A survey on modern trainable activation functions

A Apicella, F Donnarumma, F Isgrò, R Prevete - Neural Networks, 2021 - Elsevier
In neural networks literature, there is a strong interest in identifying and defining activation
functions which can improve neural network performance. In recent years there has been a …

YOLO-FA: Type-1 fuzzy attention based YOLO detector for vehicle detection

L Kang, Z Lu, L Meng, Z Gao - Expert Systems with Applications, 2024 - Elsevier
Vehicle detection is an important component of intelligent transportation systems and
autonomous driving. However, in real-world vehicle detection scenarios, the presence of …

Synthetic state of charge estimation for lithium-ion batteries based on long short-term memory network modeling and adaptive H-Infinity filter

Z Chen, H Zhao, X Shu, Y Zhang, J Shen, Y Liu - Energy, 2021 - Elsevier
Accurate state of charge estimation is essential to improve operation safety and service life
of lithium-ion batteries. This paper proposes a synthetic state of charge estimation method …

Hybrid IT2 fuzzy modelling with alpha cuts for hydrogen energy investments

Y Zhao, Y Xu, S Yüksel, H Dinçer, GG Ubay - International Journal of …, 2021 - Elsevier
The framework of this study is to weight 8 selected determinants and rank energy
alternatives for hydrogen investments. For this purpose, different criteria that are based on …

The fusion of deep learning and fuzzy systems: A state-of-the-art survey

Y Zheng, Z Xu, X Wang - IEEE Transactions on Fuzzy Systems, 2021 - ieeexplore.ieee.org
Deep learning presents excellent learning ability in constructing learning model and greatly
promotes the development of artificial intelligence, but its conventional models cannot …

[HTML][HTML] An adaptive modified neural lateral-longitudinal control system for path following of autonomous vehicles

N Tork, A Amirkhani, SB Shokouhi - Engineering Science and Technology …, 2021 - Elsevier
The full-fledged development and the practical use of autonomous vehicles (AVs) would be
a great technological achievement and would substantially reduce the enormous damages …

DT2F-TLNet: A novel text-independent writer identification and verification model using a combination of deep type-2 fuzzy architecture and Transfer Learning …

J Yang, M Shokouhifar, L Yee, AA Khan… - Expert Systems with …, 2024 - Elsevier
Identifying and verifying the identity of people based on scanned images of handwritten
documents is an applicable biometric modality with applications in forensic and historic …

A deep learned type-2 fuzzy neural network: Singular value decomposition approach

SN Qasem, A Mohammadzadeh - Applied Soft Computing, 2021 - Elsevier
The main objective of this study is to present a novel dynamic fractional-order deep learned
type-2 fuzzy logic system (FDT2-FLS) with improved estimation capability. The proposed …

More than accuracy: A composite learning framework for interval type-2 fuzzy logic systems

A Beke, T Kumbasar - IEEE Transactions on Fuzzy Systems, 2022 - ieeexplore.ieee.org
In this article, we propose a novel composite learning framework for interval type-2 (IT2)
fuzzy logic systems (FLSs) to train regression models with a high accuracy performance and …

[HTML][HTML] A novel deep belief network architecture with interval type-2 fuzzy set based uncertain parameters towards enhanced learning

AK Shukla, PK Muhuri - Fuzzy Sets and Systems, 2024 - Elsevier
This paper proposes a novel Deep Belief Network (DBN) architecture, the 'Interval Type-2
Fuzzy DBN (IT2FDBN)', which models the weights and biases with IT2 FSs. Thus, it …