Articles

Found 12 Documents
Search

Klasifikasi Kematangan Buah Manggis Ekspor dan Lokal Berdasarkan Warna dan Tekstur Menggunakan Fuzzy Neural Network Whidhiasih, Retno Nugroho; Guritman, Sugi; Suprio, Prapto Tri
Jurnal Ilmu Komputer dan Agri-Informatika Vol 1, No 2 (2012)
Publisher : Departemen Ilmu Komputer IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (206.403 KB)

Abstract

Fuzzy neural network (FNN) memiliki kemampuan untuk melakukan klasifikasi terhadap suatu pola yang berada di dalam dua kelas yang tidak dapat diklasifikasi menggunakan model klasifikasi klasik neural network (NN). Penelitian ini bertujuan mengembangkan model klasifikasi buah manggis segar secara non-destruktif dengan menggunakan FNN. FNN yang dipakai menggunakan derajat keanggotaan pada neuron output sebagai target pembelajaran. Parameter input yang digunakan adalah komponen warna hasil dari pengolahan citra yang mempunyai pengaruh terhadap tahap kematangan buah manggis dan tekstur. Hasil pemodelan FNN menjadi 2 kelas target klasifikasi (ekspor dan lokal) mendapatkan model terbaik dengan fitur penduga indeks warna merah, hijau, biru, value, a*, u*, v*, dan entropi dengan 5 neuron pada lapisan tersembunyi. Perbandingan persentase akurasi model FNN dan NN ialah 90:90, dengan perbandingan kemampuan pengenalan terhadap kelas ekspor dan lokal ialah 92:100 dan 89:75.Kata kunci: fuzzy neural network, klasifikasi, manggis, non-destructive grading, pengenalan pola
Teknik Penyembunyian Data Rahasia pada Berkas Gambar Digital Menggunakan Steganografi Least Significant Bit Variable-Size Neyman, Shelvie Nidya; Lindayati, Lindayati; Guritman, Sugi
Jurnal Ilmu Komputer dan Agri-Informatika Vol 1, No 1 (2012)
Publisher : Departemen Ilmu Komputer IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (174.412 KB)

Abstract

Salah satu teknik pengamanan data dengan cara penyisipan informasi rahasia pada berkas gambar digital sebagai media penampung ialah steganografi berbasis least significant bit (LSB) dengan penambahan kemampuan penyisipan yang bersifat variable-size. Operasi teknik steganografi ini menggunakan tiga parameter, yaitu capacity evaluation untuk menentukan kapasitas maksimum LSB dari masing-masing pixel media penampung, minimum error replacement untuk memperkecil tingkat kesalahan saat penyisipan, dan improved grayscale compensation untuk memisahkan kesalahan penempelan agar tidak berdekatan pada tempat pixel bekerja. Penelitian ini bertujuan mengimplementasikan teknik tersebut untuk menyembunyikan data rahasia pada berkas gambar digital sebagai media penampung dan menghasilkan stego-image dengan kesamaan tampilan dan ukuran berkas. Berkas hasil penyisipan (stego-image) yang diperoleh diharapkan tidak menimbulkan kecurigaan pihak lawan, serta mampu memaksimumkan kapasitas penyisipan data rahasia, dengan memungkinkan penyisipan mencapai bit ke-5 dari LSB media penampung. Hasil penelitian menunjukkan bahwa stego-image yang diperoleh secara visual memiliki tampilan hampir sama dengan media penampungnya dan kapasitas penyisipannya mencapai lebih dari 50% ukuran media penampungnya. Kapasitas ini diperoleh tanpa mempertimbangkan border dan jumlah bit data pada setiap pixel minimal berjumlah empat.Kata kunci: capacity evaluation, improved grayscale compensation, least significant bit variabel-size, steganografi
OPTIMIZATION DISTANCE LEARNING COMPUTER OF NETWORK Sutanto, Imam; Wahjuni, Sri; Prianggono, Jarot; Guritman, Sugi
Computer Engineering and Applications Journal Vol 8 No 1 (2019)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (330.243 KB) | DOI: 10.18495/comengapp.v8i1.271

Abstract

Implementation Distance Learning (DL) lecture at High School of Police Science namely Sekolah Tinggi Ilmu Kepolisian (STIK-PTIK) consisted of 32 Polisi Daerah (POLDA) in lecture Distance Learning (DL) throughout Indonesia. System bandwidth management using the method of simple queue, the simple queue is lacking both in bandwidth allocation. Optimization against computer networks in improving Quality of Service (QoS) using the method Per Connection Queue (PCQ) Queue Tree with four classes to model. Scale model of a priority bandwidth specifically as a model of optimization of computer networks with an average percentage of delay of 6.01%, packet loss decreased 0.26%, jitter of 13.56% and increased throughput became of 9.5%. The research is supported by the level of satisfaction by CSI towards PJJ / DL students, the methods of customer satisfaction index with the service quality (Servqual) questionnaire as against with levels of satisfaction the use of DL student participants with the result satisfaction levels of 74%.   Keywords:         hierarchical token bucket, per connection queue, queue tree, QoS parameters.
PENGEMBANGAN SISTEM E-VOTING DENGAN PROTOKOL TWO CENTRAL FACILITIES MENGGUNAKAN FINGERPRINT SEBAGAI OTENTIKASI VOTER Sikki, Muhammad Ilyas; Guritman, Sugi; Rahmawan, Hendra
JREC (Journal of Electrical and Electronics) Vol 1, No 3 (2013): JREC (Jurnal Of Electrical and Electronics
Publisher : JREC (Journal of Electrical and Electronics)

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

Abstract

The e-voting system which developed using two central facilities protokol consist of three componentthat is voting machine as client for interaction with voter, central legitimization agency (CLA) asserver voter authentication, and central tabulating facility (CTF) as server for result recapitulationvoter vote count. Research in this thesis just focused to voter authentication process on votingmachine toward database of voter that stored in CLA with using fingerprint biometric technology.Fingerprint biometric technology used for voter registration process, voter verification process, andvoter authentication process who will doing election. Registration process for acquire voterfingerprint image database, verification process to be sure voter database can be verificated or not,and authentication process for voter authorization who can be permitted or not by system give of votein election.Key words : E-voting, voter, authentication, fingerprint
Paper-based Verification Design of Trade Business License in Indonesia Pizaini, Pizaini; Guritman, Sugi; Sukoco, Heru
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 14, No 4: December 2016
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (250.503 KB) | DOI: 10.12928/telkomnika.v14i4.2915

Abstract

The trade business license certificate (SIUP) is a paper-based license to conduct trade businesses in Indonesia issued by the government. Until today, there is no mechanism for verifying the validity of document unless to verify it manually. The current paper presents a design that allows paper-based verification of the printed trade business license. It aims to provide the verification mechanism and ensure the document validity. Our design implemented digital signature with QR Code image that placed into the document and the digital certificate issued by a certification authority (CA). The proposed scheme generated 442Bytes of data and version 14 of QR Code to scan easily by a reader device. The experimental result indicates that our scheme is easy and feasible to implement in Indonesia with guaranteed the document integrity, authentication, and nonrepudiation.
PENGEMBANGAN SISTEM E-VOTING DENGAN PROTOKOL TWO CENTRAL FACILITIES MENGGUNAKAN FINGERPRINT SEBAGAI OTENTIKASI VOTER Sikki, Muhammad Ilyas; Guritman, Sugi; Rahmawan, Hendra
Jurnal Sistem Informasi Vol 9 No 2 (2013): Jurnal Sistem Informasi (Journal of Information System)
Publisher : Faculty of Computer Science Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (497.947 KB) | DOI: 10.21609/jsi.v9i2.359

Abstract

The e-voting system which developed using two central facilities protokol consist of three component that is voting machine as client for interaction with voter, central legitimization agency (CLA) as server voter authentication, and central tabulating facility (CTF) as server for result recapitulation voter vote count. Research in this paper just focused to voter authentication process on voting machine toward database of voter that stored in CLA with using fingerprint biometric technology. Fingerprint biometric technology used for voter registration process, voter verification process, and voter authentication process who will doing election. Registration process for acquiring voter fingerprint image database, verification process to be sure voter database can be verificated or not, and authentication process for voter authorization who can be permitted or not by system give of vote in election.
DESAIN E-VOTING PILKADA KOTA BOGOR MENGGUNAKAN PROTOKOL TWO CENTRAL FACILITIES YANG DIMODIFIKASI Kusumah, Fitrah Satrya Fajar; Guritman, Sugi; Giri, Endang Purnama
KREA-TIF Vol 3, No 2 (2015)
Publisher : Department of Informatics Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (271.538 KB)

Abstract

One of Indonesian election isthe local elections for regional head thatare still using conventional election type.The conventional election type stillspend a lot of time and prone of mistakesmade by humans, including fraudscommitted by certain parties. Thisresearch is based on two centralfacilities protocol in Schneier book(1996) and a continuation of previousresearch by Sireesha and Chakchai(2005) which has developed a secureelection with two central facilitiesprotocol that implement the developmentof Central Legitimization Agency (CLA)and the Central Tabulating Facilities(CTF) to create a secure virtualelections and Wardhani (2009) whichimplement the protocol Two centralfacilities at IPB online voting. Thisresearch collaboration with the KPUBogor and Bogor Information andCommunications, for the purposes ofanalyzing and studying the variouselections policy of regional heads ofBogor. Through this study found adesign system using a protocol e-votingTwo central facilities modified.However, this design is still requirefurther research to be applicable forBogor Regional Head election.
DETEKSI DAN IDENTIFIKASI PELAKU KECURANGAN SKEMA PEMBAGIAN RAHASIA LINEAR BERBASIS SKEMA SHAMIR Nur Ahzan, Zulkaidah; Guritman, Sugi; Silalahi, Bib Paruhum
Jurnal Karya Pendidikan Matematika Vol 7, No 1 (2020): Jurnal Karya Pendidikan Matematika Volume 7 Nomor 1 Tahun 2020
Publisher : Universitas Muhammadiyah Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (288.126 KB) | DOI: 10.26714/jkpm.7.1.2020.27-41

Abstract

The method that can be used to maintain security of secret in the form of cryptographic keys is by using secret sharing scheme (SSS). This method is first proposed by Adi Shamir in 1979, where the proposed scheme is a (k, n) threshold scheme. Shamir scheme is a perfect scheme under the assumption that all shareholders present their original share. However, if there are dishonest shareholders who present faked shares then the honest shareholders get nothing but a faked secret. Secret sharing scheme based on linear scheme is a scheme that can detect and identify cheaters who submit faked shares at the secret reconstruction. Detectability of this scheme when  and identifiability when  under the assumption that all shareholders present their shares randomly. After conducting a security analysis of the proposed scheme, it is obtained that to succeed in attack with cheaters who work together to fool honest shareholders then a new polynomial g(x) such that g(1) = , g(2) = , ?, g(k - 1) =  and a new detector that has the same value as detector d are needed.
The Construction of Arithmetic Algorithms GF(5m) Generated by Cyclic Group Properties ., Ahmadi; Guritman, Sugi; Aliatiningtyas, Nur
Cakrawala: Jurnal Pendidikan Vol 6, No 2 (2011): NOVEMBER
Publisher : Faculty of Teacher Training and Education of Universitas Pancasakti Tegal

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (193.659 KB) | DOI: 10.24905/cakrawala.v6i2.185

Abstract

To construct a cryptographic algorithm, many arithmetic concepts are needed. ElGamal encryption for example, can be defined over cyclic group Zp, the usual arithmetic concepts. If the use of this arithmetic is associated with security aspect, then it requires large computational work. This thesis aims to construct arithmetic algorithm as an alternative arithmetic that can be applied to any cryptographic scheme, especially public key scheme. This algorithm is imposed from finite field GF(5m). Thus, the procedures to construct arithmetic algorithm are as follows. The first step is to choose primitive polynomial M (x)eZ5[x] of lower degree. The second step is to find primitive root M(a)=0, thus the equation M(x)=0 has a root a in GF. The resulted arithmetic algorithms are computational procedures for standard operation in GF(5m) addition, multiplication, division, invertion, and exponentiation. It can be concluded that constructed arithmetic algorithms GF(5m) are better than standard algorithms because some operations can be reduced using primitive polynomial or cyclic group properties, and using reduction of zero. Keywords: arithmetic, cyclic group, GF(5m), primitive polynomial, cryptography.
Klasifikasi Kematangan Buah Manggis Ekspor dan Lokal Berdasarkan Warna dan Tekstur Menggunakan Fuzzy Neural Network Whidhiasih, Retno Nugroho; Guritman, Sugi; Suprio, Prapto Tri
Jurnal Ilmu Komputer dan Agri-Informatika Vol 1, No 2 (2012)
Publisher : Departemen Ilmu Komputer IPB

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (206.403 KB) | DOI: 10.29244/jika.1.2.71-77

Abstract

Fuzzy neural network (FNN) memiliki kemampuan untuk melakukan klasifikasi terhadap suatu pola yang berada di dalam dua kelas yang tidak dapat diklasifikasi menggunakan model klasifikasi klasik neural network (NN). Penelitian ini bertujuan mengembangkan model klasifikasi buah manggis segar secara non-destruktif dengan menggunakan FNN. FNN yang dipakai menggunakan derajat keanggotaan pada neuron output sebagai target pembelajaran. Parameter input yang digunakan adalah komponen warna hasil dari pengolahan citra yang mempunyai pengaruh terhadap tahap kematangan buah manggis dan tekstur. Hasil pemodelan FNN menjadi 2 kelas target klasifikasi (ekspor dan lokal) mendapatkan model terbaik dengan fitur penduga indeks warna merah, hijau, biru, value, a*, u*, v*, dan entropi dengan 5 neuron pada lapisan tersembunyi. Perbandingan persentase akurasi model FNN dan NN ialah 90:90, dengan perbandingan kemampuan pengenalan terhadap kelas ekspor dan lokal ialah 92:100 dan 89:75.Kata kunci: fuzzy neural network, klasifikasi, manggis, non-destructive grading, pengenalan pola