Pengenalan citra digital merupakan bagian yang sangat penting dalam computer vision yang menerapkan pattern recognition. Pengenalan citra digital bertujuan untuk menduplikasi kemampuan manusia dalam memahami informasi citra sehingga komputer dapat mengenali objek pada citra selayaknya manusia. Salah satu metode pattern recognition adalah Extreme Learning Machine (ELM). Extreme Learning Machine merupakan jaringan syaraf tiruan feedforward dengan satu hidden layer atau lebih dikenal dengan istilah single hidden layer feedforward neural networks (SLFNs). Extreme Learning Machine untuk pengenalan objek citra digital pada Tugas Akhir ini terdiri dari 2500 node pada input layer, 1250 node pada hidden layer, dan 3 node pada output layer. Dataset dikelompokkan berdasarkan ukuran objek dalam citra. Hasil uji coba dan evaluasi model dengan data testing menghasilkan tingkat akurasi sebesar 57,33% pada citra dengan objek berukuran kecil, 81,33% pada citra dengan objek berukuran sedang, dan 74,67% pada citra dengan objek berukuran besar.
Molecular docking or ligand binding in proteins is a developing field of computing. Molecular docking can be used to find the most appropriate interaction pattern between protein receptors and ligands and become the basis for the drug discovery and design based structures. The development of efficient docking methods and algorithms will be very useful in drug discovery simulation. Firefly algorithm is one of the method that can be used for molecular docking simulations. Firefly algorithm is used to find the optimal conformation of proteins and ligands so that the binding energy of the whole system is minimized. In this research, proteinligand complexes from the Protein Data Bank (PDB) were used to test the performance of the algorithm. The results show that the firefly algorithm can be used to solve molecular docking. Then this algorithm is used to solve molecular docking of alkaloid compounds SA2014 from Cinachyrella anomala sea sponges towards cyclin D1 protein in cancer. The results show that the SA2014 ligand affinity for cyclin D1 protein was higher than doxorubicin (a type of chemotherapy drug) so that the SA2014 compound have a great potential as an anticancer.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.