Jurnal Teknologi dan Sistem Tertanam (JTST)

INTEGRASI MULTI-SENSOR DAN BYPASS UNTUK STABILITAS NUTRISI HIDROPONIK NFT IOT KALE

2026-07-07T14:25:18+07:00

Pengelolaan larutan nutrisi secara presisi merupakan faktor determinan dalam keberhasilan sistem hidroponik Nutrient Film Technique (NFT), terutama pada tanaman dengan nilai ekonomi tinggi seperti kale (Brassica oleracea var. acephala). Tantangan utama dalam instalasi NFT konvensional adalah kemunculan gradien konsentrasi nutrisi di mana akar tanaman pada bagian hulu menyerap unsur hara secara masif, sehingga tanaman di bagian hilir mengalami defisiensi nutrisi. Selain itu, sistem otomatisasi tradisional seringkali berisiko menyebabkan kontak langsung antara akar tanaman dengan larutan pekat hasil injeksi pompa sebelum tercapai homogenitas sempurna. Penelitian ini bertujuan untuk mengatasi kendala tersebut melalui integrasi sistem multi-sensor dan inovasi mekanisme bypass distribusi berbasis Internet of Things (IoT). Sistem ini menggunakan mikrokontroler ESP32 sebagai pusat kendali yang mengolah data dari sensor Power of Hydrogen (pH) dan Electrical Conductivity (EC) menggunakan algoritma logika fuzzy untuk mengatur durasi kerja empat unit pompa peristaltik. Inovasi fundamental terletak pada desain mekanik bypass yang menggunakan sistem percabangan selang paralel untuk mendistribusikan larutan hara yang telah stabil langsung ke bagian tengah dan akhir instalasi pipa. Hasil pengujian menunjukkan bahwa mekanisme bypass ini mampu menciptakan keseragaman nilai hara di seluruh titik tanam dengan nilai PPM yang identik pada Pipa 1 hingga Pipa 4. Akurasi sensor pH berada pada tingkat yang sangat baik dengan rata-rata persentase kesalahan sebesar 2,01%. Pemantauan data secara real-time difasilitasi oleh protokol MQTT yang terintegrasi dengan database InfluxDB dan visualisasi Grafana, memungkinkan pengawasan berkelanjutan terhadap parameter lingkungan. Analisis energi menunjukkan konsumsi harian sistem sebesar 550,656 Wh, menegaskan efisiensi operasional sistem. Implementasi teknologi ini tidak hanya meminimalkan risiko kerusakan akar (nutrient burn) tetapi juga menciptakan model pertanian digital yang terukur, aman, dan berkelanjutan bagi ketahanan pangan masa depan.

ANALISIS KOMPARATIF KINERJA RF-DETR DAN YOLOV11 UNTUK DETEKSI DAN KLASIFIKASI KUALITAS CABAI

2026-07-07T14:25:18+07:00

Increasing demands for the quality and consistency of horticultural commodities highlight the limitations of manual
sorting methods, which tend to be subjective and inefficient. This study aims to develop and evaluate an automated
system for detecting and classifying chili pepper quality using a deep learning-based computer vision approach. Two
state-of-the-art object detection models, namely YOLOv11 and RF-DETR, were implemented and compared using a
dataset of chili pepper images classified into fresh, unripe, and damaged categories. The research methodology
employed a quantitative experimental approach encompassing data collection, instance segmentation annotation,
preprocessing, model training, and performance evaluation. The results show that both models demonstrate good
detection capabilities, with YOLOv11 excelling in inference speed, making it suitable for real-time applications, while
RF-DETR exhibits higher detection accuracy and stability under complex visual conditions. These findings indicate
a balance between computational efficiency and detection accuracy. This research contributes to the development of
computer vision-based automated systems to improve the efficiency and objectivity of the agricultural product grading
process.

EVALUASI SISTEM INFORMASI PELAYANAN ADMINISTRASI DI KELURAHAN TALANG KERAMAT MENGGUNAKAN METODE SYSTEM USABILITY SCALE (SUS)

2026-07-07T14:25:18+07:00

Abstract

The development of information technology has encouraged government institutions to utilize information systems to improve the quality of public services. Talang Keramat Village Office has an Android Mobile-Based Administrative Service Information System designed to facilitate the community in accessing various administrative services digitally. However, the success of a system is determined not only by the functions it provides but also by the ease with which users can operate it. This study aims to evaluate the usability level of the Android Mobile-Based Administrative Service Information System at Talang Keramat Village Office using the System Usability Scale (SUS) method. The research employed a quantitative approach through the distribution of a SUS questionnaire consisting of 10 statements to 35 respondents who were users of the system. The collected data were then processed and analyzed to determine the system's usability score. The results showed that the system achieved a total SUS score of 2782.5 with an average score of 79,5. This score falls into the Good category, receives a Grade Scale B, and is classified as Acceptable, indicating that the system has a good level of usability and is well accepted by users. Based on the evaluation results, it can be concluded that the Android Mobile-Based Administrative Service Information System at Talang Keramat Village Office has met user needs and is suitable for use as a digital administrative service platform.

Keywords: Android Mobile, Administrative Services, Information System, System Usability Scale (SUS), Usability.

Abstrak

Perkembangan teknologi informasi telah mendorong instansi pemerintahan untuk memanfaatkan sistem informasi dalam meningkatkan kualitas pelayanan publik. Kelurahan Talang Keramat memiliki Sistem Informasi Pelayanan Administrasi Berbasis Android Mobile yang digunakan untuk mempermudah masyarakat dalam mengakses berbagai layanan administrasi secara digital. Namun, keberhasilan suatu sistem tidak hanya ditentukan oleh fungsi yang tersedia, tetapi juga oleh tingkat kemudahan pengguna dalam mengoperasikannya. Penelitian ini bertujuan untuk mengevaluasi tingkat usability Sistem Informasi Pelayanan Administrasi Berbasis Android Mobile di Kelurahan Talang Keramat menggunakan metode System Usability Scale (SUS). Penelitian dilakukan dengan pendekatan kuantitatif melalui penyebaran kuesioner SUS yang terdiri dari 10 pernyataan kepada 35 responden yang merupakan pengguna sistem. Data yang diperoleh kemudian diolah dan dianalisis untuk menghasilkan skor usability sistem. Hasil penelitian menunjukkan bahwa sistem memperoleh total skor SUS sebesar 2782,5 dengan nilai rata-rata 79,5. Nilai tersebut termasuk dalam kategori Good, Grade Scale B, dan Acceptable, yang menunjukkan bahwa sistem memiliki tingkat kemudahan penggunaan yang baik serta dapat diterima oleh pengguna. Berdasarkan hasil evaluasi, dapat disimpulkan bahwa Sistem Informasi Pelayanan Administrasi Berbasis Android Mobile di Kelurahan Talang Keramat telah memenuhi kebutuhan pengguna dan layak digunakan sebagai sarana pelayanan administrasi berbasis digital.

Kata Kunci: Android Mobile, Pelayanan Administrasi, Sistem Informasi, System Usability Scale (SUS), Usability

Development of an AIoT-Driven Micro:bit Literacy Game Utilizing Ensemble k-NN and Decision Tree for Early STEAM Education

2026-07-07T14:25:19+07:00

Low literacy performance among Indonesian students, as indicated by PISA result, highlights the need for innovative learning approaches. This study proposes an interactive literacy game integrating Micro:bit and machine learning within an AIoT framework for STEAM education. The system uses accelerometer data to recognize hand gestures (left, right, up) as multiple-choice answers. A dataset of

61,148 gesture samples was collected and processed. An ensemble model combining k-Nearest Neighbor (k-NN) and Decision Tree algorithms achieved a classification accuracy of 90.25%. Real-time implementation with elementary students (n=19) yielded a gesture recognition accuracy of 95.03%. User testing showed high engagement (8.5/10) and positive learning impact (8.9/10), demonstrating the system’s effectiveness as a lightweight, interactive tool for

literacy education.

PENGEMBANGAN WEB SEKOLAH INTERAKTIF BERBASIS MEJA BELAJAR DIGITAL UNTUK MENINGKATKAN EFEKTIVITAS PEMBELAJARAN

2026-07-07T14:25:19+07:00

Abstract

This study aims to develop an Interactive School Website based on a Digital Learning Desk at Yayasan Karya Andalas Palembang to improve the effectiveness of the learning process. The identified problem is the suboptimal utilization of digital learning media that can support the needs of both students and teachers in an interactive and structured manner. The method used in this study is User-Centered Design (UCD), which focuses on users at every stage of system development. The UCD stages include context-of-use analysis within Yayasan Karya Andalas Palembang, user needs identification through observation and interviews, design solutions in the form of a Digital Desk prototype, design evaluation through user testing, and system refinement based on the evaluation results. The findings show that the developed system provides a simpler, more interactive interface that aligns with user needs in the institution. The implementation of the Digital Desk allows students to access learning materials, exercises, and learning activities in a more organized and convenient way. In addition, the test results indicate increased user comfort and engagement in the learning process. Therefore, the Interactive School Website based on a Digital Desk can serve as a solution to support more effective digital learning at Yayasan Karya Andalas Palembang.

Keywords: School Website, Digital Learning Desk, User Centered Design, Interactive Learning, Yayasan Karya Andalas

Abstrak

Penelitian ini bertujuan untuk mengembangkan Web Sekolah Interaktif berbasis Meja Belajar Digital pada Yayasan Karya Andalas Palembang guna meningkatkan efektivitas proses pembelajaran. Permasalahan yang ditemukan adalah belum optimalnya pemanfaatan media pembelajaran digital yang mampu mendukung kebutuhan siswa dan guru secara interaktif dan terstruktur. Metode yang digunakan dalam penelitian ini adalah User Centered Design (UCD) yang berfokus pada pengguna dalam setiap tahapan pengembangan sistem. Tahapan UCD meliputi analisis konteks penggunaan pada lingkungan Yayasan Karya Andalas Palembang, identifikasi kebutuhan pengguna melalui observasi dan wawancara, perancangan solusi dalam bentuk prototype Meja Digital, evaluasi desain melalui pengujian pengguna, serta perbaikan sistem berdasarkan hasil evaluasi. Hasil penelitian menunjukkan bahwa sistem yang dikembangkan mampu memberikan antarmuka yang lebih sederhana, interaktif, dan sesuai dengan kebutuhan pengguna di lingkungan yayasan. Implementasi Meja Digital memungkinkan siswa untuk mengakses materi, latihan, dan aktivitas pembelajaran secara lebih mudah dan terorganisir. Selain itu, hasil pengujian menunjukkan adanya peningkatan kenyamanan dan keterlibatan pengguna dalam proses pembelajaran. Dengan demikian, Web Sekolah Interaktif berbasis Meja Digital ini dapat menjadi solusi untuk mendukung pembelajaran digital yang lebih efektif di Yayasan Karya Andalas Palembang.

Kata Kunci: Web Sekolah, Meja Belajar Digital, User Centered Design, Pembelajaran Interaktif, Yayasan Karya Andalas

A Designing a System to Predict Faculty Publication Performance Using a Time-Series Machine Learning Model (Case Study: Information Technology Study Program, PGRI University of Madiun)

2026-07-07T14:25:19+07:00

This research presents the development of an integrated web-based application designed to forecast and assess lecturers’ publication performance through time-series machine learning techniques. The study is conducted within the Informatics Engineering Program of Universitas PGRI Madiun by utilizing historical publication records as temporally ordered data. These records are transformed into structured time-series representations to reveal productivity trends, periodic patterns, and temporal variations in academic output. The system architecture consolidates data acquisition, preprocessing, forecasting, and visualization into a single platform implemented using the Django framework. Multiple time-series forecasting models are applied and evaluated to examine their predictive capability, with performance measured using Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and the coefficient of determination (R²). The results indicate that the proposed system is capable of generating consistent and interpretable forecasts that reflect actual publication dynamics. By providing analytical insights and early trend detection, the system supports objective evaluation and assists academic management in strategic planning and continuous improvement of research productivity.