Search: (WFRF:(Barua Shaibal)) srt2:(2020-2024)
> (2024) >
Second-Order Learni...
Second-Order Learning with Grounding Alignment : A Multimodal Reasoning Approach to Handle Unlabelled Data
-
- Barua, Arnab (author)
- Mälardalens universitet,Inbyggda system
-
- Ahmed, Mobyen Uddin, Dr, 1976- (author)
- Mälardalens universitet,Inbyggda system
-
- Barua, Shaibal (author)
- Mälardalens universitet,Inbyggda system
-
show more...
-
- Begum, Shahina, 1977- (author)
- Mälardalens universitet,Inbyggda system
-
- Giorgi, A. (author)
- Department of Anatomical, Histological, FOrthopedic Sciences, Sapienza University of Rome, Rome, Italy
-
show less...
-
(creator_code:org_t)
- Science and Technology Publications, Lda, 2024
- 2024
- English.
-
In: International Conference on Agents and Artificial Intelligence. - : Science and Technology Publications, Lda. ; , s. 561-572
- Related links:
-
https://doi.org/10.5...
-
show more...
-
https://urn.kb.se/re...
-
https://doi.org/10.5...
-
show less...
Abstract
Subject headings
Close
- Multimodal machine learning is a critical aspect in the development and advancement of AI systems. However, it encounters significant challenges while working with multimodal data, where one of the major issues is dealing with unlabelled multimodal data, which can hinder effective analysis. To address the challenge, this paper proposes a multimodal reasoning approach adopting second-order learning, incorporating grounding alignment and semi-supervised learning methods. The proposed approach illustrates using unlabelled vehicular telemetry data. During the process, features were extracted from unlabelled telemetry data using an autoencoder and then clustered and aligned with true labels of neurophysiological data to create labelled and unlabelled datasets. In the semi-supervised approach, the Random Forest (RF) and eXtreme Gradient Boosting (XGBoost) algorithms are applied to the labelled dataset, achieving a test accuracy of over 97%. These algorithms are then used to predict labels for the unlabelled dataset, which is later added to the labelled dataset to retrain the model. With the additional prior labelled data, both algorithms achieved a 99% test accuracy. Confidence in predictions for unlabelled data was validated using counting samples based on the prediction score and Bayesian probability. RF and XGBoost scored 91.26% and 97.87% in counting samples and 98.67% and 99.77% in Bayesian probability, respectively.
Subject headings
- NATURVETENSKAP -- Data- och informationsvetenskap (hsv//swe)
- NATURAL SCIENCES -- Computer and Information Sciences (hsv//eng)
Keyword
- Autoencoder
- Multimodal Reasoning
- Semi-Supervised
- Supervised Alignment
Publication and Content Type
- ref (subject category)
- kon (subject category)
To the university's database