Combining Graph Convolutional Neural Networks and Label Propagation

Label Propagation Algorithm (LPA) and Graph Convolutional Neural Networks (GCN) are both message passing algorithms on graphs. Both solve the task of node classification, but LPA propagates node label information across the edges of the graph, while GCN propagates and transforms node feature information. However, while conceptually similar, theoretical relationship between LPA and GCN has not yet been systematically investigated. Moreover, it is unclear how LPA and GCN can be combined under a unified framework to improve the performance. Here we study the relationship between LPA and GCN in terms of feature/label influence , in which we characterize how much the initial feature/label of one node influences the final feature/label of another node in GCN/LPA. Based on our theoretical analysis, we propose an end-to-end model that combines GCN and LPA. In our unified model, edge weights are learnable, and the LPA serves as regularization to assist the GCN in learning proper edge weights that lead to improved performance. Our model can also be seen as learning the weights of edges based on node labels, which is more direct and efficient than existing feature-based attention models or topology-based diffusion models. In a number of experiments for semi-supervised node classification and knowledge-graph-aware recommendation, our model shows superiority over state-of-the-art baselines.

Fatty Acid Composition and Contents of Fish of Genus Salvelinus from Natural Ecosystems and Aquaculture

Fatty acids (FA) of muscle tissue of Salvelinus species and its forms, S. alpinus, S. boganidae, S. drjagini, and S. fontinalis, from six Russian lakes and two aquacultures, were analyzed. Considerable variations in FA compositions and contents were found, including contents of eicosapentaenoic and docosahexaenoic acids (EPA and DHA), which are important indicators of fish nutritive value for humans. As found, contents of EPA+DHA (mg·g−1 wet weight) in muscle tissue of Salvelinus species and forms varied more than tenfold. These differences were supposed to be primarily determined by phylogenetic factors, rather than ecological factors, including food. Two species, S. boganidae and S. drjagini, had the highest EPA+DHA contents in their biomass and thereby could be recommended as promising species for aquaculture to obtain production with especially high nutritive value. Basing on revealed differences in FA composition of wild and farmed fish, levels of 15-17-BFA (branched fatty acids), 18:2NMI (non-methylene interrupted), 20:2NMI, 20:4n-3, and 22:4n-3 fatty acids were recommended for verifying trade label information of fish products on shelves, as the biomarkers to differentiate wild and farmed charr.

A Hierarchical Sparse Discriminant Autoencoder for Bearing Fault Diagnosis

Although some traditional autoencoders and their extensions have been widely used in the research of intelligent fault diagnosis of rotating parts, their feature extraction capabilities are limited without label information. In response to this problem, this research proposes a hierarchical sparse discriminant autoencoder (HSDAE) method for fault diagnosis of rotating components, which is a new semi-supervised autoencoder structure. By considering the sparsity of autoencoders, a hierarchical sparsity strategy was proposed to improve the stacked sparsity autoencoders, and the particle swarm optimization algorithm was used to obtain the optimal sparsity parameters to improve network performance. In order to enhance the classification of the autoencoder, a class aggregation and class separability strategy was used, which is an additional discriminative distance that was added as a penalty term in the loss function to enhance the feature extraction ability of the network. Finally, the reliability of the proposed method was verified on the bearing data set of Case Western Reserve University and the bearing data set of the laboratory test platform. The results of comparison with other methods show that the HSDAE method can enhance the feature extraction ability of the network and has reliability and stability for different data sets.

Application of Artificial Intelligence in Cardiovascular Imaging

During the last two decades, as computer technology has matured and business scenarios have diversified, the scale of application of computer systems in various industries has continued to expand, resulting in a huge increase in industry data. As for the medical industry, huge unstructured data has been accumulated, so exploring how to use medical image data more effectively to efficiently complete diagnosis has an important practical impact. For a long time, China has been striving to promote the process of medical informatization, and the combination of big data and artificial intelligence and other advanced technologies in the medical field has become a hot industry and a new development trend. This paper focuses on cardiovascular diseases and uses relevant deep learning methods to realize automatic analysis and diagnosis of medical images and verify the feasibility of AI-assisted medical treatment. We have tried to achieve a complete diagnosis of cardiovascular medical imaging and localize the vulnerable lesion area. (1) We tested the classical object based on a convolutional neural network and experiment, explored the region segmentation algorithm, and showed its application scenarios in the field of medical imaging. (2) According to the data and task characteristics, we built a network model containing classification nodes and regression nodes. After the multitask joint drill, the effect of diagnosis and detection was also enhanced. In this paper, a weighted loss function mechanism is used to improve the imbalance of data between classes in medical image analysis, and the effect of the model is enhanced. (3) In the actual medical process, many medical images have the label information of high-level categories but lack the label information of low-level lesions. The proposed system exposes the possibility of lesion localization under weakly supervised conditions by taking cardiovascular imaging data to resolve these issues. Experimental results have verified that the proposed deep learning-enabled model has the capacity to resolve the aforementioned issues with minimum possible changes in the underlined infrastructure.

Multi layered Stacked Ensemble Method with Feature Reduction Technique for Multi-Label Classification

Nowadays, multi-label classification can be considered as one of the important challenges for classification problem. In this case instances are assigned more than one class label. Ensemble learning is a process of supervised learning where several classifiers are trained to get a better solution for a given problem. Feature reduction can be used to improve the classification accuracy by considering the class label information with principal Component Analysis (PCA). In this paper, stacked ensemble learning method with augmented class information PCA (CA PCA) is proposed for classification of multi-label data (SEMML). In the initial step, the dimensionality reduction step is applied, then the number of classifiers have to be chosen to apply on the original training dataset, then the stacking method is applied to it. By observing the results of experiments conducted are showing our proposed method is working better as compared to the existing methods.

Label information, nutritional composition and screening for bromate in breads sold in Umuahia, Abia State, Nigeria

Non-use of potassium bromate in bread making and printing of reproducible nutrition information/claims on bread labels are vital for consumers’ rights and protection in Nigeria. These norms are rarely observed by bread makers in Umuahia. This study evaluated nutrition information on labels, presence of potassium bromate, chemical composition and sensory characteristics of breads sold in Umuahia. Two structured questionnaires were constructed. The first was administered to 15 randomly selected full-time bread vendors in Umuahia metropolis to identify brands of market bread. The second was designed to analyze sensory quality of breads. Five sliced and five unsliced bread samples randomly selected from identified markets were analyzed for sensory properties using a 20-member sensory panelist, and for nutrient and phytochemical composition. Twenty-seven bread samples were identified; all labeled bromate-free, had varying recipes and nutrient claim/information on labels. The bread samples were bromate-free, high in carbohydrate (49.20% in B10 to 65.69% in B8) and moisture (22.67% in B8 to 38.16% in B10), but relatively low in crude protein (6.65% in B3 to 9.45% in B7) and fat (0.26% in B8 to 0.66% in B1). Ash contents ranged from 1.26% in B6 to 1.86% in B3and fiber contents from 1.24% in B2 to 1.76% in B5. Phytonutrients were low; and oxalate content ranged from 0.66 to 0.95%, tannin from 87.78 to 125.40 mg 100g–1 and phytate from 2.02 to 3.03 mg 100g–1. The bread samples had sensory scores ranging from 4.60 to 8.10 for over-all acceptability. They were all acceptable to panelists, but with B1 (sliced) and B8 (unsliced) most acceptable. Bread samples sold in Umuahia were bromate-free, varied in recipe, nutrition claims, and nutrient composition but were acceptable to panelists.

Sparse Representation Classifier Embedding Subspace Mapping and Support Vector for Facial Expression Recognition

With the development of integration and innovation of Internet and industry, facial expression recognition (FER) technology is widely applied in wireless communication and mobile edge computing. The sparse representation-based classification is a hot topic in computer vision and pattern recognition. It is one type of commonly used image classification algorithms for FER in recent years. To improve the accuracy of FER system, this study proposed a sparse representation classifier embedding subspace mapping and support vector (SRC-SM-SV). Based on the traditional sparse representation model, SRC-SM-SV maps the training samples into a subspace and extracts rich and discriminative features by using the structural information and label information of the training samples. SRC-SM-SV integrates the support vector machine to enhance the classification performance of sparse representation coding. The solution of SRC-SM-SV uses an alternate iteration method, which makes the optimization process of the algorithm simple and efficient. Experiments on JAFFE and CK+ datasets prove the effectiveness of SRC-SM-SV in FER.

Elegant Unsupervised Cross-Modal Hashing

<div><p>Unsupervised cross-modal retrieval has received increasing attention recently, because of the extreme difficulty of labeling the explosive multimedia data. The core challenge of it is how to measure the similarities between multi-modal data without label information. In previous works, various distance metrics are selected for measuring the similarities and predicting whether samples belong to the same class. However, these predictions are not always right. Unfortunately, even a few wrong predictions can undermine the final retrieval performance. To address this problem, in this paper, we categorize predictions as solid and soft ones based on their confidence. We further categorize samples as solid and soft ones based on the predictions. We propose that these two kinds of predictions and samples should be treated differently. Besides, we find that the absolute values of similarities can represent not only the similarity but also the confidence of the predictions. Thus, we first design an elegant dot product fusion strategy to obtain effective inter-modal similarities. Subsequently, utilizing these similarities, we propose a generalized and flexible weighted loss function where larger weights are assigned to solid samples to increase the retrieval performance, and smaller weights are assigned to soft samples to decrease the disturbance of wrong predictions. Despite less information is used, empirical studies show that the proposed approach achieves the state-of-the-art retrieval performance.</p><br></div>

Elegant Unsupervised Cross-Modal Hashing

<div><p>Unsupervised cross-modal retrieval has received increasing attention recently, because of the extreme difficulty of labeling the explosive multimedia data. The core challenge of it is how to measure the similarities between multi-modal data without label information. In previous works, various distance metrics are selected for measuring the similarities and predicting whether samples belong to the same class. However, these predictions are not always right. Unfortunately, even a few wrong predictions can undermine the final retrieval performance. To address this problem, in this paper, we categorize predictions as solid and soft ones based on their confidence. We further categorize samples as solid and soft ones based on the predictions. We propose that these two kinds of predictions and samples should be treated differently. Besides, we find that the absolute values of similarities can represent not only the similarity but also the confidence of the predictions. Thus, we first design an elegant dot product fusion strategy to obtain effective inter-modal similarities. Subsequently, utilizing these similarities, we propose a generalized and flexible weighted loss function where larger weights are assigned to solid samples to increase the retrieval performance, and smaller weights are assigned to soft samples to decrease the disturbance of wrong predictions. Despite less information is used, empirical studies show that the proposed approach achieves the state-of-the-art retrieval performance.</p><br></div>

Information Limits for Community Detection in Hypergraph with Label Information

In network data mining, community detection refers to the problem of partitioning the nodes of a network into clusters (communities). This is equivalent to identifying the cluster label of each node. A label estimator is said to be an exact recovery of the true labels (communities) if it coincides with the true labels with a probability convergent to one. In this work, we consider the effect of label information on the exact recovery of communities in an m-uniform Hypergraph Stochastic Block Model (HSBM). We investigate two scenarios of label information: (1) a noisy label for each node is observed independently, with 1−αn as the probability that the noisy label will match the true label; (2) the true label of each node is observed independently, with the probability of 1−αn. We derive sharp boundaries for exact recovery under both scenarios from an information-theoretical point of view. The label information improves the sharp detection boundary if and only if αn=n−β+o(1) for a constant β>0.