Search

COVID-19 (Coronavirus Disease of 2019) is one of the most challenging healthcare crises of the twenty-first century. The pandemic causes many negative impacts on all aspects of life and livelihoods. Although recent developments of relevant vaccines, such as Pfizer/BioNTech mRNA, AstraZeneca, or Moderna, the emergence of new virus mutations and their fast infection rate yet pose significant threats to public health. In this context, early detection of the disease is an important factor to reduce its effect and quickly control the spread of pandemic. Nevertheless, many countries still rely on methods that are either expensive and time-consuming (i.e., Reverse-transcription polymerase chain reaction) or uncomfortable and difficult for self-testing (i.e., Rapid Antigen Test Nasal). Recently, deep learning methods have been proposed as a potential solution for COVID-19 analysis. However, previous works usually focus on a single symptom, which can omit critical information for disease diagnosis. Therefore, in this study, we propose a multi-modal method to detect COVID-19 using cough sounds and self-reported symptoms. The proposed method consists of five neural networks to deal with different input features, including CNN-biLSTM for MFCC features, EfficientNetV2 for Mel spectrogram images, MLP for self-reported symptoms, C-YAMNet for cough detection, and RNNoise for noise-canceling. Experimental results demonstrated that our method outperformed the other state-of-the-art methods with a high AUC, accuracy, and F1-score of 98.6%, 96.9%, and 96.9% on the testing set. [ABSTRACT FROM AUTHOR]

Taiwan specialty teas are produced with distinct manufacturing processes from specific cultivars of tea plants in Camellia. Due to the widespread transplantation of Taiwan tea cultivars and active international trading of tea materials, an accurate and reliable method to identify tea cultivars at the border is vital to protect the image of premium Taiwan specialty teas. In this study, we introduced the Taiwan Tea Variety Identification (TTVID) kit, a capillary electropho-resis-based multiplex PCR assay consisting of 12 simple sequence repeat (SSR) markers. A database composing these 12 SSR loci genotypes in 144 cultivars was established for marker assessment and molecular diagnosis. The power of discrimination on a locus ranged from 0.7894 to 0.966 and the combined match probability of 12 SSR loci was 5.34e-14. Cultivar pairwise comparison among 144 accessions showed that over 90.6% of the pairs had differential genotypes on at least 10 of 12 SSR loci. Further assessment showed that the TTVID kit could unambiguously recognize the cultivars mixed in the loose-leaf teas processed with various degrees of fermentation and roasting. Our results suggested that this TTVID kit effectively identified cultivar composition in loose-leaf tea and is helpful for border control in preventing adulteration and fraud in the Taiwan tea market. [ABSTRACT FROM AUTHOR]