End-to-End Ultrasonic Hand Gesture Recognition.

As the number of electronic gadgets in our daily lives is increasing and most of them require some kind of human interaction, this demands innovative, convenient input methods. There are limitations to state-of-the-art (SotA) ultrasound-based hand gesture recognition (HGR) systems in terms of robustness and accuracy. This research presents a novel machine learning (ML)-based end-to-end solution for hand gesture recognition with low-cost micro-electromechanical (MEMS) system ultrasonic transducers. In contrast to prior methods, our ML model processes the raw echo samples directly instead of using pre-processed data. Consequently, the processing flow presented in this work leaves it to the ML model to extract the important information from the echo data. The success of this approach is demonstrated as follows. Four MEMS ultrasonic transducers are placed in three different geometrical arrangements. For each arrangement, different types of ML models are optimized and benchmarked on datasets acquired with the presented custom hardware (HW): convolutional neural networks (CNNs), gated recurrent units (GRUs), long short-term memory (LSTM), vision transformer (ViT), and cross-attention multi-scale vision transformer (CrossViT). The three last-mentioned ML models reached more than 88% accuracy. The most important innovation described in this research paper is that we were able to demonstrate that little pre-processing is necessary to obtain high accuracy in ultrasonic HGR for several arrangements of cost-effective and low-power MEMS ultrasonic transducer arrays. Even the computationally intensive Fourier transform can be omitted. The presented approach is further compared to HGR systems using other sensor types such as vision, WiFi, radar, and state-of-the-art ultrasound-based HGR systems. Direct processing of the sensor signals by a compact model makes ultrasonic hand gesture recognition a true low-cost and power-efficient input method.

Few-Shot User-Adaptable Radar-Based Breath Signal Sensing.

Vital signs estimation provides valuable information about an individual's overall health status. Gathering such information usually requires wearable devices or privacy-invasive settings. In this work, we propose a radar-based user-adaptable solution for respiratory signal prediction while sitting at an office desk. Such an approach leads to a contact-free, privacy-friendly, and easily adaptable system with little reference training data. Data from 24 subjects are preprocessed to extract respiration information using a 60 GHz frequency-modulated continuous wave radar. With few training examples, episodic optimization-based learning allows for generalization to new individuals. Episodically, a convolutional variational autoencoder learns how to map the processed radar data to a reference signal, generating a constrained latent space to the central respiration frequency. Moreover, autocorrelation over recorded radar data time assesses the information corruption due to subject motions. The model learning procedure and breathing prediction are adjusted by exploiting the motion corruption level. Thanks to the episodic acquired knowledge, the model requires an adaptation time of less than one and two seconds for one to five training examples, respectively. The suggested approach represents a novel, quickly adaptable, non-contact alternative for office settings with little user motion.

Camera-LiDAR Multi-Level Sensor Fusion for Target Detection at the Network Edge.

There have been significant advances regarding target detection in the autonomous vehicle context. To develop more robust systems that can overcome weather hazards as well as sensor problems, the sensor fusion approach is taking the lead in this context. Laser Imaging Detection and Ranging (LiDAR) and camera sensors are two of the most used sensors for this task since they can accurately provide important features such as target´s depth and shape. However, most of the current state-of-the-art target detection algorithms for autonomous cars do not take into consideration the hardware limitations of the vehicle such as the reduced computing power in comparison with Cloud servers as well as the reduced latency. In this work, we propose Edge Computing Tensor Processing Unit (TPU) devices as hardware support due to their computing capabilities for machine learning algorithms as well as their reduced power consumption. We developed an accurate and small target detection model for these devices. Our proposed Multi-Level Sensor Fusion model has been optimized for the network edge, specifically for the Google Coral TPU. As a result, high accuracy results are obtained while reducing the memory consumption as well as the latency of the system using the challenging KITTI dataset.

A compact optical instrument with artificial neural network for pH determination.

The aim of this work was the determination of pH with a sensor array-based optical portable instrument. This sensor array consists of eleven membranes with selective colour changes at different pH intervals. The method for the pH calculation is based on the implementation of artificial neural networks that use the responses of the membranes to generate a final pH value. A multi-objective algorithm was used to select the minimum number of sensing elements required to achieve an accurate pH determination from the neural network, and also to minimise the network size. This helps to minimise instrument and array development costs and save on microprocessor energy consumption. A set of artificial neural networks that fulfils these requirements is proposed using different combinations of the membranes in the sensor array, and is evaluated in terms of accuracy and reliability. In the end, the network including the response of the eleven membranes in the sensor was selected for validation in the instrument prototype because of its high accuracy. The performance of the instrument was evaluated by measuring the pH of a large set of real samples, showing that high precision can be obtained in the full range.

Multiobjective hybrid optimization and training of recurrent neural networks.

The application of neural networks to solve a problem involves tasks with a high computational cost until a suitable network is found, and these tasks mainly involve the selection of the network topology and the training step. We usually select the network structure by means of a trial-and-error procedure, and we then train the network. In the case of recurrent neural networks (RNNs), the lack of suitable training algorithms sometimes hampers these procedures due to vanishing gradient problems. This paper addresses the simultaneous training and topology optimization of RNNs using multiobjective hybrid procedures. The proposal is based on the SPEA2 and NSGA2 algorithms for making hybrid methods using the Baldwinian hybridization strategy. We also study the effects of the selection of the objectives, crossover, and mutation in the diversity during evolution. The proposals are tested in the experimental section to train and optimize the networks in the competition on artificial time-series (CATS) benchmark.