TY - JOUR
AU - Kodogiannis, V.S.
AB - Fuzzy systems are currently finding practical applications, rangingfrom "soft" regulatory control in consumer products to accurate modelling ofnon-linear systems. This paper presents the design of a classification systemfor vehicle acoustic signal classification. Traffic management and informationsystems rely on a suite of sensors for estimating traffic parameters. Currentlyinductive loop detectors and video-based systems are often used to count anddetect vehicles. Loop detectors are expensive to maintain and video-basedsystems are sensitive to environmental conditions and do not perform well invehicle classification. Vehicle classification is important in the computationof the percentages of vehicle classes that use streets and motorways. The useof an automated system can lead to adequate road surface maintenance withobvious results in cost and quality. However the sound of a working vehiclecould provide an important clue to the vehicle type. A novel approach, based onadaptive fuzzy logic systems, has been discussed in this paper. Its performanceis evaluated through a simulation study, using metered data collected from aroadside microphone-array sensor at the Valle d'Aosta highway in north-westernItaly. The results indicate that the fuzzy classifier based on the proposeddefuzzification method, namely area of balance (AOB), provide more accurateclassifications compared to other classifiers.
TI - An efficient fuzzy based technique for signal classification
JF - Journal of Intelligent and Fuzzy Systems
DO - 10.3233/ifs-2001-00155
DA - 2001-09-01
UR - https://www.deepdyve.com/lp/ios-press/an-efficient-fuzzy-based-technique-for-signal-classification-eOo93wI0kr
SP - 65
EP - 84
VL - 11
IS - 1-2
DP - DeepDyve
ER -