Claim Missing Document
Check
Articles

Found 2 Documents
Search

Internet of Things Platform for Manage Multiple Message Queuing Telemetry Transport Broker Server Wardana, Aulia Arif; Rakhmatsyah, Andrian; Minarno, Agus Eko; Anbiya, Dhika Rizki
Kinetik: Game Technology, Information System, Computer Network, Computing, Electronics, and Control Vol 4, No 3, August 2019
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (817.353 KB) | DOI: 10.22219/kinetik.v4i3.841

Abstract

This study proposed the Internet of Things (IoT) monitoring platform model to manage multiple Message Queuing Telemetry Transport (MQTT) broker server. The Broker is a part of the MQTT protocol system to deliver the message from publisher to subscriber. The single MQTT protocol that setup in a server just have one broker system. However, many users used more than one broker to develop their system. One of the problems with the user that use more than one MQTT broker to develop their system is no recording system that helps users to record configurations from multi brokers and connected devices. This can cause to slow the deployment process of the device because the configuration of the device and broker not properly managed. The platform built is expected to solve the problem. This proposed platform can manage multiple MQTT broker server and device configuration from different product or vendor. The platform also can manage the topic that connects to a registered broker on the platform. The other advantages of this platform are open source and can modify to a specific business process. After usability testing and response time testing, the proposed platform can manage multiple MQTT broker server, functional to use, and an average of response time from the platform page is not more than 10 seconds.
Voice Spoofing Classification Using Residual Bidirectional Long Short Term Memory Kasyidi, Fatan; Sukma, Rifaz Muhammad; Sopian, Annisa Mufidah; Anbiya, Dhika Rizki
JURNAL TEKNIK INFORMATIKA Vol. 18 No. 2: JURNAL TEKNIK INFORMATIKA
Publisher : Department of Informatics, Universitas Islam Negeri Syarif Hidayatullah

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15408/jti.v18i2.43281

Abstract

Voice spoofing attacks are a major security concern for speech-based biometric systems. Detection and classification of spoofed voice are essential steps for preventing unauthorized accesses. This study proposes a novel approach to voice spoofing classification using a Residual Bidirectional Long Short Term Memory (R-BLSTM) network. The goal is to enhance the accuracy and robustness of voice spoofing detection using the power of deep learning and residual connections. The current proposed approach based on bidirectional LSTM with residual connections is designed to capture long-range dependencies and latent characteristics of speech signals. Experimental evidence that the R-BLSTM model is superior to classic ML techniques is also demonstrated by observing an accuracy of 95.6% on the ASVspoof 2019 collection. The designed system can be further utilized for enriching the security of speech-based biometrics modalities and making anti-voice spoofing attacks ineffective.