Claim Missing Document
Check
Articles

Found 6 Documents
Search

Design and Development of Student Attention System using Face Recognition Based on MTCNN and FaceNet Candra, Moch. Maulana Andhika; Hudino, Hudiono; Isnomo, Yoyok Heru Prasetyo
Jurnal Jaringan Telekomunikasi Vol 13 No 3 (2023): Vol. 13 No. 03 (2023) : September 2023
Publisher : Politeknik Negeri Malang

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

Abstract

Employees use their level of attendance or absence to demonstrate their presence at work or absence from it in an agency. This absence is connected to how discipline is applied, which is decided by each organization or institution. It can be inferred from this that student absenteeism in a setting where there is activity serves to increase discipline and demonstrate attendance. With IP Camera technology, it can be applied to the attendance system using the MTCNN method as face detection and FaceNet to extract high-quality features from the face. The system created can detect faces at a distance of 40 cm – 180 cm with an accuracy of 90.5% and can detect more than 1 object in 1 frame so that the IP Camera function is in accordance with the design in real-time. Tested the object of 3 pairs of twin faces produces a maximum accuracy of 90% where the level of match between the faces and the data is appropriate.
Quadcopter Take Off and Landing System with Blob Detection Method and Optical Flow Ramadhan, Rofy Wahyu; yulianto, Ahmad Wilda; Isnomo, Yoyok Heru Prasetyo
Jurnal Jaringan Telekomunikasi Vol 13 No 3 (2023): Vol. 13 No. 03 (2023) : September 2023
Publisher : Politeknik Negeri Malang

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

Abstract

Quadcopter is a type of UAV (Unmanned Aerial Vehicle) which is currently developing and very useful in various fields. With four motors as the main propulsion, the quadcopter has the ability to maneuver, take-off and land vertically in places that have limited space. However, in an autonomous system, the quadcopter is still difficult to operate, one of which is to keep it stable, when in a position where there is minimal GPS signal. Therefore, in this study, we will use the Blob detection method that uses the OpenCV library to determine the landing place and is assisted by an optical flow sensor, aiming to catch roll, pitch and yaw motions. The results of this study indicate that the accuracy of the lidar sensor as a height sensor with an accuracy of 82.16 % is more accurate above 30 cm, the results of distance accuracy for image processing successfully detect up to a height of 600 cm with a light intensity value of around 50-70 lux. optical flow, light intensity and altitude distance greatly affect the motion produced by the quadcopter, but it can still move stably at a minimum value of light intensity of approximately 300 lux at an altitude of 300 cm.
Designing Image Processing-Based Banknote Identification Device for Blind People Hartanto, Agung Dwi; Isnomo, Yoyok Heru Prasetyo; Purwandi , Ahmad Wahyu
Jurnal Jaringan Telekomunikasi Vol 14 No 1 (2024): Vol. 14 No. 01 (2024) : Maret 2024
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jartel.v14i1.691

Abstract

Money is a tool used all over the world to make buying and selling transactions and must reach an agreement to complete the transaction. It is certain that everyone needs money as a daily necessity, even for people with disabilities such as the blind. The limitations of blind people are problems in vision and relying on hearing for communication. The method used is a camera that detects the images contained in banknotes and sends data to the Raspberry Pi as the main controller in the system. The Raspberry Pi will process the received data signal and produce output in the form of sound. Tests carried out by calculating the success of the tool in detecting each currency. And from testing the data, it was found that the success of reading the system is almost 100% in all tests that users can use to identify banknotes.
Smart hand glove terapi pasien pasca stroke berbasis internet of things (IoT) Mustafa, Lis Diana; Imamuddien, Azam Muzakhim; Isnomo, Yoyok Heru Prasetyo
JURNAL ELTEK Vol. 21 No. 1 (2023): April 2023
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/eltek.v21i1.3012

Abstract

Stroke Transient Ischemic Attack (TIA) adalah kondisi stroke ringan yang dapat disebabkan oleh berkurangnya suplai darah menuju otak diakibatkan pembuluh darah tersumbat. Kurangnya aliran darah ke otak dapat menyebabkan kelumpuhan, biasanya hanya pada satu sisi tubuh. Fisioterapi pada pasien pasca stroke ringan dilakukan dengan metode terapi gerakan antara lain yaitu elbow dan knee flexion. Fisioterapi adalah metode pengobatan yang umum digunakan oleh masyarakat, pengobatan ini mahal dan memerlukan mobilitas. Berdasarkan data riset kesehatan dasar, ditemukan bahwa status ekonomi merupakan salah satu penentu utama efektivitas fisioterapi. Oleh karena itu, dibuatlah alat smart hand glove terapi pasien pasca stroke yang digunakan pada bagian tangan dan dilengkapi sebuah aplikasi yang disebut sebagai "Therapy Stroke Technology (TASTECH) untuk monitoring. Alat ini bekerja dengan integrasi antara sensor MPU6050 dan MAX30102 yang terhubung dengan ESP32 serta dapat dimonitoring oleh dokter atau terapis. Dari hasil pengujian akurasi sensor MPU6050 mampu mendeteksi sudut dari 100-900 sebesar 98,64%. Kemudian untuk sensor MAX30102 setelah diuji akurasi dengan perbandingan pulse oximeter tipe Lk87 didapatkan nilai akurasi SPO2 99,37% dan rata-rata BPM 99,22%. Aplikasi TASTECH ini dilengkapi dengan berbagai menu menarik seperti pusat informasi dan konsultasi yang dibuat dengan user friendly, TASTECH juga dapat digunakan dimana dan kapan saja dikarenakan bentuk alat ini yang portable dan tentunya ergonomis. ABSTRACTTransient Ischemic Attack (TIA) stroke is a mild stroke condition that can be caused by reduced blood supply to the brain due to blocked blood vessels. Lack of blood flow to the brain can cause paralysis, usually on only one side of the body. Physiotherapy in post-stroke patients is carried out using movement therapy methods, including elbow and knee flexion. Physiotherapy is a treatment method that is commonly used by the community, this treatment is expensive and requires mobility. Based on Basic Health Research data, it was found that economic status is one of the main determinants of the effectiveness of physiotherapy. Therefore, a Smart Hand Glove tool was created for post-stroke patient therapy which was used on the hands and equipped with an application called "Therapy Stroke Technology (TASTECH) for monitoring. TASTECH works by integrating the MPU6050 and MAX30102 sensors that are connected to the ESP32 and can be monitored by a doctor or therapist. From the results of testing the accuracy of the MPU6050 sensor is able to detect angles from 100-900 by 98.64%. Then for the MAX30102 sensor after being tested for accuracy with a comparison of the Lk87 type pulse oximeter, the SPO2 accuracy value is 99.37% and the BPM average is 99.22%. The TASTECH application is equipped with various interesting menus such as an information center and consultation which is made user friendly, TASTECH can also be used anywhere and anytime due to the shape of this tool which is portable and of course ergonomic.
Implementasi algoritma elgamal untuk pengamanan data pada wireless sensor network Zakaria, M. Nanak; Isnomo, Yoyok Heru Prasetyo; Prasetyo, Junaedi Adi; Rosyidan, Dwinnar
JURNAL ELTEK Vol. 23 No. 1 (2025): April 2025
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/eltek.v23i1.6910

Abstract

Perkembangan teknologi informasi menimbulkan tantangan keamanan data, terutama pada Wireless Sensor Network (WSN) yang rentan terhadap penyadapan. LoRa (Long Range) sering digunakan dalam WSN, tetapi memiliki kelemahan dalam keamanan komunikasi antar node. Untuk mengatasi hal ini, diperlukan sistem autentikasi yang kuat, seperti manajemen kunci. Algoritma ElGamal dipilih karena keamanannya berbasis logaritma diskret dan fleksibilitasnya dalam pengaturan ukuran kunci. Penelitian ini mengimplementasikan Algoritma ElGamal pada WSN dengan LoRa sebagai media transmisi. Perangkat yang digunakan adalah ESP32 Devkit V1 dan LoRa Ra-2 SX1278 pada node master, serta sensor HC-SR04 dan Flame Sensor pada node slave. Hasil menunjukkan Algoritma ElGamal mencapai ketepatan 100% dalam pengiriman data dengan delay 0,289 detik. Daya tahan baterai mencapai 2 jam 58 menit 38 detik. Pengujian intrusi membuktikan Algoritma ElGamal mampu mengamankan data melalui enkripsi dan dekripsi. Kesimpulannya, implementasi Algoritma ElGamal berhasil menjaga keamanan komunikasi dalam WSN, memastikan keaslian pesan, serta menjaga kinerja perangkat selama proses pengiriman dan penerimaan data.   ABSTRACT   The advancement of information technology presents data security challenges, especially in Wireless Sensor Networks (WSN), which are vulnerable to eavesdropping. LoRa (Long Range) is commonly used in WSN but has weaknesses in securing node communication. To address this, a strong authentication system is required, such as key management. The ElGamal algorithm is chosen for its security based on discrete logarithms and flexibility in key size configuration. This study implements the ElGamal algorithm in a WSN system using LoRa as the transmission medium. Devices used include the ESP32 Devkit V1 and LoRa Ra-2 SX1278 on the master node, along with the HC-SR04 sensor and Flame Sensor on the slave node. Results show that the ElGamal algorithm achieves 100% accuracy in data transmission with a delay of 0.289 seconds. The battery lasts for 2 hours, 58 minutes, and 38 seconds. Intrusion testing proves that the ElGamal algorithm secures data through encryption and decryption. In conclusion, implementing the ElGamal algorithm successfully ensures secure communication in WSN, maintains message authenticity, and sustains device performance during data transmission and reception.
Perbandingan performansi pengiriman data antar node wireless sensor menggunakan kriptografi RSA dan RC 4 Zakaria, M. Nanak; Isnomo, Yoyok Heru Prasetyo; Rahayu, Martanti Puri
JURNAL ELTEK Vol. 23 No. 2 (2025): Oktober 2025
Publisher : Politeknik Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/eltek.v23i2.8614

Abstract

Wireless Sensor Network (WSN) adalah teknologi jaringan nirkabel untuk mengumpulkan dan mengirimkan data, namun rentan terhadap penyadapan sehingga memerlukan pengamanan menggunakan kriptografi. Penelitian ini membandingkan algoritma RSA (asimetris) dan RC4 (simetris) pada komunikasi antar node berbasis LoRa E220, menggunakan Arduino Nano, sensor DHT22, sensor tegangan, dan sensor arus ACS712 pada node pengirim serta node penerima untuk dekripsi. Pengujian menggunakan data sensor dan data string sepanjang 8–100 karakter, dengan kedua algoritma mencapai keberhasilan enkripsi dan dekripsi 100%. Waktu enkripsi rata-rata RSA adalah 0,0104 detik dan dekripsi 9,1284 detik, sedangkan RC4 mencatat 0,1894 detik untuk enkripsi dan 0,1616 detik untuk dekripsi. RC4 lebih cepat pada data pendek hingga menengah (0,027–0,132 ms) namun lebih lambat pada data besar (0,389 ms vs RSA: 0,092 ms).  Dari sisi keamanan, pengujian brute force menunjukkan RSA sangat tahan karena tidak terbobol hingga 952,871–1001,652 s (±15 16 menit) pada berbagai variasi pesan dan kunci, sedangkan RC4 lebih rentan dengan kunci ditemukan dalam 52,871–85,983 s (±0,88–1,43 menit) dan seluruh pesan berhasil didekripsi. RC4 mengonsumsi energi lebih rendah (0,233–0,322 joule) dibanding RSA (0,2954–0,4024 joule). Kesimpulannya, RC4 unggul untuk komunikasi data pendek yang efisien, sedangkan RSA lebih andal dalam keamanan distribusi kunci.   ABSTRACT Wireless Sensor Network (WSN) is a wireless network technology for collecting and transmitting data, but it is vulnerable to interception and therefore requires security using cryptography. This study compares the RSA (asymmetric) and RC4 (symmetric) algorithms in LoRa E220-based node-to-node communication, using an Arduino Nano, DHT22 sensor, voltage sensor, and ACS712 current sensor on both the transmitter and receiver nodes for decryption. Testing was conducted using sensor data and string data ranging from 8 to 100 characters, with both algorithms achieving 100% encryption and decryption success rates. The average encryption time for RSA was 0.0104 seconds and decryption was 9.1284 seconds, while RC4 recorded 0.1894 seconds for encryption and 0.1616 seconds for decryption. RC4 is faster for short to medium-length data (0.027–0.132 ms) but slower for large data (0.389 ms vs. RSA: 0.092 ms). In terms of security, brute force testing showed that RSA is highly resistant, as it remained unbroken for 952.871–1001.652 seconds (±15–16 minutes) across various message and key variations, while RC4 is more vulnerable, with keys found in 52,871–85,983 s (±0.88–1.43 minutes) and all messages successfully decrypted. RC4 consumes less energy (0.233–0.322 joules) compared to RSA (0.2954–0.4024 joules). In conclusion, RC4 is superior for efficient short-term data communication, while RSA is more reliable in key distribution security.