Article Per Year (5 Year)
p-Index From 2021 - 2026
2.133
P-Index
This Author published in this journals
All Journal JURTEKSI Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal JOURNAL OF SCIENCE AND SOCIAL RESEARCH Jurnal Ilmiah Padma Sri Kreshna Jurnal Sistim Informasi dan Teknologi Jurnal Teknisi Jurnal Masyarakat Indonesia
Lubis, Mustopa Husein
Unknown Affiliation
Agriculture, Biological Sciences & Forestry Humanities Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Environmental Science Social Sciences

Published : 12 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 12 Documents
Search

 1   2 
Pemberdayaan Masyarakat Diversifikasi Produk Olahan Buah Balakka Terintegrasi Smart Production Berbasis IOT Lubis, Mustopa Husein; tanjung, akhir abadi; Andrianto, richi -
Jurdimas (Jurnal Pengabdian Kepada Masyarakat) Royal Vol. 7 No. 1 (2024): Januari 2024
Publisher : STMIK Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurdimas.v7i1.2818

Abstract

Utilization of balakka fruit is a typical fruit of North Padang Lawas Regency which can be used for superior preparations such as balakka fruit dodol. So far, balakka fruit has only been used for balakka syrup and juice. For this reason, community service was created in innovating balakka fruit by processing balakka fruit into balakka fruit dodol based on smart production. The urgency is expected to be used as an effective and efficient solution to increase people's knowledge and skills in processing balakka fruit. This community service activity aims to carry out dissemination and training on smart production-based balakka fruit dodol processing in the community of Padang Garugur Village, North Padang Lawas Regency, so that the community can be more productive with a technological approach. It is hoped that the results of the research will increase community knowledge and skills in processing balakka fruit into dodol based on smart production so that this service activity directly influences community productivity.. Keywords: Balakka Fruit; Product; Smart Production; IOT
INTEGRASI SENSOR IOT DAN OPTIMASI ALGORITMA MACHINE LEARNING UNTUK DETEKSI REAL-TIME TINGKAT STRES MAHASISWA Andrianto, Richi; Lubis, Mustopa Husein; Irawan, Rina; Irawan, Yuda; Utami, Urfi
JOURNAL OF SCIENCE AND SOCIAL RESEARCH Vol 9, No 1 (2026): February 2026
Publisher : Smart Education

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54314/jssr.v9i1.5178

Abstract

Abstract: High levels of stress among university students are a critical issue that can affect mental health, well-being, and academic performance. This study aims to develop a real-time student stress detection system using physiological data integrated with IoT technology and machine learning algorithms. The data used includes body temperature, blood oxygen saturation (SpO₂), heart rate, and blood pressure, acquired via embedded sensors and automatically transmitted to the cloud. The classification model was built using a combination of Random Forest and XGBoost, with enhanced accuracy through SMOTE-based data balancing and hyperparameter optimization using Optuna. The system was tested on a dataset of 3,420 records, classified into four stress levels: anxious, calm, tense, and relaxed. Evaluation results showed that the Random Forest model achieved the highest accuracy of 91%, followed by RF + XGBoost and RF + XGBoost + Optuna with accuracies of 90% each. The final model was deployed in a user interface using Streamlit, allowing real-time stress classification from IoT sensor input and manual input testing. The system proved to be effective and responsive in detecting stress objectively and can support digital-based mental health monitoring and counseling services for students. Keywords: Stress detection, IoT, Machine Learning, Random Forest, XGBoost Abstrak: Tingkat stres yang tinggi di kalangan mahasiswa merupakan permasalahan serius yang dapat memengaruhi kesehatan mental, kesejahteraan, dan performa akademik. Penelitian ini bertujuan untuk mengembangkan sistem deteksi tingkat stres mahasiswa secara real-time menggunakan data fisiologis berbasis teknologi IoT dan algoritma machine learning. Data yang digunakan meliputi suhu tubuh, kadar oksigen dalam darah (SpO₂), detak jantung, dan tekanan darah yang diperoleh melalui sensor terintegrasi dan dikirim ke cloud secara otomatis. Model klasifikasi yang dikembangkan memanfaatkan kombinasi algoritma Random Forest dan XGBoost, dengan peningkatan akurasi melalui teknik balancing data menggunakan SMOTE dan optimasi hyperparameter otomatis menggunakan Optuna. Sistem diuji menggunakan dataset berjumlah 3.420 data dengan distribusi empat kelas stres: cemas, tenang, tegang, dan rileks. Hasil evaluasi menunjukkan bahwa model Random Forest menghasilkan akurasi tertinggi sebesar 91%, disusul oleh RF + XGBoost dan RF + XGBoost + Optuna dengan akurasi masing-masing sebesar 90%. Model akhir kemudian diintegrasikan ke dalam antarmuka pengguna berbasis Streamlit, yang memungkinkan klasifikasi stres secara real-time dari data sensor IoT dan juga melalui input manual. Sistem ini terbukti efektif dan responsif dalam mendeteksi stres secara objektif dan dapat digunakan untuk mendukung layanan konseling atau pemantauan kesehatan mental mahasiswa secara digital. Kata kunci: Deteksi stres, IoT, Machine Learning, Random Forest, XGBoost
Co-Authors Feri irawan Harahap, Ali Hamdani Harahap, Munawir Sajali Irawan, Rina Iskandar Iskandar Januardi Rosyidi Lubis, Juwita Siregar, Emmi Martina, Desy Purnomo, Nopi Richi Andrianto Siregar, Selamat Riadi Sumijan, S Supriyanto, Asep Tanjung, Akhir Abadi Tar Muhammad Raja Gunung Utami, Urfi Yuda Irawan