Claim Missing Document
Check
Articles

Found 15 Documents
Search

Classifying Gender Based on Face Images Using Vision Transformer Tahyudin, Ganjar Gingin; Sulistiyo, Mahmud Dwi; Arzaki, Muhammad; Rachmawati, Ema
JOIV : International Journal on Informatics Visualization Vol 8, No 1 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.1.1923

Abstract

Due to various factors that cause visual alterations in the collected facial images, gender classification based on image processing continues to be a performance challenge for classifier models. The Vision Transformer model is used in this study to suggest a technique for identifying a person’s gender from their face images. This study investigates how well a facial image-based model can distinguish between male and female genders. It also investigates the rarely discussed performance on the variation and complexity of data caused by differences in racial and age groups. We trained on the AFAD dataset and then carried out same-dataset and cross-dataset evaluations, the latter of which considers the UTKFace dataset.  From the experiments and analysis in the same-dataset evaluation, the highest validation accuracy of  happens for the image of size  pixels with eight patches. In comparison, the highest testing accuracy of  occurs for the image of size  pixels with  patches. Moreover, the experiments and analysis in the cross-dataset evaluation show that the model works optimally for the image size  pixels with  patches, with the value of the model’s accuracy, precision, recall, and F1-score being , , , and , respectively. Furthermore, the misclassification analysis shows that the model works optimally in classifying the gender of people between 21-70 years old. The findings of this study can serve as a baseline for conducting further analysis on the effectiveness of gender classifier models considering various physical factors.
Note on Algorithmic Investigations of Juosan Puzzles Ammar, Muhammad Tsaqif; Arzaki, Muhammad; Wulandari, Gia Septiana
Jurnal Ilmu Komputer dan Informasi Vol. 17 No. 1 (2024): Jurnal Ilmu Komputer dan Informasi (Journal of Computer Science and Informatio
Publisher : Faculty of Computer Science - Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jiki.v17i1.1184

Abstract

We investigate several algorithmic and mathematical aspects of the Juosan puzzle—a one-player pencil-and- paper puzzle introduced in 2014 and proven NP-complete in 2018. We introduce an optimized backtracking technique for solving this puzzle by considering some invalid subgrid configurations and show that this algorithm can solve an arbitrary Juosan instance of size m × n in O(2mn) time. A C++ implementation of this algorithm successfully found the solution to all Juosan instances with no more than 300 cells in less than 15 seconds. We also discuss the special cases of Juosan puzzles of size m × n where either m or n is less than 3. We show that these types of puzzles are solvable in linear time in terms of the puzzle size and establish the upper bound for the number of solutions to the Juosan puzzle of size 1 × n. Finally, we prove the tractability of arbitrary m × n Juosan puzzles whose all territories do not have constraint numbers.
Secure and Space Efficient Accounts Storage System Using Three-Dimensional Bloom Filter Muhammad Arzaki; Raissa Henardianti Hanifa; Farah Afianti
(IJCSAM) International Journal of Computing Science and Applied Mathematics Vol. 9 No. 1 (2023)
Publisher : LPPM Institut Teknologi Sepuluh Nopember

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

Abstract

This paper investigates the application of a three dimensional Bloom Filter (3DBF) to accomplish a secure and efficient accounts storage system by exploiting hashes of usernames and their corresponding passwords. We conducted numerical experiments and mathematical analysis to study the efficiency level of several 3DBF schemes. Our experimental results and analysis show that the level of occupancy for 3DBF is positively correlated to the value of its false positive rate, viz., if the occupancy level increases then so does the value of the false positive rate. Moreover, we also derive a formula for determining the minimum number of bits for storing some data in a 3DBF scheme given the value of its acceptable false positive rate and its occupancy level. We infer that the product of the dimensional parameter of a 3DBF scheme is inversely proportional to the false positive rate and occupancy level used in the scheme.
Elementary Analysis of the Communication Complexity of Divide-and-Conquer Diffie-Hellman Key Agreement Protocol Muhammad Arzaki
(IJCSAM) International Journal of Computing Science and Applied Mathematics Vol. 8 No. 2 (2022)
Publisher : LPPM Institut Teknologi Sepuluh Nopember

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

Abstract

We present a rigorous elementary analysis of the communication complexity of the Divide-and-Conquer Diffie-Hellman Key Agreement Protocol (DC-DHKA). The analysis is conducted by first determining the number of transmissions in DC-DHKA and then comparing the resulting communication complexity of this protocol with other variants of Diffie-Hellman key agreement protocols that utilize regular Diffie-Hellman key, namely the ING, GDH.1, GDH.2, and GDH.3 protocols. The mathematical and numerical analyses show that the total number of bits transmitted in the DC-DHKA protocol is always fewer than those of ING, GDH.1, and GDH.2 protocols for a group of N >= 19 participants. In addition, we also prove that the total number of bits required for the entire messages’ transmissions in DC-DHKA protocol for N participants that uses the multiplicative group Fq* is log2(q) 2^(log2(N)) (log2(N) + 1) - 2.
Solving Yin-Yang Puzzles Using Exhaustive Search and Prune-and-Search Algorithms Made Indrayana Putra; Muhammad Arzaki; Gia Septiana Wulandari
(IJCSAM) International Journal of Computing Science and Applied Mathematics Vol. 8 No. 2 (2022)
Publisher : LPPM Institut Teknologi Sepuluh Nopember

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

Abstract

We investigate some algorithmic and mathematical aspects of Yin-Yang/Shiromaru-Kuromaru puzzles. Specifically, we discuss two algorithms for solving arbitrary Yin-Yang puzzles, namely the exhaustive search approach and the prune-and-search technique. We show that both algorithms have an identical asymptotic running time of O(max{mn, 2^(mn−h)}) for finding all solutions of a Yin-Yang instance with h hints of size m x n. Nevertheless, our experiments show that the practical running time of the prune-and-search technique outperforms the conventional exhaustive search approach.