The early and reliable detection of COVID-19 infected patients is essential to prevent and limit its outbreak. The PCR tests for COVID-19 detection are not available in many countries, and also, ...there are genuine concerns about their reliability and performance. Motivated by these shortcomings, this article proposes a deep uncertainty-aware transfer learning framework for COVID-19 detection using medical images. Four popular convolutional neural networks (CNNs), including VGG16, ResNet50, DenseNet121, and InceptionResNetV2, are first applied to extract deep features from chest X-ray and computed tomography (CT) images. Extracted features are then processed by different machine learning and statistical modeling techniques to identify COVID-19 cases. We also calculate and report the epistemic uncertainty of classification results to identify regions where the trained models are not confident about their decisions (out of distribution problem). Comprehensive simulation results for X-ray and CT image data sets indicate that linear support vector machine and neural network models achieve the best results as measured by accuracy, sensitivity, specificity, and area under the receiver operating characteristic (ROC) curve (AUC). Also, it is found that predictive uncertainty estimates are much higher for CT images compared to X-ray images.
Autonomous Vehicles (AVs) have shown indelible and revolutionary effects on accident reduction and more efficient use of travel time, with outstanding socio‐economic impact. Despite these benefits, ...to make AVs accepted by a wide demographic and produce them on an industrial scale with a reasonable price, there are still a number of technological and social challenges that need to be tackled. Path Tracking Controller (PTC) of AVs is one of the high potential subsystems that can be further improved in order to achieve more accurate, robust and comfortable tracking performance. This study provides a critical review and simulation study of several selected techniques used for the design of PTC of AVs. The AVs are assumed to have limited controllability due to non‐holonomic constraints, such as car‐like vehicles and differential drive mobile robots. A detailed discussion will be provided on the simulation outcomes as well as the pros and cons of each technique for the sake of implementation and improvement of state‐of‐the‐art PTC.
Staying at the top is getting tougher and more challenging due to the fast-growing and changing digital technologies and AI-based solutions. The world of technology, mass customization, and advanced ...manufacturing is experiencing a rapid transformation. Robots are becoming even more important as they can now be coupled with the human mind by means of brain–machine interface and advances in artificial intelligence. A strong necessity to increase productivity while not removing human workers from the manufacturing industry is imposing punishing challenges on the global economy. To counter these challenges, this article introduces the concept of Industry 5.0, where robots are intertwined with the human brain and work as collaborator instead of competitor. This article also outlines a number of key features and concerns that every manufacturer may have about Industry 5.0. In addition, it presents several developments achieved by researchers for use in Industry 5.0 applications and environments. Finally, the impact of Industry 5.0 on the manufacturing industry and overall economy is discussed from an economic and productivity point of view, where it is argued that Industry 5.0 will create more jobs than it will take away.
Uncertainty quantification (UQ) methods play a pivotal role in reducing the impact of uncertainties during both optimization and decision making processes. They have been applied to solve a variety ...of real-world problems in science and engineering. Bayesian approximation and ensemble learning techniques are two widely-used types of uncertainty quantification (UQ) methods. In this regard, researchers have proposed different UQ methods and examined their performance in a variety of applications such as computer vision (e.g., self-driving cars and object detection), image processing (e.g., image restoration), medical image analysis (e.g., medical image classification and segmentation), natural language processing (e.g., text classification, social media texts and recidivism risk-scoring), bioinformatics, etc. This study reviews recent advances in UQ methods used in deep learning, investigates the application of these methods in reinforcement learning, and highlights fundamental research challenges and directions associated with UQ.
•We provided an extensive review of uncertainty quantification methods in deep learning.•We covered popular and efficient Bayesian approaches for uncertainty quantification.•We listed notable ensemble techniques for quantifying uncertainty.•We discussed various applications of uncertainty quantification methods.•We summarized major open challenges and research gaps in uncertainty quantification.
Optical measurement techniques and recent advances in wearable technology have made heart rate (HR) sensing simpler and more affordable.
The Polar OH1 is an arm worn optical heart rate monitor. The ...objectives of this study are two-fold; 1) to validate the OH1 optical HR sensor with the gold standard of HR measurement, electrocardiography (ECG), over a range of moderate to high intensity physical activities, 2) to validate wearing the OH1 at the temple as an alternative location to its recommended wearing location around the forearm and upper arm.
Twenty-four individuals participated in a physical exercise protocol, by walking on a treadmill and riding a stationary spin bike at different speeds while the criterion measure, ECG and Polar OH1 HR were recorded simultaneously at three different body locations; forearm, upper arm and the temple. Time synchronised HR data points were compared using Bland-Altman analyses and intraclass correlation.
The intraclass correlation between the ECG and Polar OH1, for the aggregated data, was 0.99 and the estimated mean bias ranged 0.27-0.33 bpm for the sensor locations. The three sensors exhibited a 95% limit of agreement (LoA: forearm 5.22, -4.68 bpm; upper arm 5.15, -4.49; temple 5.22, -4.66). The mean of the ECG HR for the aggregated data was 112.15 ± 24.52 bpm. The intraclass correlation of HR values below and above this mean were 0.98 and 0.99 respectively. The reported mean bias ranged 0.38-0.47 bpm (95% LoA: forearm 6.14, -5.38 bpm; upper arm 6.07, -5.13 bpm; temple 6.09, -5.31 bpm), and 0.15-0.16 bpm (95% LoA: forearm 3.99, -3.69 bpm; upper arm 3.90, -3.58 bpm; temple 4.06, -3.76 bpm) respectively. During different exercise intensities, the intraclass correlation ranged 0.95-0.99 for the three sensor locations. During the entire protocol, the estimated mean bias was in the range -0.15-0.55 bpm, 0.01-0.53 bpm and -0.37-0.48 bpm, for the forearm, upper arm and temple locations respectively. The corresponding upper limits of 95% LoA were 3.22-7.03 bpm, 3.25-6.82 bpm and 3.18-7.04 bpm while the lower limits of 95% LoA were -6.36-(-2.35) bpm, -6.46-(-2.30) bpm and -7.42-(-2.41) bpm.
Polar OH1 demonstrates high level of agreement with the criterion measure ECG HR, thus can be used as a valid measure of HR in lab and field settings during moderate and high intensity physical activities.
Deep neural networks (DNNs) have been widely applied for detecting COVID-19 in medical images. Existing studies mainly apply transfer learning and other data representation strategies to generate ...accurate point estimates. The generalization power of these networks is always questionable due to being developed using small datasets and failing to report their predictive confidence. Quantifying uncertainties associated with DNN predictions is a prerequisite for their trusted deployment in medical settings. Here we apply and evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray (CXR) images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced. Through comprehensive experiments, it is shown that networks pertained on CXR images outperform networks pretrained on natural image datasets such as ImageNet. Qualitatively and quantitatively evaluations also reveal that the predictive uncertainty estimates are statistically higher for erroneous predictions than correct predictions. Accordingly, uncertainty quantification methods are capable of flagging risky predictions with high uncertainty estimates. We also observe that ensemble methods more reliably capture uncertainties during the inference. DNN-based solutions for COVID-19 detection have been mainly proposed without any principled mechanism for risk mitigation. Previous studies have mainly focused on on generating single-valued predictions using pretrained DNNs. In this paper, we comprehensively apply and comparatively evaluate three uncertainty quantification techniques for COVID-19 detection using chest X-Ray images. The novel concept of uncertainty confusion matrix is proposed and new performance metrics for the objective evaluation of uncertainty estimates are introduced for the first time. Using these new uncertainty performance metrics, we quantitatively demonstrate when we could trust DNN predictions for COVID-19 detection from chest X-rays. It is important to note the proposed novel uncertainty evaluation metrics are generic and could be applied for evaluation of probabilistic forecasts in all classification problems.
COVID-19 has caused many deaths worldwide. The automation of the diagnosis of this virus is highly desired. Convolutional neural networks (CNNs) have shown outstanding classification performance on ...image datasets. To date, it appears that COVID computer-aided diagnosis systems based on CNNs and clinical information have not yet been analysed or explored. We propose a novel method, named the CNN-AE, to predict the survival chance of COVID-19 patients using a CNN trained with clinical information. Notably, the required resources to prepare CT images are expensive and limited compared to those required to collect clinical data, such as blood pressure, liver disease, etc. We evaluated our method using a publicly available clinical dataset that we collected. The dataset properties were carefully analysed to extract important features and compute the correlations of features. A data augmentation procedure based on autoencoders (AEs) was proposed to balance the dataset. The experimental results revealed that the average accuracy of the CNN-AE (96.05%) was higher than that of the CNN (92.49%). To demonstrate the generality of our augmentation method, we trained some existing mortality risk prediction methods on our dataset (with and without data augmentation) and compared their performances. We also evaluated our method using another dataset for further generality verification. To show that clinical data can be used for COVID-19 survival chance prediction, the CNN-AE was compared with multiple pre-trained deep models that were tuned based on CT images.
The sensation of self-motion in the absence of physical motion, known as
vection
, has been scientifically investigated for over a century. As objective measures of, or physiological correlates to, ...vection have yet to emerge, researchers have typically employed a variety of subjective methods to quantify the phenomenon of vection. These measures can be broadly categorized into the occurrence of vection (e.g., binary choice yes/no), temporal characteristics of vection (e.g., onset time/latency, duration), the quality of the vection experience (e.g., intensity rating scales, magnitude estimation), or indirect (e.g., distance travelled) measures. The present review provides an overview and critical evaluation of the most utilized vection measures to date and assesses their respective merit. Furthermore, recommendations for the selection of the most appropriate vection measures will be provided to assist with the process of vection research and to help improve the comparability of research findings across different vection studies.
•Propose a two-step hierarchical shrinking search space when a descriptoris used.•Transfer learning via CNNs is utilized for the first stage shrinking.•A selection pool using Radon transform is ...created for further shrinking.•Difference between two orthogonal Radon projections is considered in the pool.•A state-of-the-art result is achieved on the IRMA challenging dataset.
Closing the semantic gap in medical image analysis is critical. Access to large-scale datasets might help to narrow the gap. However, large and balanced datasets may not always be available. On the other side, retrieving similar images from an archive is a valuable task to facilitate better diagnosis. In this work, we concentrate on forming a search space, consisting of the most similar images for a given query, to be used for a similarity-based search technique in a retrieval system. We propose a two-step hierarchical shrinking search space when local binary patterns are used. Transfer learning via convolutional neural networks is utilized for the first stage of search space shrinking, followed by creating a selection pool using Radon transform for further reduction. The difference between two orthogonal Radon projections is considered in the selection pool to extract more information. The IRMA dataset, from ImageCLEF initiative, containing 14,400 X-ray images, is used to validate the proposed scheme. We report a total IRMA error of 168.05 (or 90.30% accuracy) which is the best result compared with existing methods in the literature for this dataset when real-time processing is considered.
Providing autonomous systems with an effective quantity and quality of information from a desired task is challenging. In particular, autonomous vehicles, must have a reliable vision of their ...workspace to robustly accomplish driving functions. Speaking of machine vision, deep learning techniques, and specifically convolutional neural networks, have been proven to be the state of the art technology in the field. As these networks typically involve millions of parameters and elements, designing an optimal architecture for deep learning structures is a difficult task which is globally under investigation by researchers. This study experimentally evaluates the impact of three major architectural properties of convolutional networks, including the number of layers, filters, and filter size on their performance. In this study, several models with different properties are developed, equally trained, and then applied to an autonomous car in a realistic simulation environment. A new ensemble approach is also proposed to calculate and update weights for the models regarding their mean squared error values. Based on design properties, performance results are reported and compared for further investigations. Surprisingly, the number of filters itself does not largely affect the performance efficiency. As a result, proper allocation of filters with different kernel sizes through the layers introduces a considerable improvement in the performance. Achievements of this study will provide the researchers with a clear clue and direction in designing optimal network architectures for deep learning purposes.
PDF
