cover
Contact Name
Fawaidul Badri
Contact Email
fawaidulbadri@unisma.ac.id
Phone
+6285812461163
Journal Mail Official
infotron@unisma.ac.id
Editorial Address
Department of Electrical Engineering Faculty of Engineering Universitas Islam Malang (UNISMA)
Location
Kota malang,
Jawa timur
INDONESIA
Informatics, Electrical and Electronics Engineering
ISSN : -     EISSN : 27980197     DOI : 10.33474/infotron
The focus and scope of InfoTron are periodic scientific publications in the field of computer and electrical engineering, and informatics engineering to accommodate the research for lecturers and researchers, who want to publish the results of his scientific work. The Topics cover the following areas (but are not limited to): Computer Vision Signal and image processing Mobile computing Kecerdasan buatan Pattern recognition Machine learning Big data Data Mining Cloud computing Geoinformatic Information System Game dan multimedia Jaringan komputer dan keamanan Rekayasa perangkat lunak Sistem Informasi Robotika dan emmbeded system Pembangkit (generator) Distribusi Transmisi Konversi daya Sistem proteksi Bahan tenaga listrik Pembangkit energi terbarukan Sistem kontrol (automation,PLC,SCADA) Smart grid Elektronika daya
Articles 64 Documents
Sistem Monitoring Daya Sel Surya Pada Mobil Listrik Surya Unisla Berbasis IoT Bachri, Affan; Laksono, Arief Budi; Susilo, Purnomo Hadi; Hartantyo, Sugeng Dwi; Rohman, Mohammad Ainur
Jurnal Teknik Elektro dan Informatika Vol 5 No 1 (2025): INFOTRON
Publisher : Universitas Islam Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33474/infotron.v5i1.22945

Abstract

In this study, Unisla's solar electric vehicles uses five 100Wp solar panels assembled in series so that it has a total power of 500Wp. The design of this solar cell power monitoring system uses ESP32 as a microcontroller with the concept of Internet of Things (IoT) so that the device can be connected to the internet in real-time. The sensors used to read the current and voltage flowing from the solar panel are the ACS712 sensor and the voltage sensor is a voltage divider circuit made from resistors with R1 66100 Ohm and R2 3200 Ohm values respectively. Of the 10 test samples, the average error value of the voltage sensor used had a fairly good accuracy, with an average error of only 0.301%. This shows that the measurement difference between the sensor and the multimeter is relatively small. Meanwhile, the measurement difference between the ACS712 sensor and the power supply is very small, ranging from 0.01 to 0.02 Amperes with an average error of 0.01%. This shows that the measurement deviation of the ACS712 sensor compared to the reference value is very small, making it reliable for current measurement applications. The power monitoring tool developed was successfully implemented on Unisla Solar Electric Vehicles in real-time. Tests show that the appliance can read the voltage, current, and power generated by 5 solar panels assembled in series with a total power of 500Wp. The highest rated voltage data is 73.12Volts at 14.00, while the lowest data is 65.22Volts at 17.00, the rated highest rated current is 7.11A at 12.00, while the lowest current is 1.10A at 17.00, the highest rated power is 505.65Watt at 13.00, while the lowest power is 71.74 Watts.
Leveraging BiLSTM for Deep Learning-Based Mental Health Chatbots Agustina, Nur Afnis; Fauzan, Abd. Charis; Harliana, Harliana
Jurnal Teknik Elektro dan Informatika Vol 5 No 1 (2025): INFOTRON
Publisher : Universitas Islam Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33474/infotron.v5i1.23242

Abstract

The high prevalence of mental health issues and limited access to professional information and support have driven the search for innovative solutions. One promising approach is the development of chatbot systems that provide quick and accessible mental health information. This study evaluates the performance of the Bidirectional Long Short-Term Memory (BiLSTM) algorithm in identifying and classifying user inputs within a mental health chatbot system. BiLSTM is chosen for its ability to process sequential data in both directions, allowing it to capture context more effectively than unidirectional models and better understand user intent. Deep learning methods like BiLSTM have also demonstrated higher accuracy compared to traditional machine learning models. This study focuses solely on BiLSTM to evaluate its performance in this context. The mental health dataset used in this study was sourced from previous research published on the GitHub platform and contains 100 classes of mental health-related questions and statements. This dataset was used to train the BiLSTM model to recognize user intent and generate relevant responses. The model achieved 98% accuracy on the training data. For evaluation on the test set, a confusion matrix was used, yielding an accuracy of 82%. The chatbot is implemented as a web-based application using a Python framework and is designed to provide users with insights and knowledge through text-based interactions. These results highlight the potential of the BiLSTM-based chatbot system to deliver effective and efficient mental health information services
WhatsApp Chatbot Implementation of New Student Admission Information Service in Universitas Nahdlatul Ulama Sidoarjo Bilqis Brillyana Citra Zoraya; Syahri, Syahri Mumin; Awang, Awang Andhyka
Jurnal Teknik Elektro dan Informatika Vol 5 No 1 (2025): INFOTRON
Publisher : Universitas Islam Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33474/infotron.v5i1.23365

Abstract

Universitas Nahdlatul Ulama Sidoarjo (UNUSIDA) is experiencing obstacles in providing fast and efficient new student admission information services. The high volume of inquiries, limited human resources, and the need for instant response are the main challenges. This research aims to implement whatsapp chatbot technology to improve services at the University of Nahdlatul Ulama Sidoarjo. Using the Agile method, chatbot development is carried out iteratively and incrementally to ensure that the resulting solution meets user needs. The method used in this research includes the development of a chatbot system using a suitable programming platform, followed by testing the functionality and effectiveness in providing information. The test results show that the whatsapp chatbot is able to provide accurate and relevant responses in an average time of 3 seconds. Prior to the implementation of the chatbot, the response time to prospective student questions ranged from 15-30 minutes. The implementation of whatsapp chatbot significantly improves the efficiency of information services, reduces the workload of PMB staff and increases prospective student satisfaction. This research proves the effectiveness of chatbots in improving the quality of UNUSIDA PMB information services. This research serves as an example for other institutions in utilizing chatbot technology to improve public services effectively and make a significant contribution to the development of service technology in higher education.
PV Optimization With Genetic Algorithm-Based MPPT Method Hadi, Ayas Sutomo Hadi; Alawiy, Taqijjudin; Wirateruna, Efendi S
Jurnal Teknik Elektro dan Informatika Vol 5 No 1 (2025): INFOTRON
Publisher : Universitas Islam Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33474/infotron.v5i1.23470

Abstract

This research designs and implements a Maximum Power Point Tracking (MPPT) system based on genetic algorithm (GA) on buck-boost converter using Arduino microcontroller to increase energy conversion efficiency on PV system. The GA algorithm is used to adjust the PWM duty cycle to achieve the maximum power point (MPP) optimally. Tests were conducted to analyze the performance of the GA compared to the Perturb and Observe (P&O) algorithm and the system without MPPT. The results show that the GA is able to achieve a maximum power of 26.16 W, higher than the P&O algorithm (23.77 W) and the system without MPPT (1.59 W). The GA also reaches MPP faster, maintains output stability, and reduces power fluctuations. Voltage and current sensor testing showed high accuracy with Mean Absolute Percentage Error (MAPE) of 0.291% and 0.206%, respectively. The system was shown to improve energy conversion efficiency under various lighting and load conditions dynamically. With these results, the genetic algorithm proved to be more effective in optimizing the output power of solar panels than conventional methods.