Towards Automated Microfluidic-based Platforms: Optimizing Hydrogenation Efficiency of Nitrobenzene through π-π Interactions in Pd Nanoparticles on Covalent Organic Frameworks.

Microplatform with timed automata has been leveraged for guiding the preparation of molecules, whereas the requirement of handling expertise and sophisticated instrument is inevitable in combination with heterogeneous catalysis. Here we report a microfluidic-based autolab with open structures, called Put & Play Automated Microplatform (PPAM). It shows the efficient hydrogenation performance of palladium nanoparticles on the triphenylene-based covalent organic frameworks (Pd/TP-COFs) in which the π-π interactions of TP rings in the vicinity of Pd is optimized by easy change-over of catalyst and simple tuning of reactor geometries in PPAM. Using experiment/simulation of the Pd/TP-COFs coating (PCC) and mixing (PCM) across PPAM with different channel sizes, the turnover frequencies are 60 times the commonly used batch reactor, and aniline productivity of 8.8 g h-1 is achieved in 0.09 cm3 . This work will raise awareness about the benefits of the catalyst-loaded microplatform in future materials performance campaigns.

Named entity recognition of rice genes and phenotypes based on BiGRU neural networks.

Named Entity Recognition (NER) is a fundamental but crucial task in natural language processing (NLP) and big data analysis, with wide application range. NER for rice genes and phenotypes is a technique to identify genes and phenotypes from a large amount of text. NER for rice genes and phenotypes can facilitate the acquisition of information in the field of crops and provide references for our research on higher quality crops. At the same time, named entity recognition still faces many challenges. In this paper, we propose an improved bidirectional gated recurrent unit neural network (BI-GRU) method, which is used to automatically identify the required entities (i.e. gene names, rice phenotypes) from relevant rice literature and patents. The neural network model is combined with the Softmax function to directly output the probabilities of labels, forming the BI-GRU-SF model. With the ability of deep learning methods, the semantic information in the context can be learned without the need for feature engineering. Finally, we conducted experiments, and the results showed that our proposed model provided better performance compared to other models. All datasets and resource codes of BI-GRU-SF are available at https://github.com/qqeeqq/NER for academic use.

A Magnetic-Multiplier-Enabled Hybrid Generator with Frequency Division Operation and High Energy Utilization Efficiency.

The hybrid electromagnetic-triboelectric generator (HETG) is a prevalent device for mechanical energy harvesting. However, the energy utilization efficiency of the electromagnetic generator (EMG) is inferior to that of the triboelectric nanogenerator (TENG) at low driving frequencies, which limits the overall efficacy of the HETG. To tackle this issue, a layered hybrid generator consisting of a rotating disk TENG, a magnetic multiplier, and a coil panel is proposed. The magnetic multiplier not only forms the EMG part with its high-speed rotor and the coil panel but also facilitates the EMG to operate at a higher frequency than the TENG through frequency division operation. The systematic parameter optimization of the hybrid generator reveals that the energy utilization efficiency of EMG can be elevated to that of rotating disk TENG. Incorporating a power management circuit, the HETG assumes the responsibility for monitoring the water quality and fishing conditions by collecting low-frequency mechanical energy. The magnetic- multiplier-enabled hybrid generator demonstrated in this work offers a universal frequency division approach to improve the overall outputs of any hybrid generator that collects rotational energy, expanding its practical applications in diverse multifunctional self-powered systems.

Efficient and accurate identification of ear diseases using an ensemble deep learning model.

Early detection and appropriate medical treatment are of great use for ear disease. However, a new diagnostic strategy is necessary for the absence of experts and relatively low diagnostic accuracy, in which deep learning plays an important role. This paper puts forward a mechanic learning model which uses abundant otoscope image data gained in clinical cases to achieve an automatic diagnosis of ear diseases in real time. A total of 20,542 endoscopic images were employed to train nine common deep convolution neural networks. According to the characteristics of the eardrum and external auditory canal, eight kinds of ear diseases were classified, involving the majority of ear diseases, such as normal, Cholestestoma of the middle ear, Chronic suppurative otitis media, External auditory cana bleeding, Impacted cerumen, Otomycosis external, Secretory otitis media, Tympanic membrane calcification. After we evaluate these optimization schemes, two best performance models are selected to combine the ensemble classifiers with real-time automatic classification. Based on accuracy and training time, we choose a transferring learning model based on DensNet-BC169 and DensNet-BC1615, getting a result that each model has obvious improvement by using these two ensemble classifiers, and has an average accuracy of 95.59%. Considering the dependence of classifier performance on data size in transfer learning, we evaluate the high accuracy of the current model that can be attributed to large databases. Current studies are unparalleled regarding disease diversity and diagnostic precision. The real-time classifier trains the data under different acquisition conditions, which is suitable for real cases. According to this study, in the clinical case, the deep learning model is of great use in the early detection and remedy of ear diseases.