Robotic grippers can be equipped with tactile sensing systems to extract information from a
manipulated object. The real-time classification of the physical properties of a grasped …

Overfitting is a common problem in machine learning, which means the model too closely fits
the training data while performing poorly in the test data. Among various methods of co** …

Wearable systems require resource-constrained embedded devices for the elaboration of
the sensed data. These devices have to host energy-efficient artificial intelligence (AI) …

Currently, most fatigue driving detection methods rely on complex neural networks whose
feasibility in hardware implementation needs to be further improved. This paper proposes an …

The availability of new datasets and deep learning techniques have led to a surge of effort
directed towards the creation of new models that can exploit the large amount of data …

Abstract The introduction of Point Of Care (POC) devices is revolutionizing the field of
diagnostics, thanks to their ease of use, portability, and real-time results. However, despite …

The deployment of the inference phase in self–standing systems, which have resource–
constrained embedded units, is faced with many challenges considering computational cost …

Variable energy constraints affect the implementations of neural networks on battery-
operated embedded systems. This paper describes a learning algorithm for randomization …

The increase in neural network recognition accuracy is accompanied by a significant
increase in the scales of networks and computations. To make deep learning frameworks …

In the past few years, the use of transformer-based models has experienced increasing
popularity as new state-of-the-art performance was achieved in several natural language …