Claim Missing Document
Check
Articles

Found 3 Documents
Search

Accurate, Fast and Low Computation Cost of Voice Biometrics Performance using Model of CNN Depthwise Separable Convolution and Method of Hybrid DWT-MFCC for Security System Haris Isyanto; Ibrahim, Wahyu; Samsinar, Riza
Buletin Pos dan Telekomunikasi Vol. 22 No. 1 (2024): June 2024
Publisher : Centre for Research and Development on Resources, Equipment, and Operations of Posts and I

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17933/bpostel.v22i1.393

Abstract

Identity theft, a pervasive criminal risk in the digital realm, particularly in online transactions, demands innovative security solutions. Voice biometrics, a cutting-edge technology, have been developed to ensure the protection of one's identification. This study, a significant step forward, focuses on the development of voice biometrics using deep learning, specifically CNN Depthwise Separable Convolution (DSC) and CNN Residual. The research on these two systems was conducted to determine accuracy, performance evaluation, computing load, and training process time for effectively, rapidly, and accurately verifying user voice for banking transaction security. The initial CNN residual test yielded a high validation accuracy of 98.6345%. However, the large number of CNN residual parameters resulted in a training time of 7.37 seconds, increasing the computational workload. The second CNN DSC test exhibited a high validation accuracy of 98.3542%. The CNN DSC was successful in decreasing the parameter count, resulting in a reduction of 5.12 seconds in training time. Upon analyzing the test results, it is clear that the CNN DSC has superior performance, resulting in faster training times and less memory consumption. This effectively addresses the problem of high computational costs and significantly enhances user identity security in banking transactions, a crucial aspect of modern banking.
SISTEM KEAMANAN DENGAN SENSOR PASSIVE INFRARED RECEIVER (PIR) DAN SOLENOID DOOR LOCK MENGGUNAKAN NODE MCU ESP8266 BERBASIS TELEGRAM Ibrahim, Wahyu; Pusparini, Nur Nawaningtyas; Muryono, Tupan Tri
EBID: Ekonomi Bisnis Digital Vol 2, No 2 (2024): Desember
Publisher : STMIK Widuri Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37365/ebid.v2i2.340

Abstract

Human needs for a more practical life are met by technological advances, one of which is in the health sector. This is the background of this research. By utilizing NodeMCU and Arduino Uno as microcontrollers for the IoT-based Smart Home system at the DKI Jakarta Health Office, it is hoped that the value of efficiency and security can be achieved through the implementation of an IoT-based Smart Home system. In this study, NodeMCU is used as a microcontroller in an IoT-based smart home system. Telegram Messenger is used in the design of this system as an input or notification medium. The chat input data is read out by the program for verification when the chat comes in. If verification fails, the system does not respond, and the chat input is reprogrammed. Conversely, if the lever is successful, the BOT will respond and send an input signal to the microcontroller to manage. After the microcontroller has processed the input signal, it will send an output signal (On/Off) to the relay, which will then send it to the output components (solenoid door lock, type sensor, and buzzer). take advantage of the technology that is already available by placing a Smart Home system that uses the Internet of Things. Since only those with certain access can control the home, such as viewing type sensors and unlocking doors remotely, IoT-based Smart Home systems are also secure.
Perancangan Alat Monitoring Kinerja Panel Surya Thin Film Berbasis Internet Of Things Isyanto, Haris; Ibrahim, Wahyu; Agustin, Rizky
RESISTOR (Elektronika Kendali Telekomunikasi Tenaga Listrik Komputer) Vol 7, No 2 (2024): RESISTOR (Elektronika Kendali Telekomunikasi Tenaga Listrik Komputer)
Publisher : Universitas Muhammadiyah Jakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24853/resistor.7.2.131-142

Abstract

ABSTRAKIndonesia merupakan negara yang berada tepat dengan garis khatulistiwa dengan tingkat garis radiasi matahari yang sangat tinggi dengan menyiari 10 hingga 12 jam setiap harinya. Yang mana dapat dimanfaatkan sebagai modal utama pembangkit dengan menggunakan solar cell sebagai alat yang menyerap energi matahari lalu mengubah cahaya matahari tersebut menjadi sumber Listrik. Dalam penelitian ini dirancang sistem internet of things untuk mempermudah sistem monitoring kinerja panel surya thin film 80wp. Data yang dibaca pada setiap sensor nantinya akan ditampilkan pada aplikasi blynk. Teknologi ini diharapkan dapat memudahkan para teknisi pada panel surya dan sumber Listrik lainnya sebagai sistem monitoring jarak jauh seacara realtime. Dari hasil yang didapatkan tegangan puncak pada alat ukur dan sensor sebesar 35,05 V dan 35,24 V dengan persentase eror 0,54% dan keberhasilan 99,46%, pada arus didapatkan arus puncak pada pengukuran alat ukur 2,24A dan sensor 2,26A dengan persentase eror 0,89% dan keberhasilan 99,11%, lalu pada daya didapatkan daya puncak pada pengukuran alat ukur dan sensor sebesar 78,51 W dan 79,64 W dengan persentase eror 1,44% dan keberhasilan 98,56%, pada suhu puncak pada didapatkan pengukuran alat ukur 55,72 oC dan sensor 55,81 oC dengan persentase eror 0,16% dan keberhasilan 99,84%,lalu intensitas cahaya puncak pada alat ukr 729 w/m2  , sensor 735 w/m2 dengan persentase ero 0,82% dan keberhasilan 99,18%, lalu pada efisiensi didapatkan efisisensi puncak pada pengukuran alat ukur 13,98% dan sensor 13,76%dengan persentase erornya 0,612% dan keberhasilannya 99,388% Yang mana hasil data tertinggi pada tegangan, arus, daya, suhu, intensitas cahaya, dan efisiensi terjadi pada pukul 13:00 WIB.Kata Kunci :  Panel Surya Thin Film 80 WP, Internet of ThingsABSTRACTA Indonesia is a country located right on the equator with a very high level of solar radiation with 10 to 12 hours of irradiation every day. Which can be utilized as the main capital plant by using solar cells as a tool that absorbs solar energy and then converts the sunlight into a source of electricity. ACS712 current sensor which is the amount of voltage and current generated based on the amount of light intensity read using a BH1750 sensor light intensity sensor, and DS18B20 as a temperature sensor. In this research, an internet of things system is designed to facilitate the performance monitoring system of 80wp thin film solar panels. The data read on each sensor will be displayed on the blynk application. This technology is expected to facilitate technicians on solar panels and other electricity sources as a realtime remote monitoring system. From the results obtained, the peak voltage on the measuring instrument and sensor is 35.05 V and 35.24 V with a percentage error of 0.54% and a success of 99.46%, on the current obtained peak current on measuring instrument 2.24A and sensor 2.26A with a percentage error of 0.89% and a success of 99.11%, then on the power obtained peak power on measuring instrument and sensor measurements of 78.51 W and 79.64 W with a percentage error of 1.44% and a success of 98.56%, at peak temperature obtained measuring instrument 55, 72 oC and 55.81 oC sensors with a percentage error of 0.16% and a success of 99.84%, then the peak light intensity at measuring instrument measurements of 729 w/m2 and sensor measurements of 735 w/m2 with a percentage error of 0.82% and a success of 99.18%, then at the efficiency obtained peak efficiency at measuring instrument measurements of 13.98% and sensors of 13.76% with a percentage error of 0.612% and a success of 99.388% Where the highest data results in voltage, current, power, temperature, light intensity, and efficiency occur at 13:00 WIB.Keywords : Solar Cell Thin Film80WP , Internet Of Things