BPS via PODES) that affect the number of cases of DBD (whose data is always updated by DKK) in Semarang city, by creating the best regression models using stepwise technique. Regression model analysis of results obtained best is Y = 23.029 + 0.004 X1 ? 0.074 X2 + 0.070X3, where Y is IR/10000 PDDK, that is the number of residents affected by DBD for each 10000 inhabitants, X1 is the number of residents aged 15-24 years, X2 is total area of land of rice fields and X3 is area of land for buildings and grounds around the page. Keywords: DBD, Characteristics of the Neighborhood, Regression, Stepwise
PENGENALAN POLA IRIS MATA MENGGUNAKAN METODE TEMPLATE MATCHING DENGAN LIBRARY OPENCV Afrizal, Sahid Nur; Sarwoko, Eko Adi
MATEMATIKA Vol 19, No 2 (2016): Jurnal Matematika
Publisher : MATEMATIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (314.242 KB)

Abstract

Biometrics is a technology that used on computer systems in the introduction of a person using a part of the human body. One part of the body that can be used in biometric systems are human iris, due to the nature of the iris of the eye that will not change and is unique among person with another person. One application of biometrics using human iris is on the smartphone. The system was built using OpenCV as the main library. Proposed recognition system was divided into two stages, there was iris recognition stage and iris matching stage. Recognition stage began with taking the image, and then do the pre-processing stage which consists of scaling operations to a smaller size and grayscaling, then proceed to the segmentation stage, using Canny edge detection method, circle Hough transform method for detecting circle of the iris and the pupil, and Daugman's rubber sheet models for normalization, then proceed to the feature extraction stage using Gabor Filter and Average Absolute Deviation. Matching phase was made using euclidean distance method to measure the similarity distance between two iris features. Tests carried out with 10 eye images, each of which 5 left and right eye images are derived from the research subjects. The results of this study concluded that the optimal threshold for this system was 475 with a percentage of 36% False Reject Rate, False Acceptance Rate 40%, 38% system error ratio, and the Genuine Acceptance Rate 64%.
LEARNING VECTOR QUANTIZATION PADA PENGENALAN POLA TANDATANGAN Prabowo, Anindito; Sarwoko, Eko Adi; Riyanto, Djalal Er
JURNAL SAINS DAN MATEMATIKA Volume 14 issue 4 Year 2006
Publisher : JURNAL SAINS DAN MATEMATIKA

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (675.167 KB)

Abstract

ABSTRAK---Pengenalan pola tandatangan dimaksudkan agar komputer dapat mengenali tandatangan dengan cara mengkonversi gambar, baik yang dicetak ataupun ditulis tangan ke dalam kode. Metode yang dipilih dalam pengenalan pola tandatangan ini adalah metode pembelajaran Kohonen Neural Network(Kohonen) dan Learning Vector Quantization(LVQ). Metode Kohonen mengambil bobot awal secara acak, kemudian bobot tersebut di-update hingga dapat mengklasifikasikan diri sejumlah kelas yang diinginkan. Pada metode LVQ bobot awal di-update dengan menggunakan pola yang sudah ada. Dalam penelitian ini, diberikan hasil pengamatan dan perbandingan tentang tingkat keakuratan dan waktu yang dibutuhkan dalam proses pembelajaran terhadap pola tandatangan pada metode Kohonen dan LVQ menggunakan bahasa pemrograman Microsoft Visual Basic 6.0 Enterprise Edition.Kata kunci: metode Kohonen, neural network, metode Learning Vector Quantization
Studi Analisis Pengenalan Pola Tulisan Tangan Angka Arabic (Indian) menggunakan Metode K- Nearest Neighbors dan Connected Component Labeling Akbar, Roni; Sarwoko, Eko Adi
Dinamika Rekayasa Vol 12, No 2 (2016): Dinamika Rekayasa - Agustus 2016
Publisher : Jenderal Soedirman University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20884/1.dr.2016.12.2.144

Abstract

Handwriting refers to the result of writing by hand (not typed). The writing style of people are not the same. One of the United Nations official languages, Arabic, has a numerical system known as Arabic (Indian) numeral. The identification of feature help humans to be able distinguish the patterns. The grouping patterns can be applied to the machine for recognizing object in the image. Connected component labeling is used for separating characters to be easily recognizable. K- nearest neighbors is used to find the similarity value between query image and template images are based on the nearest neighbors class. This analytical study was tested using 100 test images. The top three classification results of Arabic (Indian) handwritten recognition use k- nearest neighbors  (KNN) are 86% when k = 1, 84% when k = 3, and 83% with k = 5.