Q-Learning based Metaheuristic Optimization Algorithms: A short review and perspectives

Hamad, Qusay Shihab; Samma, Hussein; Suandi, Shahrel Azmin

doi:10.21203/rs.3.rs-1950095/v1

Cited by 3 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These algorithms combine the strengths of reinforcement learning and metaheuristic algorithms to improve the efficiency and performance of the model. Many reinforcement learning based metaheuristic algorithms have been proposed in recent years [42]. For instance, Zhao et al [43] proposed an inverse reinforcement learning framework with Q-learning mechanism named IRLMFO, to improve the performance of the moth-flame optimisation (MFO) algorithm in a large-scale real-parameter optimisation problem.…”

Section: Related Workmentioning

confidence: 99%

Early Mental Stress Detection Using Q-Learning Embedded Starling Murmuration Optimiser-Based Deep Learning Model

Moosavi,

Zafar,

Sanfilippo

et al. 2023

IEEE Access

View full text Add to dashboard Cite

Stress affects individual of all ages as a regular part of life, but excessive and chronic stress can lead to physical and mental health problems, decreased productivity, and reduced quality of life. By identifying stress at an early stage, individuals can take steps to manage it effectively and improve their overall wellbeing. Feature selection is a critical aspect of early stress detection because it helps identify the most relevant and informative features that can differentiate between stressed and non-stressed individuals. This paper firstly proposes a variance based feature selection technique that uses q-learning embedded Starling Murmuration Optimiser (QLESMO) to choose relevant features from a publicly available dataset in which stresses experienced by nurses working during the Covid'19 Pandemic is recorded using bio-signals and user surveys. Furthermore, a comparative study with other metaheuristic based feature selection techniques have been demonstrated. Next, to evaluate the efficacy of the proposed algorithm, 10 benchmark test functions have been used. The reduced feature subset is then classified through a 1D convolutional neural network (CNN) model (QLESMO-CNN) and is seen to perform well in terms of the evaluation metrics in comparison to other competitive algorithms. Finally, the proposed technique is compared with the State-of-the-Art methodologies present in literature. The experiments provide a strong basis to determine features that are most relevant for early mental stress classification using a hybrid model combining CNN, Reinforcement Learning and metaheuristic algorithms.

show abstract

Section: Related Workmentioning

confidence: 99%

Early Mental Stress Detection Using Q-Learning Embedded Starling Murmuration Optimiser-Based Deep Learning Model

Moosavi,

Zafar,

Sanfilippo

et al. 2023

IEEE Access

View full text Add to dashboard Cite

show abstract

RNA-Seq analysis for breast cancer detection: a study on paired tissue samples using hybrid optimization and deep learning techniques

Yaqoob,

Verma,

Aziz

et al. 2024

J Cancer Res Clin Oncol

View full text Add to dashboard Cite

Applications and Techniques of Machine Learning in Cancer Classification: A Systematic Review

Yaqoob,

Musheer Aziz,

verma

2023

Hum-Cent Intell Syst

View full text Add to dashboard Cite

The domain of Machine learning has experienced Substantial advancement and development. Recently, showcasing a Broad spectrum of uses like Computational linguistics, image identification, and autonomous systems. With the increasing demand for intelligent systems, it has become crucial to comprehend the different categories of machine acquiring knowledge systems along with their applications in the present world. This paper presents actual use cases of machine learning, including cancer classification, and how machine learning algorithms have been implemented on medical data to categorize diverse forms of cancer and anticipate their outcomes. The paper also discusses supervised, unsupervised, and reinforcement learning, highlighting the benefits and disadvantages of each category of Computational intelligence system. The conclusions of this systematic study on machine learning methods and applications in cancer classification have numerous implications. The main lesson is that through accurate classification of cancer kinds, patient outcome prediction, and identification of possible therapeutic targets, machine learning holds enormous potential for improving cancer diagnosis and therapy. This review offers readers with a broad understanding as of the present advancements in machine learning applied to cancer classification today, empowering them to decide for themselves whether to use these methods in clinical settings. Lastly, the paper wraps up by engaging in a discussion on the future of machine learning, including the potential for new types of systems to be developed as the field advances. Overall, the information included in this survey article is useful for scholars, practitioners, and individuals interested in gaining knowledge about the fundamentals of machine learning and its various applications in different areas of activities.

show abstract

Q-Learning based Metaheuristic Optimization Algorithms: A short review and perspectives

Cited by 3 publications

References 51 publications

Early Mental Stress Detection Using Q-Learning Embedded Starling Murmuration Optimiser-Based Deep Learning Model

Early Mental Stress Detection Using Q-Learning Embedded Starling Murmuration Optimiser-Based Deep Learning Model

RNA-Seq analysis for breast cancer detection: a study on paired tissue samples using hybrid optimization and deep learning techniques

Applications and Techniques of Machine Learning in Cancer Classification: A Systematic Review

Contact Info

Product

Resources

About