Graph Convolutional Networks (GCNs) are widely used in graph-based applications, such as social networks and recommendation systems. Nevertheless, large-scale graphs or deep aggregation layers in full-batch GCNs consu...
详细信息
When natural or man-made disasters occur at sea, a maritime unmanned rescue system-of-systems (MURSoSs), as an important guarantee for the safety of people's lives and property, has a rapid response to emergency r...
详细信息
Biomedical relation extraction seeks to automatically extract biomedical relations from biomedical text, which plays an important role in biomedical studies. However, constructing high-quality biomedical annotation da...
详细信息
In the field of robust audio watermarking,how to seek a good trade-off between robustness and imperceptibility is challenging. The existing studies use the same embedding parameter for each part of the audio signal, w...
详细信息
In the field of robust audio watermarking,how to seek a good trade-off between robustness and imperceptibility is challenging. The existing studies use the same embedding parameter for each part of the audio signal, which ignores that different parts may have different requirements for embedding parameters. In this work, the constraints on imperceptibility are first ***, we present a segment multi-objective optimization model of the scaling parameter under the constrained Signal-to-noise ratio(SNR) in Spread spectrum(SS)audio watermarking. Additionally, we adopt the Nondominated sorting genetic algorithm Ⅱ(NSGA-Ⅱ) to solve the proposed model. Finally, we compare our algorithm(called SS-SNR-NSGA-Ⅱ) with the existing methods. The experimental results show that the proposed SS-SNRNSGA-Ⅱ not only provides flexible choices for different application demands but also achieves more and better trade-offs between imperceptibility and robustness.
In the edge-cloud computing, the applications usually are delivered as services, each of which runs independently and can cooperate to construct the complicated applications. However, it is difficult to monitor the se...
详细信息
Coreference resolution aims at linking all mentions that refer to the same entity, which are widely adopted in many biomedical and bioinformatics tasks, such as biomedical knowledge graph construction and metabolic pa...
详细信息
作者:
Lintai CuiLiuqi JinKey Laboratory of Knowledge
Engineering with Big Data of the Ministry of Education School of Computer Science and Information Engineering Hefei University of Technology Hefei China
Hospital-acquired pressure injury (HAPI) is a se-rious healthcare problem for intensive care unit (ICU) patients, which significantly affects their quality of life and prognosis, and increases hospitalization time and...
Hospital-acquired pressure injury (HAPI) is a se-rious healthcare problem for intensive care unit (ICU) patients, which significantly affects their quality of life and prognosis, and increases hospitalization time and medical expenses. The current prediction models cannot accurately predict the pressure injury (PI) in ICU wards, as these models usually only predict based on the patient's current physical condition and electronic health record data, resulting in poor recall and precision, which affects the prediction performance. To solve this problem, we applied the multivariate time series data of I CU patients from admission to discharge and established a PI prediction model for ICU patients by utilizing the bidirectional long short-term memory neural network (Bi-LSTM) model. Experiments on the MIMIC-III (Medical Information Mart for Intensive Care) dataset show that the Bi-LSTM model has an F1 score of 0.24 and an AUC (Area Under Curve) value of 0.81, which are better than other models. This validates the effectiveness of the Bi-LSTM on the multivariate time series data to predict the occurrence of PI in ICU wards and assist nursing staff to allocate nursing resources more effectively.
knowledge base question generation (KBQG) aims to generate natural language questions from a set of triplet facts extracted from KB. Existing methods have significantly boosted the performance of KBQG via pre-trained ...
详细信息
Tables, as an important means of data storage, are widely used in spreadsheets, web tables, and PDFs. By integrating information from table data with knowledge re-trieved from an external knowledge base, and examining...
详细信息
ISBN:
(数字)9781665410205
ISBN:
(纸本)9781665410212
Tables, as an important means of data storage, are widely used in spreadsheets, web tables, and PDFs. By integrating information from table data with knowledge re-trieved from an external knowledge base, and examining the correspondences between cell values in the table and instances in the knowledge base, we can extract knowledge from the table to augment and enrich the knowledge base. To achieve this goal, we first need to classify table cells based on their functions in the layout. Due to the diverse structures arising from the arrangements of rows and columns, as well as the complexity of content resulting from concise data storage, current automation techniques heavily rely on stylistic features of table cells, such as font or color. Moreover, these methods are rarely experimented with or validated on tables without style features. Recent literature indicates that large language models (LLMs) demonstrate an ability to understand the structure and content of tables in tasks such as table judgment reasoning. Even without extensive feature inputs or pre-training, LLMs still show comparable results to machine learning and deep learning in these tasks. Therefore, this paper attempts to apply LLMs to table cell classification without using other stylistic features. We have designed a 4-component prompt paradigm (Classification Definition, Instruction, Table, Com-pletion), representing respectively the classification definition, task instructions, table data, and result output. We conduct experiments on three datasets CIUS, SAUS, and DEEX for table cell classification with one-shot learning. Our experimental results show that with the assistance of LLMs, better results can be achieved without utilizing stylistic features.
Dear editor,Frequent itemset mining (FIM) is important in many data mining applications [1], such as web log mining and trend analysis. However, if the data are sensitive (e.g., web browsing history), directly releasi...
详细信息
Dear editor,Frequent itemset mining (FIM) is important in many data mining applications [1], such as web log mining and trend analysis. However, if the data are sensitive (e.g., web browsing history), directly releasing frequent itemsets and their support may breach user privacy. The protection of user privacy while obtaining statistical information is im-
暂无评论