Open AccessWarning Sign Analysis of Traffic Sign Data-Set Using Supervised Spiking Neuron Technique
Author(s) -
Mohd Safirin Karis,
Nursabillilah Mohd Ali,
Muhammad Izzuddin Azahar,
Shafrizal Nazreen Shaari,
Nurasmiza Selamat,
Wira Hidayat Mohd Saad,
Amar Faiz Zainal Abidin,
Kamaru Adzha Kadiran,
Zairi Ismael Rizman
Publication year - 2018
Publication title -
international journal of engineering and technology
Language(s) - English
Resource type - Journals
ISSN - 2227-524X
DOI - 10.14419/ijet.v7i3.14.16898
Subject(s) - sign (mathematics) , computer science , rotation (mathematics) , process (computing) , artificial intelligence , pattern recognition (psychology) , image (mathematics) , word error rate , limit (mathematics) , usable , value (mathematics) , threshold limit value , computer vision , algorithm , mathematics , machine learning , medicine , mathematical analysis , environmental health , world wide web , operating system
In this paper, two types of conditions have been applied to analyze the performance of SNN towards usable traffic sign, which are hidden region and rotational effect. There are 20 warning traffic signs being focused on where there are regularly seen around Malacca area. These traffic sign needed to be embedded in this system as a databased to counter the output for mean error and recognition process for both conditions applied. Early hypothesis was design as the mean error and recognition process will degraded its performance as more intrusion get introduced in the system. For hidden region, the values show a critically rising error value at 62.5% = 0.123. While for mean error rotational effect, the values show an increasing abruptly for error value between 80 ̊ to 90 ̊ with 0.087% to 0.130%. For recognition process at 6.25% hidden region, 100% of images are correctly matchup to its own image. At 50% of hidden region, there is only 10% of image that able to be recognize while at 56.25% and 62.5% are leaving to outperform. At 10 ̊ rotation, 100% of images are perfectly recognized to its own image. At 60%, there is 30% of image able to recognize leaving others at 70%, 80% and 90% degrees rotation of images were outperformed. In view of element occasion driven handling, they open up new skylines for creating models with a colossal sum limit of recollecting and a solid capacity to quick adjustment. SNNs include another component, the transient hub, to the representation limit and the handling capacities of neural systems.