Genetic Algorithm Learning Research Articles

An Efficient Model for Lung Cancer Detection through the Integration of Genetic Algorithm and Machine Learning

Prompt lung cancer detection is essential for patient health. Deep Learning (DL) models have been intensively used for lung cancer screening, as they provide high accuracy in diagnoses. However, DL models require significant computational power, which may not be accessible in all settings. Conventional Machine Learning (ML) models may not produce high prediction accuracy, especially with large data. This study uses a Genetic Algorithm (GA) approach to select optimal features from lung cancer images and reduce their dimensionality. This allows conventional ML models to achieve a high prediction accuracy when classifying medical images while using lower computational power compared with DL models. The proposed model integrates GA along with ML for lung cancer detection. The experimental results show that using GA with a feed-forward neural network classifier achieved high performance, reaching 99.70% classification accuracy.

Two-step optimization algorithm operated by heuristic and machine learning methods

Heuristics aim to provide approximate solutions for NP-hard combinatorial optimization (CO) problems in a reasonable time. They are faster than deterministic methods, where the solving process may take days. This paper presents an attempt to combine a heuristic algorithm and some machine learning (ML) methods for solving the Multidimensional Knapsack Problem (MKP), which is a well-known CO case. The approach named Genetic Algorithm and Machine Learning (GAML) is a two-step algorithm that first uses four machine methods to produce four solutions and then integrates the best one within the GA. For this purpose, (1) This approach builds models by training four machine learning (ML) methods using the decision variables obtained from the optimal solutions of simple MKP instances. The decision variable of an item is equal to one if it is selected in the knapsack and zero otherwise. (2) The four models are applied to predict the decision variables for complex MKP instances. (3) A dummy algorithm constructs feasible solutions from the predictions by adding the selected items randomly while the constraints are not violated. (4) For each MKP instance, the best feasible solution among the four built is integrated with the initialization and the crossing operators of a genetic algorithm. An experiment has been conducted on well-known complex MKP benchmarks. The results proved that the models were able to provide high-quality solutions. Also, the proposed algorithm was faster than other approaches in the literature.

Integrated Genetic Algorithm and Deep Learning Approach for Effective Cyber-Attack Detection and Classification in Industrial Internet of Things (IIoT) Environments

AbstractCyber-attack detection within Industrial Internet of Things (IIoT) environments presents unique challenges due to the complex, resource-constrained, and real-time nature of these networks. Traditional detection techniques often struggle to adapt to the dynamic environment of IIoT. For instance, many existing methods rely on signature-based detection, which fails to identify evolving threats. Other approaches, such as anomaly-based detection, can generate a high rate of False Positives, leading to inefficiencies in threat management. To address these challenges, we propose a novel detection and classification model specifically tailored for IIoT environments. The proposed model integrates Genetic Algorithms (GA) and Deep Learning (DL) to enhance cyber-attack detection within IIoT environments. The GA component optimises feature selection from raw network data, ensuring the extraction of meaningful and relevant features. Leveraging these selected features, the DL component constructs a robust model capable of accurately detecting and classifying various cyber-attack patterns across IIoT devices. Through experimentation on real-world IIoT network traffic (UNSW-NB 15 dataset), the proposed approach demonstrates its efficacy in improving attack detection accuracy and adaptability. The integration of GA and DL offers a synergistic solution that addresses the complexities of IIoT cybersecurity, contributing to a more secure and resilient IIoT ecosystem. The integrated GA–DL classification model developed in this work achieved 98% precision, 96% accuracy, 94% recall, and 12% losses with only less than 50% of the features of the UNSW-NB 15 dataset. The reduction in features required for the identification and classification of cyber-attacks reduces the processing time by 50%.

An optimal fast fractal method for breast masses diagnosis using machine learning

This article introduces a fast fractal method for classifying breast cancerous lesions in mammography. While fractal methods are valuable for extracting information, they often come with a high computational load and time consumption. This paper demonstrates that extracting optimal fractal information and focusing only on valuable information for classification not only improves computation speed and reduces process load but also enhances classification accuracy. To achieve this, we define an objective function based on accurate classification of benign and malignant masses to identify the best scale. Instead of extracting information from all nine scales, we extract and employ information solely from the best scale for classification. We validate the obtained scales using three classifiers: Support Vector Machine (SVM), Genetic Algorithm (GA), and Deep Learning (DL), which confirm the effectiveness of the proposed method. Comparative analysis with other studies reveals improved classification performance with the presented method.

Enhancing corporate bankruptcy prediction via a hybrid genetic algorithm and domain adaptation learning architecture

In the contemporary business landscape, accurately evaluating a company’s financial health is essential for stakeholders to mitigate risks and avert bankruptcy. This study presents an innovative approach to improving business bankruptcy prediction through the hybrid integration of Domain Adaptation Learning (DAL) and Genetic Algorithm (GA) techniques. The hybrid model harnesses DAL to address distributional changes in real-world scenarios and utilises GA’s proficiency in feature selection. Six machine learning models are rigorously evaluated against the proposed hybrid model: Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR), Gradient Boosting (GB), k-Nearest Neighbours (k-NN), and Stacking Ensemble (SE). Our hybrid model performs well on imbalanced target datasets using the Area Under the Precision–Recall Curve metric: 0.93 (RF), 0.93 (SVM), 0.89 (LR), 0.91 (GB), 0.88 (k-NN), and 0.92 (SE). These findings highlight the model’s ability to overcome the limitations of traditional approaches, offering a more reliable predictive framework for stakeholders to make informed decisions and proactively manage financial stability. Future research directions may explore the applicability of this hybrid model across different industries and the integration of additional techniques to further enhance its performance.

Semiconductors for enhanced solar photovoltaic-thermoelectric 4E performance optimization: Multi-objective genetic algorithm and machine learning approach

In this study, a groundbreaking exploration of a concentrated photovoltaic-thermoelectric (CPV-TE) module employing an unprecedented selection of six thermoelectric materials across diverse temperature ranges is presented. This work innovatively employs a multi-objective optimization framework that combines genetic algorithms and goal attainment methods, aiming to optimize energy, exergy, environmental, and economic (4 E) performance. Notably, this study is the first to construct and evaluate five regression-based machine learning models with an emphasis on minimal root mean squared error and mean absolute error for rapid CPV-TE performance predictions, essential for real-world applications. Our analysis unveils that among the tested materials, the CPV-TE module incorporating lead telluride (PbTe) achieves the highest 4 E performance, demonstrating a peak exergy efficiency of 14.2 %, and annual energy savings and carbon reduction of 13.5 kWh and 6.4 kg, respectively. Furthermore, the Gaussian Process Regression model is identified as the most effective among the machine learning models for forecasting performance across the materials. This study significantly advances the field by providing novel insights into thermoelectric material selection and optimization for CPV-TE modules, and establishing pioneering forecasting tools that catalyze the efficient deployment of these systems.

Designing unique and high-performance Al alloys via machine learning: Mitigating data bias through active learning

Data-driven modelling, such as machine learning (ML), has great potential to streamline the complexity involved in designing new alloys. However, such powerful predictive models require a high-quality dataset, which is limited in the alloy field due to selection and reporting biases. These biases lead to out-of-distribution (OOD) regions where ML models suffer from predictive performance degradation, limiting the design of innovative alloys. To overcome this problem, we propose a ML-based design strategy for unique and high-performance aluminium (Al) alloys, incorporating multi-objective genetic algorithm (MOGA) and active learning. To guide active learning, the cosine similarity metric embedded MOGA pinpoints unique and high-strength Al alloys in OOD regions for experiments. Our study demonstrates the deficiency of initial ML models when trained on the biased dataset and subsequent improvement in retrained models after applying active learning with alloys suggested by MOGA. On this basis, a new Al alloy that is distinct from the existing dataset is developed with a yield tensile strength of 688 MPa, ultimate tensile strength of 738 MPa, and elongation of 7.5 %. This finding highlights the importance of the inclusion of OOD results and the efficiency of ML in alloy design.

Application of Improved Genetic Algorithm and Deep Learning in Cold Chain Logistics Distribution Demand Prediction

In order to solve the problem of inaccurate prediction results caused by the excessive impact of downstream on upstream suppliers in the process of cold chain logistics transportation demand prediction, the author proposes a demand prediction system Multi agent based on improved genetic algorithm and deep learning. The system will improve genetic algorithm, combine deep learning with practical problems in cold chain logistics supply chain, and evaluate the improved model through instance simulation. The results are as follows: After optimization, the order quantity of each stratum reduces the influence of retailers on upstream suppliers by more than 70%. As for the overall transportation cost, it shows a continuous upward trend within 20 cycles, while the total cost of each cycle fluctuates in a lower range after optimization, reducing the overall total cost by about 50%. It shows the reliability of the improved demand forecasting system in this study to greatly reduce storage and transportation costs.

Static video summarization based on genetic algorithm and deep learning approach

Static video summarization based on genetic algorithm and deep learning approach

Design Algorithmic Trading Strategies with Expert Advisor Using Linear Weighted Moving Average (LWMA) and Stochastic Oscillator Technical Indicators

Earlier this decade, the financial sector saw a paradigm change, with automated trading (AT) systems gaining popularity as essential tools for traders and investors. This research explores deeply the design and implementation of Expert Advisors (EAs) for automated financial built using a combination of the Linear Weighted Moving Average (LWMA) and Stochastic oscillator technical indicators. The EAs are built using the programming language MetaQuotes Language 4 (MLQ4) at Metatrader 4 (MT4) platform, enabling automated trade execution. It implements a machine learning genetic algorithm, trained on historical data to optimize the parameters of the LWMA and Stochastic trading rules. The core strategy relies on the LWMA to identify the overall market trend direction while the Stochastic oscillator provides additional signals for timing entry and exit points based on momentum. The EAs were coded to generate automated buy and sell signals for algorithmic trading (AT) based on a set of defined rules using thresholds for each indicators. Extensive historical backtesting using Gold (XAU/USD) currency pair across multiple timeframes from 5-minute (M5) up to 4-hour (H4) charts was conducted using 5 years of price data from 2019 to 2023 for evaluation. The goal of this study is to assess if the EAs could potentially produce consistent profits over time while minimizing drawdowns in different market conditions. The results demonstrate that the system was able to generate annual returns ranging from 3.04% up to 232.19% depending on the aggression of the timeframe settings. Meanwhile, maximum drawdowns were controlled to reasonable levels between 0.5% to 8.27% which is below 10% of potential loss throughout the backtests. An hourly timeframe configuration provided a balanced blend between strong profitability and drawdown control based on the backtest analysis. All the timeframes used for the test show positive results and the M5 timeframe is the best chosen timeframe to trade using this EAs implementation.

An efficient position optimization method based on improved genetic algorithm and machine learning for sparse array

Sparse array antennas are significant in communication and radar systems due to the advantages of high resolution, low complexity, and immunity to interference. In this letter, a novel array synthesis method based on an improved genetic algorithm (IGA) is proposed to optimize the antenna position in the sparse array. Different from the traditional generic methods with high computational complexity, a method combined with Gaussian process regression (GPR) prediction is proposed to optimize the antenna position with low computational complexity. The proposed method can minimize the peak sidelobe level (PSLL) during the beam scanning procedures. Moreover, the minimum antenna spacing constraint is also considered to ensure a physically achievable solution. Simulation results show that the proposed method can achieve a lower PSLL with fewer iterations and provide a global optimization solution for large array synthesis compared with existing methods. Furthermore, a prototype of the sparse array principle optimized by IGA is designed. Measurement results indicate that the optimized sparse array has good synthesis performance in high frequency.

RETRACTED: Application of an adaptive genetic algorithm and machine learning in an English text analysis teaching system

This article has been retracted. A retraction notice can be found at https://doi.org/10.3233/JIFS-219433.

A hybrid approach integrating genetic algorithm and machine learning to solve the order picking batch assignment problem considering learning and fatigue of pickers

Modeling human behaviors has become increasingly relevant to improving the performance of manual order-picking systems. However, although a vast corpus of literature has recently started to consider the human factors in these systems, several gaps remain uncovered. Specifically, mental and physical human factors, like learning and fatigue, and quantitative and spatial features of picking orders have never been considered jointly to estimate the time a human order picker requires to execute a specific picking mission. Furthermore, little attention has been given to assigning and sequencing orders to pickers to minimize the picking time acting on their individual learning and fatigue characteristics. This study thus proposes a novel approach integrating machine learning and genetic algorithms to solve the problem. A non-linear machine learning-based predictive model has been adopted to predict the picking time of batches of orders based on quantitative and spatial features of batches and learning and fatigue indicators of pickers. These predictions have thus been adopted to guide a genetic algorithm to find the best assignment of future planned batches of orders to pickers. One year of picking data collected from the warehouse of a grocery retailer has been adopted to investigate the potential of the proposed approach. Furthermore, multiple comparisons have been performed. First, the advantages of predicting the batch-picking time with the proposed non-linear model have been compared with predictions executed based on linear models. In addition, an ablation analysis has been performed to investigate the advantages of predicting the batch picking time while simultaneously considering the quantitative and spatial features of batches and the learning and fatigue indicators of pickers. Moreover, the advantages of the proposed batch assignment strategy, which considers learning and fatigue indicators, have been compared with an assignment strategy that does not optimize these elements. Lastly, an explainability analysis of the predictive model has been performed to understand how and how much quantitative and spatial features of batches and learning and fatigue indicators of pickers affect the batch picking time.

Optical Beamforming tuning with Genetic Algorithm and Deep Learning

Optical Beamforming tuning with Genetic Algorithm and Deep Learning

A novel zero emission combined power and cooling system for concentrating solar power: Thermodynamic and economic assessments and optimization

This study aims to develop a zero-emission multi-generation system based on concentrated solar power to reduce solar thermal power cost and improve the efficiency of power generation. The multi-generation system mainly includes concentrated solar power system, supercritical carbon dioxide recompression Brayton cycle, organic flash cycle and absorption refrigeration cycle. A comprehensive energy, exergy, environment and economic analysis is carried out. Five key parameters are considered to assess the effect of decision parameters on system performance. An optimization method combining genetic algorithm and machine learning is used to accelerate the optimization process. Results display that compared with the stand-alone supercritical carbon dioxide recompression Brayton cycle, the energy utilization factor and exergy efficiency of the multi-generation system can improve 18.7 % and 6.4 %, respectively, and the decrement of levelized cost of electricity is reduced by 4 %. A higher turbine-Ⅰ inlet temperature can improve the exergy efficiency and reduce the levelized cost of electricity. Using the proposed optimization method, the long optimization time of complex multi-generation system is overcome. Comparing the exergy efficiency optimization case with the basic case and the cost optimization case, the exergy efficiency optimization case has the highest net power output and exergy efficiency. This work exhibits great potential in utilizing solar energy for power and cooling.

Cooperative Multiagent Reinforcement Learning Coupled With A* Search for Ship Multicabin Equipment Layout Considering Pipe Route

_ The paper presents a novel approach of cooperative multiagent reinforcement learning (CMARL) combined with A* search to address ship multicabin equipment layout considering pipe route, aiming to minimize pipe cost while considering practical requirements. The formulation is established through equipment simplification and grid marking, and A* search is utilized to value the pipe route. By designing equipment states, the equipment layout in each cabin is solved using a CMARL approach that involves three actions. Subsequently, comparative experiments were conducted on an engine room case by CMARL against genetic algorithm and single multiagent reinforcement learning methods under the condition of coupling with A* search. The parameter values for these methods were sampled using Latin Hypercube. The findings demonstrate that CMARL has superior combination properties. Keywords ship equipment layout; multicabin layout; cooperative multiagent reinforcement learning; A* search; pipe route

Hybrid wrapper feature selection method based on genetic algorithm and extreme learning machine for intrusion detection

Intrusion detection systems play a critical role in the mitigation of cyber-attacks on the Internet of Things (IoT) environment. Due to the integration of many devices within the IoT environment, a huge amount of data is generated. The generated data sets in most cases consist of irrelevant and redundant features that affect the performance of the existing intrusion detection systems (IDS). The selection of optimal features plays a critical role in the enhancement of intrusion detection systems. This study proposes a sequential feature selection approach using an optimized extreme learning machine (ELM) with an SVM (support vector machine) classifier. The main challenge of ELM is the selection of the input parameters, which affect its performance. In this study, the genetic algorithm (GA) is used to optimize the weights of ELM to boost its performance. After the optimization, the algorithm is applied as an estimator in the sequential forward selection (wrapper technique) to select key features. The final obtained feature subset is applied for classification using SVM. The IoT_ToN network and UNSWNB15 datasets were used to test the model's performance. The performance of the model was compared with other existing state-of-the-art classifiers such as k-nearest neighbors, gradient boosting, random forest, and decision tree. The model had the best quality of the selected feature subset. The results indicate that the proposed model had a better intrusion detection performance with 99%, and 86% accuracy for IoT_ToN network dataset and UNSWNB15 datasets, respectively. The model can be used as a promising tool for enhancing the classification performance of IDS datasets.

Learning for Cellular Neural Networks Using the GARPLA Algorithm

The main content of this article is to build a hybrid algorithm between genetic algorithm and Recurrent Perceptron Learning Algorithm to determine the weight set for standard cellular neural networks. In particular, the Recurrent Perceptron Learning Algorithm was announced by Gukzelis in 1998 to determine the weight set for CeNNs, however, the nature of the algorithm built according to LMS learning rules means there is still a possibility of local convergence problems of algorithm. Meanwhile, the genetic algorithm originates from natural selection problems and is capable of determining the local optimal domain of the problem. Therefore, the GARPLA hybrid algorithm will fully determine the optimal weight set for the CeNNs network, reducing potential local optimization problems encountered in the RPLA algorithm.

Enhancing performance of multi-pressure evaporation organic Rankine Cycle/Supercritical Carbon Dioxide Brayton cycle through genetic algorithm and Machine learning optimization

The Supercritical Carbon Dioxide Brayton combined cycle is one of the most important ways to enhance the performance of the cycle. Since the considerable exergy loss resulting from large temperature differences in the heat exchangers of combined cycles, the multi-pressure evaporation concept was adopted from Organic Rankine cycle research. Two novel multi-pressure evaporation configurations, namely parallel evaporation Brayton combined cycle and series evaporation Brayton combined cycle, are designed with the purpose of enhancing SCO2 Brayton cycle performance. The performance of the two new cycles was compared with that of the baseline cycle. Moreover, Printed Circuit Heat Exchangers were employed to improve the overall compactness of the cycles. The results from model calculations were utilized to train an Artificial intelligence neural network model using machine learning techniques which allowed to simplify the cycle and improves the computational speed. Subsequently, genetic algorithm was employed to conduct multi-objective optimization on the three cycles. Finally, a detailed exploration was conducted from the perspective of thermal and exergy to elucidate the reasons for the advantages and differences between the two new cycles compared to the baseline cycle. The results indicate that the series Brayton combined cycle exhibits the highest performance, and the combined cycle of multi-pressure evaporation helps to improve the performance of the combined cycle. Compared to the baseline cycle, the combined cycle efficiency of both series and parallel combined cycles has increased from 45.54% to 46.18% and 46.29%, respectively, while the bottom cycle efficiency has improved from 3.81% to 4.93% and 5.03%. The ratio of heat exchange area to net output power increased from 0.6051 to 0.6614 and 0.6740 for the parallel and series cycles, respectively. Thermal analysis shows that, the fundamental purpose of changing the layout is to improve the specific power per unit of working medium in the cycle. Exergy analysis shows that, the two new combined cycles improve cycle efficiency by reducing exergy losses in the intermediate heat exchanger. Compared to the parallel version, the series version's staged compression allows for a lower temperature difference in intermediate heat exchanger 1, resulting in smaller exergy losses and higher cycle efficiency. This work will contribute to an enhanced understanding of Supercritical Carbon Dioxide combined cycles within the academic community and the introduction of multi-pressure evaporation will further improve the performance of these important cycles.

Improving Coverage and Vulnerability Detection in Smart Contract Testing Using Self-Adaptive Learning GA

In the domain of software testing, the generation of test cases is a critical process for detecting system errors and bugs. However, automated test case generation for smart contracts often encounters challenges related to automation, vulnerability diversity, and coverage. This paper presents a novel method, the self-adaptive learning Genetic Algorithm (self-adaptive learning GA), designed to address these issues. Our research methodology incorporates several construction models, namely the Control Dependence Graph (CDG), Control Flow Graph (CFG), and Application Binary Interface (ABI). Initially, the ABI model provides essential information for generating and executing test cases. The CFG model subsequently visualizes potential execution paths through the functions of smart contracts. Ultimately, the CDG model identifies potential vulnerabilities in smart contracts. Using these models, our method enhances automatic test case generation in smart contracts by improving coverage and reducing execution time. We selected a variety of smart contracts from the Decentralized Finance (DeFi) ecosystem for data collection and comparative analysis. The experimental results show superior performance rates, with an average code coverage rate of 98.1%, a total of 3500 vulnerabilities detected, a vulnerability detection rate of 98.7%, a false positive rate of 1.3%, a recall of 98.2%, precision of 98.8%, a path uniqueness rate of 96.4%, false negative rate of 3.5%, an execution time of 25 s, and test case generation time of 16 s. In conclusion, our proposed approach demonstrates a significant improvement over existing methods for test case generation by providing a promising solution for the robustness of smart contracts and security enhancement in the DeFi ecosystem.