MFIR: Multimodal fusion and inconsistency reasoning for explainable fake news detection

Information Fusion, Год журнала: 2023, Номер 100, С. 101944 - 101944

Опубликована: Июль 26, 2023

Язык: Английский

---

QMFND: A quantum multimodal fusion-based fake news detection model for social media

Information Fusion, Год журнала: 2023, Номер 104, С. 102172 - 102172

Опубликована: Ноя. 30, 2023

Язык: Английский

---

CAF-ODNN: Complementary attention fusion with optimized deep neural network for multimodal fake news detection

Information Processing & Management, Год журнала: 2024, Номер 61(3), С. 103653 - 103653

Опубликована: Янв. 14, 2024

Язык: Английский

---

Multi-Objective Teaching-Learning-Based Optimizer for a Multi-Weeding Robot Task Assignment Problem

Tsinghua Science & Technology, Год журнала: 2024, Номер 29(5), С. 1249 - 1265

Опубликована: Май 2, 2024

With the emergence of artificial intelligence era, all kinds robots are traditionally used in agricultural production. However, studies concerning robot task assignment problem agriculture field, which is closely related to cost and efficiency a smart farm, limited. Therefore, Multi-Weeding Robot Task Assignment (MWRTA) addressed this paper minimize maximum completion time residual herbicide. A mathematical model set up, Multi-Objective Teaching-Learning-Based Optimization (MOTLBO) algorithm presented solve problem. In MOTLBO algorithm, heuristic-based initialization comprising an improved Nawaz Enscore, Ham (NEH) heuristic load-based generate initial population with high level quality diversity. An effective teaching-learning-based optimization process designed dynamic grouping mechanism redefined individual updating rule. multi-neighborhood-based local search strategy provided balance exploitation exploration algorithm. Finally, comprehensive experiment conducted compare proposed several state-of-the-art algorithms literature. Experimental results demonstrate significant superiority for solving under consideration.

Язык: Английский

---

Not all fake news is semantically similar: Contextual semantic representation learning for multimodal fake news detection

Information Processing & Management, Год журнала: 2023, Номер 61(1), С. 103564 - 103564

Опубликована: Окт. 31, 2023

Язык: Английский

---

Emotion detection for misinformation: A review

Information Fusion, Год журнала: 2024, Номер 107, С. 102300 - 102300

Опубликована: Фев. 12, 2024

Язык: Английский

---

AMPLE: Emotion-Aware Multimodal Fusion Prompt Learning for Fake News Detection

Lecture notes in computer science, Год журнала: 2025, Номер unknown, С. 86 - 100

Опубликована: Янв. 1, 2025

Язык: Английский

---

Graph Contrastive Learning With Feature Augmentation for Rumor Detection

IEEE Transactions on Computational Social Systems, Год журнала: 2023, Номер 11(4), С. 5158 - 5167

Опубликована: Май 4, 2023

While online social media brings convenience to people's communication, it has also caused the widespread spread of rumors and brought great harm. Recent deep-learning approaches attempt identify by engaging in interactive user feedback. However, performance these models suffers from insufficient noisy labeled data. In this article, we propose a novel rumor detection model called graph contrastive learning with feature augmentation (FAGCL), which injects noise into space learns contrastively constructing asymmetric structures. FAGCL takes preference news embedding as initial features propagation tree then adopts attention network update node representations. To obtain graph-level representation for classification, fuses multiple pooling techniques. Moreover, an auxiliary task constrain consistency. Contrastive on data mines supervision information itself, making more robust effective. Results two real-world datasets demonstrate that our proposed achieves significant improvements over baseline models.

Язык: Английский

---

Coevolution modeling of group behavior and opinion based on public opinion perception

Knowledge-Based Systems, Год журнала: 2023, Номер 270, С. 110547 - 110547

Опубликована: Апрель 6, 2023

Язык: Английский

---

MMTFN: Multi‐modal multi‐scale transformer fusion network for Alzheimer's disease diagnosis

International Journal of Imaging Systems and Technology, Год журнала: 2023, Номер 34(1)

Опубликована: Сен. 27, 2023

Abstract Alzheimer's disease (AD) is a severe neurodegenerative that can cause dementia symptoms. Currently, most research methods for diagnosing AD rely on fusing neuroimaging data of different modalities to exploit their heterogeneity and complementarity. However, effectively using such multi‐modal information construct fusion remains challenging problem. To address this issue, we propose multi‐scale transformer network (MMTFN) computer‐aided diagnosis AD. Our comprises 3D residual block (3DMRB) layers the Transformer jointly learns potential representations data. The 3DMRB with aggregation efficiently extracts local abnormal related in brain. We conducted five experiments validate our model MRI PET images 720 subjects from Disease Neuroimaging Initiative (ADNI). experimental results show proposed outperformed existing models, achieving final classification accuracy 94.61% Normal Control.

Язык: Английский

---