Intelligent tires can be used for a wide array of applications ranging from tire pressure monitoring to analyzing tire/road interactions, wheel loading, and tread wear monitoring. In this article, we develop a measurement system for intelligent tires equipped with a 3-D 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%.

Smart tire technologies offer a novel sensing methodology for vehicle environment perception by providing direct measurements of tire dynamics parameters. This information can be utilized in advanced driver assistance systems as well as autonomous vehicle control to enhance vehicle performance and safety. Considering these criteria, we develop algorithms for categorizing road types based on tire sensor signals. Road differentiation is a complex task due to the non-linear and non-stationary nature of the measured tire signals. To address this challenge, we fuse time-frequency distributions with machine learning approaches. Maintaining the robustness of the predictions, we integrate our own measurement system into a Nissan Leaf test vehicle and collect data involving diverse environmental factors and operational conditions, mimicking real-world scenarios. We showed that by experiments our predictions strongly correlate with road quality, which can be utilized in automatic vehicle control, such as intelligent speed adaptation.

In this work we propose proof-of-concept methods to detect malfunctions of the braking system in passenger vehicles. In particular, we investigate the problem of detecting deformations of the brake disc based on data recorded by acceleration sensors mounted on the suspension of the vehicle. Our core hypothesis is that these signals contain vibrations caused by brake disc deformation. Since faults of this kind are typically monitored by the driver of the vehicle, the development of automatic fault-detection systems becomes more important with the rise of autonomous driving. In addition, the new brake boosters separate the brake pedal from the hydraulic system which results in less significant effects on the brake pedal force. Our paper offers two important contributions. Firstly, we provide a detailed description of our novel measurement scheme, the type and placement of the used sensors, signal acquisition and data characteristics. Then, in the second part of our paper we detail mathematically justified signal representations and different algorithms to distinguish between deformed and normal brake discs. For the proper understanding of the phenomenon, different brake discs were used with measured runout values. Since, in addition to brake disc deformation, the vibrations recorded by our accelerometers are nonlinearly dependent on a number of factors (such as the velocity, suspension, tire pressure, etc.), data-driven models are considered. Through experiments, we show that the proposed methods can be used to recognize faults in the braking system caused by brake disc deformation.

The occipital cortex responds to visual stimuli regardless of a patient’s level of consciousness or attention, offering a noninvasive diagnostic tool for both ophthalmologists and neurologists. This response signal manifests as a unique waveform referred to as the visually evoked potential (VEP), which can be extracted from the electroencephalogram (EEG) activity of a human being. We propose a trainable VEP representation to disentangle the underlying explanatory factors of the data. To enhance the learning process with domain knowledge, we present an innovative parameterization of classical Hermite functions that effectively captures VEP pattern variations arising from patient-specific factors, disorders, and measurement setup influences. Then, we introduce a differentiable variable projection (VP) layer to fuse Hermite basis function expansions (BFEs) of VEP signals with machine learning (ML) approaches. We prove the existence of an optimal set of parameters in the least-squares sense, assess the representation power of such layers, and calculate their analytical derivatives, which allows us to utilize backpropagation for training. Finally, we evaluate the effectiveness of the proposed learning framework in VEP-based color classification. To achieve this, we have designed a novel measurement system dedicated to intraoperative clinical use cases, which presents new ways for patient monitoring during neurosurgical procedures.