Genetic Algorithms

This paper presents an approach that uses both genetic algorithm (GA) and fuzzy inference system (FIS), for feature selection for descriptor in a quantitative structure activity relationships (QSAR) classification and prediction problem. Unlike the traditional techniques that employed GA, the FIS is used to evaluate an individual population in the GA process. So, the fitness function is introduced and defined by the error rate of the GA and FIS combination. The proposed approach has been implemented and tested using a data set with experimental value anti-human immunodeficiency virus (HIV) molecules. The statistical parameters q2 (leave many out) is equal 0.59 and r (coefficient of correlation) is equal 0.98. These results reveal the capacity for achieving subset of descriptors, with high predictive capacity as well as the effectiveness and robustness of the proposed approach.

Recent studies on financial markets have demonstrated that technical analysis can help us effectively predict the stock market index trend. Business systems are widely used for stock market analysis. This paper uses a genetic algorithm (GA) to develop a stock market trading optimization system. Our proposed system can generate a decision-making strategy for buying, holding, and selling stocks for each day and generate high returns for each stock. The system consists of two stages: removing restricted stocks and producing a stock trading strategy. Accordingly, evolutionary computation, like GA, is highly promising because of its intelligence, flexibility, and search strength (fast and efficient). The multiple-objective nature of the utilized algorithm can be regarded as the center of gravity of the research question. The proper functioning or malfunctioning of the resulting portfolio management can be employed as a benchmark for selecting or discarding the algorithm. On the other hand, the research question is focused on the application of technical analysis indicators. Therefore, both aspects of the research question, namely the multiple-objective nature of the algorithm in terms of the analysis method and technical indicators in terms of features selected for analysis, must be taken into account.

This study aims to apply automatic machine-learning approaches using genetic algorithms to enhance heart disease prediction. Heart disease has remained the major cause of mortality in the world, necessitating an effective and timely diagnosis. Most current diagnostic and assessment processes are lengthy and expensive, relying heavily on clinical expert knowledge. To help address these issues, machine learning approaches, which derive their utility from examining substantial datasets for the recognition of patterns, have emerged as a potential solution, providing solutions beyond those achievable by human recognition alone. Genetic algorithms are also suited to addressing these issues as they mimic natural evolution to perfect high-caliber machine-learning models, feature selection, and parameter selection in machine-learning applications. This study examines the utilization of genetic algorithms working alongside AutoML frameworks to improve accuracy in heart disease predictions. Reducing to the best combination of attributes and the optimum parameters for each attribute is a time-consuming task, so automating this aspect of the process allows for more accurate and prompt predictions, consequently reducing the manual work. The AutoML approach followed in this research is TPOT, which uses genetic algorithms to ascertain optimally designed machine-learning pipelines. The application of AutoML, together with genetic algorithms, is the most prominent finding that yields a significant improvement in the quality of the predictions for heart disease compared to the traditional assessment approaches, with an accuracy of 93.8%. This approach will enhance diagnostic accuracy and enable early diagnosis, thereby reducing the likelihood of misdiagnoses or ineffective treatments and ultimately lowering associated costs.