A survey on machine learning for data fusion

Meng, Tong; Jing, Xuyang; Yan, Zheng; Pedrycz, Witold

doi:10.1016/j.inffus.2019.12.001

Cited by 471 publications

(208 citation statements)

References 64 publications

Supporting

Mentioning

202

Contrasting

Unclassified

Order By: Relevance

“…Information fusion techniques have been actively researched for decades and there is a myriad of different ways to approach the problem. The approaches can be roughly divided into techniques fusing information on raw data/input level, on feature/intermediate level, or on decision/output level [210]. An overview of the main data fusion approaches in multi-modal scenarios is illustrated in Fig.…”

Section: Multi-modal Information Fusionmentioning

confidence: 99%

Collaborative Multi-Robot Search and Rescue: Planning, Coordination, Perception, and Active Vision

et al. 2020

View full text Add to dashboard Cite

Search and rescue (SAR) operations can take significant advantage from supporting autonomous or teleoperated robots and multi-robot systems. These can aid in mapping and situational assessment, monitoring and surveillance, establishing communication networks, or searching for victims. This paper provides a review of multi-robot systems supporting SAR operations, with system-level considerations and focusing on the algorithmic perspectives for multi-robot coordination and perception. This is, to the best of our knowledge, the first survey paper to cover (i) heterogeneous SAR robots in different environments, (ii) active perception in multi-robot systems, while (iii) giving two complementary points of view from the multi-agent perception and control perspectives. We also discuss the most significant open research questions: shared autonomy, sim-to-real transferability of existing methods, awareness of victims' conditions, coordination and interoperability in heterogeneous multi-robot systems, and active perception. The different topics in the survey are put in the context of the different challenges and constraints that various types of robots (ground, aerial, surface, or underwater) encounter in different SAR environments (maritime, urban, wilderness, or other post-disaster scenarios). The objective of this survey is to serve as an entry point to the various aspects of multi-robot SAR systems to researchers in both the machine learning and control fields by giving a global overview of the main approaches being taken in the SAR robotics area.

show abstract

Section: Multi-modal Information Fusionmentioning

confidence: 99%

Collaborative Multi-Robot Search and Rescue: Planning, Coordination, Perception, and Active Vision

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Data fusion is a technique to bind information from multiple sources to obtain more consistent, informative or comprehensive, and accurate representation about a process or entity [20]. In particular, data fusion can be used to improve epileptic seizure detection robustness to false-positives by increasing data variability.…”

Section: Data Fusionmentioning

confidence: 99%

Robust Epileptic Seizure Detection on Wearable Systems with Reduced False-Alarm Rate

Zanetti

Aminifar

Atienza

2020

2020 42nd Annual International Conference of the IEEE Engineering in Medicine &Amp; Biology Society (EMBC)

View full text Add to dashboard Cite

Epilepsy affects more than 50 million people and ranks among the most common neurological diseases worldwide. Despite advances in treatment, one-third of patients still suffer from refractory epilepsy. Wearable devices for real-time patient monitoring can potentially improve the quality of life for such patients and reduce the mortality rate due to seizure-related accidents and sudden death in epilepsy. However, the majority of employed seizure detection techniques and devices suffer from unacceptable false-alarm rate. In this paper, we propose a robust seizure detection methodology for a wearable platform and validate it on the Physionet.org CHB-MIT Scalp EEG database. It reaches sensitivity of 0.966 and specificity of 0.925, and reducing the false-alarm rate by 34.7%. We also evaluate the battery lifetime of the wearable system including our proposed methodology and demonstrate the feasibility of using it in real time for up to 40.87 hours on a single battery charge. Clinical relevance-We propose a methodology to increase classification robustness and reduce the false-alarm rate for epileptic seizure detection using wearable systems.

show abstract

“…But no details are given on how to resolve data conflicts in data fusion. Tong et al [22] outline 52 data fusion models combined with machine learning. Although many models ensure the quality of data after data fusion and prevent data faultage to some extent.…”

Section: Related Researchmentioning

confidence: 99%

Processing on Structural Data Faultage in Data Fusion

Chen

et al. 2020

Data

View full text Add to dashboard Cite

With the rapid development of information technology, the development of information management system leads to the generation of heterogeneous data. The process of data fusion will inevitably lead to such problems as missing data, data conflict, data inconsistency and so on. We provide a new perspective that combines the theory in geology to conclude such kind of data errors as structural data faultage. Structural data faultages after data integration often lead to inconsistent data resources and inaccurate data information. In order to solve such problems, this article starts from the attributes of data. We come up with a new solution to process structural data faultages based on attribute similarity. We use the relation of similarity to define three new operations: Attribute cementation, Attribute addition, and Isomorphous homonuclear. Isomorphous homonuclear uses digraph to combine attributes. These three operations are mainly used to handle multiple data errors caused by data faultages, so that the redundancy of data can be reduced, and the consistency of data after integration can be ensured. Finally, it can eliminate the structural data faultage in data fusion. The experiment uses the data of doctoral dissertation in Shanghai University. Three types of dissertation data tables are fused. In addition, the structural data faultages after fusion are processed by the new method proposed by us. Through the statistical analysis of the experiment results and compare with the existing algorithm, we verify the validity and accuracy of this method to process structural data faultages.

show abstract

A survey on machine learning for data fusion

Cited by 471 publications

References 64 publications

Collaborative Multi-Robot Search and Rescue: Planning, Coordination, Perception, and Active Vision

Collaborative Multi-Robot Search and Rescue: Planning, Coordination, Perception, and Active Vision

Robust Epileptic Seizure Detection on Wearable Systems with Reduced False-Alarm Rate

Processing on Structural Data Faultage in Data Fusion

Contact Info

Product

Resources

About