Space computing devices expand handwritten input from two-dimensional screens into three-dimensional space, providing an unrestricted interactive experience. Due to the high degree of freedom and lack of tactile feedback in in-air handwriting, handwritten characters not only become less legible but also lose the writer's personal style. This paper proposes a method for reconstructing discrete in-air handwriting using continuous diffusion models, capturing the writing process and style from a small number of user-provided handwritten tracks and images, to restore the legibility of characters and mimics the writer's style. We represent handwritten track data in binary form and model it with continuous diffusion models, recovering discrete handwritten track data through threshold processing. Our approach reconstructs in-air handwritten characters in two stages. During the content preservation phase, we propose a partial noise injection strategy based on reference sequence modeling, using the content information of the original character as a guiding condition to maintain content consistency in handwritten character. In the style aggregation phase, we adaptively fuse the visual style of the handwritten in the image modality with the dynamic writing process in the sequence modality, overcoming issues of insufficient style capture due to noise interference in the backward process. Qualitative and quantitative experiments demonstrate the superiority of our method.

The core of font generation technology lies in preserving character structure and accurately transferring stylistic features. While extensive research has been conducted on Chinese character generation, studies on Yi script font generation remain in their infancy. This paper, therefore, proposes a framework that employs a multi-scale conditional diffusion model to generate Yi script fonts. A Multi-scale Content Perception (MCP) module is designed. This module employs a constructed channel-space dual-domain multi-scale attention coordination mechanism to hierarchically capture multi-scale spatial and content information of characters within images. To achieve cross-modal feature fusion for Yi characters, an Efficient Style Insertion (ESI) module was developed. This module employs a cross-attention mechanism integrating multi-head mechanisms and Efficient Channel Attention (ECA) to enable cross-modal interaction of font style features. It further introduces block-wise attention to overcome computational redundancy issues inherent in traditional cross-attention. Finally, comparative experiments across Yi font datasets — including the Public Standardized Yi Font File (PSFF-Yi) dataset, Self-Built Handwritten Yi (SBHW-Yi) dataset, and Ancient Manuscript Handwritten Yi (AMHW-Yi) dataset — demonstrate the feasibility of this approach.

In this study, we present a comprehensible classifier AFSNN that embeds a new type of coherence membership function, which builds upon the theoretical findings of the axiomatic fuzzy set (AFS) theory into the hidden layer of neural network with random weights (NNRWs). Borrowing from the idea of NNRWs that employs the random initialization technique, the relation among attributes, simple concepts, and complex concepts are randomly determined. Complex concepts are generated through the combination of randomly selected simple concepts by AFS logic operation. The output weights of NNRWs are utilized to evaluate the confidence of each complex concept for every target class, which means that the feasibility of complex concepts for every class is determined analytically rather than through the tuning parameters of constraint conditions such as in conventional AFS-based classifiers. For the proposed method, compared to other neural-network-based classification methods, the fuzzy descriptions generated from complex concepts in hidden layer make classification result human understandable. We have experimented with several benchmark datasets and compared the results with other neural network-based classifiers. We show that our method outperforms Ensemble, EvRBFN, NNEP, LVQ, and iRProp+ in the seven out of ten datasets. The results show that the performance of AFSNN is competitive in terms of classification accuracy and the network shows a distinctive capability of providing explicit knowledge in the form of linguistic description.

Web community detection is one of the important ways to enhance retrieval quality of web search engine. How to design one highly effective algorithm to partition network community with few domain knowledge is the key to network community detection. Traditional algorithms, such as Wu-Huberman algorithm, need priori information to detect community, the Radichi algorithm relies on the triangle number in the network, the extremal optimization algorithm proposed by Duch J. is extremely sensitive to the initial solution, easy to fall into the local optimum. This article proposes a new model based on particle swarm optimization to detect network community, and with different scale network chart, Zachary, Krebs and dolphins network architecture to test the algorithm, the experimental results indicate this model can effectively find web communities of network structure without any domain information.