Claim Missing Document
Check
Articles

Found 2 Documents
Search

Development of Fuzzy Algorithm as Mobility Aid for Blind Person Using Two Sensor Points: Visual Aid for Blind Person Tata Supriyadi; Ridwan Solihin; Endang Habinuddin; Sudrajat Sudrajat
International Journal of Engineering Continuity Vol. 3 No. 2 (2024): ijec
Publisher : Sultan Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58291/ijec.v3i2.336

Abstract

White canes are an ideal choice for blind person to do independent mobility because of its relatively cheap price. However, whitecane has the disadvantage of only being able to identify objects in front of it when they have been touched and cannot provide a choice of direction. This study developed a prototype whitecane with a feature that can provide a choice of direction based on the results of identifying the distance of the object to its user. This prototype was designed and implemented using two ultrasonic sensors installed on the stick as a replacement for the spatial sensing system. Both distance data from the sensors are processed in the Arduino Nano microcontroller to carry out the Fuzzy process stages. Fuzzy input process, rule-based Fuzzy inference, and Defuzzification for decision output. The results of the decision are translated into voice information to the user. Experiments with three scenarios showed that the utilization of the system with constant contact O&M technique showed a success rate of 100% while the other two techniques were only 33.3%. So the constant contact O&M technique can support effective mobility for the use of assistive aids and can be developed into a new technique.
A Hybrid Neural Network and Sugeno-Type Fuzzy Approach for Object Classification to Assist Navigation of Visually Impaired Individuals Using Ultrasonic Sensor Arrays Ridwan Solihin; Rahmawati Hasanah; Budi Setiadi; Tata Supriyadi; Sudrajat Sudrajat; R Wahyu Tri Hartono
International Journal of Engineering Continuity Vol. 4 No. 2 (2025): ijec
Publisher : Sultan Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58291/ijec.v4i2.416

Abstract

This study proposes a hybrid neural network that integrates a multilayer perceptron (MLP) with optimised Sugeno-type fuzzy reasoning for object classification. The system employs a vertically mounted array of ultrasonic sensors arranged 10 cm apart at heights ranging from 80 cm to 180 cm. Each sensor measures the distance of passing objects, producing eleven readings that capture vertical distance patterns. These readings are processed by an MLP with a single hidden layer of 22 neurones to identify characteristic spatial signatures. A refined similarity-based classification is then performed using an optimised Sugeno-type fuzzy inference system configured with five linguistic variables: Very Low (VL), Low (L), Medium (M), High (H), and Very High (VH). Training and testing were conducted using datasets collected at SLBN-A Citeureup, Cimahi, comprising two object categories: human (visually impaired individuals) and nonhuman (inanimate objects). The model was trained for 100 epochs with a learning rate of 0.001. Experimental results show accuracy exceeding 90%, with the hybrid model outperforming the conventional MLP by 1.83%. This improvement reduces false positives and prevents erroneous obstacle warnings. The integration of fuzzy reasoning also enhances the system's robustness to uncertainty and stabilises decision-making when class boundaries overlap.