Current mainstream super-resolution algorithms based on deep learning use a deep convolution neural network (CNN) framework to realize end-to-end learning from low-resolution (LR) image to high-resolution (HR) images, and have achieved good image restoration effects. However, as the number of layers in the network is increased, better results are not necessarily obtained, and there will be problems such as slow training convergence, mismatched sample blocks, and unstable image restoration results. We propose a preclassified deep-learning algorithm (MGEP-SRCNN) using Multilabel Gene Expression Programming (MGEP), which screens out a sample sub-bank with high relevance to the target image before image block extraction, preclassifies samples in a multilabel framework, and then performs nonlinear mapping and image reconstruction. The algorithm is verified through standard images, and better objective image quality is obtained. The restoration effect under different magnification conditions is also better.

With the rapid expansion of data volume, traditional data storage methods have been unable to meet the practical application requirements of blockchain cloud storage. Aiming for the cloud storage problem of blockchain, a new storage access method for predicting dynamic file load is proposed. By predicting the load status of cloud storage files in advance, the load of each blockchain data node at the next moment is first estimated. A hierarchical genetic algorithm is used to construct the connection weights between the hidden layer and the output layer, which makes the data network converge faster and more accurate, thereby effectively predicting the node load. In addition, based on the file allocation, an evaluation analysis model is constructed to obtain the time response capability of each file during the allocation process. The node’s periodic load prediction value is used to calculate the corresponding weight of the node and it is continuously updated, retaining the advantages of the static weighted polling algorithm. Combined with the genetic algorithm to help predict the file assignment access strategy of the later load of each node, it can meet the system requirements under complex load conditions and provide a reasonable and effective cloud storage method. The experimental evaluation of the proposed new strategy and new algorithm verifies that the new storage method has a faster response time, more balanced load, and greatly reduced energy consumption.

Zero-shot sketch-based image retrieval (ZS-SBIR) refers to retrieving natural images with similar contours and semantics using query sketches in zero-shot scenarios. Existing works mainly focus on using teacher networks to mitigate catastrophic forgetting of models. They aim to retain the knowledge learned by pre-trained models on large-scale datasets, thereby improving the zero-shot generalization ability of models. However, naively using teacher networks is difficult to effectively mitigate catastrophic forgetting and leads to overfitting risks in some cases. In addition, previous methods ignore the explicit utilization of structural knowledge and fail to guide the model to fully mine the structural knowledge of category semantic information, thereby neglecting the learning of inter-class relations. To address these issues, we propose an adapter with textual knowledge graph (ATKG) for ZS-SBIR. Specifically, we employ a dual constraint of prompt learning strategies and teacher networks to suppress catastrophic forgetting and reduce overfitting risks. Additionally, to effectively learn inter-class relationships, we introduce an adapter with textual knowledge graph. This method treats category semantic information and visual features as nodes, computing their edges using cosine similarity. Subsequently, a graph convolutional network (GCN) is used to mine the structural knowledge between nodes, further effectively learning relationships among different categories. Extensive experiments on the Sketchy, TU-Berlin, and QuickDraw datasets demonstrate that our proposed method achieves better retrieval performance than state-of-the-art competitors. Specifically, on Sketchy split1, TU-Berlin and QuickDraw datasets, mAP@all is improved by 8.5%, 4.3% and 5.1% compared to ZSE or CLIP-all, respectively. On the more challenging Sketchy split2 dataset, mAP@all is improved by 3.7% compared to CLIP-all.

This paper proposes a novel method, the Convergent Radiation Algorithm (CRA), aimed at multi-attribute group decision-making (MAGDM) in circular intuitionistic fuzzy settings. The approach is aimed at reaching geometric consensus among experts, with uncertainties and hesitancies expressed via circular intuitionistic fuzzy numbers (CIFNs). First, the qualitative judgment in professionals is converted into a geometric space where experts’ assessments are represented as spatial points that reflect the differences between the opinions. All these points are gradually combined with the help of a radiation–reflection–convergence mechanism, which iteratively finds the Optimal Consensus Point (OCP) to minimize the overall weighted divergence over the evaluations. After that, a projection-based scoring method is used to locate good and bad optimal solutions, and the alternatives are ranked based on a comparison of their projection distance. It presents a numerical example with data supplied by the Hubei agro-ecological zone to demonstrate that the offered method helps to capture collective agreement and convergence behavior that is consistent, and makes the decision results readable and reliable.

We address information fusion and spatial structure modeling in high-dimensional fuzzy multi-attribute decision-making by proposing a novel framework that couples Triangular Intuitionistic Fuzzy Numbers (TIFNs) with the Plant Growth Simulation Algorithm (PGSA). The method first maps the triangular intuitionistic fuzzy information of experts on each evaluation scheme into high-dimensional spatial points to realize the structured expression of decision-making information. Subsequently, the PGSA is used to perform dynamic global optimization search on the high-dimensional point cloud to determine the optimal set point and realize the intelligent aggregation of heterogeneous fuzzy data from multiple sources. The algorithm breaks through the limitation of traditional linear aggregation on the portrayal of information spatial distribution and is able to improve the accuracy and consistency of decision-making results in high-dimensional complex environments. The experimental results show that the method in this paper outperforms the mainstream aggregation methods in a number of evaluation indexes such as weighted Hamming distance, correlation, information energy and correlation coefficient. The proposed model provides a new technical path for intelligent solution and theory expansion of high-dimensional fuzzy decision-making problems.