Search

Underwater communication signals typically suffer from distortion due to motion-induced Doppler. Especially in shallow water environments, recovering the signal is challenging due to the time-varying Doppler effects distorting each path differently. However, conventional Doppler estimation algorithms typically model uniform Doppler across all paths and often fail to provide robust Doppler tracking in multipath environments. In this paper, we propose a dynamic programming-inspired method, called online segmented recursive least-squares (OSRLS) to sequentially estimate the time-varying non-uniform Doppler across different multipath arrivals. By approximating the non-linear time distortion as a piece-wise-linear Markov model, we formulate the problem in a dynamic programming framework known as segmented least-squares (SLS). In order to circumvent an ill-conditioned formulation, perturbations are added to the Doppler model during the linearization process. The successful operation of the algorithm is demonstrated in a simulation on a synthetic channel with time-varying non-uniform Doppler.

The ability to extrapolate gene expression dynamics in living single cells requires robust cell segmentation, and one of the challenges is the amorphous or irregularly shaped cell boundaries. To address this issue, we modified the U-Net architecture to segment cells in fluorescence widefield microscopy images and quantitatively evaluated its performance. We also proposed a novel loss function approach that emphasizes the segmentation accuracy on cell boundaries and encourages shape feature preservation. With a 97% sensitivity, 93% specificity, 91% Jaccard similarity, and 95% Dice coefficient, our proposed method called Residual Attention U-Net with edge-enhancement surpassed the state-of-the-art U-Net in segmentation performance as evaluated by the traditional metrics. More remarkably, the same proposed candidate also performed the best in terms of the preservation of valuable shape features, namely area, eccentricity, major axis length, solidity and orientation. These improvements on shape feature preservation can serve as useful assets for downstream cell tracking and quantification of changes in cell statistics or features over time.

The domain of public safety in the form of search \& rescue, wildland firefighting, structure firefighting, and law enforcement operations have drawn great interest in the field of aerospace engineering, human-robot teaming, autonomous systems, and robotics. However, a divergence exists in the assumptions made in research and how state-of-the-art technologies may realistically transition into an operational capacity. To aid in the alignment between researchers, technologists, and end users, we aim to provide perspective on how small Uncrewed Aerial Systems (sUAS) have been applied in 114 real world incidents as part of a technical rescue team from 2016 to 2021. We highlight the main applications, integration, tasks, and challenges of employing UAS within five primary use cases including searches, evidence collection, SWAT, wildland firefighting, and structure firefighting. Within these use cases, key incidents are featured that provide perspective on the evolving and dynamic nature of UAS tasking during an operation. Finally, we highlight key technical directions for improving the utilization and efficiency of employing aerial technology in all emergency types., Accepted to the International Conference of Unmanned Aerial Systems (ICUAS) 2022

Early prediction of patients at risk of clinical deterioration can help physicians intervene and alter their clinical course towards better outcomes. In addition to the accuracy requirement, early warning systems must make the predictions early enough to give physicians enough time to intervene. Interpretability is also one of the challenges when building such systems since being able to justify the reasoning behind model decisions is desirable in clinical practice. In this work, we built an interpretable model for the early prediction of various adverse clinical events indicative of clinical deterioration. The model is evaluated on two datasets and four clinical events. The first dataset is collected in a predominantly COVID-19 positive population at Stony Brook Hospital. The second dataset is the MIMIC III dataset. The model was trained to provide early warning scores for ventilation, ICU transfer, and mortality prediction tasks on the Stony Brook Hospital dataset and to predict mortality and the need for vasopressors on the MIMIC III dataset. Our model first separates each feature into multiple ranges and then uses logistic regression with lasso penalization to select the subset of ranges for each feature. The model training is completely automated and doesn't require expert knowledge like other early warning scores. We compare our model to the Modified Early Warning Score (MEWS) and quick SOFA (qSOFA), commonly used in hospitals. We show that our model outperforms these models in the area under the receiver operating characteristic curve (AUROC) while having a similar or better median detection time on all clinical events, even when using fewer features. Unlike MEWS and qSOFA, our model can be entirely automated without requiring any manually recorded features. We also show that discretization improves model performance by comparing our model to a baseline logistic regression model.

The Industrial Internet of Things (IIoT) plays a powerful role in smart manufacturing by performing real-time analysis for large volumes of data. In addition, IIoT systems can monitor several factors, such as data accuracy, network bandwidth and operations latency. To perform these operations securely and in a privacy-preserving manner, one solution is to use cryptographic primitives. However, most cryptographic solutions add performance overhead causing latency. In this paper, we propose an Edge Lightweight Searchable Attribute-based encryption system (ELSA). ELSA leverages the cloud-edge architecture to improve search time beyond the state-of-the-art. The main contributions of this paper are as follows. First, we present an untrusted cloud/trusted edge architecture, which optimises the efficiency of data processing and decision making in the IIoT context. Second, we enhance search performance over current state-of-the-art (LSABE-MA) by an order of magnitude. We achieve this by improving the organisation of the data to provide better than linear search performance. We leverage the edge server to cluster data indices by keyword and introduce a query optimiser. The query optimiser uses k-means clustering to improve the efficiency of range queries, removing the need for linear search. In addition, we achieve this without sacrificing accuracy over the results.

Development and testing of Advanced Driver Assistance Systems (ADAS) is largely based on models and simulations, but real data are indispensable for many reasons – to determine the relevant scenarios, to establish a connection between the results of the simulations and the real situation and of course as elements to set up realistic models. Using data, however, is not trivial, as not all data are informative, and even extensive data sets are often incomplete. Indeed, data is not automatically information, and the richness of the data sets is more important than their size. Data should be diverse not only with respect to different scenarios but also geographically in order to be not biased towards a specific location. In this paper, we present a new aerial-view dataset “Drone Over Roads” (DORA) of highway exits and entrances. The data have been collected by the Johannes Kepler University Linz (JKU), Austria and Italy and contain positions, velocities, and accelerations (in both local and global coordinate systems) of cars, vans, and trucks for Austria and additionally for motorbikes and buses in Italy. The uniqueness of the dataset consists not only in the measurements in different countries, but also in the flight height in Austria, where the recordings have been taken from 300 meters altitude allowing to observe an over 600 meters long section of the road. For non-commercial use, the dataset is available free of charge at the IEEE DataPort. Version of record

In response to the shortage of ventilators caused by the COVID-19 pandemic, many organizations have designed low-cost emergency ventilators. Many of these devices are pressure-cycled pneumatic ventilators, which are easy to produce but often do not include the sensing or alarm features found on commercial ventilators. This work reports a low-cost, easy-to-produce electronic sensor and alarm system for pressure-cycled ventilators that estimates clinically useful metrics such as pressure and respiratory rate and sounds an alarm when the ventilator malfunctions. A low-complexity signal processing algorithm uses a pair of nonlinear recursive envelope trackers to monitor the signal from an electronic pressure sensor connected to the patient airway. The algorithm, inspired by those used in hearing aids, requires little memory and performs only a few calculations on each sample so that it can run on nearly any microcontroller., Comment: Open-source hardware and software: https://rapidalarm.github.io/