scholarly journals Heterogeneous Data Fusion Method to Estimate Travel Time Distributions in Congested Road Networks

Sensors ◽  
2017 ◽  
Vol 17 (12) ◽  
pp. 2822 ◽  
Author(s):  
Chaoyang Shi ◽  
Bi Yu Chen ◽  
William H. K. Lam ◽  
Qingquan Li
Keyword(s):  
Data Fusion ◽  
Travel Time ◽  
Road Networks ◽  
Heterogeneous Data ◽  
Fusion Method ◽  
Estimate Travel Time

scholarly journals Multimodal Fusion Method Based on Self-Attention Mechanism

2020 ◽  
Vol 2020 ◽  
pp. 1-8
Author(s):  
Hu Zhu ◽  
Ze Wang ◽  
Yu Shi ◽  
Yingying Hua ◽  
Guoxia Xu ◽  
...  
Keyword(s):  
Computational Complexity ◽  
Data Fusion ◽  
Heterogeneous Data ◽  
Attention Mechanism ◽  
Multimodal Fusion ◽  
Fusion Method ◽  
Data Set ◽  
Multimodal Data ◽  
Public Data ◽  
Multimodal Data Fusion

Multimodal fusion is one of the popular research directions of multimodal research, and it is also an emerging research field of artificial intelligence. Multimodal fusion is aimed at taking advantage of the complementarity of heterogeneous data and providing reliable classification for the model. Multimodal data fusion is to transform data from multiple single-mode representations to a compact multimodal representation. In previous multimodal data fusion studies, most of the research in this field used multimodal representations of tensors. As the input is converted into a tensor, the dimensions and computational complexity increase exponentially. In this paper, we propose a low-rank tensor multimodal fusion method with an attention mechanism, which improves efficiency and reduces computational complexity. We evaluate our model through three multimodal fusion tasks, which are based on a public data set: CMU-MOSI, IEMOCAP, and POM. Our model achieves a good performance while flexibly capturing the global and local connections. Compared with other multimodal fusions represented by tensors, experiments show that our model can achieve better results steadily under a series of attention mechanisms.

Inconsistency detection and data fusion in USAR task

2017 ◽  
Vol 34 (1) ◽  
pp. 18-32 ◽  
Author(s):  
Pei-Ju Lee ◽  
Peng-Sheng You ◽  
Yu-Chih Huang ◽  
Yi-Chih Hsieh
Keyword(s):  
Linear System ◽  
Data Fusion ◽  
Information Fusion ◽  
Spatial Data ◽  
Least Squares Method ◽  
Heterogeneous Data ◽  
Sensor Data ◽  
Fusion Method ◽  
Content Type ◽  
Inconsistency Detection

Purpose The historical data usually consist of overlapping reports, and these reports may contain inconsistent data, which may return incorrect results of a query search. Moreover, users who issue the query may not learn of this inconsistency even after a data cleaning process (e.g. schema matching or data screening). The inconsistency can exist in different types of data, such as temporal or spatial data. Therefore, this paper aims to introduce an information fusion method that can detect data inconsistency in the early stages of data fusion. Design/methodology/approach This paper introduces an information fusion method for multi-robot operations, for which fusion is conducted continuously. When the environment is explored by multiple robots, the robot logs can provide more information about the number and coordination of targets or victims. The information fusion method proposed in this paper generates an underdetermined linear system of overlapping spatial reports and estimates the case values. Then, the least squares method is used for the underdetermined linear system. By using these two methods, the conflicts between reports can be detected and the values of the intervals at specific times or locations can be estimated. Findings The proposed information fusion method was tested for inconsistency detection and target projection of spatial fusion in sensor networks. The proposed approach examined the values of sensor data from simulation that robots perform search tasks. This system can be expanded to data warehouses with heterogeneous data sources to achieve completeness, robustness and conciseness. Originality/value Little research has been devoted to the linear systems for information fusion of tasks of mobile robots. The proposed information fusion method minimizes the cost of time and comparison for data fusion and also minimizes the probability of errors from incorrect results.

Data Fusion in Environment Monitoring Systems with Extended Dempster-Shafer Theory

2014 ◽  
Vol 543-547 ◽  
pp. 1074-1077
Author(s):  
Jin Gang Li ◽  
Chun Na Zheng ◽  
Hong Wei Xuan ◽  
Yan Jiang
Keyword(s):  
Data Fusion ◽  
Mathematical Description ◽  
Computing System ◽  
Heterogeneous Data ◽  
Monitoring Systems ◽  
Fusion Method ◽  
Environment Monitoring ◽  
Dempster Shafer Theory ◽  
Shafer Theory ◽  
Fusion Approach

In order to improve the accuracy and reliability of multi-source heterogeneous data in the collection process for environment monitoring, according to the analysis of the limitations, the existing methods and the features of data collected, a new kind of data fusion approach based on extended Dempster-Shafer theory is proposed. The mathematical description of extended Dempster-Shafer theory based on the data fusion is defined and the corresponding model is developed in which the data fusion method and the implementation of the algorithm are discussed. Finally, the proposed approach is applied to a computing system. The study of this approach can supply scientific accordance for comprehensive monitoring of environment.

Sign in / Sign up

Export Citation Format

Share Document