Road Abnormality Detection Using Piezoresistive Force Sensors and Adaptive Signal Models

Abstract

Intelligent tires can be employed for a wide array of applications ranging from tire pressure monitoring to analyzing tire/road interactions, wheel loading as well as tread wear monitoring. In this paper we develop a measurement system for intelligent tires equipped with a 3-dimensional piezoresistive force sensor. The output of the sensor is segmented into tire revolution cycles, which are then represented by a transformation relying on adaptive Hermite functions. The underlying idea behind this step is to extract relevant features which capture tire dynamics. Then we evaluate the proposed measurement system in a potential vehicle application, that is, abnormal road surface detection. We deal with the corresponding binary classification problem by developing both low-complexity analytical and data-driven machine learning algorithms, which are tested on real-world measurement data. Our experiments showed that the proposed methods are able to detect abnormalities on the road surface with a mean accuracy of over 97%.

Arrhythmia Detection Using Spiking Variable Projection Neural Networks

“…Experimental results, obtained on binary classification task of VEB beats, demonstrated the effectiveness of VPSNN as a lightweight solution for ML assisted edge computations. As future work, we are planning to implement VPSNN with FPGA support and investigate applications in other domains, such as tire sensor signal classification [11], and visually evoked potential classification [12].…”

Road Type Classification Using Time-Frequency Representations of Tire Sensor Signals

“…These strain measurements are less sensitive to the previously mentioned noise components [7]; however, extensive tire deformation can result in their detachment from the inner liner. To address these limitations, we recently developed a piezoresistive MEMS sensor [8], and showed that there is a strong correlation between the measured electrical resistance signal and the direction as well as the magnitude of the mechanical forces acting on the tire. Besides the tire sensing technologies employed, it is equally important to process the measured data.…”

“…Note that previous works have involved simulated data and laboratory measurements, typically conducted under limited operational and environmental conditions. In contrast, our sensing system [8] is fully integrated into a vehicle, enabling real-world measurements to be conducted on public roads.…”

On Apostol-Type Hermite Degenerated Polynomials

“…Multi-index and multi-variable special functions are also necessary for solving problems in several branches of mathematics, such as partial differential equations and abstract group theory. Hermite polynomials, developed by Hermite [24][25][26][27], are an example of such special functions, which are important in combinatorics, numerical analysis, and physics. They are associated with the quantum harmonic oscillator and are utilized in solving the Schrödinger equation for the oscillator.…”