Sentence Representation Method Based on Multi-Layer Semantic Network

Zheng, Wenfeng; Liu, Xiangjun; Yin, Lirong

doi:10.3390/app11031316

Cited by 138 publications

(76 citation statements)

References 28 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…From the pre-processed data, the current study selects the earthquake activity data that meets the conditions of Ms ≥ 2.0 and Ms ≥ 7.0 from 1900 to 2015. The sliding window was set to two years, and a month was considered a sliding step [36][37][38]. Strong earthquakes in the earthquake zone were analyzed by using the R/S method.…”

Section: Analysis Of Earthquake Time Series In the Eurasian Earthquake Zone Using The R/s Methodsmentioning

confidence: 99%

The Nonlinear Time Sequence Analysis in the Alpine-Himalayan Earthquake Zone

Chen

Yan

et al. 2021

E3S Web Conf.

View full text Add to dashboard Cite

The characteristics of the earthquake activity in the Eurasian earthquake zone, which is the second largest earthquake zone in the world, was investigated by researchers. The earthquake activity of the Eurasian earthquake zone was analysed in various disciplines, such as earth dynamics, rock mechanics, geology and tectonics. The emergence of fractal theory provided a new direction in exploring the characteristics of the earthquake activity in the Eurasian earthquake zone. This study processed the data on the earthquake activity in the Eurasian earthquake zone by self-similarity method and scaled invariant feature test and used the rescaled range analysis method to analyse the nonlinear time series fractal characteristics of the earthquake activity in the Eurasian earthquake zone. Results show that the time series of earthquake activity in the study area is not an independent Poisson process, which exhibits the characteristics of scale invariance and long-range correlation. Approximately 80% of the H values of the earthquake activity iteratively increase and decrease for moderate earthquakes, which is mainly concentrated during the increasing stage. The time difference of the H value between the two-neighbouring earthquake shows that the H value fluctuates in the active earthquake region and is stationary in the relatively stable region. Strong earthquakes will likely occur in the next few years because the H value fluctuates.

show abstract

Section: Analysis Of Earthquake Time Series In the Eurasian Earthquake Zone Using The R/s Methodsmentioning

confidence: 99%

The Nonlinear Time Sequence Analysis in the Alpine-Himalayan Earthquake Zone

Chen

Yan

et al. 2021

E3S Web Conf.

View full text Add to dashboard Cite

show abstract

“…Thus, the dynamic model of the teleoperation system cannot be unified, so the dynamic model is increased. It is difficult to design a bilateral controller [30][31][32][33]. Therefore, it is necessary to use the master robot and slave robot workspace kinematics model to transform the dynamic model of the operator module and environment module workspace into joint space.…”

Section: Space Dynamic Model Of Combined Teleoperation System Jointmentioning

confidence: 99%

Adaptive Neural Network Control of Time Delay Teleoperation System Based on Model Approximation

Wang¹,

Tian

Liu

et al. 2021

Sensors

Self Cite

View full text Add to dashboard Cite

A bilateral neural network adaptive controller is designed for a class of teleoperation systems with constant time delay, external disturbance and internal friction. The stability of the teleoperation force feedback system with constant communication channel delay and nonlinear, complex, and uncertain constant time delay is guaranteed, and its tracking performance is improved. In the controller design process, the neural network method is used to approximate the system model, and the unknown internal friction and external disturbance of the system are estimated by the adaptive method, so as to avoid the influence of nonlinear uncertainties on the system.

show abstract

“…Most non-deep learning models are based on Bayesian theory. Some researchers [2][3][4][5][6][7][8][9][10][11][12][13] proposed a Bayesian framework, predicting the type of answer to a question and generating an answer. Mateusz et al proposed the multi-world question and answer model in 2014, proposed the DAQUAR data set, and modeled visual question and answer as SWQA model [14].…”

Section: Introductionmentioning

confidence: 99%

Improving Visual Reasoning Through Semantic Representation

et al. 2021

Self Cite

View full text Add to dashboard Cite

In visual reasoning, the achievement of deep learning significantly improved the accuracy of results. Image features are primarily used as input to get answers. However, the image features are too redundant to learn accurate characterizations within a limited complexity and time. While in the process of human reasoning, abstract description of an image is usually to avoid irrelevant details. Inspired by this, a higher-level representation named semantic representation is introduced. In this paper, a detailed visual reasoning model is proposed. This new model contains an image understanding model based on semantic representation, feature extraction and process model refined with watershed and u-distance method, a feature vector learning model using pyramidal pooling and residual network, and a question understanding model combining problem embedding coding method and machine translation decoding method. The feature vector could better represent the whole image instead of overly focused on specific characteristics. The model using semantic representation as input verifies that more accurate results can be obtained by introducing a highlevel semantic representation. The result also shows that it is feasible and effective to introduce high-level and abstract forms of knowledge representation into deep learning tasks. This study lays a theoretical and experimental foundation for introducing different levels of knowledge representation into deep learning in the future.

show abstract

Sentence Representation Method Based on Multi-Layer Semantic Network

Cited by 138 publications

References 28 publications

The Nonlinear Time Sequence Analysis in the Alpine-Himalayan Earthquake Zone

The Nonlinear Time Sequence Analysis in the Alpine-Himalayan Earthquake Zone

Adaptive Neural Network Control of Time Delay Teleoperation System Based on Model Approximation

Improving Visual Reasoning Through Semantic Representation

Contact Info

Product

Resources

About