Fast semi-supervised evidential clustering

Antoine, Violaine; Guerrero, José Atilio; Xie, Jiarui

doi:10.1016/j.ijar.2021.03.008

Cited by 16 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…After observing the data y, our knowledge about θ is represented by the possibility distribution π θ|y . By Zadeh's extension principle (1), our knowledge of Y new conditionally on U = u is, thus, represented by the possibility distribution π Ynew|y,u = ϕ(π θ|y , u) defined as…”

Section: Evidential Likelihood-based Inferencementioning

confidence: 99%

See 1 more Smart Citation

Uncertainty quantification in logistic regression using random fuzzy sets and belief functions

Denœux

2024

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

Section: Evidential Likelihood-based Inferencementioning

confidence: 99%

“…In machine learning, DS theory has been applied to clustering [1,18], classification [10,34] and partially supervised learning [45,22]. In classification, an important direction of research has been to design evidential classifiers quantifying classification uncertainty using belief functions [12,51].…”

Section: Introductionmentioning

confidence: 99%

Uncertainty quantification in logistic regression using random fuzzy sets and belief functions

Denœux

2024

International Journal of Approximate Reasoning

View full text Add to dashboard Cite

“…Predicting calibrated probabilities offers some key benefits to making IoT application decision making more rational and cost-sensitive. Probability calibration provides a method to set a threshold, and only predictions made above that threshold can be trusted to make a rational decision in a given scenario [ 54 , 55 ]. Well-calibrated probabilities also make decision making cost-sensitive by calculating the expected cost of taking an action.…”

Section: A Har Risk-based Iot Decision Making Frameworkmentioning

confidence: 99%

A Risk-Based IoT Decision-Making Framework Based on Literature Review with Human Activity Recognition Case Studies

Hussain

Nugent

Moore

et al. 2021

Sensors

View full text Add to dashboard Cite

The Internet of Things (IoT) is a key and growing technology for many critical real-life applications, where it can be used to improve decision making. The existence of several sources of uncertainty in the IoT infrastructure, however, can lead decision makers into taking inappropriate actions. The present work focuses on proposing a risk-based IoT decision-making framework in order to effectively manage uncertainties in addition to integrating domain knowledge in the decision-making process. A structured literature review of the risks and sources of uncertainty in IoT decision-making systems is the basis for the development of the framework and Human Activity Recognition (HAR) case studies. More specifically, as one of the main targeted challenges, the potential sources of uncertainties in an IoT framework, at different levels of abstraction, are firstly reviewed and then summarized. The modules included in the framework are detailed, with the main focus given to a novel risk-based analytics module, where an ensemble-based data analytic approach, called Calibrated Random Forest (CRF), is proposed to extract useful information while quantifying and managing the uncertainty associated with predictions, by using confidence scores. Its output is subsequently integrated with domain knowledge-based action rules to perform decision making in a cost-sensitive and rational manner. The proposed CRF method is firstly evaluated and demonstrated on a HAR scenario in a Smart Home environment in case study I and is further evaluated and illustrated with a remote health monitoring scenario for a diabetes use case in case study II. The experimental results indicate that using the framework’s raw sensor data can be converted into meaningful actions despite several sources of uncertainty. The comparison of the proposed framework to existing approaches highlights the key metrics that make decision making more rational and transparent.

show abstract

“…DST is based on the representation of elementary items of evidence by belief functions, and their combination by a specific operator called Dempster's rule of combination. In recent years, DST has generated considerable interest and has had a great success in various fields, including information fusion [33][34] [35], classification [36][37] [38], clustering [28][39] [40], and image segmentation [41][42] [43].…”

Section: Introductionmentioning

confidence: 99%

Lymphoma segmentation from 3D PET-CT images using a deep evidential network

Huang,

Ruan,

Decazes

et al. 2022

Preprint

View full text Add to dashboard Cite

An automatic evidential segmentation method based on Dempster-Shafer theory and deep learning is proposed to segment lymphomas from three-dimensional Positron Emission Tomography (PET) and Computed Tomography (CT) images. The architecture is composed of a deep feature-extraction module and an evidential layer. The feature extraction module uses an encoder-decoder framework to extract semantic feature vectors from 3D inputs. The evidential layer then uses prototypes in the feature space to compute a belief function at each voxel quantifying the uncertainty about the presence or absence of a lymphoma at this location. Two evidential layers are compared, based on different ways of using distances to prototypes for computing mass functions. The whole model is trained end-to-end by minimizing the Dice loss function. The proposed combination of deep feature extraction and evidential segmentation is shown to outperform the baseline UNet model as well as three other state-of-the-art models on a dataset of 173 patients.

show abstract

Fast semi-supervised evidential clustering

Cited by 16 publications

References 25 publications

Uncertainty quantification in logistic regression using random fuzzy sets and belief functions

Uncertainty quantification in logistic regression using random fuzzy sets and belief functions

A Risk-Based IoT Decision-Making Framework Based on Literature Review with Human Activity Recognition Case Studies

Lymphoma segmentation from 3D PET-CT images using a deep evidential network

Contact Info

Product

Resources

About