Retinal fundus diseases can lead to irreversible visual impairment without timely diagnoses and appropriate treatments. Single disease-based deep learning algorithms had been developed for the detection of diabetic retinopathy, age-related macular degeneration, and glaucoma. Here, we developed a deep learning platform (DLP) capable of detecting multiple common referable fundus diseases and conditions (39 classes) by using 249,620 fundus images marked with 275,543 labels from heterogenous sources. Our DLP achieved a frequency-weighted average F1 score of 0.923, sensitivity of 0.978, specificity of 0.996 and area under the receiver operating characteristic curve (AUC) of 0.9984 for multi-label classification in the primary test dataset and reached the average level of retina specialists. External multihospital test, public data test and tele-reading application also showed high efficiency for multiple retinal diseases and conditions detection. These results indicate that our DLP can be applied for retinal fundus disease triage, especially in remote areas around the world.

In this Letter, we study the scattering dynamics of a pair of solitary waves in the Fermi-Pasta-Ulam model with interaction potential V(x)=alphax(2)/2+x(4)/4 and establish a quantitative connection between the scattering property and the energy transport behavior. The energy and momentum conservation laws are obtained and the scattering rates of solitary waves are calculated. Our studies suggest that the anharmonic limit model with alpha=0 can be taken as a paradigm model for studying lattice solitary waves.

Acoustic communication has an important role in the reproductive behaviour of anurans. Although males of the concave-eared frog (Odorrana tormota) have shown an ultrasonic communication capacity adapted to the intense, predominately low-frequency ambient noise from local streams, whether the females communicate with ultrasound remains unclear. Here we present evidence that females exhibit no ultrasonic sensitivity. Acoustic playback experiments show that the calls from male evoke phonotaxis and vocal responses from gravid females, whereas the ultrasonic components (frequencies above 20 kHz) of the calls do not elicit any phonotaxis or vocalization in the females. Electrophysiological recordings from the auditory midbrain reveal an upper frequency limit at 16 kHz in females. Laser Doppler vibrometer measurements show that the velocity amplitude of the tympanic membranes peaks at 5 kHz in females and at ~7 kHz in males. The auditory sex differences in O. tormota imply that ultrasonic hearing has evolved only in male anurans.

Motor-imagery-based brain-computer interfaces (BCIs) commonly use the common spatial pattern (CSP) as preprocessing step before classification. The CSP method is a supervised algorithm. Therefore a lot of time-consuming training data is needed to build the model. To address this issue, one promising approach is transfer learning, which generalizes a learning model can extract discriminative information from other subjects for target classification task. To this end, we propose a transfer kernel CSP (TKCSP) approach to learn a domain-invariant kernel by directly matching distributions of source subjects and target subjects. The dataset IVa of BCI Competition III is used to demonstrate the validity by our proposed methods. In the experiment, we compare the classification performance of the TKCSP against CSP, CSP for subject-to-subject transfer (CSP SJ-to-SJ), regularizing CSP (RCSP), stationary subspace CSP (ssCSP), multitask CSP (mtCSP), and the combined mtCSP and ssCSP (ss + mtCSP) method. The results indicate that the superior mean classification performance of TKCSP can achieve 81.14%, especially in case of source subjects with fewer number of training samples. Comprehensive experimental evidence on the dataset verifies the effectiveness and efficiency of the proposed TKCSP approach over several state-of-the-art methods.