In this letter, we propose a novel clustering-based detector for spatial modulation multiple-input multiple-output (MIMO) system. Specifically, we first convert unconstrained optimization problem of conventional K-means algorithm to the constrained optimization by controlling the number of received symbols in each cluster. Then, a low complexity greedy algorithm is designed for solving the constrained optimization problem to determine the cluster centroids of proposed detector, and a novel detector based on the greedy algorithm is proposed accordingly. The simulation results show that proposed detector efficiently avoids the occurrence of error floor effects of conventional Kmeans detector and can achieve near-ML performance even if the number of clusters is large while effectively reducing the complexity compared to existing blind detectors.

Text data augmentation is essential in the field of medicine for the tasks of natural language processing (NLP). However, most of the traditional text data augmentation focuses on the English datasets, and there is little research on the Chinese datasets to augment Chinese sentences. Nevertheless, the traditional text data augmentation ignores the semantics between words in sentences, besides, it has limitations in alleviating the problem of the diversity of augmented sentences. In this paper, a novel medical data augmentation (MDA) is proposed for NLP tasks, which combines the medical knowledge graph with text data augmentation to generate augmented data. Experiments on the named entity recognition task and relational classification task demonstrate that the MDA can significantly enhance the efficiency of the deep learning models compared to cases without augmentation.

Knowledge graph-based question answering is an intelligent approach to deducing the answer to a natural language question from structured knowledge graph information. As one of the mainstream knowledge graph-based question answering approaches, information retrieval-based methods infer the correct answer by constructing and ranking candidate paths, which achieve excellent performance in simple questions but struggle to handle complex questions due to rich entity information and diverse relations. In this paper, we construct a joint system with three subsystems based on the information retrieval methods, where candidate paths can be efficiently generated and ranked, and a new text-matching method is introduced to capture the semantic correlation between questions and candidate paths. Results of the experiment conducted on the China Conference on Knowledge Graph and Semantic Computing 2019 Chinese Knowledge Base Question Answering dataset verify the superiority and efficiency of our approach.

Medication recommendation based on Electronic Health Records (EHRs) is a significant research direction in the field of intelligent medicine, which aims to recommend personalized medication combinations for patients based on their historical and current physical conditions. However, since the structural and temporal characteristics of medical records are affected by many uncertain factors, there are many limitations in medication recommendation methods based on EHRs. Specifically, most existing works either fail to adequately assess the structural correlation and temporal dependency among various medical entities or ignore existing knowledge of Drug–Drug Interactions (DDI), which could lead to adverse outcomes. These factors contribute to poor recommendation quality. Therefore, we propose a medical ontology tree model combined with the Graph Attention Networks (GAT) for medication recommendations. First, the class hierarchy extracted from the medical ontology and the GAT model is used to learn the ICD-9 codes of diagnoses and procedures, which enriches the semantic representation of medical entities. Secondly, Gate Recurrent Units (GRU) are used to learn the temporal characteristics of medical entities. Finally, memory bank, dynamic memory and DDI graph are used to optimize the hidden layer results, which improve the accuracy of the model. Experimental results show that the proposed model is superior to the previous methods in all evaluation indicators, and the recommended results have a lower DDI rate.

Zero-shot relation extraction (ZSRE) is essential for improving the understanding of natural language relations and enhancing the accuracy and efficiency of natural language processing methods in practical applications. However, the existing ZSRE models ignore the importance of semantic information fusion and possess limitations when used for zero-shot relation extraction tasks. Thus, this paper proposes a dual contrastive learning framework and a cross-attention network module for ZSRE. First, our model designs a dual contrastive learning framework to compare the input sentences and relation descriptions from different perspectives; this process aims to achieve better separation between different relation categories in the representation space. Moreover, the cross-attention network of our model is introduced from the computer vision field to enhance the attention paid by the input instance to the relevant information of the relation description. The experimental results obtained on the Wiki-ZSL and FewRel datasets fully demonstrate the effectiveness of our approach.