Comparative Analysis of Audio Processing Techniques on Doppler Radar Signature of Human Walking Motion Using CNN Models.

Artificial intelligence (AI) radar technology offers several advantages over other technologies, including low cost, privacy assurance, high accuracy, and environmental resilience. One challenge faced by AI radar technology is the high cost of equipment and the lack of radar datasets for deep-learning model training. Moreover, conventional radar signal processing methods have the obstacles of poor resolution or complex computation. Therefore, this paper discusses an innovative approach in the integration of radar technology and machine learning for effective surveillance systems that can surpass the aforementioned limitations. This approach is detailed into three steps: signal acquisition, signal processing, and feature-based classification. A hardware prototype of the signal acquisition circuitry was designed for a Continuous Wave (CW) K-24 GHz frequency band radar sensor. The collected radar motion data was categorized into non-human motion, human walking, and human walking without arm swing. Three signal processing techniques, namely short-time Fourier transform (STFT), mel spectrogram, and mel frequency cepstral coefficients (MFCCs), were employed. The latter two are typically used for audio processing, but in this study, they were proposed to obtain micro-Doppler spectrograms for all motion data. The obtained micro-Doppler spectrograms were then fed to a simplified 2D convolutional neural networks (CNNs) architecture for feature extraction and classification. Additionally, artificial neural networks (ANNs) and 1D CNN models were implemented for comparative analysis on various aspects. The experimental results demonstrated that the 2D CNN model trained on the MFCC feature outperformed the other two methods. The accuracy rate of the object classification models trained on micro-Doppler features was 97.93%, indicating the effectiveness of the proposed approach.

Association of self-reported allergic rhinitis with dengue severity: A case-control study.

BACKGROUND: The severity of dengue infection has been reportedly associated with patients' allergic reactions. To further elucidate the role of allergy in dengue severity, we conducted a matched case-control study to assess the association between allergic background and dengue shock syndrome. METHODS: This is a matched case-control study that was carried out in the Hospital for Tropical Diseases, Ho Chi Minh City, Vietnam from January to December 2017. Dengue infection was determined by non-structure protein 1 (NS1) diagnostic quick test or anti-dengue antibodies (IgM). The total and dengue-specific IgE levels were measured using ELISA. Patients' demographics, clinical, and allergic profiles were collected using a structured questionnaire. RESULTS: A total of 572 dengue patients with positive NS1 (92.7%) or IgM antibodies (7.3%) results were included in this study. Of these patients, 143 patients developed dengue shock syndrome (case group) while the other 429 patients did not (control group). None of the baseline characteristics including age, sex, or being overweight was significantly different between the two groups (p>0.05). In multivariable analysis, having a history of dengue infection (OR=3.35, 95% CI: 1.8-6.17, p<0.001) and allergic rhinitis (OR=1.95, 95% CI: 1.11-3.4, p = 0.019) were found to be associated with dengue shock syndrome. Higher levels of dengue-specific IgE were not associated with worse outcomes in patients with allergies (p = 0.204) or allergic rhinitis (p = 0.284). CONCLUSION: Dengue patients presenting with a history of a previous dengue infection or allergic rhinitis should be considered high-risk patients for the development of dengue shock syndrome.

Antiretroviral pre-exposure prophylaxis preferences among men who have sex with men in Vietnam: results from a nationwide cross-sectional survey.

Background: The HIV/AIDS epidemic in Vietnam is concentrated in subgroups of the population, including men who have sex with men (MSM). Pre-exposure prophylaxis (PrEP) is a viable strategy for HIV prevention, but knowledge about and preferences for PrEP delivery among Vietnamese MSM are not well understood. Methods: In 2015, an online survey was conducted with recruitment via social networking websites for MSM and peer recruitment. A description of daily oral, long-acting injectable, and rectal microbicide formulations of PrEP was provided to participants. Participants were asked about their prior awareness of and interest in PrEP, and ranked their most preferred PrEP modality. Multivariable logistic regression models were used to assess factors associated with having heard of PrEP and preference for each PrEP modality. Results: Of 548 participants who answered demographic and PrEP-related questions, 26.8% had previously heard of PrEP and most (65.7%) endorsed rectal microbicides as their most preferred PrEP delivery modality. Commonly-cited perceived barriers to uptake of PrEP included concern about side-effects, perception about being HIV positive, and family or friends finding out about their sexual behaviour. In multivariable models, older participants less often endorsed rectal microbicides (adjusted odds ratio (AOR) 0.95 per year, 95% confidence interval (CI) 0.91-0.99) and more often endorsed long-acting injectables (AOR 1.08 per year, 95% CI 1.03 to 1.14) as their preferred PrEP modality. Participants who were willing to pay more for PrEP less often endorsed rectal microbicides (AOR 0.81, 95% CI 0.72-0.92) and more often endorsed long-acting injectables (AOR 1.17, 95% CI 1.01-1.35) and daily oral pills (AOR 1.16, 95% CI 1.00-1.35) as their preferred form of PrEP. Conclusions: A variety of PrEP modalities were acceptable to MSM in Vietnam, but low knowledge of PrEP may be a barrier to implementation.