Contextual Word2Vec Model for Understanding Chinese Out of Vocabularies on Online Social Media

Article Computer Science, Artificial Intelligence

Information Entropy Augmented High Density Crowd Counting Network

Yu Hao et al.

Summary: This research proposes an innovative structure for a density map-based crowd counting network, which is augmented by information entropy. The network consists of a front-end network for feature extraction and a back-end network for density map generation. Experimental results show that the network is capable of accurately estimating the count in extremely high crowd density, and it performs better compared to similar networks without the entropy feature. This result proves that information entropy can enhance the efficiency of density map-based crowd counting approaches.

INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A New Alignment Word-Space Approach for Measuring Semantic Similarity for Arabic Text

Shimaa Ismail et al.

Summary: This study presents a new alignment word-space approach for measuring the similarity between two snipped texts. The approach combines alignment-based and vector space-based similarity measurement methods and has been proven effective through experiments.

INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS (2022)

添加到收藏夹

Article Computer Science, Artificial Intelligence

AUV-Based Efficient Data Collection Scheme for Underwater Linear Sensor Networks

Zahoor Ahmed et al.

Summary: The research on underwater wireless sensor networks focuses on developing a reliable communication protocol for various underwater sensing devices for applications such as offshore exploration and pollution monitoring. However, there are issues with the heterogeneity and network coverage of the sensor nodes.

INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS (2022)

添加到收藏夹

Review Medical Informatics

Path-based knowledge reasoning with textual semantic information for medical knowledge graph completion

Yinyu Lan et al.

Summary: This paper proposes two novel path-based reasoning methods to address entity and path sparsity issues in MedKGC by utilizing textual semantic information. By leveraging the pre-trained BERT model, the task of symbolic reasoning in the medical KG is modeled as a numerical computing problem in textual semantic representation. Experiment results show that the proposed method outperforms state-of-the-art path-based knowledge graph reasoning methods in completing the impaired symptom knowledge graph.

BMC MEDICAL INFORMATICS AND DECISION MAKING (2021)

添加到收藏夹

Article Computer Science, Information Systems