Claim Missing Document
Check
Articles

Found 2 Documents
Search

Design, Construction, and Testing of an Electric Wheelchair Operated by Arduino Uno R3 Microcontroller Yusuf Subagyo; Sendie Yuliarto Margen; Baharudin Priwintoko; Fariz Wisda Nugraha; Hartanto Prawibowo
Multidisciplinary Innovations and Research in Applied Engineering Vol. 2 No. 1 (2025)
Publisher : Akademi Inovasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.70935/ha1z3r27

Abstract

The research aims to design and develop an electric wheelchair based on the Arduino Uno microcontroller as a mobility solution for individuals with disabilities. A conventional wheelchair was modified by integrating an electric drive system controlled by an analog joystick, which is connected to the Arduino Uno and DC motors via a BTS 760 motor driver. The wheelchair design complies with ISO 7176-5 standards and is adapted to the anthropometric dimensions of Indonesian users. Test results indicate that the control system functions effectively, allowing responsive control of wheelchair movements forward, backward, left, and right according to joystick operation. However, several challenges were encountered during the chain adjustment and gear welding processes, requiring further development to achieve optimal performance. This study demonstrates that utilizing the Arduino Uno as the central control unit enables the production of an electric wheelchair at a more affordable cost.
AUTOMATED VISUAL INSPECTION PADA PRODUK CASTING MANUFACTURING MENGGUNAKAN DEEP CONVOLUTIONAL NEURAL NETWORK Imaduddien Ariefa; Sendie Yuliarto Margen; Della Kumalaningrum; Komar Roni; Hawa Rizka
JURNAL ILMIAH MOMENTUM Vol 22 No 2 (2026): Oktober
Publisher : Universitas Wahid Hasyim

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36499/jim.v22i2.15624

Abstract

Untuk mencegah faktor subjektivitas dan potensi human error saat pengecekan kualitas produk casting manufacturing secara manual, penelitian ini bertujuan mengembangkan sistem Automated Visual Inspection (AVI) berbasis AI. Metode yang digunakan dengan pendekatan Deep learning berbasis Convolutional Neural Network (CNN) dengan membandingkan kinerja antara arsitektur AlexNet dan Development architecture. Proses evaluasi menggunakan 6.633 citra riil hasil preprocessing yang terbagi atas kelas defect dan non-defect untuk data training dan validasi. Hasil eksperimen membuktikan keunggulan architecture AlexNet yang mencatatkan akurasi hingga 99,25% dengan validation loss sebesar 0,02481, sementara architecture pengembangan hanya menghasilkan tingkat akurasi 89,07%. Hasil analisis confusion matrix juga memperlihatkan tingkat kestabilan AlexNet yang sangat tinggi dengan nilai presisi, recall, serta F1-score melebihi 0,99. Kesimpulan dari penelitian ini menegaskan bahwa architecture AlexNet memiliki efektivitas yang jauh lebih tinggi dalam mendeteksi cacat pada komponen pengecoran logam, menjadikannya opsi yang sangat relevan untuk diaplikasikan dalam sistem kendali mutu otomatis di industri.