6 June 2020 in Scientific Programming
In the field of object detection, recently, tremendous success is achieved, but still it is a very challenging task to detect and identify objects accurately with fast speed. Human beings can detect and recognize multiple objects in images or videos with ease regardless of the object’s appearance, but for computers it is challenging to identify and distinguish between things. In this paper, a modified YOLOv1 based neural network is proposed for object detection. The new neural network model has been improved in the following ways. Firstly, modification is made to the loss function of the YOLOv1 network. The improved model replaces the margin style with proportion style. Compared to the old loss function, the new is more flexible and more reasonable in optimizing the network error. Secondly, a spatial pyramid pooling layer is added; thirdly, an inception model with a convolution kernel of 1 1 is added, which reduced the number of weight parameters of the layers. Extensive experiments on Pascal VOC datasets 2007/2012 showed that the proposed method achieved better performance.
16 November 2018 in IEEE Access
Efficient document classification techniques are crucial to current legal applications such as case based reasoning, and legal citations, etc. However, Chinese judgment documents are large and highly-complex, so the traditional machine leaning based classification models are often inefficient to Chinese document classification due to the fact that they fail to incorporate the overall structure and extra domain specific knowledge. In this paper, we propose an ontology driven knowledge block summarization approach to computing document similarity for Chinese judgment document classification. First, the extra semantic knowledge for Chinese judgment documents is adopted from perspectives of the top-level ontology and domain specific ontologies, where how to merge the different kinds of ontologies together in an extensible manner is further represented. Second, the core semantic knowledge residing in Chinese judgment documents can be summarized into knowledge blocks by ontology-based information extraction. Third, we use WMD is to calculate the similarity between different knowledge blocks instead of their original Chinese judgment documents. At last, the KNN-based experiments for Chinese judgment document classification were made to illustrate that our approach is more effective in achieving higher classification accuracy and has faster computation speed, compared to the original WMD approach.
4 February 2026 in Information Sciences
30 October 2024 in Expert Systems with Applications
6 April 2025 in Expert Systems with Applications
27 September 2024 in IEEE Transactions on Fuzzy Systems
Recently, many post-hoc GNN explanation methods have been explored to uncover GNNs' predictive behaviors by analyzing the embeddings produced by the GNN models. However, these methods suffer from explanation ambiguity inherent in learned graph embeddings because aggregation-based embeddings can lead to the loss of unique identifiers for individual graph components and thus allow non-causal nodes that are adjacent to true causal patterns to unintentionally embody causal information in their embeddings, hindering the explanations from faithfully representing the true insights of GNNs' predictive reasoning. In this paper, we present an Embedding AmbiguitySensitive GNN Explanation framework (EAGX). EAGX can effectively mitigate the impact of embedding-induced explanation ambiguity by creating edges' ambiguity feature extractor, exploring edges' predictive relevance, and integrating them into the explanation process, thereby capturing each graph component's contribution to the predictions. Specifically, we first propose a Centroid-constrained Fuzzy c-Means (C-FCM) algorithm to construct an ambiguity feature extractor. Then, we leverage the ambiguity features for edges to develop the ambiguity-based edge attribution module for assigning a prediction relevance score to each edge. Finally, instead of focusing only on the edges with high influence to the GNN prediction, we introduce a joint optimization strategy to refine the learning process of our edge attribution module, empowering EAGX to capture the subtle interplay of both causal and non-causal subgraphs on model predictions, which further improve the explainability of GNN predictions. Experimental results demonstrate that EAGX outperforms the leading explainers on most evaluation metrics, underscoring its effectiveness in generating reliable and precise explanations for GNNs