Monitoring of Domestic Activities Using Multiple Beamformers and Attention Mechanism

This study discusses about language use occurred by male and female host in Hitam Putih talk show. The method of this research is descriptive qualitative. The subjects of this study are male and female host in Hitam Putih talk show. The data are the utterances produced by male and female host in Hitam Putih talk show. This research focuses on the show broadcasted on October 2016 by taking 4 videos randomly. The objective of this study is to describe kinds of the language use uttered by male and female host in Hitam Putih talk show. The findings showed that the kinds of language use consist of 6 parts. The dominant language use uttered by male host is expletive, because male’s utterances are frequently stated in a negative connotation. On the other hand, female host utterances are found in specialized vocabulary as the most dominant because female host has more interest in talking family affairs, such as the education of children, clothes, cooking, and fashion, etc. Women also tended to talk about one thing related to the home and domestic activities. However, the representation of language use uttered by male and female are deficit, dominance and different. Keywords: Language Use, Gender, Talk Show

Download Full-text

A New Time-Frequency Attention Mechanism for TDNN and CNN-LSTM-TDNN, with Application to Language Identification

10.21437/interspeech.2019-1256 ◽

2019 ◽

Cited By ~ 3

Author(s):

Xiaoxiao Miao ◽

Ian McLoughlin ◽

Yonghong Yan

Keyword(s):

Attention Mechanism ◽

Language Identification ◽

Time Frequency ◽

New Time

Download Full-text

Dam Deformation Interpretation and Prediction Based on a Long Short-Term Memory Model Coupled with an Attention Mechanism

Applied Sciences ◽

10.3390/app11146625 ◽

2021 ◽

Vol 11 (14) ◽

pp. 6625

Author(s):

Yan Su ◽

Kailiang Weng ◽

Chuan Lin ◽

Zeqin Chen

Keyword(s):

Short Term Memory ◽

Attention Mechanism ◽

Impact Factors ◽

Nonlinear Prediction ◽

Time Dimension ◽

Short Term ◽

Deformation Prediction ◽

Term Memory ◽

Long Short Term Memory ◽

Dam Deformation

An accurate dam deformation prediction model is vital to a dam safety monitoring system, as it helps assess and manage dam risks. Most traditional dam deformation prediction algorithms ignore the interpretation and evaluation of variables and lack qualitative measures. This paper proposes a data processing framework that uses a long short-term memory (LSTM) model coupled with an attention mechanism to predict the deformation response of a dam structure. First, the random forest (RF) model is introduced to assess the relative importance of impact factors and screen input variables. Secondly, the density-based spatial clustering of applications with noise (DBSCAN) method is used to identify and filter the equipment based abnormal values to reduce the random error in the measurements. Finally, the coupled model is used to focus on important factors in the time dimension in order to obtain more accurate nonlinear prediction results. The results of the case study show that, of all tested methods, the proposed coupled method performed best. In addition, it was found that temperature and water level both have significant impacts on dam deformation and can serve as reliable metrics for dam management.

Download Full-text