Abstract
Analysis of sports performance using mobile and wearable devices is becoming increasingly popular, helping users improve their sports practice. In this context, the goal of this work has been the development of an Apple Watch application, capable of detecting important strokes in the table tennis sport, using a deep learning (DL) model. A dataset of table tennis strokes has been created based on the watch's accelerometer and gyroscope sensors. The dataset collection was done in the Portuguese table tennis federation training sites, from several athletes, supervised by their coaches. To obtain the best DL model, three different architecture models where trained, compared and evaluated, using the complete dataset: a LSTM based on Create ML/Core ML frameworks (62.70% F1 score) and two Tensorflow based architectures, a CNN-LSTM (96.02% F1 score) and a ConvLSTM (97.33% F1 score).

Abstract
This study explores the resistive switching phenomena present in 4 mu m(2) amorphous Indium-Gallium-Zinc Oxide (IGZO) memristors. Despite being extensively reported in the literature, not many studies detail the mechanisms that dominate conduction on the different states of IGZO-based devices. In this article, we demonstrate that resistive switching occurs due to the modulation of the Schottky barrier present at the bottom interface of the device. Furthermore, thermionic field emission and field emission regimes are identified as the dominant conduction mechanisms at the high resistive state of the device, while the bulk-limited ohmic conduction is found at the low resistive state. Due to the high complexity associated with creating compact models of resistive switching, a data-driven model is drafted taking systematic steps. (C) 2022 Author(s).

Abstract
Memristor crossbar arrays can compose the efficient hardware for artificial intelligent applications. However, the requirements for a linear and symmetric synaptic weight update and low cycle-to-cycle (C2C) and device-to-device variability as well as the sneak-path current issue have been delaying its further development. This study reports on a thin-film amorphous oxide-based 4x4 1-transistor 1-memristor (1T1M) crossbar. The a-IGZO crossbar is built on a flexible polyimide substrate, enabling IoT and wearable applications. In the novel framework, the thin-film transistor and memristor are fabricated at the same level, with the same processing steps and sharing the same materials for all layers. The 1T1M cells show linear and symmetrical plasticity characteristic with low C2C variability. The memristor performs like an analog dot product engine and vector-matrix multiplications in the 4x4 crossbars is demonstrated experimentally, in which the sneak-path current issue is successfully suppressed, resulting in a proof-of-concept for a cost-effective, flexible artificial neural networks hardware.

Abstract
In this paper, the most suited analog-to-digital (A/D) converters (ADCs) for Internet of Things (IoT) applications are compared in terms of complexity, dynamic performance, and energy efficiency. Among them, an innovative hybrid topology, a digital-delta (& UDelta;) modulator (& UDelta;M) ADC employing noise shaping (NS), is proposed. To implement the active building blocks, several standard-cell-based synthesizable comparators and amplifiers are examined and compared in terms of their key performance parameters. The simulation results of a fully synthesizable Digital-& UDelta;M with NS using passive and standard-cell-based circuitry show a peak of 72.5 dB in the signal-to-noise and distortion ratio (SNDR) for a 113 kHz input signal and 1 MHz bandwidth (BW). The estimated FoMWalden is close to 16.2 fJ/conv.-step.

Abstract
Background: Multiple sclerosis (MS) is a neurologic disease of the central nervous system which affects almost three million people worldwide. MS is characterized by a demyelination process that leads to brain lesions, allowing these affected areas to be visualized with magnetic resonance imaging (MRI). Deep learning techniques, especially computational algorithms based on convolutional neural networks (CNNs), have become a frequently used algorithm that performs feature self-learning and enables segmentation of structures in the image useful for quantitative analysis of MRIs, including quantitative analysis of MS. To obtain quantitative information about lesion volume, it is important to perform proper image preprocessing and accurate segmentation. Therefore, we propose a method for volumetric quantification of lesions on MRIs of MS patients using automatic segmentation of the brain and lesions by two CNNs. Methods: We used CNNs at two different moments: the first to perform brain extraction, and the second for lesion segmentation. This study includes four independent MRI datasets: one for training the brain segmentation models, two for training the lesion segmentation model, and one for testing. Results: The proposed brain detection architecture using binary cross-entropy as the loss function achieved a 0.9786 Dice coefficient, 0.9969 accuracy, 0.9851 precision, 0.9851 sensitivity, and 0.9985 specificity. In the second proposed framework for brain lesion segmentation, we obtained a 0.8893 Dice coefficient, 0.9996 accuracy, 0.9376 precision, 0.8609 sensitivity, and 0.9999 specificity. After quantifying the lesion volume of all patients from the test group using our proposed method, we obtained a mean value of 17,582 mm(3). Conclusions: We concluded that the proposed algorithm achieved accurate lesion detection and segmentation with reproducibility corresponding to state-of-the-art software tools and manual segmentation. We believe that this quantification method can add value to treatment monitoring and routine clinical evaluation of MS patients.

Abstract
It has been known for a while that the problem of multi-source domain adaptation can be regarded as a single source domain adaptation task where the source domain corresponds to a mixture of the original source domains. Nonetheless, how to adjust the mixture distribution weights remains an open question. Moreover, most existing work on this topic focuses only on minimizing the error on the source domains and achieving domain-invariant representations, which is insufficient to ensure low error on the target domain. In this work, we present a novel framework that addresses both problems and beats the current state of the art by using a mildly optimistic objective function and consistency regularization on the target samples.