A Transferable Belief Model Decision Support Tool over Complementary Clinical Conditions

Henni, Abderraouf Hadj; Pasquier, David; Betrouni, Nacim

doi:10.1007/978-3-319-78759-6_37

Cited by 2 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Following a similar reasoning, we define the threshold (η 1 , η 2 ) representing the highest value that perception conflict pair is allowed to take when sensors are considered agree. The computation led to (η 1 , η 2 ) = (0, 0.25) as shown in (14) in appendix VI.…”

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

“…For the threshold (ε 1 , ε 2 ), we use the computational approach presented in [14] to define the value of a posteriori conflict from which we drop the temporal fusion results. We consider that the a posteriori conflict occurs when m perc (D) 0.5 and m pred (D) 0.5.…”

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

“…We consider that the a posteriori conflict occurs when m perc (D) 0.5 and m pred (D) 0.5. According to (5), (6) and 8 This leads to (ε 1 , ε 2 ) = (0.25, 0.25) according to computation method of [14].…”

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

“…The issue now is how to define the threshold (δ 1 , δ 2 ) on the evolution of the conflict pair since the computation approach in [14] concerns rather the conflict pair and not the evolution of conflict pair. Therefore, a novel mathematical proof is provided in appendix VI that illustrates how we have obtained (δ 1 , δ 2 ) = (−0.375, −0.625 + α pred 2 ).…”

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

“…6) Now, since we have from (14) the range of the perception conflict (m s1∩s2 (φ), Dif Bet perc ) when the sensors agree, and we have from (20) the range of (m temp (φ), Dif Bet a post ) when prediction is in conflict with the agreed sensors, hence, let's find ranges of 2 ) represents the threshold for dynamic obstacle detection.…”

Section: Appendixmentioning

confidence: 99%

See 4 more Smart Citations

Improved dynamic object detection within evidential grids framework

Henni

Soriano

López

et al. 2019

2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

The deployment of autonomous robots/vehicles is increasing in several domains. To perform tasks properly, a robot must have a good perception about its environment while detecting dynamic obstacles. Recently, evidential grids have attracted more interest for environment perception since they permit more effective uncertainty handling. The latest studies on evidential grids relied on the use of thresholds for information management e.g. the use of a threshold, for the conflict characterized by the mass of empty set, in order to detect dynamic objects. Nevertheless, the mass of empty set alone is not consistent in some cases. Also, the thresholds used were chosen either arbitrary or tuned manually without any computational method. In this paper, first the conflict is composed of two parameters instead of mass of empty set alone, and dynamic objects detection is performed using a threshold on the evolution of this conflict pair. Secondly, the paper introduces a general threshold along with a mathematical demonstration to compute it which can be used in different dynamic object detection cases. A real-time experiment is performed using the RB1-BASE robot equipped with a RGB-D camera and a laser scanner.

show abstract

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

Section: Environment Perception and Dynamic Object Detectionmentioning

confidence: 99%

Section: Appendixmentioning

confidence: 99%

See 3 more Smart Citations

Improved dynamic object detection within evidential grids framework

Henni

Soriano

López

et al. 2019

2019 IEEE 15th International Conference on Automation Science and Engineering (CASE)

View full text Add to dashboard Cite

show abstract

Enhanced Multiplex Binary PIR Localization Using the Transferable Belief Model

et al. 2019

Self Cite

View full text Add to dashboard Cite

Pyro-electric Infra Red (PIR) sensors have been widely used in different indoor localization applications during the last decade. These sensors are cheap, non-intrusive and nonwearable, nevertheless, the binary PIR sensor detects only the presence of a human motion in its field of view without any other information about the actual location. Therefore, to localize a person in different zones of interest, the use of several PIR sensors with overlapping field of view is necessary. To reduce the number of sensors used, we use multiplex masks with the binary PIR sensors to obtain a compressed overlapping structure. Such a structure induces ambiguity during transitions between zones. In this paper, we show how to circumvent this issue by using a novel localization algorithm based on the transferable belief model TBM. Besides, we show how to tune efficiently the parameters of our algorithm, by choosing an appropriate discounting factor within (TBM). Experiments using standard commercialized sensors equipped with the multiplex masks, emphasize the performance of our novel method

show abstract

A Transferable Belief Model Decision Support Tool over Complementary Clinical Conditions

Cited by 2 publications

References 18 publications

Improved dynamic object detection within evidential grids framework

Improved dynamic object detection within evidential grids framework

Enhanced Multiplex Binary PIR Localization Using the Transferable Belief Model

Contact Info

Product

Resources

About