Automatic pain assessment is an application in healthcare serving personalized pain care, and patients cannot self-report pain. Pain at the present is inferred from physiological dynamics at the present and in the near past. However, heterogeneous pain responses cross-subject and cross-type hinder accurate recognition of pain. This work solves the adaptive pain recognition problem across pain types. We concrete the adaptivity problem into recognizing both phasic/short and tonic/long pain from the physiological sequences of the same length. The adaptivity of the proposed solution (TCAtt-PainNet) was ensured by hybrid temporal-channel attention when fusing multivariate time-series of electrocardiogram (ECG) and galvanic skin response (GSR) features. The attention was obtained by learning the dependencies between the point at present and the sequence in the near past, where sequence point temporal attention was constructed via modified self-attention, and the following feature channel attention was constructed by squeeze-and-excitation temporal attention weighted deep feature sequence. The proposed solution successfully enhanced recognition adaptivity by addressing relevant information only from long input sequences when testing with tonic and phasic pain databases, making progress towards automatic pain assessment for real application scenarios with attributes unknown pain.

This paper presents an investigation into the use of a heteroscedastic Bayesian neural network (HBNN) for predicting sea ice concentration (SIC) using both passive microwave (PM) and atmospheric data. The primary objective is to provide accurate estimates for downstream services that require uncertainty estimates. To achieve this, HBNNs are implemented using a multilayer perceptron (MLP) architecture with methods for uncertainty quantification based on the Bayes by backprop (BBB) algorithm and a heteroscedastic loss function. The models are trained and tested using data collected from the Eastern Arctic regions. The results of numerical analysis demonstrate that the HBNNs are able to significantly reduce estimation error compared to deterministic NNs. The study also investigates the spatial and seasonal variation of uncertainty in detail.

Algorithms designed for ice–water classification of synthetic aperture radar (SAR) sea ice imagery produce only binary (ice and water) output typically using manually labeled samples for assessment. This is limiting because only a small subset of labeled samples are used, which, given the nonstationary nature of the ice and water classes, will likely not reflect the full scene. To address this, we implement a binary ice–water classification in a more informative manner considering the uncertainty associated with each pixel in the scene. To accomplish this, we have implemented a Bayesian convolutional neural network (CNN) with variational inference to produce both aleatoric (data-based) and epistemic (model-based) uncertainty. This valuable information provides feedback as to regions that have pixels more likely to be misclassified and provides improved scene interpretation. Testing was performed on a set of 21 RADARSAT-2 dual-polarization SAR scenes covering a region in the Beaufort Sea captured regularly from April to December. The model is validated by demonstrating: 1) a positive correlation between misclassification rate and model uncertainty and 2) a higher uncertainty during the melt and freeze-up transition periods, which are more challenging to classify. By incorporating the iterative region growing with semantics (IRGS) segmentation algorithm and an uncertainty value-based thresholding algorithm, the Bayesian CNN classification outputs are improved significantly via both numerical analysis and visual inspection.

Atrial fibrillation (AF) is one of the clinic's most common arrhythmias with high morbidity and mortality. Developing an intelligent auxiliary diagnostic model of AF based on a body surface electrocardiogram (ECG) is necessary. Convolutional neural network (CNN) is one of the most commonly used models for AF recognition. However, typical CNN is not compatible with variable-duration ECG, so it is hard to demonstrate its universality and generalization in practical applications. Hence, this paper proposes a novel Time-adaptive densely network named MP-DLNet-F. The MP-DLNet module solves the problem of incompatibility between variable-duration ECG and 1D-CNN. In addition, the feature enhancement module and data imbalance processing module are respectively used to enhance the perception of temporal-quality information and decrease the sensitivity to data imbalance. The experimental results indicate that the proposed MP-DLNet-F achieved 87.98% classification accuracy, and F1-score of 0.847 on the CinC2017 database for 10-second cropped/padded single-lead ECG fragments. Furthermore, we deploy transfer learning techniques to test heterogeneous datasets, and in the CPSC2018 12-lead dataset, the method improved the average accuracy and F1-score by 21.81% and 16.14%, respectively. Experimental results indicate that our method can update the constructed model's parameters and precisely forecast AF with different duration distributions and lead distributions. Combining these advantages, MP-DLNet-F can exemplify all kinds of varied-duration or imbalance medical signal processing problems such as Electroencephalogram (EEG) and Photoplethysmography (PPG).

Monitoring sea ice in polar regions is essential for environmental modeling and ship navigation. National ice agencies expect robust sea ice classification methods for operational use. However, fully supervised machine learning models require large training datasets, which are usually limited to the sea ice classification domain. Therefore, a semi-supervised sea ice classification model is proposed to address this challenge. First, the IRGS segmentation is applied to generate superpixels that construct the graph. Then, two graph convolutional layers are utilized to learn the features of each node. Finally, a softmax layer assigns labels to the nodes in the graph. The proposed model is named IRGS-GCN and tested on four RADARSAR-2 dual-polarized scenes. The experimental results show that the IRGS-GCN achieves an overall accuracy of 95.17% and outperforms fully-supervised random foreset and ResNet trained on limited data. Most of the sea ice boundary and leads are successfully preserved in the results.

Atrial fibrillation (AF) is a serious medical condition of the heart potentially leading to stroke, which can be diagnosed by analyzing electrocardiograms (ECG). Technologies of Artificial Intelligence of Things (AIoT) enable smart abnormality detection by analyzing streaming healthcare data from the sensor end of users. Analyzing streaming data in the cloud leads to challenges of response latency and privacy issues, and local inference by a model deployed on the user end brings difficulties in model update and customization. Therefore, we propose an AIoT Platform with AF recognition neural networks on the sensor edge with model retraining ability on a resource-constrained embedded system. To this aim, we proposed to combine simple but effective neural networks and an ECG feature selection strategy to reduce computing complexity while maintaining recognition performance. Based on the platform, we evaluated and discussed the performance, response time, and requirements for model retraining in the scenario of AF detection from ECG recordings. The proposed lightweight solution was validated with two public datasets and an ECG data stream simulation on an ATmega2560 processor, proving the feasibility of analysis and training on edge.

In this article, an efficient high-throughput depth engine is proposed to generate high-quality 3-D depth maps for speckle-pattern structured-light depth cameras. A dynamic-binarization (DB) method is introduced with a significant reduction of computational complexity in contrast to the sum-of-absolute-distance (SAD) method. The depth map evaluation shows good robustness compared with other window-based correlation methods. Parallel architecture and reuse of intermediate results are employed for efficient hardware implementation. Our design is verified on a field-programmable gate array (FPGA) and implemented in the SMIC 55-nm CMOS technology, achieving a frame rate of 1731.77 fps ($640\times480$) with an area efficiency of 3.75 fps/KGE. The proposed engine shows a$2.71\times $promotion of area efficiency in contrast to the SAD-based implementation. In addition, the subpixel estimation algorithm deployed in postprocessing is optimized for efficient hardware implementation, reducing the gate count by 69.2% without significant performance loss.

The Canadian RADARSAT Constellation Mission (RCM) proposes a new synthetic aperture radar (SAR) data mode called compact (hybrid or partial) polarimetry (CP) in a wide swath. Compact polarimetry maximizes the measurement potential if the multilook complex (MLC) coherence matrix of the SAR backscattered field is used. The MLC CP coherence matrix follows the Wishart distribution. In this paper, an unsupervised region-based semantic segmentation of the MLC CP coherence matrix data using the complex Wishart distribution is presented. The segmentation method is an extension of the iterative region growing with semantics (IRGS) to complex CP data. The proposed algorithm is called CP-IRGS and is formulated based on conditional random fields (CRFs) incorporating edge strength over the image. Applications of the algorithm are demonstrated using a simulated MLC CP data set and a real single-look complex (SLC) quadrature polarimetric (QP) SAR data set which is used to derive the MLC CP data.

An analog neural network computing engine based on CMOS-compatible charge-trap transistor (CTT) is proposed in this paper. CTT devices are used as analog multipliers. Compared to digital multipliers, CTT-based analog multiplier shows significant area and power reduction. The proposed computing engine is composed of a scalable CTT multiplier array and energy efficient analog-digital interfaces. By implementing the sequential analog fabric, the engine's mixed-signal interfaces are simplified and hardware overhead remains constant regardless of the size of the array. A proof-of-concept 784 by 784 CTT computing engine is implemented using TSMC 28-nm CMOS technology and occupies 0.68 mm2. The simulated performance achieves 76.8 TOPS (8-bit) with 500 MHz clock frequency and consumes 14.8 mW. As an example, we utilize this computing engine to address a classic pattern recognition problem-classifying handwritten digits on MNIST database and obtained a performance comparable to state-of-the-art fully connected neural networks using 8-bit fixed-point resolution.

Automatic classification methods using satellite imagery are beneficial in the sea-ice-type mapping of the Arctic regions. In the near future, the RADARSAT Constellation Mission (RCM) will be launched, providing unique compact polarimetric (CP) synthetic aperture radar (SAR) data, expected to be an improvement over the current RADARSAT-2 dual-polarimetric SAR imagery. This motivates the implementation of a CP-dedicated automatic scene classification approach. First, an existing unsupervised segmentation algorithm called iterative region growing using semantics (IRGS) is used to segment ice-class homogeneous regions to reduce the impact of speckle noise. Second, a support vector machine (SVM) is used to classify the ice-type labels for each homogeneous region. Two complex quad-polarimetric RADARSAT-2 scenes are used to mathematically simulate the corresponding CP scenes for algorithm testing. Classification accuracy shows that using only the two CP intensity images leads to improved results compared with standard dual-polarimetric scenes. Using the CP data, the best classification results are obtained with the reconstructed QP data for the IRGS segmentation and all derived CP features for the SVM labeling. The results support the expected potential that CP scenes will provide improved sea-ice classification than the current operational dual-pol scenes.

Facial expressions are among behavioral signs of pain that can be employed as an entry point to develop an automatic human pain assessment tool. Such a tool can be an alternative to the self-report method and particularly serve patients who are unable to self-report like patients in the intensive care unit and minors. In this paper, a wearable device with a biosensing facial mask is proposed to monitor pain intensity of a patient by utilizing facial surface electromyogram (sEMG). The wearable device works as a wireless sensor node and is integrated into an Internet of Things (IoT) system for remote pain monitoring. In the sensor node, up to eight channels of sEMG can be each sampled at 1000 Hz, to cover its full frequency range, and transmitted to the cloud server via the gateway in real time. In addition, both low energy consumption and wearing comfort are considered throughout the wearable device design for long-term monitoring. To remotely illustrate real-time pain data to caregivers, a mobile web application is developed for real-time streaming of high-volume sEMG data, digital signal processing, interpreting, and visualization. The cloud platform in the system acts as a bridge between the sensor node and web browser, managing wireless communication between the server and the web application. In summary, this study proposes a scalable IoT system for real-time biopotential monitoring and a wearable solution for automatic pain assessment via facial expressions.

In medical care, it is essential to assess and manage acute painful conditions adequately. Heart rate variability (HRV) analysis is based on the acquisition of electrocardiogram (ECG), which is available from both patient monitor and wearable device. As HRV analysis can reflect autonomic nervous system activity which is unconsciously regulated, HRV analysis in ultra-short-term is getting attention in indicating the reaction due to acute pain. Different HRV features in different window lengths are involved in pain monitoring studies as a signal index or part of a multi-parameter model. In this work, seven HRV features and median heart rate (HR) in ultra-short-term are evaluated for their competence in indicating experimental acute pain. Also, the choice of time window length in HRV analysis and its relation with pain detection are discussed. The results of the normalized HRV analysis from healthy volunteers show that the changes of lnRMSSD, pNN20 and median HR associated with the intensity of experimental electrical pain; and in the tests with experimental thermal pain, lnLF and ln(LF/HF) changed along with pain intensity. The fusion of the HRV features could tell pain from no pain. With either experimental pain stimulation, optimal time window length was observed around or larger than 40 seconds with better correlation analysis result and HRV feature fusion performance.

A better lifestyle starts with a healthy heart. Unfortunately, millions of people around the world are either directly affected by heart diseases such as coronary artery disease and heart muscle disease (Cardiomyopathy), or are indirectly having heart-related problems like heart attack and/or heart rate irregularity. Monitoring and analyzing these heart conditions in some cases could save a life if proper actions are taken accordingly. A widely used method to monitor these heart conditions is to use ECG or electrocardiography. However, devices used for ECG are costly, energy inefficient, bulky, and mostly limited to the ambulatory environment. With the advancement and higher affordability of Internet of Things (IoT), it is possible to establish better health-care by providing real-time monitoring and analysis of ECG. In this paper, we present a low-cost health monitoring system that provides continuous remote monitoring of ECG together with automatic analysis and notification. The system consists of energy-efficient sensor nodes and a fog layer altogether taking advantage of IoT. The sensor nodes collect and wirelessly transmit ECG, respiration rate, and body temperature to a smart gateway which can be accessed by appropriate care-givers. In addition, the system can represent the collected data in useful ways, perform automatic decision making and provide many advanced services such as real-time notifications for immediate attention.

This letter presents a novel method for ship classification that uses synthetic-aperture-radar images to distinguish ships based on superstructure scattering features. The ratio of dimensions, which combines the 2-D and 3-D properties of scattering, is explored as an effective and credible means to describe the scattering features of ships. The proposed method consists of three main stages: 1) ship isolation from the sea; 2) parametric vector (F) estimation; and 3) categorization using a support vector machine (SVM) classifier. To depict ship features more accurately and reduce feature redundancy, we propose employing peak extraction to divide a ship into bow, middle, and stern instead of into three equal parts. The classification method is tested with RadarSat-2 images, and ground-truth information is supplied by an automatic identification system. The experimental results show that the proposed method can achieve satisfactory ship-classification performance compared with existing methods, with an overall accuracy exceeding 80%.