Search

With the trend of people expressing opinions and emotions via images online, increasing attention has been paid to affective analysis of visual content. Traditional image affective analysis mainly focuses on single-label classification, but an image usually evokes multiple emotions. To this end, emotion distribution learning is proposed to describe emotions more explicitly. However, most current studies ignore the ambiguity included in emotions and the elusive correlations with complex visual features. Considering that emotions evoked by images are delivered through various visual features, and each feature in the image may have multiple emotion attributes, this paper develops a novel model that extracts multiple features and proposes an enhanced fuzzy k-nearest neighbor (EFKNN) to calculate the fuzzy emotional memberships. Specifically, the multiple visual features are converted into fuzzy emotional memberships of each feature belonging to emotion classes, which can be regarded as an intermediate representation to bridge the affective gap. Then, the fuzzy emotional memberships are fed into a fully connected neural network to learn the relationships between the fuzzy memberships and image emotion distributions. To obtain the fuzzy memberships of test images, a novel sparse learning method is introduced by learning the combination coefficients of test images and training images. Extensive experimental results on several datasets verify the superiority of our proposed approach for emotion distribution learning of images. [ABSTRACT FROM AUTHOR]

Spectral clustering is an important component of clustering method, via tightly relying on the affinity matrix. However, conventional spectral clustering methods 1). equally treat each data point, so that easily affected by the outliers; 2). are sensitive to the initialization; 3). need to specify the number of cluster. To conquer these problems, we have proposed a novel spectral clustering algorithm, via employing an affinity matrix learning to learn an intrinsic affinity matrix, using the local PCA to resolve the intersections; and further taking advantage of a robust clustering that is insensitive to initialization to automatically generate clusters without an input of number of cluster. Experimental results on both artificial and real high-dimensional datasets have exhibited our proposed method outperforms the clustering methods under comparison in term of four clustering metrics. [ABSTRACT FROM AUTHOR]

Feature selection is an important preprocessing step for dealing with high dimensional data. In this paper, we propose a novel unsupervised feature selection method by embedding a subspace learning regularization (i.e., principal component analysis (PCA)) into the sparse feature selection framework. Specifically, we select informative features via the sparse learning framework and consider preserving the principal components (i.e., the maximal variance) of the data at the same time, such that improving the interpretable ability of the feature selection model. Furthermore, we propose an effective optimization algorithm to solve the proposed objective function which can achieve stable optimal result with fast convergence. By comparing with five state-of-the-art unsupervised feature selection methods on six benchmark and real-world datasets, our proposed method achieved the best result in terms of classification performance. [ABSTRACT FROM AUTHOR]

Previous Spectral Feature Selection (SFS) methods output promising feature selection results in many real-world applications, which deeply depend on the preservation of the local or global structures of the data via learning a graph matrix. However, current SFS methods 1) learn the graph matrix in the original data which may contain a number of noise to affect the results of feature selection, 2) conduct the learning of a low-dimensional feature space and the graph matrix individually, thus hard achieve the optimal results of feature selection even though both of these two steps achieve their individual optimization, and 3) consider either the local or global structure of data to difficult provide complementary information for feature selection. To address the above issues, this paper proposes a novel supervised feature selection algorithm to simultaneously preserve the local structure (via adaptive structure learning in a low-dimensional feature space of the original data) and the global structure (via a low-rank constraint) of the data. Moreover, we also propose a new optimization method to fast optimize the resulting objective function. We finally verify the proposed method on eight real-word and benchmark datasets, by comparing with the state-of-the-art feature selection methods, and experimental results show that our proposed method achieves competitive results in term of classification performance. [ABSTRACT FROM AUTHOR]

In order to select informative features from a high-dimensional multi-view dataset, we have proposed a feature selection method that simultaneously embedding the low-rank constraint, sparse representation, global and local structure learning into a unified framework. Firstly, we utilize the conventional regression function ( i.e. the least square loss function) to form a novel regression framework by introducing a low-rank constraint and a relaxation term. And then we employ an l 21 -norm regularization term to filter out the redundant and irrelative features. Furthermore, we utilize a hypergraph based regularization term rather than the simple graph to construct a Laplacian matrix that will be used in enhancing the inherent association of data. Besides, we proposed a novel optimization algorithm to solve the objective function. Finally, we feed the reduced data got by the proposed feature selection method into Support Vector Machines (SVM) in term of classification accuracy. The experimental results showed that the proposed method achieved the best classification performance, compared with the state-of-the-art feature selection methods on real multi-view dataset. [ABSTRACT FROM AUTHOR]

The sentiment analysis of microblog text has always been a challenging research field due to the limited and complex contextual information. However, most of the existing sentiment analysis methods for microblogs focus on classifying the polarity of emotional keywords while ignoring the transition or progressive impact of words in different positions in the Chinese syntactic structure on global sentiment, as well as the utilization of emojis. To this end, we propose the emotion-semantic-enhanced bidirectional long short-term memory (BiLSTM) network with the multi-head attention mechanism model (EBILSTM-MH) for sentiment analysis. This model uses BiLSTM to learn feature representation of input texts, given the word embedding. Subsequently, the attention mechanism is used to assign the attentive weights of each words to the sentiment analysis based on the impact of emojis. The attentive weights can be combined with the output of the hidden layer to obtain the feature representation of posts. Finally, the sentiment polarity of microblog can be obtained through the dense connection layer. The experimental results show the feasibility of our proposed model on microblog sentiment analysis when compared with other baseline models. [ABSTRACT FROM AUTHOR]

• A probabilistic modelling framework was proposed to better assess the effect of cascade reservoir regulation on ice-jam flooding. • Incorporating both regulated and naturalized flows, the modelling framework provides a credible assessment. • The modelling framework was successfully verified for the Sanhuhekou bend reach regulated by eight cascade reservoirs. In regulated rivers, dams and their reservoirs are the main means to change the flow conditions, and strategic reservoir operations can be an important measure for mitigating ice-jam flooding (IJF). Previous studies have shown the effect of single reservoir operation on IJF probabilities, but little is known about the effect of cascade reservoir operation on IJF occurrences and severity. This study presents a probabilistic modelling framework that couples machine learning (LSTM, Long Short-Term Memory) and river ice (RIVICE) models to assess the effects of regulated and naturalized flows on IJF backwater levels. The trained LTSM shows good performance in both validation (RMSE = 398.88, R = 0.86 and NSE = 0.67) and testing (RMSE = 366.57, R = 0.84 and NSE = 0.71) periods and the calibrated RIVICE can well simulate backwater levels caused by three IJFs from 2008 to 2010 with total volumes of incoming ice for 0.4 million m3, 0.55 million m3 and 0.32 million m3. The completed framework was used to assess IJF hazard along the Sanhuhekou bend, a reach of the upper Yellow River, whose hydraulic regime is impacted by eight upstream reservoirs. The effect of naturalized and regulated flows on IJF are compared from two aspects. Firstly, comparing the median of naturalized and regulated IJF backwater level ensembles, the results show that regulation increases the IJF backwater levels. Secondly, comparing the extreme values of naturalized and regulated IJF backwater level ensembles, results show that regulation can increase the hazard of IJF inundation when annual exceedance probability (AEP) is less severe than 1:100 and regulation can decrease the hazard of IJF when AEP is more severe than 1:125. [ABSTRACT FROM AUTHOR]

Feature selection remove the noisy/irrelevant samples and select the subset of representative features, in general, from the high-dimensional space of data has been a fatal significant technique in computer vision and machine learning. Afterwards, motivated by the interpretable ability of feature selection patterns, beside, and the successful use of low-rank constraint in static and sparse learning in the field of machine learning. We present a novel feature selection model with unsupervised learning by using low-rank regression on loss function, and a sparsity term plus K-means clustering method on regularization term during this article. In order to distinguish from those existing state-of-the-art attribute selection measures, the propose method have described as follows: (1) represent the every feature by other features (including itself) via utilize the corresponding loss function with a feature-level self-express way; (2) embed K-means to generate pseudo class label information for the attribute selection as an pseudo supervised method, because of the supervised learning usually have the better recognition results than unsupervised learning; (3) also use the low-rank constraint to feature selection which considers two aspects of information inherent in data. The low-rank constraint takes the correlation of response variables into account, while an ℓ 2, p -norm regularizer considers the correlation between feature vectors and their corresponding response variables. The extensive relevant results of experiment on three multi-model comparison data demonstrated that our new unsupervised feature selection pattern outperforms the related approaches. [ABSTRACT FROM AUTHOR]

• A real-time ice-jam risk assessment system was developed to better regulate reservoir discharges. • The modelling system improves ice-jam flood predictions considering the influence of reservoir regulation. • Machine learning with deterministic modelling provides more accurate ice-jam flood predictions of regulated rivers. • The modelling system was successfully verified for the Sanhuhekou bend reach regulated by the Sanshenggong reservoir. To effectively alleviate ice-jam flood disasters, it is necessary to carry out hazard assessments and predictions of ice-jam flooding influenced by the operational scheme of a reservoir. However, traditional hydrologic flood routing techniques cannot effectively address the huge uncertainties caused by the many factors that lead to ice-jam flooding. In this paper, a hazard assessment system for regulating flood discharge schemes is developed; it is composed of a machine learning (ML) model, Long Short-Term Memory (LSTM), and a river-ice dynamic model (RIVICE) within a probabilistic method. The modelling system is to aid in the challenge of predicting ice-jam flooding downstream of reservoirs. The LSTM model forecasts the downstream flow under the operational discharge scheme and, combined with the RIVICE model, the backwater level profile of ice jams can be forecasted. Furthermore, a set of backwater level profiles can be provided by probabilistic modelling, and the probability of ice-jam flood inundation can be calculated by comparing backwater levels with the elevation of the river bank; this information can be used to warn of the hazard induced by operational discharges to better aid in the preparedness and mitigation of ice-jam floods. This system was tested successfully for the ice-cover breakup period in the spring of 2008 and 2018 along the Sanhuhekou bend reach of the Yellow River in China. [ABSTRACT FROM AUTHOR]