Search

Tissue hysteresivity is an important marker for determining the onset and progression of respiratory diseases, calculated from forced oscillation lung function test data. This study aims to reduce the number and duration of required measurements by combining multivariate data from various sensing devices. We propose using the Forced Oscillation Technique (FOT) lung function test in both a low-frequency prototype and the commercial RESMON device, combined with continuous monitoring from the Equivital (EQV) LifeMonitor and processed by artificial intelligence (AI) algorithms. While AI and deep learning have been employed in various aspects of respiratory system analysis, such as predicting lung tissue displacement and respiratory failure, the prediction or forecasting of tissue hysteresivity remains largely unexplored in the literature. In this work, the Long Short-Term Memory (LSTM) model is used in two ways: (1) to estimate the hysteresivity coefficient η using heart rate (HR) data collected continuously by the EQV sensor, and (2) to forecast η values by first predicting the heart rate from electrocardiogram (ECG) data. Our methodology involves a rigorous two-hour measurement protocol, with synchronized data collection from the EQV, FOT, and RESMON devices. Our results demonstrate that LSTM networks can accurately estimate the tissue hysteresivity parameter η, achieving an R2 of 0.851 and a mean squared error (MSE) of 0.296 for estimation, and forecast η with an R2 of 0.883 and an MSE of 0.528, while significantly reducing the number of required measurements by a factor of three (i.e., from ten to three) for the patient. We conclude that our novel approach minimizes patient effort by reducing the measurement time and the overall ambulatory time and costs while highlighting the potential of artificial intelligence methods in respiratory monitoring.

In this study two elastic polyester fabrics differentiated by a graphene-printed pattern, called honeycomb (HC) and spider web (SW), were analyzed with a focus on their thermal, mechanical, moisture management and sensorial properties, aiming to identify the fabric with the most elevated heat dissipation and comfort for sportswear. The shape of the graphene-printed circuit did not lead to significant difference between the mechanical properties of the fabrics SW and HC assessed by the Fabric Touch Tester (FTT). Fabric SW outperformed fabric HC with respect of drying time, air permeability, moisture, and liquid management properties. On the other hand, both the Infrared (IR) thermography and FTT-predicted warmness clearly showed that fabric HC dissipates heat faster on its surface along the graphene circuit. This fabric was also predicted by the FTT as smoother and softer than fabric SW and had a better overall fabric hand. The results revealed that both graphene patterns resulted in comfortable fabrics with great potential applications in sportswear fields, in specific use scenario's.

This study investigated the application of a dynamic control strategy in an aerobic granular sludge (AGS) reactor treating real variable brewery/bottling wastewater. For 482 days, the anaerobic and aerobic reaction steps in a lab-scale AGS system were controlled dynamically. A pH-based control was used for the anaerobic step, and an oxygen uptake rate (OUR) based control for the aerobic step. Additionally, the effect of an elongated aerobic step, and the effect of the removal of the suspended solids from the influent, on AGS formation were also investigated. In comparison to a static operation, the dynamic operation resulted in similar reactor performance, related to effluent quality and the anaerobic dissolved organic carbon (DOC) uptake efficiency, while the organic loading rate was significantly higher. The removal of suspended solids from the influent by chemical coagulation with FeCl 3 turned hybrid floccular-granular sludge into fully granular sludge. The granulation coincided with a significant increase in the abundance of the glycogen-accumulating Candidatus Competibacter and an increase in the content of gel-forming EPS to respectively around 14% and 30%. In conclusion, this study showed the successful application of a dynamic control strategy based on common and low-cost sensors for AGS treatment of industrial wastewater.

Gaze gestures are extensively used in the interactions with agents/computers/robots. Either remote eye tracking devices or head-mounted devices (HMDs) have the advantage of hands-free during the interaction. Previous studies have demonstrated the success of applying machine learning techniques for gaze gesture recognition. More recently, graph neural networks (GNNs) have shown great potential applications in several research areas such as image classification, action recognition, and text classification. However, GNNs are less applied in eye tracking researches. In this work, we propose a graph convolutional network (GCN)-based model for gaze gesture recognition. We train and evaluate the GCN model on the HideMyGaze! dataset. The results show that the accuracy, precision, and recall of the GCN model are 97.62%, 97.18%, and 98.46%, respectively, which are higher than the other compared conventional machine learning algorithms, the artificial neural network (ANN) and the convolutional neural network (CNN)., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Shi, Copot and Vanlanduit.)

Safety is an important issue in human-robot interaction (HRI) applications. Various research works have focused on different levels of safety in HRI. If a human/obstacle is detected, a repulsive action can be taken to avoid the collision. Common repulsive actions include distance methods, potential field methods, and safety field methods. Approaches based on machine learning are less explored regarding the selection of the repulsive action. Few research works focus on the uncertainty of the data-based approaches and consider the efficiency of the executing task during collision avoidance. In this study, we describe a system that can avoid collision with human hands while the robot is executing an image-based visual servoing (IBVS) task. We use Monte Carlo dropout (MC dropout) to transform a deep neural network (DNN) to a Bayesian DNN, and learn the repulsive position for hand avoidance. The Bayesian DNN allows IBVS to converge faster than the opposite repulsive pose. Furthermore, it allows the robot to avoid undesired poses that the DNN cannot avoid. The experimental results show that Bayesian DNN has adequate accuracy and can generalize well on unseen data. The predictive interval coverage probability (PICP) of the predictions along x , y , and z directions are 0.84, 0.94, and 0.95, respectively. In the space which is unseen in the training data, the Bayesian DNN is also more robust than a DNN. We further implement the system on a UR10 robot, and test the robustness of the Bayesian DNN and the IBVS convergence speed. Results show that the Bayesian DNN can avoid the poses out of the reach range of the robot and it lets the IBVS task converge faster than the opposite repulsive pose., Competing Interests: The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest., (Copyright © 2021 Shi, Copot and Vanlanduit.)

Treatment of rapidly varying wastewaters in anaerobic/aerobic aerobic granular sludge (AGS) systems remains problematic. This study investigated AGS formation and the impact of varying COD and phosphorus concentrations on an enhanced biological phosphorus removal (EBPR) AGS SBR with a conductivity based anaerobic and OUR based aerobic dynamically controlled step. Phase 1 investigated the development of AGS. Phase 2 examined the flexibility of the dynamic control strategy and AGS efficiency while rapidly altering the influent composition. AGS was formed successfully in phase 1: the DV50 increased to 285 µm, and the SVI5 and SVI30 decreased to 51 and 40 ml/g respectively. In phase 2 the effluent COD and PO4-P concentration remained low at respectively 58 ± 27 mg/L and 0.53 ± 0.77 mg/L. With an anaerobic DOC uptake efficiency of 98.4 ± 0.9%., (Copyright © 2019 Elsevier Ltd. All rights reserved.)

This paper presents a new tuning method for fractional-order (FO)PID controllers to simplify current tuning and make FOPID controllers more convenient for industry, i.e. facilitate transition from state-of-art to state-of-use. The number of tuning parameters is reduced from five to three based on popular specification settings for PID controllers without the need for reduced process models which introduce modeling errors. A test batch of 133 simulated processes and two real-life processes are used to test the presented method. A comparative study between the new method and the established CRONE controller, quantifies the performance. The conclusion states that the new method gives fractional controllers with similar performances as the current methods but with a significantly decreased tuning complexity making FOPID controllers more acceptable to industry., (Copyright © 2018 ISA. Published by Elsevier Ltd. All rights reserved.)

Sensing is an important element to quantify productivity, product quality and to make decisions. Applications, such as mapping, surveillance, exploration and precision agriculture, require a reliable platform for remote sensing. This paper presents the first steps towards the development of a smart flying sensor based on an unmanned aerial vehicle (UAV). The concept of smart remote sensing is illustrated and its performance tested for the task of mapping the volume of grain inside a trailer during forage harvesting. Novelty lies in: (1) the development of a position-estimation method with time delay compensation based on inertial measurement unit (IMU) sensors and image processing; (2) a method to build a 3D map using information obtained from a regular camera; and (3) the design and implementation of a path-following control algorithm using model predictive control (MPC). Experimental results on a lab-scale system validate the effectiveness of the proposed methodology.