DB-Net and DVR-Net: Optimized New Deep Learning Models for Efficient Cardiovascular Disease Prediction DOI Creative Commons

Aymin Javed,

Nadeem Javaid, Nabil Alrajeh

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(22), P. 10516 - 10516

Published: Nov. 15, 2024

Cardiovascular Disease (CVD) is one of the main causes death in recent years. To overcome challenges faced during diagnosing CVD at an early stage, deep learning has been used. With advancements technology, clinical practice health care industry likely to transform significantly. predict CVD, we constructed two models: Dense Belief Network (DB-Net) and Deep Vanilla Recurrent (DVR-Net). Proximity Weighted Random Affine Shadow sampling balancing technique used for highly imbalanced Heart Health Indicator dataset. SHapley Additive exPlanations exhibits each feature’s contribution. It visualize features contribution output DB-Net DVR-Net prediction. Furthermore, 10-Fold Cross Validation performed evaluating proposed models performance. Cross-dataset evaluation also conducted on see how well our generalize unseen data. Various measures are assessment models. The outperforms all base by achieving accuracy 91%, F1-score precision 93%, recall 89%, execution time 1883 s 30 epochs with batch size 32. beats state-of-art 90%, 2853

Language: Английский

Sliding Window Iterative Identification for Nonlinear Closed‐Loop Systems Based on the Maximum Likelihood Principle DOI
Lijuan Liu, Fu Li, Wei Liu

et al.

International Journal of Robust and Nonlinear Control, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 1, 2024

ABSTRACT The parameter estimation problem for the nonlinear closed‐loop systems with moving average noise is considered in this article. For purpose of overcoming difficulty that dynamic linear module and static lead to identification complexity issues, unknown parameters from both modules are included a vector by use key term separation technique. Furthermore, an sliding window maximum likelihood least squares iterative algorithm gradient derived estimate parameters. numerical simulation indicates efficiency proposed algorithms.

Language: Английский

Citations

10
A gazelle optimization expedition for key term separated fractional nonlinear systems with application to electrically stimulated muscle modeling DOI
Taimoor Ali Khan, Naveed Ishtiaq Chaudhary, Chung-Chian Hsu

et al.

Chaos Solitons & Fractals, Journal Year: 2024, Volume and Issue: 185, P. 115111 - 115111

Published: June 15, 2024

Language: Английский

Citations

7
Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review DOI Open Access
Ivan Malashin, В С Тынченко, Andrei Gantimurov

et al.

Polymers, Journal Year: 2024, Volume and Issue: 16(18), P. 2607 - 2607

Published: Sept. 14, 2024

This review explores the application of Long Short-Term Memory (LSTM) networks, a specialized type recurrent neural network (RNN), in field polymeric sciences. LSTM networks have shown notable effectiveness modeling sequential data and predicting time-series outcomes, which are essential for understanding complex molecular structures dynamic processes polymers. delves into use models polymer properties, monitoring polymerization processes, evaluating degradation mechanical performance Additionally, it addresses challenges related to availability interpretability. Through various case studies comparative analyses, demonstrates different science applications. Future directions also discussed, with an emphasis on real-time applications need interdisciplinary collaboration. The goal this is connect advanced machine learning (ML) techniques science, thereby promoting innovation improving predictive capabilities field.

Language: Английский

Citations

7
The Aitken Accelerated Gradient Algorithm for a Class of Dual‐Rate Volterra Nonlinear Systems Utilizing the Self‐Organizing Map Technique DOI
Junwei Wang, Weili Xiong, Feng Ding

et al.

International Journal of Robust and Nonlinear Control, Journal Year: 2025, Volume and Issue: unknown

Published: April 22, 2025

ABSTRACT This article focuses on the parameter estimation issues for dual‐rate Volterra fractional‐order autoregressive moving average models. In case of sampling, we derive a identification model system and implement intersample output with help an auxiliary method. Then, combined self‐organizing map technique, propose Aitken multi‐innovation gradient‐based iterative algorithm. The parameters are estimated using algorithm, whereas differential orders determined Moreover, computational cost proposed algorithm is analyzed floating point operation. Finally, convergence analysis simulation examples show effectiveness

Language: Английский

Citations

0
A novel filtering-based recursive identification method for a fractional-order Hammerstein state space system with piecewise nonlinearity DOI

Hongguang Lang,

Yiqun Bi,

Meihang Li

et al.

Proceedings of the Institution of Mechanical Engineers Part I Journal of Systems and Control Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 28, 2025

This paper investigates parameters and states estimation for a class of fractional-order state space systems with colored noises. To provide accurate parameter estimation, we suggest novel gradient descent algorithm based on the extended Kalman filtering. The new approach features lower error variances faster convergence rate than conventional algorithm. A data filtering is introduced to filter input output data, thereby reducing impact noises accuracy estimates.

Language: Английский

Citations

0
Nonlinear Adaptive Control of Maglev System Based on Parameter Identification DOI Creative Commons
Haiyan Qiang,

Qiao Sheng,

Hsin-Cheng Huang

et al.

Actuators, Journal Year: 2025, Volume and Issue: 14(3), P. 115 - 115

Published: Feb. 26, 2025

To address the nonlinearity and control problems of Maglev system caused by external disturbances internal factors system, this study first established a kinematic model single-point levitation system. Secondly, based on nonlinear characteristics model, Gaussian noise was introduced into as input disturbance, neural network used to train constructed model. A autoregressive with exogenous inputs constructed, Recursive Least Squares method Forgetting Factor (RLS-FF) perform parameter identification combining training data, further constructing an accurate Then, backstepping adopted design adaptive controller for its stability verified. Simulation analysis conducted MATLAB/Simulink platform, comparisons were made LQR Fuzzy-PID that verified designed had faster response speed better self-regulation ability. At same time, interference signals simulation simulate actual scene, good anti-interference ability performance

Language: Английский

Citations

0
Nonlinear Marine Predator Algorithm for Robust Identification of Fractional Hammerstein Nonlinear Model under Impulsive Noise with Application to Heat Exchanger System DOI
Zeshan Aslam Khan, Taimoor Ali Khan,

Muhammad Waqar

et al.

Communications in Nonlinear Science and Numerical Simulation, Journal Year: 2025, Volume and Issue: unknown, P. 108809 - 108809

Published: March 1, 2025

Language: Английский

Citations

0
Design of quantum computing-based avain navigation optimization algorithm for parameter estimation of input nonlinear output error model with key term separation DOI
Khizer Mehmood, Naveed Ishtiaq Chaudhary, Zeshan Aslam Khan

et al.

Modern Physics Letters A, Journal Year: 2025, Volume and Issue: unknown

Published: March 28, 2025

In recent years, quantum computing has been applied in optimizing different challenging systems the domains of science and engineering. This work reflects identification input nonlinear output error (I-NOE) model by using Quantum-based avian navigation optimizer algorithm (QANA). QANA is an evolutionary method inspired precision migratory birds. The assessment achieved on various iterations, population, noise levels. complexity, statistical, convergence investigation with arithmetic optimization (AOA), coati (COA), grey wolf (GWO), particle swarm (PSO), synergistic (SSOA), velocity pausing (VPPSO) approves robustness for I-NOE identification.

Language: Английский

Citations

0
A novel hybrid adaptive differential evolution for global optimization DOI Creative Commons
Zhiyong Zhang, Jianyong Zhu, Feiping Nie

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 24, 2024

Differential Evolution (DE) stands as a potent global optimization algorithm, renowned for its application in addressing myriad of practical engineering issues. The efficacy DE is profoundly influenced by control parameters and mutation strategies. In light this, we introduce refined algorithm characterized adaptive dual strategies (APDSDE). APDSDE inaugurates an switching mechanism that alternates between two innovative strategies: DE/current-to-pBest-w/1 DE/current-to-Amean-w/1. Furthermore, novel parameter adaptation technique rooted cosine similarity established, with the derivation explicit calculation formulas both scaling factor weight crossover rate weight. pursuit optimizing convergence speed whilst preserving population diversity, sophisticated nonlinear size reduction method proposed. robustness each rigorously evaluated against CEC2017 benchmark functions, empirical evidence underscoring superior performance comparison to host advanced variants.

Language: Английский

Citations

2
Mathematical modeling of allelopathic stimulatory phytoplankton species using fractal–fractional derivatives DOI Creative Commons

Sangeeta Kumawat,

Sanjay Bhatter,

Bhamini Bhatia

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Aug. 28, 2024

In the current study, we employ novel fractal-fractional operator in Atangana-Baleanu sense to investigate dynamics of an interacting phytoplankton species model. Initially, utilize Picard-Lindelöf theorem validate uniqueness and existence solutions for We then explore equilibrium points within model conduct Hyers-Ulam stability analysis. Additionally, present a numerical scheme utilizing Newton polynomial our analytical findings. Numerical simulations illustrate dynamical behavior across various fractal fractional parameter values, visualized through graphical representations. Our reveal that is not significantly impacted with long-term memory effect, which characterized by order values. However, increase parameters accelerates convergence their intended states.

Language: Английский

Citations

2