Selecting key data subsets for model training is an effective way to improve training efficiency. Existing methods generally utilize a well-trained model to evaluate samples and select crucial subsets, ignoring the fact that the sample importance changes dynamically during model training, resulting in the selected subset only being critical in a specific training epoch rather than a changing training phase. To address this issue, we attempt to evaluate the significant changes in sample importance during dynamic training and propose a novel data selection method to improve model training efficiency. Specifically, the temporal changes in sample importance are considered from three perspectives: (i) loss, the difference between the predicted labels and the true labels of samples in the current training epoch; (ii) instability, the dispersion of sample importance in the recent training phase; and (iii) inconsistency, the comparison of the changing trend in the importance of an individual sample relative to the average importance of all samples in the recent training phase. Extensive experiments demonstrate that dynamic data selection can reduce computational costs and improve model training efficiency. Additionally, we find that the difficulty level of the training task influences the data selection strategy.

Magnetic Resonance Imaging (MRI) is crucial for diagnosing various knee-related diseases, and developing automatic diagnostic models based on knee MRI data is highly valuable. However, this task presents significant challenges due to the need to manage MRI data with multiple sequences and numerous images, where different diseases are often associated with specific images within certain sequences. To address these challenges, we propose a multi-label classification framework designed to effectively process MRI data and handle a large-scale label space encompassing hundreds of disease categories. Our approach introduces a Slice-Level Label Attention mechanism, which enables the model to learn the alignment between labels and images within sequences, thereby enhancing both performance and interpretability. Additionally, we present a Global-Guided Attention Regularization mechanism that further improves the consistency and robustness of the Slice-Level Label Attention results. We validate our framework on a large-scale MRI dataset involving multi-label classification across hundreds of fine-grained disease categories. Experimental results demonstrate that our method not only achieves superior performance but also provides more robust and consistent interpretability.

In the practice of dentistry, oral dental CT images are frequently used to assist doctors in diagnosis. Filtered back projection (FBP) technique is widely employed in practice for the reconstruction of CT images obtained from X-ray calculations. However, when metal objects occur in a patient’s oral cavity, the CT images would show density discontinuities due to the metals’ “X-ray absorption coefficient is much larger than human tissues. When the FBP algorithm is applied to CT images with metals, severe metal artifacts would be obtained, which significantly reconstructed images. Therefore, metal artifact reduction (MAR) work is becoming an important problem in dentistry image processing. In this paper, we propose a novel iterative sinogram metal artifact reduction model (IS-MARM) to solve the problem. Inspired by the Diffusion model, we propose a new method to reduce metal artifacts and interpolate new data in sinogram of dentistry images iteratively. This approach reduces the difficulty of model learning and achieves good results. Secondly, we proposed a new simple method of iterative data generating to simulate real-world metals in CT sinogram images. Finally, we have demonstrated the effectiveness of our method through experiments on dental CT MAR work.

We introduce BioSentEval, a toolkit for evaluating the quality of medical sentence representations. BioSentEval contains a variety of tasks, medical term normalization, medical text classification a nd m edical s entences s emantic relationship determination. This set of tasks was selected based on CBLUE (Chinese Biomedical Language Understanding Evaluation), a Chinese biomedical information processing leaderboard led by CHIP (China Health Information Processing) Committee. Our toolkit provides scripts for pre-processing the datasets, as well as a simple interface for evaluating sentence representations. Given the popularity of SentEval, our aim is to generalize the idea from general domain to biomedical domain and to motivate further research works of biomedical sentence representations.

With the continuous development and popularity of depth cameras, skeleton-based human action recognition has attracted people's wide attention. Graph Convolutional Network (GCN) has achieved remarkable performance. However, the existing methods do not better consider the semantic characteristics, which can help to express the current concept and scene information. Semantic information can also help with better granularity classification. In addition, most of the existing models require a lot of computation. What's more, adaptive GCN can automatically learn the graph structure and consider the connections between joints. In this paper, we propose a relatively less computationally intensive model, which combines semantic and adaptive graph network (SAGN) for skeleton-based human action recognition. Specifically, we mainly combine the dynamic characteristics and bone information to extract the data, taking the correlation between semantics into the model. In the training process, SAGN includes an adaptive network so that we can make attention mechanism more flexible. We design the Convolutional Neural Network (CNN) for feature extraction on the time dimension. The experimental results show that SAGN achieves the state-of-the-art performance on NTU-RGB+D 60 and NTU-RGB+D 120 datasets. SAGN can promote the study of skeleton-based human action recognition. The source code is available at https://github.com/skeletonNN/SAGN.

In the process of online shopping, consumers usually compare the review information of the same product in different e-commerce platforms. The sentiment orientation of online reviews from different platforms interactively influences on consumers’ purchase decision. However, due to the limitation of the ability to process information manually, it is difficult for a consumer to accurately identify the sentiment orientation of all reviews one by one and describe the process of their interactive influence. To this end, we proposed an online shopping support model using deep-learning–based opinion mining and q-rung orthopair fuzzy interaction weighted Heronian mean (q-ROFIWHM) operators. First, in the proposed method, the deep-learning model is used to automatically extract different product attribute words and opinion words from online reviews, and match the corresponding attribute-opinion pairs; meanwhile, the sentiment dictionary is used to calculate sentiment orientation, including positive, negative, and neutral sentiments. Second, the proportions of the three kinds of sentiments about each attribute of the same product are calculated. According to the proportion value of attribute sentiment from different platforms, the sentiment information is converted into multiple cross-decision matrices, which are represented by the q-rung orthopair fuzzy set. Third, considering the interactive characteristics of decision matrix, the q-ROFIWHM operators are proposed to aggregate this cross-decision information, and then the ranking result was determined by score function to support consumers' purchase decisions. Finally, an actual example of mobile phone purchase is given to verify the rationality of the proposed method, and the sensitivity and the comparison analysis are used to show its effectiveness and superiority.

As the approaching of the UGC era, numerous short videos flood into the Internet every day, but at the present stage, it costs much resources and takes a lot of time to calculate the recommended videos. It is inevitable to search for a feasible recommended algorithm. In this paper, this issue has been studied based on distributed computing, innovatively combining the optimization of user tag cloud model. And then we has proposed practical schemes. Experimental results show that the proposed scheme is feasible but also efficient.