Selective detection of trace carbon monoxide at room temperature based on CuO nanosheets exposed to (111) crystal facets.

In recent years, carbon monoxide (CO) intoxication incidents occur frequently, and the sensitive detection of CO is particularly significant. At present, most reported carbon monoxide (CO) sensors meet the disadvantage of high working temperature. It is always a challenge to realize the sensitive detection of carbon monoxide at room temperature. In this study, CuO nanosheets exposed more (111) active crystal facets and oxygen vacancy defects were synthesized by a simple and environmentally friendly one-step hydrothermal method. The sensor has good comprehensive gas sensing performance, compared with other sensors that can detect CO at room temperature. The response value to 100 ppm CO at room temperature is as high as 39.6. In addition, it also has excellent selectivity, low detection limit (100 ppb), good reproducibility, moisture resistance and long-term stability (60 days). This excellent gas sensing performance is attributed to the special structural characteristics of 2D materials and the synergistic effect of more active crystal facets exposed on the crystal surface and oxygen vacancy defects. Therefore, it is expected to become a promising sensitive material for rapid and accurate detection of trace CO gas under low energy consumption, reduce the risk of poisoning, and then effectively protect human life safety.

Design and Assessment of Convolutional Neural Network Based Methods for Vitiligo Diagnosis.

Background: Today's machine-learning based dermatologic research has largely focused on pigmented/non-pigmented lesions concerning skin cancers. However, studies on machine-learning-aided diagnosis of depigmented non-melanocytic lesions, which are more difficult to diagnose by unaided eye, are very few. Objective: We aim to assess the performance of deep learning methods for diagnosing vitiligo by deploying Convolutional Neural Networks (CNNs) and comparing their diagnosis accuracy with that of human raters with different levels of experience. Methods: A Chinese in-house dataset (2,876 images) and a world-wide public dataset (1,341 images) containing vitiligo and other depigmented/hypopigmented lesions were constructed. Three CNN models were trained on close-up images in both datasets. The results by the CNNs were compared with those by 14 human raters from four groups: expert raters (>10 years of experience), intermediate raters (5-10 years), dermatology residents, and general practitioners. F1 score, the area under the receiver operating characteristic curve (AUC), specificity, and sensitivity metrics were used to compare the performance of the CNNs with that of the raters. Results: For the in-house dataset, CNNs achieved a comparable F1 score (mean [standard deviation]) with expert raters (0.8864 [0.005] vs. 0.8933 [0.044]) and outperformed intermediate raters (0.7603 [0.029]), dermatology residents (0.6161 [0.068]) and general practitioners (0.4964 [0.139]). For the public dataset, CNNs achieved a higher F1 score (0.9684 [0.005]) compared to the diagnosis of expert raters (0.9221 [0.031]). Conclusion: Properly designed and trained CNNs are able to diagnose vitiligo without the aid of Wood's lamp images and outperform human raters in an experimental setting.