Siti Mariyam Shamsuddin
Universiti Teknologi Malaysia

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal Generic

Enhanced Self Organizing Map (SOM) and Particle Swarm Optimization (PSO) for Classification Shafaatunnur Hasan; Siti Mariyam Shamsuddin; Bariah binti Yusob
Generic Vol 5 No 2 (2010): Vol 5, No 2 (2010)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

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

Abstract

Hybrid technique for Self Organizing Map and Particle Swarm Optimization approach is commonly implemented in clustering area. In this paper, a hybrid approach that is based on Enhanced Self Organizing Map and Particle Swarm Optimization (ESOM/PSO) for classification is proposed. Enhanced Self Organization map which based on Kohonen network structure is to improve the quality of the data classification and labeling. New formulation of hexagonal lattice area is used for the enhancement Self Organizing Map structure. The proposed hybrid ESOM/PSO algorithm uses PSO to evolve the weights for ESOM. The weights are trained by ESOM in the first stage. In the second stage, they are optimized by PSO. In the proposed algorithm, the result is measured by using a classification accuracy and quantization error techniques.
An Integrated Formulation of Zernike Invariant for Mining Insect Images Norsharina Abu Bakar; Siti Mariyam Shamsuddin; Maslina Darus
Generic Vol 6 No 1 (2011): Vol 6, No 1 (2011)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

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

Abstract

This paper presents mathematical integration of Zernike Moments and United Moment Invariant for extracting printed insect images. These features are further mining for granular information by investigating the variance of Interclass and intra-class. The results reveal that the proposed integrated formulation yield better analysis compared to conventional Zernike moments and United Moment Invariant.
Penerapan Jaringan Syaraf Berbobot Tiga untuk Identifikasi Pembuat Tulisan Tangan Syamsuryadi Syamsuryadi; Siti Mariyam Shamsuddin
Generic Vol 8 No 2 (2013): Vol 8, No 2 (2013)
Publisher : Fakultas Ilmu Komputer, Universitas Sriwijaya

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

Abstract

Tulisan tangan seseorang dapat dijadikan perantara untuk mengetahui identitas pembuatnya. Untuk mengetahui identitas personal ini memerlukan proses pembangkitan penciri dari seseorang tersebut melalui tahap ekstraksi ciri pada setiap kata tulisan tangan seseorang. Metode ekstrasi ciri yang digunakan adalah Zernike aspect moment invariants (ZAMI) sedangkan metode pelatihan dan pengenalan menggunakan Jaringan Syaraf Bobot Tiga (JSBT). Hasil ekstraksi ciri dari setiap tulisan tangan seorang dilakukan pelatihan menggunakan Prinsip Kontinuitas Homogen (PKH) sebagai dasar pengetahuan awal terhadap sampel tersebut. Tujuan artikel ini adalah menentukan kepemilikan tulisan tangan yang sah berdasarkan teks bebas menggunakan JSBT. Hasil eksperimen memperlihatkan bahwa kinerja model yang digunakan mencapai 98% dengan menggunakan berbagai variasi sampel uji dan latih.