Search

Abstract During music recommendation scenarios, sparsity and cold start problems are inevitable. Auxiliary information has been utilized in music recommendation algorithms to provide users with more accurate music recommendation results. This study proposes an end-to-end framework, MMSS_MKR, that uses a knowledge graph as a source of auxiliary information to serve the information obtained from it to the recommendation module. The framework exploits Cross & Compression Units to bridge the knowledge graph embedding task with recommendation task modules. We can obtain more realistic triple information and exclude false triple information as much as possible, because our model obtains triple information through the music knowledge graph, and the information obtained through the recommendation module is used to determine the truth of the triple information; thus, the knowledge graph embedding task is used to perform the recommendation task. In the recommendation module, multiple predictions are adopted to predict the recommendation accuracy. In the knowledge graph embedding module, multiple calculations are used to calculate the score. Finally, the loss function of the model is improved to help us to obtain more useful information for music recommendations. The MMSS_MKR model achieved significant improvements in music recommendations compared with many existing recommendation models.

Abstract Melanoma is a fatal skin disease, and there are many challenging tasks in the detection of melanoma through neural network at this stage. We propose a new method for melanoma diagnosis based on EfficientNet and patch strategy. The diagnosis method has three stages of operation. First, Cyclegan is applied offline to synthesize the under-represented category samples from the over-represented category samples, and the original image and the synthesized samples are combined into a new training set to complete the conditional image synthesis task; second, we creatively propose the patch strategy and implement the patch algorithm, and apply the patch strategy offline to obtain the patch image of the newly merged training set; finally, the newly merged training set and the obtained patch image are sent to the classification network. Where, the model we proposed is composed of three parts: Basic Convolutional Neural Network, Auxiliary Convolutional Neural Network, and Fusion Convolutional Neural Network, and applies a weighted integration strategy. We evaluated the proposed method on the ISIC 2016 Skin Injury Challenge classification dataset. Experiments show that the patch strategy plays an important role in the field of melanoma classification, and the melanoma detection method proposed in this paper obtains an accuracy of 0.852 and an AUC value of 0.854 on the test set. This method can focus the attention of the classification network on the meaningful area of the skin lesion image through manual intervention, and can effectively solve the problem of category imbalance, thereby improving the performance of skin lesion classification.

Abstract Background Currently, cardiovascular disease has become a major disease endangering human health, and the number of such patients is growing. Electrocardiogram (ECG) is an important basis for {medical doctors to diagnose the cardiovascular disease, which can truly reflect the health of the heart. In this context, the contradiction between the lack of medical resources and the surge in the number of patients has become increasingly prominent. The use of computer-aided diagnosis of cardiovascular disease has become particularly important, so the study of ECG automatic classification method has a strong practical significance. Methods This article proposes a new method for automatic identification and classification of ECG.We have developed a dense heart rhythm network that combines a 24-layer Deep Convolutional Neural Network (DCNN) and Bidirectional Long Short-Term Memory (BiLSTM) to deeply mine the hierarchical and time-sensitive features of ECG data. Three different sizes of convolution kernels (32, 64 and 128) are used to mine the detailed features of the ECG signal, and the original ECG is filtered using a combination of wavelet transform and median filtering to eliminate the influence of noise on the signal. A new loss function is proposed to control the fluctuation of loss during the training process, and convergence mapping of the tan function in the range of 0–1 is employed to better reflect the model training loss and correct the optimization direction in time. Results We applied the dataset provided by the 2017 PhysioNet/CINC challenge for verification. The experiment adopted ten-fold cross validation,and obtained an accuracy rate of 89.3 $$\%$$ % and an F1 score of 0.891. Conclusions This article proposes its own method in the aspects of ECG data preprocessing, feature extraction and loss function design. Compared with the existing methods, this method improves the accuracy of automatic ECG classification and is helpful for clinical diagnosis and self-monitoring of atrial fibrillation.

To fully extract the local and long-range information of amino acid sequences and enhance the effective information, this research proposes a secondary structure prediction model of protein based on a multi-scale convolutional attentional neural network. The model uses a multi-channel multi-scale parallel architecture to extract amino acid structure features of different granularity according to the window size. The reconstructed feature maps are obtained via multiple convolutional attention blocks. Then, the reconstructed feature map is fused with the input feature map to obtain the enhanced feature map. Finally, the enhanced feature map is fed to the Softmax classifier for prediction. While the traditional cross-entropy loss cannot effectively solve the problem of non-equilibrium training samples, a modified correlated cross-entropy loss function may alleviate this problem. After numerous comparison and ablation experiments, it is verified that the improved model can indeed effectively extract amino acid sequence feature information, alleviate overfitting, and thus improve the overall prediction accuracy.

Proteins play a vital role in organisms, which suggests that in-depth study of the function of proteins is helpful to the application of proteins in a more accurate and effective way. Accordingly, protein structure will become the focus of discussion and research for a long time. In order to fully extract the effective information from the protein structure and improve the classification accuracy of the protein secondary sequence, a deep residual network model using different residual units was proposed to predict the secondary structure. This algorithm uses sliding window method to represent amino acid sequences and combines the powerful feature extraction ability of resent network. In this paper, the parameters of the neural network are debugged through experiments, and then the extracted features are classified and verified. The experimental results on CASP9, CASP10, CASP11 and CASP12 data sets imply that the improved deep residual network model based on different residual units can express amino acid sequences more accurately, which is more superior than existing methods.

The representation-based classification method has become a research hotspot in recent years. Representation-based classifiers assign class labels directly to test samples based on a structured dictionary. The structured dictionary is composed of training samples. We call the samples in the dictionary as atoms. To further improve the expression ability of different training atoms in the classifier to the test samples, we propose an ensemble-enhanced sparse classification algorithm based on the correlation coefficient. The model proceeds from two aspects: the representation coefficient level and the similarity between different samples. First, a sparse dictionary is combined with the multiplicative property of training samples to build and solve the sparse and collaborative representation algorithm. The fusion representation coefficients are obtained by weighted sparse representation coefficients and collaborative representation coefficients. The test samples are reconstructed by fusing the representation coefficients, and the minimization recovery residuals for each class of samples are calculated. Second, the correlation coefficient value between the test sample and the training sample is calculated, and the maximum correlation quotient between the test sample and the training sample is obtained. Finally, the maximum correlation quotient and the minimization recovery residual are weighted, and the decision classification is carried out in the decision function to achieve the final face recognition. Experiments on AR, Extended Yale B, Georgia Tech and other general face databases show the effectiveness of the algorithm. The main contribution of this model is that it is more robust than a single sparse or collaborative representation model and can improve recognition accuracy.

In the field of deep learning, the processing of large network models on billions or even tens of billions of nodes and numerous edge types is still flawed, and the accuracy of recommendations is greatly compromised when large network embeddings are applied to recommendation systems. To solve the problem of inaccurate recommendations caused by processing deficiencies in large networks, this paper combines the attributed multiplex heterogeneous network with the attention mechanism that introduces the softsign and sigmoid function characteristics and derives a new framework SSN_GATNE-T (S represents the softsign function, SN represents the attention mechanism introduced by the Softsign function, and GATNE-T represents the transductive embeddings learning for attribute multiple heterogeneous networks). The attributed multiplex heterogeneous network can help obtain more user-item information with more attributes. No matter how many nodes and types are included in the model, our model can handle it well, and the improved attention mechanism can help annotations to obtain more useful information via a combination of the two. This can help to mine more potential information to improve the recommendation effect; in addition, the application of the softsign function in the fully connected layer of the model can better reduce the loss of potential user information, which can be used for accurate recommendation by the model. Using the Adam optimizer to optimize the model can not only make our model converge faster, but it is also very helpful for model tuning. The proposed framework SSN_GATNE-T was tested for two different types of datasets, Amazon and YouTube, using three evaluation indices, ROC-AUC (receiver operating characteristic-area under curve), PR-AUC (precision recall-area under curve) and F1 (F1-score), and found that SSN_GATNE-T improved on all three evaluation indices compared to the mainstream recommendation models currently in existence. This not only demonstrates that the framework can deal well with the shortcomings of obtaining accurate interaction information due to the presence of a large number of nodes and edge types of the embedding of large network models, but also demonstrates the effectiveness of addressing the shortcomings of large networks to improve recommendation performance. In addition, the model is also a good solution to the cold start problem.

In recommendation algorithms, data sparsity and cold start problems are inevitable. To solve such problems, researchers apply auxiliary information to recommendation algorithms, mine users’ historical records to obtain more potential information, and then improve recommendation performance. In this paper, ST_RippleNet, a model that combines knowledge graphs with deep learning, is proposed. This model starts by building the required knowledge graph. Then, the potential interest of users is mined through the knowledge graph, which stimulates the spread of users’ preferences on the set of knowledge entities. In preference propagation, we use a triple multi-layer attention mechanism to obtain triple information through the knowledge graph and use the user preference distribution for candidate items formed by users’ historical click information to predict the final click probability. Using ST_RippleNet model can better obtain triple information in knowledge graph and mine more useful information. In the ST_RippleNet model, the music data set is added to the movie and book data set; additionally, an improved loss function is used in the model, which is optimized by the RMSProp optimizer. Finally, the tanh function is added to predict the click probability to improve recommendation performance. Compared with current mainstream recommendation methods, ST_RippleNet achieves very good performance in terms of the area under the curve (AUC) and accuracy (ACC) and substantially improves movie, book and music recommendations.

Pneumonia remains the leading infectious cause of death in children under the age of five, killing about 700,000 children each year and affecting 7% of the world’s population. X-ray images of lung become the key to the diagnosis of this disease, skilled doctors in the diagnosis of a certain degree of subjectivity, if the use of computer-aided medical diagnosis to automatically detect lung abnormalities, will improve the accuracy of diagnosis. This research aims to introduce a deep learning technology based on the combination of Xception neural network and long-term short-term memory (LSTM), which can realize automatic diagnosis of patients with pneumonia in X-ray images. First, the model uses the Xception network to extract the deep features of the data, passes the extracted features to the LSTM, and then the LSTM detects the extracted features, and finally selects the most needed features. Secondly, in the training set samples, the traditional cross-entropy loss cannot more balance the mismatch between categories. Therefore, this research combines Pearson’s feature selection ideas, fusion of the correlation between the two loss functions, and optimizes the problem. The experimental results show that the accuracy rate of this paper is 96%, the receiver operator characteristic curve accuracy rate is 99%, the precision rate is 98%, the recall rate is 91%, and the F1 score accuracy rate is 94%. Compared with the existing technical methods, the research has achieved expected results on the currently available datasets. And assist doctors to provide higher reliability in the classification task of childhood pneumonia.