Noise-Level Aware Compressed Analysis Framework for Robust Electrocardiography Signal Monitoring.

Compressed sensing (CS) has drawn much attention in electrocardiography (ECG) signal monitoring for its effectiveness in reducing the transmission power of wireless sensor systems. Compressed analysis (CA) is an improved methodology to further elevate the system's efficiency by directly performing classification on the compressed data at the back-end of the monitoring system. However, conventional CA lacks of considering the effect of noise, which is an essential issue in practical applications. In this work, we observe that noise causes an accuracy drop in the previous CA framework, thus discovering that different signal-to-noise ratios (SNRs) require different sizes of CA models. We propose a two-stage noise-level aware compressed analysis framework. First, we apply the singular value decomposition to estimate the noise level in the compressed domain by projecting the received signal into the null space of the compressed ECG signal. A transfer-learning-aided algorithm is proposed to reduce the long-training-time drawback. Second, we select the optimal CA model dynamically based on the estimated SNR. The CA model will use a predictive dictionary to extract features from the ECG signal, and then imposes a linear classifier for classification. A weight-sharing training mechanism is proposed to enable parameter sharing among the pre-trained models, thus significantly reducing storage overhead. Lastly, we validate our framework on the atrial fibrillation ECG signal detection on the NTUH and MIT-BIH datasets. We show improvement in the accuracy of 6.4% and 7.7% in the low SNR condition over the state-of-the-art CA framework.

Maximising the potential of voluntary counselling and testing for HIV: sexually transmitted infections and HIV epidemiology in a population testing for HIV and its implications for practice.

OBJECTIVES: This study aimed to describe the epidemiology of HIV infection and sexually transmitted infections (STIs) among persons who attended voluntary counselling and testing (VCT) service for HIV and to assess whether the VCT programme reached the right population at risk in Taiwan. METHODS: From 2006 to 2010, questionnaire interview, integrated pretesting and post-testing counselling, followed by serological tests for HIV, Treponema pallidum and Entamoeba histolytica were performed for all VCT clients; additional tests for Chlamydia trachomatis and Neisseria gonorrhoeae using PCR assays of urine specimens were provided when the assays became available in two periods. RESULTS: During the study period, 10 198 VCT attendances occurred in 6863 clients, in whom 1685 (24.6%) had re-attendances. Male clients, men who have sex with men and clients with one-night stand and casual sexual partners were more likely to re-attend VCT service in the next 12 months. The overall STI prevalence was 3.5% for HIV infection, 2.2% syphilis, 1.0% amoebiasis, 4.7% chlamydia and 0.7% gonorrhoea. In logistic regression model, men who have sex with men were consistently independently associated with HIV infection, syphilis and amoebiasis. Among the repeaters, the incidence rate of HIV infection and syphilis was 3.4 and 1.6 per 100 person-years of follow-up, respectively. In Cox regression analysis, clients who used illicit non-injection recreational drugs and who practiced unprotected anal sex were at significantly higher risk of acquiring HIV infection and syphilis. CONCLUSIONS: With higher rates of re-attendances and STIs, the VCT programme reached the population most at risk for HIV and STIs compared with other screening programmes in Taiwan. The potential of VCT programme can be maximised in the prevention and control of HIV infection and STIs by providing tests for more STIs and counselling to avoid use of recreational drugs and to promote safe sex.