Claim Missing Document
Check
Articles

Found 2 Documents
Search

Optimization in Time and Score using IID Algorithm for K-Modes Clustering Yulianti, Farah; Sen, Tjong Wan
Building of Informatics, Technology and Science (BITS) Vol 4 No 4 (2023): March 2023
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v4i4.2791

Abstract

Nowadays, there are numerous methods for analyzing data, one of which is cluster analysis. Because most practical data in today's analysis contains categorical attributes, categorical data clustering has recently received a lot of attention. To cluster categorical data, unsupervised machine learning techniques, which used frequency-based method, such as K-Mode’s clustering are used. The K-Modes algorithm takes advantage of the differences between the data points (total mis-matches or dissimilarities). The lower the dissimilarities, the more similar the data points, and thus the better the cluster. This paper aims to improve K-Mode’s clustering performance by incorporating the intercluster and intracluster dissimilari-ty measure, or IID measure, into the K-Modes algorithm rather than just using the standard simple-matching method to increase the algorithm's accuracy and execution time. This combined algorithm improves accuracy and execution time of the K-Modes algorithm. As a result, this algorithm can be used as an alternative to better cluster categorical data.
A Hybrid Cryptographic and Biometric Framework for Real-Time Signer Verification in Digital Signing Systems Yulianti, Farah
International Journal of Social Service and Research Vol. 6 No. 4 (2026): International Journal of Social Service and Research
Publisher : Ridwan Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46799/ijssr.v6i4.1372

Abstract

Digital document signing systems are widely adopted to support legally binding electronic transactions by ensuring practicality, integrity, authenticity, and non-repudiation in electronic workflows. Current digital signing platforms rely on public key Infrastructure (PKI) combined with secondary verification mechanisms such as one-time password (OTP) delivered via email, SMS, or messaging applications to strengthen signer authentication. While OTP mechanisms provides additional account level security, they primarily verify control over a communication channel and do not guarantee the individual performing the signing action is physically present or intentional participation of the signer at the time of document execution. This limitation creates potential vulnerabilities in cases of communication channel compromise. This paper investigated the security limitations of OTP based signer verification in digital signing environments and proposes a hybrid framework that integrates cryptographic signatures, OTP verification, and gesture-based facial liveness detection. The objective is to bind the signing action to real-time human presence while preserving the integrity guarantees of PKI. The results indicate that while OTP only verification maintains high usability, it is vulnerable under simulated channel-compromise conditions. Biometric liveness detection reduces presentation attack success, and the hybrid configuration demonstrates improved resistance to unauthorized signing compared with OTP only verification. These findings suggest that integrating lightweight biometric liveness detection into digital signing workflows can enhance identity assurance without replacing existing PKI infrastructure. This paper contributes to the discussion on strengthening signer legitimacy in electronic document execution through multi-layer identity verification.