TY  - JOUR
N2  - Ensuring safe and independent mobility for visually impaired individuals requires efficient obstacle detection systems. This study introduces an innovative smart knee glove, integrating machine learning technologies for real-time obstacle detection and alerting. The system is equipped with ultrasonic sensor, PIR sensor and a buzzer, with data processing managed by an Arduino Uno microcontroller. To enhance detection accuracy, multiple machine learning algorithms including Decision Tree (DT), Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Random Forest (RF) and Gaussian Naïve Bayes (GNB) are utilized. A novel Voting Classifier ensemble method is proposed, effectively combining the strengths of these classifiers to maximize performance. Rigorous cross-fold validation ensures robust evaluation under varying conditions. Experimental results demonstrates that the system achieves an impressive 98.34% detection accuracy within a 4-meter range, with high precision, recall and F1 scores. These findings underscore the system?s reliability and potential to empower visually impaired users with safer, more autonomous navigation, marking a significant advancement in obstacle detection technologies.
A1  - Ikram, Sunnia
A1  - Bajwa, Imran Sarwar
A1  - Ikram, Amna
A1  - Díez, Isabel de la Torre
A1  - Uc Ríos, Carlos Eduardo
A1  - Kuc Castilla, Ángel Gabriel
AV  - public
KW  - Obstacle detection
KW  -  IoT
KW  -  sensors
KW  -  visually impaired
KW  -  machine learning
KW  -  android application
EP  - 35321
VL  - 13
JF  - IEEE Access
SN  - 2169-3536
UR  - http://doi.org/10.1109/ACCESS.2025.3543299
SP  - 35309
TI  - Obstacle Detection and Warning System for Visually Impaired Using IoT Sensors
Y1  - 2025/02//
ID  - uniromana17412
ER  -