Two-dimensional molybdenum ditelluride waveguide-integrated near-infrared photodetector.

Low-cost, small-sized, and easy integrated high-performance photodetectors for photonics are still the bottleneck of photonic integrated circuits applications and have attracted increasing attention. The tunable narrow bandgap of two-dimensional (2D) layered molybdenum ditelluride (MoTe2) from ∼0.83 to ∼1.1 eV makes it one of the ideal candidates for near-infrared (NIR) photodetectors. Herein, we demonstrate an excellent waveguide-integrated NIR photodetector by transferring mechanically exfoliated 2D MoTe2onto a silicon nitride (Si3N4) waveguide. The photoconductive photodetector exhibits excellent responsivity (R), detectivity (D*), and external quantum efficiency at 1550 nm and 50 mV, which are 41.9 A W-1, 16.2 × 1010Jones, and 3360%, respectively. These optoelectronic performances are 10.2 times higher than those of the free-space device, revealing that the photoresponse of photodetectors can be enhanced due to the presence of waveguide. Moreover, the photodetector also exhibits competitive performances over a broad wavelength range from 800 to 1000 nm with a highRof 15.4 A W-1and a largeD* of 59.6 × 109Jones. Overall, these results provide an alternative and prospective strategy for high-performance on-chip broadband NIR photodetectors.

Recognition of eye diseases based on deep neural networks for transfer learning and improved D-S evidence theory.

BACKGROUND: Human vision has inspired significant advancements in computer vision, yet the human eye is prone to various silent eye diseases. With the advent of deep learning, computer vision for detecting human eye diseases has gained prominence, but most studies have focused only on a limited number of eye diseases. RESULTS: Our model demonstrated a reduction in inherent bias and enhanced robustness. The fused network achieved an Accuracy of 0.9237, Kappa of 0.878, F1 Score of 0.914 (95% CI [0.875-0.954]), Precision of 0.945 (95% CI [0.928-0.963]), Recall of 0.89 (95% CI [0.821-0.958]), and an AUC value of ROC at 0.987. These metrics are notably higher than those of comparable studies. CONCLUSIONS: Our deep neural network-based model exhibited improvements in eye disease recognition metrics over models from peer research, highlighting its potential application in this field. METHODS: In deep learning-based eye recognition, to improve the learning efficiency of the model, we train and fine-tune the network by transfer learning. In order to eliminate the decision bias of the models and improve the credibility of the decisions, we propose a model decision fusion method based on the D-S theory. However, D-S theory is an incomplete and conflicting theory, we improve and eliminate the existed paradoxes, propose the improved D-S evidence theory(ID-SET), and apply it to the decision fusion of eye disease recognition models.