arXiv subjects

Yossra H. Ali

Publications and source records attributed to Yossra H. Ali.

6 recordsLinked to original sources

arXiv2025

Artificial Liver Classifier: A New Alternative to Conventional Machine Learning Models

Supervised machine learning classifiers sometimes face challenges related to the performance, accuracy, or overfitting. This paper introduces the Artificial Liver Classifier (ALC), a novel supervised learning model inspired by the human liver's detoxification function. The ALC is characterized by its simplicity, speed, capability to reduce overfitting, and effectiveness in addressing multi-class classification problems through straightforward mathematical operations. To optimize the ALC's parameters, an improved FOX optimization algorithm (IFOX) is employed during training. We evaluate the proposed ALC on five benchmark datasets: Iris Flower, Breast Cancer Wisconsin, Wine, Voice Gender, and MNIST. The results demonstrate competitive performance, with ALC achieving up to 100\% accuracy on the Iris dataset--surpassing logistic regression, multilayer perceptron, and support vector machine--and 99.12\% accuracy on the Breast Cancer dataset, outperforming XGBoost and logistic regression. Across all datasets, ALC consistently shows smaller generalization gaps and lower loss values compared to conventional classifiers. These findings highlight the potential of biologically inspired models to develop efficient machine learning classifiers and open new avenues for innovation in the field.

cs.AI↗

arXiv2025

An Improved FOX Optimization Algorithm Using Adaptive Exploration and Exploitation for Global Optimization

Optimization algorithms are essential for solving many real-world problems. However, challenges such as getting trapped in local minima and effectively balancing exploration and exploitation often limit their performance. This paper introduces an improved variation of the FOX optimization algorithm (FOX), termed Improved FOX (IFOX), incorporating a new adaptive method using a dynamically scaled step-size parameter to balance exploration and exploitation based on the current solution's fitness value. The proposed IFOX also reduces the number of hyperparameters by removing four parameters (C1, C2, a, Mint) and refines the primary equations of FOX. To evaluate its performance, IFOX was tested on 20 classical benchmark functions, 61 benchmark test functions from the congress on evolutionary computation (CEC), and ten real-world problems. The experimental results showed that IFOX achieved a 40% improvement in overall performance metrics over the original FOX. Additionally, it achieved 880 wins, 228 ties, and 348 losses against 16 optimization algorithms across all involved functions and problems. Furthermore, non-parametric statistical tests, including the Friedman and Wilcoxon signed-rank tests, confirmed its competitiveness against recent and state-of-the-art optimization algorithms, such as LSHADE and NRO, with an average rank of 5.92 among 17 algorithms. These findings highlight the significant potential of IFOX for solving diverse optimization problems, establishing it as a competitive and effective optimization algorithm.

cs.AI↗

arXiv2025

QF-tuner: Breaking Tradition in Reinforcement Learning

In reinforcement learning algorithms, the hyperparameters tuning method refers to choosing the optimal parameters that may increase the overall performance. Manual or random hyperparameter tuning methods can lead to different results in the reinforcement learning algorithms. In this paper, we propose a new method called QF-tuner for automatic hyperparameter tuning in the Q learning algorithm using the FOX optimization algorithm (FOX). Furthermore, a new objective function has been employed within FOX that prioritizes reward over learning error and time. QF tuner starts by running the FOX and tries to minimize the fitness value derived from observations at each iteration by executing the Q-learning algorithm. The proposed method has been evaluated using two control tasks from the OpenAI Gym: CartPole and FrozenLake. The empirical results indicate that the QF-tuner outperforms other optimization algorithms, such as particle swarm optimization (PSO), bees algorithm (BA), genetic algorithms (GA), and the random method. However, on the FrozenLake task, the QF-tuner increased rewards by 36% and reduced learning time by 26%, while on the CartPole task, it increased rewards by 57% and reduced learning time by 20%. Thus, the QF-tuner is an essential method for hyperparameter tuning in Q-learning algorithms, enabling more effective solutions to control task problems.

cs.LG↗

arXiv2024

FOXANN: A Method for Boosting Neural Network Performance

Artificial neural networks play a crucial role in machine learning and there is a need to improve their performance. This paper presents FOXANN, a novel classification model that combines the recently developed Fox optimizer with ANN to solve ML problems. Fox optimizer replaces the backpropagation algorithm in ANN; optimizes synaptic weights; and achieves high classification accuracy with a minimum loss, improved model generalization, and interpretability. The performance of FOXANN is evaluated on three standard datasets: Iris Flower, Breast Cancer Wisconsin, and Wine. The results presented in this paper are derived from 100 epochs using 10-fold cross-validation, ensuring that all dataset samples are involved in both the training and validation stages. Moreover, the results show that FOXANN outperforms traditional ANN and logistic regression methods as well as other models proposed in the literature such as ABC-ANN, ABC-MNN, CROANN, and PSO-DNN, achieving a higher accuracy of 0.9969 and a lower validation loss of 0.0028. These results demonstrate that FOXANN is more effective than traditional methods and other proposed models across standard datasets. Thus, FOXANN effectively addresses the challenges in ML algorithms and improves classification performance.

cs.NE↗

arXiv2024

Unraveling the Versatility and Impact of Multi-Objective Optimization: Algorithms, Applications, and Trends for Solving Complex Real-World Problems

Multi-Objective Optimization (MOO) techniques have become increasingly popular in recent years due to their potential for solving real-world problems in various fields, such as logistics, finance, environmental management, and engineering. These techniques offer comprehensive solutions that traditional single-objective approaches fail to provide. Due to the many innovative algorithms, it has been challenging for researchers to choose the optimal algorithms for solving their problems. This paper examines recently developed MOO-based algorithms. MOO is introduced along with Pareto optimality and trade-off analysis. In real-world case studies, MOO algorithms address complicated decision-making challenges. This paper examines algorithmic methods, applications, trends, and issues in multi-objective optimization research. This exhaustive review explains MOO algorithms, their methods, and their applications to real-world problems. This paper aims to contribute further advancements in MOO research. No singular strategy is superior; instead, selecting a particular method depends on the natural optimization problem, the computational resources available, and the specific objectives of the optimization tasks.

cs.NE↗

arXiv2024

BCDDO: Binary Child Drawing Development Optimization

A lately created metaheuristic algorithm called Child Drawing Development Optimization (CDDO) has proven to be effective in a number of benchmark tests. A Binary Child Drawing Development Optimization (BCDDO) is suggested for choosing the wrapper features in this study. To achieve the best classification accuracy, a subset of crucial features is selected using the suggested BCDDO. The proposed feature selection technique's efficiency and effectiveness are assessed using the Harris Hawk, Grey Wolf, Salp, and Whale optimization algorithms. The suggested approach has significantly outperformed the previously discussed techniques in the area of feature selection to increase classification accuracy. Moderate COVID, breast cancer, and big COVID are the three datasets utilized in this study. The classification accuracy for each of the three datasets was (98.75, 98.83%, and 99.36) accordingly.

cs.NE↗