ABSTRACT
Human biometric recognition has always been of interest to researchers. This biometric recognition can broadly be classified into physiological and behavioral recognition based on the modality being considered. The former covers face, fingerprint, palm vein, palmprint and the latter covers gait, keystroke and more. Within the physiological set, vein recognition methods like palm vein, finger vein and wrist vein recognition are attracting more attention due to their subcutaneous nature. Veins being subcutaneous contributes to the possibility of developing contactless biometric systems which is essential in a post COVID-19 pandemic era. In vein recognition, palm vein and finger vein methods have been extensively reviewed and researched. However, there is very limited information on wrist vein recognition. This limits exploring the full potential of wrist vein recognition. In this paper we systematically review recent relevant research on wrist vein recognition and highlight its advantages and disadvantages. Wrist vein images are easier to capture and process when compared to other vascular biometric images. This conducted literature review revealed that wrist vein recognition is promising when used in conjunction with deep learning methods and can be successfully used in designing contactless wrist biometric systems. This study would aid future research and application of wrist vein biometric systems.
ABSTRACT
Human biometric recognition has always been of interest to researchers. This biometric recognition can broadly be classified into physiological and behavioral recognition based on the modality being considered. The former covers face, fingerprint, palm vein, palmprint and the latter covers gait, keystroke and more. Within the physiological set, vein recognition methods like palm vein, finger vein and wrist vein recognition are attracting more attention due to their subcutaneous nature. Veins being subcutaneous contributes to the possibility of developing contactless biometric systems which is essential in a post COVID-19 pandemic era. In vein recognition, palm vein and finger vein methods have been extensively reviewed and researched. However, there is very limited information on wrist vein recognition. This limits exploring the full potential of wrist vein recognition. In this paper we systematically review recent relevant research on wrist vein recognition and highlight its advantages and disadvantages. Wrist vein images are easier to capture and process when compared to other vascular biometric images. This conducted literature review revealed that wrist vein recognition is promising when used in conjunction with deep learning methods and can be successfully used in designing contactless wrist biometric systems. This study would aid future research and application of wrist vein biometric systems. © 2022 Asia-Pacific of Signal and Information Processing Association (APSIPA).
ABSTRACT
A recurring theme during the pandemic was the shortage of hospital beds. Despite all efforts, the healthcare system still faces 25 % of resource strain felt during the first peak of coronavirus. Digitisation of Electronic Healthcare Records (EHRs) and the pandemic have brought about many successful applications of Recurrent Neural Networks (RNNs) to predict patients' current and future states. Despite their strong per-formance, it remains a challenge for users to delve into the black box which has heavily influenced researchers to utilise more interpretable techniques such as ID-Convolutional neural networks. Others focus on using more interpretable machine learning techniques but only achieve high performance on a select subset of patients. By collaborating with medical experts and artificial intelligence scientists, our study improves on the REverse Time AttentIoN EX model, a feature and visit level attention network, for increased interpretability and usability of RNNs in predicting COVID-19-related hospitalisations. We achieved 82.40 % area under the receiver operating characteristic curve and showcased effective use of the REverse Time AttentIoN EXTension model and EHRs in understanding how individual medical codes contribute to hospitalisation risk prediction. This study provides a guideline for researchers aiming to design interpretable temporal neural networks using the power of RNNs and data mining techniques. © 2022 IEEE.
ABSTRACT
During 2 July- 11 August, 2020, an outbreak of coronavirus disease 2019 (COVID-19) occurred at a boys' overnight summer school retreat in Wisconsin. The retreat included 152 high school-aged boys, counselors, and staff members from 21 states and territories and two foreign countries. All attendees were required to provide documentation of either a positive serologic test result* within the past 3 months or a negative reverse transcription polymerase chain reaction tests result for SARS-CoV-2 7 days before travel, to self-quarantine within their households for 7 days before travel, and to wear masks during travel. On 15 July, the Wisconsin Department of Health Services began an investigation after being notified that two students at the retreat had received positive SARS-CoV-2 RT-PCR test results. WDHS offered RT-PCR testing to attendees on 28 July and serologic testing on August 5 and 6. Seventy-eight attendees received positive RT-PCR results, and 38 met clinical criteria for COVID-19 without a positive RT-PCR result. By the end of the retreat, 118 persons had received a positive serologic test result. Among 24 attendees with a documented positive serologic test result before the retreat, all received negative RT-PCR results. After RT-PCR testing on 28 July, WDHS recommended that remaining susceptible persons (asymptomatic and with negative RT-PCR test results) quarantine from other students and staff members at the retreat. Recommended end dates for isolation or quarantine were based on established guidance and determined in coordination with CDC. All attendees were cleared for interstate and commercial air travel to return home on 11 August. This outbreak investigation documented rapid spread of SARS-CoV-2, likely from a single student, among adolescents and young adults in a congregate setting. Mitigation plans that include prearrival quarantine and testing, cohorting, symptom monitoring, early identification and isolation of cases, mask use, enhanced hygiene and disinfection practices, and maximal outdoor programming are necessary to prevent COVID-19 outbreaks in these settings.