Prayag Tiwari

Prayag Tiwari

Professor/Researcher in AI

Posts by Collection

portfolio

publications

Structural block driven enhanced convolutional neural representation for relation extraction

Published in Applied Soft Computing, 2020

Twe propose a novel lightweight relation extraction approach of structural block driven convolutional neural learning.

Recommended citation: Wang, D., Tiwari, P., Garg, S., Zhu, H., & Bruza, P. (2020). Structural block driven enhanced convolutional neural representation for relation extraction. Applied Soft Computing, 86, 105913. https://www.sciencedirect.com/science/article/pii/S1568494619306945

Quantum-Like Structure in Multidimensional Relevance Judgements

Published in European Conference on Information Retrieval, 2020

This paper to show violation of the Kolmogorovian probability especially in decision-making under uncertainty, and provide quantum-like structure to model those uncertainty.

Recommended citation: Uprety, S., Tiwari, P., Dehdashti, S., Fell, L., Song, D., Bruza, P., & Melucci, M. (2020, April). Quantum-like structure in multidimensional relevance judgements. In European Conference on Information Retrieval (pp. 728-742). Springer, Cham. https://link.springer.com/chapter/10.1007/978-3-030-45439-5_48

Learning interaction dynamics with an interactive LSTM for conversational sentiment analysis

Published in Neural Networks, 2021

we propose an interactive long short-term memory (LSTM) network for conversational sentiment analysis to model interactions between speakers in a conversation by (1) adding a confidence gate before each LSTM hidden unit to estimate the credibility of the previous speakers and (2) combining the output gate with the learned influence scores to incorporate the influences of the previous speakers.

Recommended citation: Y. Zhang, P. Tiwari, D. Song et al., Learning interaction dynamics withan interactive LSTM for conversational sentiment analysis.Neural Networks(2021), doi:https://doi.org/10.1016/j.neunet.2020.10.001. https://www.sciencedirect.com/science/article/pii/S0893608020303567#!

DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning

Published in Neural Networks, 2021

we propose the distance-aware reward in the reinforcement learning framework to assign different rewards for different positions.

Recommended citation: P. Tiwari, H. Zhu, H.M. Pandey et al., DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning .Neural Networks(2021), doi:https://doi.org/10.1016/j.neunet.2020.11.012. https://www.sciencedirect.com/science/article/pii/S089360802030410X

Intelligent system for depression scale estimation with facial expressions and case study in industrial intelligence

Published in International Journal of Intelligent Systems, 2021

This paper presents an end‐to‐end trainable intelligent system to generate high‐level representations over the entire video clip for audiovisual depression detection

Recommended citation: He, L, Guo, C, Tiwari, P, Pandey, HM, Dang, W. Intelligent system for depression scale estimation with facial expressions and case study in industrial intelligence. Int J Intell Syst. 2021; 1‐ 17. https://doi.org/10.1002/int.22426 https://onlinelibrary.wiley.com/doi/full/10.1002/int.22426

CFN: A Complex-valued Fuzzy Network for Sarcasm Detection in Conversations

Published in IEEE Transactions on Fuzzy Systems, 2021

we propose a complex-valued fuzzy network (CFN) by leveraging the mathematical formalisms of quantum theory (QT) and fuzzy logic

Recommended citation: Y. Zhang, Y. Liu, Q. Li, P. Tiwari et al., "CFN: A Complex-valued Fuzzy Network for Sarcasm Detection in Conversations," in IEEE Transactions on Fuzzy Systems, doi: 10.1109/TFUZZ.2021.3072492. https://ieeexplore.ieee.org/document/9400728

Neural variational sparse topic model for sparse explainable text representation

Published in Information Processing & Management, 2021

we propose a semantic reinforcement neural variational sparse topic model (SR-NSTM) towards explainable and sparse latent text representation learning.

Recommended citation: Q. Xie, P. Tiwari, D. Gupta, J. Huang, M. Peng, "Neural variational sparse topic model for sparse explainable text representation," in Information Processing & Management, https://doi.org/10.1016/j.ipm.2021.102614. https://www.sciencedirect.com/science/article/abs/pii/S0306457321001102

A Collaborative AI-enabled Pretrained Language Model for AIoT Domain Question Answering

Published in IEEE Transactions on Industrial Informatics, 2021

We propose RoBERTa-AIoT to address the problem of the lack of high-quality large-scale labeled AIoT QA datasets.

Recommended citation: Zhu, H., Tiwari, P., Ghoneim, A., & Hossain, M. S. (2021). A Collaborative AI-enabled Pretrained Language Model for AIoT Domain Question Answering. IEEE Transactions on Industrial Informatics. https://ieeexplore.ieee.org/abstract/document/9484781

Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition

Published in International Journal of Computer Vision, 2021

We propose a cascaded Split-and-Aggregate Learning (SAL)

Recommended citation: Yang, Y., Tan, Z., Tiwari, P., Pandey, H. M., Wan, J., Lei, Z., ... & Li, S. Z. (2021). Cascaded Split-and-Aggregate Learning with Feature Recombination for Pedestrian Attribute Recognition. International Journal of Computer Vision, 1-14. https://link.springer.com/article/10.1007/s11263-021-01499-z

DepNet: An automated industrial intelligent system using deep learning for video-based depression analysis

Published in International Journal of Intelligent Systems, 2021

In this paper, an integrated framework, termed DepNet, for automatic diagnosis of depression that adopts facial images sequence from videos is proposed.

Recommended citation: He, L, Guo, C, Tiwari, P, Su, R, Pandey, HM, Dang, W. DepNet: An automated industrial intelligent system using deep learning for video-based depression analysis. Int J Intell Syst. 2021; 1- 21. doi:10.1002/int.22704 https://onlinelibrary.wiley.com/doi/abs/10.1002/int.22704

Deep learning for depression recognition with audiovisual cues: A review

Published in Information Fusion, 2021

We review the DL methods for automatic detection of depression.

Recommended citation: L. He, M. Niu, P. Tiwari, P. Marttinen, R. Su, J. Jiang, C. Guo, H. Wang, S. Ding, Z. Wang, X. Pan, and W. Dang, “Deep learning for depression recognition with audiovisual cues: A review,” Information Fusion, 2021, doi.org/10.1016/j.inffus.2021.10.012 https://www.sciencedirect.com/science/article/abs/pii/S1566253521002207

COVIDNet: An Automatic Architecture for COVID-19 Detection with Deep Learning from Chest X-ray Images

Published in IEEE Internet of Things Journal, 2021

This paper presents an integrated framework, named COVIDNet, for classifying COVID-19 patients and healthy controls.

Recommended citation: L. He, P. Tiwari, R. Su, X. Shi, P. Marttinen and N. Kumar, "COVIDNet: An Automatic Architecture for COVID-19 Detection with Deep Learning from Chest X-ray Images," in IEEE Internet of Things Journal, doi: 10.1109/JIOT.2021.3126471. https://ieeexplore.ieee.org/document/9608952

SANTM: Efficient Self-attention-driven Network for Text Matching

Published in ACM Transactions on Internet Technology, 2021

we leverage attractive properties of self-attention mechanism and proposes an attention-based network that incorporates three key components for inter-sequence attention: global pointwise features, preceding attentive features, and contextual features while updating the rest of the components.

Recommended citation: P. Tiwari, A.K. Jaiswal, S. Garg, I. You , "SANTM: Efficient Self-attention-driven Network for Text Matching," in ACM Transactions on Internet Technology, doi: 10.1145/3426971. https://dl.acm.org/doi/abs/10.1145/3426971

Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentificationg

Published in IEEE Transactions on Neural Networks and Learning Systems, 2021

we propose a novel recurrent autoencoder (RAE) framework to unify these two kinds of methods and inherit their merits. Specifically, the proposed RAE includes three modules, i.e., a feature-transfer (FT) module, a pixel-transfer (PT) module, and a fusion module.

Recommended citation: Y. Yang, G. Wang, P. Tiwari, H.M. Pandey, Z. Lei, "Pixel and Feature Transfer Fusion for Unsupervised Cross-Dataset Person Reidentificationg," in IEEE Transactions on Neural Networks and Learning Systems, doi: 10.1109/TNNLS.2021.3128269. https://ieeexplore.ieee.org/abstract/document/9632271

C-loss based Higher-order Fuzzy Inference Systems for Identifying DNA N4-methylcytosine Sites

Published in IEEE Transactions on Fuzzy Systems, 2022

This study proposes a fuzzy model with correntropy induced loss (C-loss) function to identify DNA N4-methylcytosine (4mC) sites

Recommended citation: Y. Ding, P. Tiwari, Q. Zou, F. Guo and H. M. Pandey, "C-loss based Higher-order Fuzzy Inference Systems for Identifying DNA N4-methylcytosine Sites," in IEEE Transactions on Fuzzy Systems, doi: 10.1109/TFUZZ.2022.3159103. https://ieeexplore.ieee.org/document/9735344

EEG based Emotion Recognition: A Tutorial and Review

Published in ACM Computing Surveys, 2022

We review the recent representative works in the EEG-based emotion recognition research and provide a tutorial to guide the researchers to start from the beginning.

Recommended citation: X. Li, Y. Zhang, P. Tiwari, D. Song, B. Hu, M. Yang, Z. Zhao, N. Kumar, and P. Marttinen, "EEG based Emotion Recognition: A Tutorial and Review," in ACM Computing Surveys, doi: 10.1145/3524499. https://dl.acm.org/doi/abs/10.1145/3524499

Kernel Method based on Non-Linear Coherent States in Quantum Feature Space

Published in Journal of Physics A: Mathematical and Theoretical, 2022

we propose quantum kernel functions based on generalized hypergeometric functions, as orthogonal polynomial functions

Recommended citation: Tiwari, P., Dehdashti, S., Obeid, A. K., Marttinen, P., & Bruza, P. (2022). Kernel Method based on Non-Linear Coherent States in Quantum Feature Space. Journal of Physics A: Mathematical and Theoretical. https://iopscience.iop.org/article/10.1088/1751-8121/ac818e/meta

talks

Quantum Machine Learning

Published:

The main goal of this talk is about to provide the basic understanding of Quantum Machine Learning

teaching

Undergraduate course

Bachelor courses, RGPV, 2011

I was involved in the design and teaching the following courses:

Data Mining

Masters course in Data Mining, School of Information Technology, Halmstad University, 2022

  • Data Mining 7.50HP DT8013 50% NML Halmstad FRIS,PROG,FRIS ht 2022
  • Consist of Lectures, Labs, Research paper seminar, and Project