Claim Missing Document
Check
Articles

Found 2 Documents
Search

Verifikasi Tanda Tangan Online Menggunakan Algoritma Genetika Dan Support Vector Machine Pima Hani Safitri; Anditya Arifianto; Kurniawan Nur RAMADHANI
eProceedings of Engineering Vol 5, No 2 (2018): Agustus 2018
Publisher : eProceedings of Engineering

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

Abstract

Abstrak Tanda tangan merupakan salah satu alat autentifikasi yang sering digunakan. Banyak hal didunia ini yang diresmikan menggunakan tanda tangan. Setiap orang memiliki karakteristik tanda tangan yang cukup beragam. Pengenalan tanda tangan secara offline masih mungkin memiliki banyak kesalahan karena itu dikembangkan pengenalan tanda tangan secara online dengan menggunakan fitur-fitur dinamis dari tanda tangan. Pada penelitian ini, dibangun dua skema yaitu tanpa pemilihan fitur menggunakan Algoritma Genetika dan tanpa pemilihan fitur. Sistem verifikasi ini menggunakan algoritma Support Vector Machine(SVM) untuk memverifikasi tanda tangan karena SVM sudah terbukti di penelitian sebelumnya dapat menghasilkan akurasi yang baik. Penelitian ini juga ditujukan untuk menemukan fitur-fitur yang penting dalam sebuah tanda tangan dari enam kelompok fitur yang diuji. Dataset yang digunakan adalah dataset SVC2004 yang berisi tanda tangan 5 orang yang masing masing memiliki 20 tanda tangan asli dan 20 tanda tangan palsu yang ditiru oleh professional. Hasil penelitian menunjukkan Algoritma Genetika dapat menghasilkan akurasi 94.40% dan lebih baik 4.21% dibandingkan tanpa melalui pemilihan fitur. Kelompok fitur yang berpengaruh adalah kelompok fitur Geometry dan Miscellaneous karena menghasilkan akurasi yang lebih baik daripada kelompok fitur lainnya. Kata kunci : verifikasi tanda tangan, algoritma genetika, Support Vector Machine(SVM), kelompok fitur Abstract Signatures are one of the most commonly used authentication tools. Many things in this world are inaugurated using signatures. Everyone has signature characteristics that are quite diverse. The verification of offline signatures may still have many errors because it developed the verification of signatures online by using the dynamic features of the signature. In this research, two schemes are built without the feature selection using Genetic Algorithm and without feature selection. This verification system uses the Support Vector Machine (SVM) algorithm to verify the signature because SVM has been proven in previous research to produce good accuracy. The study is also intended to find important features in a signature of the six groups of features tested. The dataset used is a SVC2004 dataset containing 20 authentic signatures and 20 fake signatures imitated by professionals of 5 users. The results showed Genetic Algorithm can produce 94.40% and 4.21% better than without the selection of features. Influential feature groups are Geometry and Miscellaneous feature groups because they produce better accuracy than other feature groups. Keywords: signature verification, Genetic Algorithm, Support Vector Machine(SVM), feature group
ADAPTIVE AL-QUR’AN MEMORIZATION RECOMMENDATION SYSTEM BASED ON FUZZY LOGIC COGNITIVE MEMORY AND PROFILE MATCHING Afifah Fikriyah Dhiya'ulhaq; Muhammad Dzulfikar Fauzi; Pima Hani Safitri
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 11 No. 3 (2026): JITK Issue February 2026
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v11i3.8048

Abstract

Memorizing mutasyabihat verses in the Qur’an is particularly challenging due to similarities in structure, linguistic patterns, and semantic density that place a heavy load on short-term memory. Conventional memorization approaches do not account for individual cognitive differences when dealing with verse complexity. This study proposes an adaptive recommender system based on cognitive modeling to align verse group selection with the user’s memory profile.The system models memory capacity as a multidimensional profile using fuzzy inference derived from three quantitative indicators: continuous memory score, total correct recall, and average response time. This profile is matched with verse group feature vectors through a profile matching approach and a weighted Euclidean distance similarity measure within a Multi-Attribute Decision Making (MADM) framework. Four verse characteristics are considered: thematic (35%), semantic (25%), linguistic (25%), and pattern (15%).An adaptive calibration phase combines 20% of the initial cognitive profile with 80% of actual memorization performance, reflecting the dominance of behavioral evidence over initial assessment. System evaluation employs the Top-N Accuracy method commonly used in recommender systems.Testing with 29 participants resulted in a Top-3 success rate of 66% and an overall Top-N accuracy of 62.07%. These results indicate that cognitive profile–based multidimensional similarity can adaptively match verse complexity to individual memory capacity. This study demonstrates that fuzzy cognitive modeling and profile matching can be effectively implemented in adaptive personalized learning systems to optimize memorization of mutasyabihat verses