Unsupervised cross-modal hashing has achieved great success in various information retrieval applications owing to its efficient storage usage and fast retrieval speed. Recent studies have primarily focused on training the hash-encoded networks by calculating a sample-based similarity matrix to improve the retrieval performance. However, there are two issues remain to solve: (1) The current sample-based similarity matrix only considers the similarity between image-text pairs, ignoring the different information densities of each modality, which may introduce additional noise and fail to mine key information for retrieval; (2) Most existing unsupervised cross-modal hashing methods only consider alignment between different modalities, while ignoring consistency between each modality, resulting in semantic conflicts. To tackle these challenges, a novel Deep High-level Concept-mining Jointing Hashing (DHCJH) model for unsupervised cross-modal retrieval is proposed in this study. DHCJH is able to capture the essential high-level semantic information from image modalities and integrate into the text modalities to improve the accuracy of guidance information. Additionally, a new hashing loss with a regularization term is introduced to avoid the cross-modal semantic collision and false positive pairs problems. To validate the proposed method, extensive comparison experiments on benchmark datasets are conducted. Experimental findings reveal that DHCJH achieves superior performance in both accuracy and efficiency. The code of DHCJH is available at Github.

Ground-based cloud image sequence prediction provides valuable insights into cloud motion and meteorological conditions, which are essential for photovoltaic power generation systems. Most existing models are, however, recurrent-based, which is problematic in providing satisfactory forecasting results with rapid speed because these recurrent-based models do not support parallel inference and usually suffer from slow inference speed. A novel recurrent-free deep learning-based framework, called multiscale spatiotemporal attention network (MSTANet) to address the issues is proposed in this study. The MSTANet leverages a multiscale spatiotemporal attention (MSTA) module to extract the multiscale, nonlinear spatiotemporal dependencies from cloud image sequences and uses a multiscale temporal attention (MTA) module to reinforce the temporal dependencies by capturing the high- and low-frequency spatiotemporal fluctuations of clouds. A gated aggregation unit (GAU) to mitigate the ghosting effects that are prevalent in spatiotemporal prediction tasks is introduced to filter the useful context information by integrating the historical information with the updated predictions. Additionally, a multiorder differential divergence regularization term is introduced into the loss function to improve the model’s performance by encouraging MSTANet to focus on the evolving trends of the neighborhood of clouds. Experimental results show that the proposed MSTANet outperforms the state-of-the-art (SOTA) prediction methods. It reduces 46% parameters and mean-squared-error (MSE) by 4.31% on the Moving Mnist dataset and reduces 22% parameters with a 1.82% performance improvement on the Folsom dataset compared to the baseline temporal attention unit (TAU). The codes are available athttps://github.com/Csorasky/MSTANet.

We investigate essential relationships between generalization capabilities and fuzziness of fuzzy classifiers (viz., the classifiers whose outputs are vectors of membership grades of a pattern to the individual classes). The study makes a claim and offers sound evidence behind the observation that higher fuzziness of a fuzzy classifier may imply better generalization aspects of the classifier, especially for classification data exhibiting complex boundaries. This observation is not intuitive with a commonly accepted position in “traditional” pattern recognition. The relationship that obeys the conditional maximum entropy principle is experimentally confirmed. Furthermore, the relationship can be explained by the fact that samples located close to classification boundaries are more difficult to be correctly classified than the samples positioned far from the boundaries. This relationship is expected to provide some guidelines as to the improvement of generalization aspects of fuzzy classifiers.

When fuzzy IF-THEN rules initially extracted from data have not a satisfying performance, we consider that the rules require refinement. Distinct from most existing rule-refinement approaches that are based on the further reduction of training error, this paper proposes a new rule-refinement scheme that is based on the maximization of fuzzy entropy on the training set. The new scheme, which is realized by solving a quadratic programming problem, is expected to have the advantages of improving the generalization capability of initial fuzzy IF-THEN rules and simultaneously overcoming the overfitting of refinement. Experimental results on a number of selected databases demonstrate the expected improvement of generalization capability and the prevention of overfitting by a comparison of both training and testing accuracy before and after the refinement.

Fuzzy Production Rules (FPRs) are widely used in expert systems to represent uncertainty concepts. In order to enhance the representation capability and to improve the reasoning-accuracy of FPRs, some useful knowledge representation parameters such as certainty factor, local weight and global weight have been included in FPRs. However, the acquisition of the values of these parameters is difficult and time-consuming. Usually the principle to determine these parameters is to further reduce the training error. This paper proposes a new principle, i.e., the maximum entropy principle, for solving these parameters. Firstly we present a parametric tuning method based on the maximization of fuzzy entropy on the training set, then a genetic algorithm-based optimization technique is applied to determine the values of the weights in FPRs. Experimental results demonstrate a number of advantages of our method such as automatic acquisition of the weights, avoiding the over-fitting to a great extent and non-changing the number of the initial FPRs.

The generalization capability of a classifier will probably be degenerated when the classifier is generated from a dataset containing redundancy. To remove the redundancy, sample selection methods which choose the most valuable and representative instances from the original date set, can be used to obtain a subset of the original dataset. It is expected that the classifier trained from the subset can achieve no lower generalization capability than the classifier trained from the original data set. This paper proposes a sample selection method based on maximum entropy of testing instances in the fuzzy decision tree induction, and also gives the related theoretical analyses.