With the continuous development of deep learning, pre-trained models have achieved sound effects in the field of natural language processing. However, text summarization research is far from what people want, especially in abstractive summarization. A high-quality summarization system needs to focus on the topic content of the document and the similarity between the summary and the source document. In this paper, we propose a topic information fusion and semantic relevance for text summarization based on Fine-tuning BERT(TIF-SR). Primarily, considering the critical role of topic information in summary generation, we extract topic keywords and fusion them with source documents as part of the input. Secondly, make the summary closer to the source document by calculating the semantic similarity between the generated summary and the source document, the quality of the abstract is improved. The experimental data indicate that the ROUGE index and readability have improved in this model, so these shreds of evidence suggest that the method proposed by our model is sufficient.

Ultrasonic particle manipulation technique is a non-contact label-free method for manipulating micro- and nano-scale particles using ultrasound, which has obvious advantages over traditional optical, magnetic, and electrical micro-manipulation techniques; it has gained extensive attention in micro-nano manipulation in recent years. This paper introduces the basic principles and manipulation methods of ultrasonic particle manipulation techniques, provides a detailed overview of the current mainstream acoustic field generation methods, and also highlights, in particular, the applicable scenarios for different numbers and arrangements of ultrasonic transducer devices. Ultrasonic transducer arrays have been used extensively in various particle manipulation applications, and many sound field reconstruction algorithms based on ultrasonic transducer arrays have been proposed one after another. In this paper, unlike most other previous reviews on ultrasonic particle manipulation, we analyze and summarize the current reconstruction algorithms for generating sound fields based on ultrasonic transducer arrays and compare these algorithms. Finally, we explore the applications of ultrasonic particle manipulation technology in engineering and biological fields and summarize and forecast the research progress of ultrasonic particle manipulation technology. We believe that this review will provide superior guidance for ultrasonic particle manipulation methods based on the study of micro and nano operations.

Bidirectional Encoder Representations from Transformers represents the latest incarnation of pre-trained language models which have been obtained a satisfactory effect in text summarization tasks. However, it has not achieved good results for the generation of Chinese short text summaries. In this work, we propose a novel short text summary generation model based on keyword templates, which uses templates found in training data to extract keywords to guide summary generation. The experimental results of the LCSTS data set show that our model performs better than the baseline model. The analysis shows that the methods used in our model can generate high-quality summaries.

In order to improve the speed of tracking based on keypoint, we proposed an ORB-based tracking algorithm. We used the Gaussian mixture model to estimate the background. The difference of frame and background was treated as the foreground. All the ORB keypoints composed the feature set of object, which were extracted from foreground. In the foreground of each frame, we extracted ORB feature to match with the feature set of object and selected the good keypoints. We employed the Hamming distance to evaluate the quality of match. Then, these keypoints were used to find the position and update the feature set. The experiment results show that our tracking algorithm has a higher speed compared with SIFT-based algorithm and SURF-based algorithm, and accurately find the position of object.

Training a convolutional neural network requires a large number of sample data and a large amount of computing power. In some practical application scenarios, there may be difficulties in sample data collection and complex network model construction. To improve the classification accuracy and fitting speed of the convolutional neural network, a transfer learning classification method for an animal image is proposed. The fully connected layer of the pre-trained ResNet18 network is modified, and the eight animals in the animal-10 dataset on Kaggle are used to fine-tune the network model. The best classification accuracy of the obtained network model for a single animal is 97%, and the classification accuracy for all animals is 92%. Compared with the model that did not use transfer learning training, this kind of transfer learning network model has a great improvement in accuracy and fitting speed.