Showing papers in "Smart Health in 2021"

TL;DR: This work globally presents the applied mask-to-face deformable model for permitting the generation of other masked face images, notably with specific masks and their combination for the global masked face detection (MaskedFace-Net).

TL;DR: In the wake of COVID-19 disease, caused by the SARS-CoV-2 virus, a predictive model based on Artificial Intelligence (AI) and Machine Learning (ML) algorithms to determine the health risk and predict the mortality risk of patients with CoV-19 was developed in this paper.

TL;DR: This paper explores the possibility of monitoring respiration rates (RR) of COVID-19 patients using a widely-available technology at home – WiFi and proposes Wi-COVID, a non-invasive and non-wearable technology to monitor the patient and track RR for the healthcare provider.

TL;DR: This work presents a novel gait-based continuous authentication method by applying multimodal learning on jointly recorded accelerometer and ground contact force data from smart wearable devices that can continuously authenticate a user.

TL;DR: iWash is a hybrid deep neural network based system that is optimized for on-device processing to ensure high accuracy with minimal processing time and battery usage and offers touch-free interaction between the user and the smartwatch that minimizes the risk of germ transmission.

TL;DR: The authors' geosocial features achieved significant performance improvement compared to baseline for predicting both momentary loneliness and companionship type, with the effect stronger for the loneliness prediction task.

TL;DR: In this article, the symbiotic relationship between blockchain and intelligent health is discussed and the obstacles for integrating blockchain-based applications in the health sector and several future research prospects are discussed.

TL;DR: This work provides a step forward in providing clinical informatics tool to assist clinician in providing early detections of abnormal heart conditions by utilising the first and second heart sounds produced due to vibrations during the closure of heart valves.

TL;DR: Noise robustness of SER models can be improved by combining the magnitude spectrogram with the modified group delay spectrogram, by including synthetic noise in the training data, and by using an attention mechanism.

TL;DR: A wireless sensing system capable of detecting voluntary coughs, sneezes, and face touching with alert based notifications sent to a mobile application and designed a set of fuzzy logic IF-THEN rules that can differentiate each activity from each other with an overall accuracy of 96%.

TL;DR: The region is recommended to leverage on the rapid expansion of internet and telecommunication in addition to adopting a mix of strategies to set up an infrastructure for providing scale up of telemedicine and overcome barriers to implementation during COVID-19 and beyond.

TL;DR: A deep Multi-Source Adversarial Domain Adaptation (MSADA) framework that opportunistically helps select the most relevant feature representations from multiple source domains and establish such mappings to the target domain by learning the perplexity scores is proposed.

TL;DR: In this paper, a deep learning model was developed using long short-term memory networks to predict the number of confirmed cases within the next week and demonstrated a promising prediction result with a coefficient of determination (R 2 ) of up to approximately 0.91.

TL;DR: A field test with over 30 subjects proved the usability and reliability of the system, while all data are made available for the community and first results of this campaign are presented within this paper.

TL;DR: In this paper, a survey of inter-device distance estimation methods is presented, which can be formulated as a network localization problem, and the performance of each on real and simulated Bluetooth Low Energy (BLE) measurement datasets with respect to both distance estimate accuracy and the proximity detection problem is evaluated.

TL;DR: Project SMART as discussed by the authors is a cooperative educational game originally designed to raise children awareness of sustainable active transportation to and from school, which was adapted to focus on the health and educational benefits of moderate to vigorous physical activity, leveraging organized physical activity opportunities during the school day.

TL;DR: A smartphone based fundu camera for the early detection of the retinal diseases for the people in destitute areas who do not have access to the costly fundus camera and ophthalmologists is developed and an automation technique to identify the best fundus images from the video with low processing overhead is proposed.

TL;DR: In this paper, a scalable and lightweight ubiquitous screening technique, validated via ground truth data collected through self assessment survey, was proposed for detecting signs of intimate partner violence by analyzing individual-level Google search histories.

TL;DR: This paper embeds motion sensors in a headband and deploy the sensors on the temporalis muscles to sense mastication dynamics accurately and less intrusively and extracts 65 hand-crafted features from each chewing sequence to explicitly characterize themastication dynamics using motion sensor data.

TL;DR: Evidence that the method for compressing the multivariate control problem into a multidimensional model of the user’s physiological state is a viable approach for closed-loop control of a multimodal environment is shown.

TL;DR: A novel approach for reducing the volume and frequency of data transmission through data sample prediction based on applying advanced machine learning techniques to determine when data transmissions are skipped, and by implicitly making the gateway aware of the omitted samples in order to achieve accurate signal reconstruction.

TL;DR: A formal security analysis is presented proving that AC-AC protocol is resilient to multiple attacks, therefore feasible for an acute care timeline.

TL;DR: In this article, the authors proposed a perceived stress prediction system based on the history data of micro-EMA for identifying risks 7 days earlier, which can achieve around 4.26 (10.65% of the scale) mean absolute error for predicting the next 7 day's PSS scores.

TL;DR: This paper demonstrates that attended robotic process automation reduces the human effort to verify a prescription and facilitates a superior employee experience and underpin the importance of prescription data to the healthcare community at large.

TL;DR: In this paper, the authors used smartphones as the edge computing device and implemented pre-trained machine learning algorithms in the smartphone app for computing disease-related Events-of-Interest (EoI).

TL;DR: An ontology to depict the knowledge domain of this disease, symptoms and its related treatments is presented to show the high degree of user acceptance and accuracy of the semantic rule based expert system.

TL;DR: This paper proposes a wearable motion sensor-based chewing side detection method using a heuristic-rules based method to exclude non-chewing data and segment each chew accurately.