Claim Missing Document
Check
Articles

Found 17 Documents
Search

Rancang Bangun Vending Machine Komponen Elektronika dengan Identifikasi RFID Berbasis IoT Soleh, M. Zikri; Salamah, Irma; Rakhman, Abdul
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 1 (2023): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i1.573

Abstract

Electronic components are objects that are supporting parts of an electronic circuit that can operate according to their application. Among them are PCB boards, resistors, transistors, and many more. In assembling a series of students, additional components are often needed which are caused by errors in assembling a circuit. An error in assembling causes a component to be damaged, because the electronic component given by the lecturer is only once. Based on the explanation above, a solution can be found in the form of the application of vending machines for electronic components that can be applied in certain places, such as in the Telecommunication Engineering lab of the Indonesian National Police.  Vending machine is a machine that can accommodate certain objects and can eject them automatically with a trigger programed by the designer, in this case electronic components are used as objects that will be removed from the box. With this tool aims to make it easier for students to get electronic components for free practically and not spend a lot of time, they can use Radio Frequency Identification (RFID) as a detection tool on the vending machine. This research uses RFID technology where, when the user wants to take one of the components of the vending machine, the user must have an RFID-based card that has been previously made so that it can proceed to the next stage, namely component retrieval.
Sistem Keamanan Pintu dan Jendela Rumah Berbasih IoT Kurniasih, Wahyuni; Rakhman, Abdul; Salamah, Irma
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 5, No 2 (2020): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v5i2.212

Abstract

The house is the most valuable asset, therefore security at home is also very important. Therefore a home security system is created that combines a microcontroller with an Android smartphone application. The microcontroller used is the Raspberry Pi which is equipped with a camera as a home security monitoring system and various sensors as detectors such as magnetic, PIR sensors and solenoids as automatic door locks. So if the sensors that are installed detect something at home, then the homeowner will immediately get a notification sent by the database to the smartphone application, and the homeowner can monitor the state of the house right then through photos and videos recorded by cameras that have been installed at home.
Prototype Smart Home Menggunakan Modul Wifi ESP8266 Dengan Aplikasi Telegram Oktari, Nisa Gracella Aslamia; Nurdin, Ali; Rakhman, Abdul
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 5, No 2 (2020): Edisi Agustus
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v5i2.211

Abstract

Smart Home is a technology that can make it easier for users to manage comfort and safety at home so they can control the equipment used, homeowners can open the gate automatically and check the temperature and humidity of the existing room at home. Sometimes homeowners forget to turn off or turn on the equipment used, and forget to close the gate again when no one is at home. From the above problems made a tool that can be used as a remote home appliance controller or can also be called smart home. This tool uses the ESP8266 wifi module as the main device and sensor control that is connected to the Telegram Application to give commands to the ESP8266 wifi module so that it can control the equipment used and is at home.
SYSTEM DESIGN FOR EARLY DETECTION OF DIABETES MELLITUS USING IOT-BASED NON-INVASIVE SENSORS Widya, Afni Rara; Handayani, Ade Silvia; Rakhman, Abdul
JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika) Vol 10, No 2 (2025)
Publisher : STKIP PGRI Tulungagung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29100/jipi.v10i2.6198

Abstract

This research aims to design a diabetes mellitus early detection tool using IoT-based non-invasive sensors. This tool uses blood pressure sensors and color sensors to detect glucose levels in urine. The data obtained from these sensors is sent to the Arduino Uno microcontroller, displayed on the LCD screen, and saved to the Firebase platform for further monitoring and analysis. The test results show that this tool is able to measure and display blood pressure data and urine glucose levels accurately and in real time so that it can be used as a practical and efficient diabetes mellitus diagnostic tool. This research makes a very important contribution to the development of IoT-based health technology, especially in facilitating early detection of diabetes non-invasively. This research aims to design a diabetes mellitus early detection tool using IoT-based non-invasive sensors. 
Rancang Bangun Sistem Penyiram dan Pemupuk Otomatis Menggunakan Fuzzy Logic Berbasis Internet of Things (IoT) Miranda, Nadia; Ahmad Taqwa; Abdul Rakhman
Jurnal Teknologi Sistem Informasi dan Aplikasi Vol. 8 No. 1 (2025): Jurnal Teknologi Sistem Informasi dan Aplikasi
Publisher : Program Studi Teknik Informatika Universitas Pamulang

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

Abstract

This research aims to design and build an automatic watering and fertilization system for moon orchids (Phalaenopsis) based on the Internet of Things (IoT) using the Fuzzy Logic method. Moon orchids have slow growth and are affected by environmental factors such as temperature and humidity, where the optimal temperature ranges from 25-27°C and air humidity between 60-85%. The system is designed to monitor and control the plant's environmental conditions in real time, as well as perform automatic watering when the soil humidity is below 35% and stop it when it is above 35%. Tests showed error rates between the various sensors used, such as a difference of 1.61% between the DHT22 temperature sensor and a thermometer, 1.78% for humidity between the DHT22 sensor and a hygrometer, and 8.32% between the soil moisture sensor and a soil moisture meter. The Purple Bloom application used in this system experienced an average delay of 6.11 seconds caused by the speed of the internet. Although there is a slight delay, this system provides convenience and efficiency in the maintenance of moon orchids. The use of IoT technology and artificial intelligence shows great potential in improving the productivity and efficiency of plant care.
Integrasi Kamera dan YOLOv5 pada Sistem Keamanan Safety Box Berbasis IoT Rizky Tarmizi, Kgs.M.Dian Akbar; Taqwa, Ahmad; Rakhman, Abdul
Jurnal Teknik Elektro dan Komputasi (ELKOM) Vol 7, No 2 (2025): ELKOM
Publisher : Universitas Muhammadiyah Jember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32528/elkom.v7i2.22636167

Abstract

Peningkatan keamanan terhadap akses fisik menjadi isu penting dalam pengembangan sistem berbasis Internet of Things (IoT), khususnya pada aplikasi autentikasi biometrik. Penelitian ini bertujuan untuk mengembangkan sistem keamanan safety box berbasis IoT yang mengintegrasikan kamera digital, algoritma YOLOv5 untuk autentikasi wajah real-time, dan mikrokontroler ESP32 sebagai pengendali aktuator pengunci elektronik. Sistem ini dirancang untuk mengenali wajah secara lokal tanpa ketergantungan pada layanan cloud guna meningkatkan efisiensi, privasi, dan kecepatan respons. Evaluasi dilakukan melalui pengujian fungsional dan analisis metrik performa, termasuk precision, recall, confusion matrix, dan mean Average Precision (mAP). Hasil pengujian menunjukkan bahwa sistem mampu mengidentifikasi wajah terdaftar dan menolak wajah yang tidak terdaftar secara akurat, dengan nilai mAP sebesar 66,3% pada threshold IoU 0,5. Sistem juga menunjukkan ketahanan terhadap variasi pencahayaan, sudut pandang, dan ekspresi wajah. Temuan ini menunjukkan bahwa kombinasi YOLOv5 dan ESP32 dapat diterapkan secara efektif dalam sistem autentikasi wajah real-time untuk aplikasi keamanan berbasis IoT berskala kecil hingga menengah.
Pengembangan Algoritma Convolutional Neural Network dalam Menganalisis Emosi Suara Menggunakan Mel-Spektogram Zakka, Iqlima Sabila; Rakhman, Abdul; Lindawati, Lindawati
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.7875

Abstract

Speech Emotion Recognition (SER) still faces challenges in accuracy, especially in distinguishing acoustically similar emotions. Conventional approaches such as MFCC (Mel Frequency Cepstral Coefficients) are often ineffective in capturing the emotional nuances of voice. To address this, this study aims to develop a Convolution Neural Network (CNN) model based on the Spec-ResNet architecture that uses Mel-Spectrogram as input to improve the system's ability to extract and recognize emotional signatures from speech signals. Another objective is to evaluate the performance of primary emotion classification in the RAVDESS dataset and measure model consistency through 5-fold cross-validation. The model used, Spec-ResNet, is an adaptation of the ResNet architecture equipped with residual learning to maximize the multi-stage feature extraction process. Experiments were conducted with the RAVDESS dataset containing 1,440 voice samples from six primary emotions: neutral, happy, sad, angry, afraid, and surprised. The test results showed a significant increase in accuracy, with a macro score reaching 92%, up from the MLP/SVM baseline of 83%. Neutral and happy emotions were classified very well (F1-scores of 93% and 90%), but emotions such as fear and surprise remained difficult to distinguish due to the similarity of their vocal patterns. Validation through 5-fold cross-validation yielded an average accuracy of 91.5% ± 0.8%. This study demonstrates the great potential of Mel-spectrograms in SER, while also underscoring the need for advanced approaches such as attention mechanisms to handle ambiguous emotions.