Tuning XGBoost by Planet Optimization Algorithm: An Application for Diabetes Classification

Jovanovic, Luka; Djuric, Marko; Živković, Miodrag; Jovanovic, Dijana; Strumberger, Ivana; Antonijevic, Milos; Budimirović, Nebojša; Bačanin, Nebojša

doi:10.1007/978-981-19-7753-4_60

Cited by 17 publications

(5 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To assess the adequacy of finite element simulation against field data, a new stochastic optimizer known as the planet algorithm (PA) was employed. Furthermore, the PA was utilized to determine the optimal parameters of extreme learning machines in order to enhance their ability in diabetes diagnostics [33].…”

Section: Plos Onementioning

confidence: 99%

See 1 more Smart Citation

Optimal controller design for reactor core power stabilization in a pressurized water reactor: Applications of gold rush algorithm

Abdelfattah,

Esmail,

kotb

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

Nuclear energy (NE) is seen as a reliable choice for ensuring the security of the world’s energy supply, and it has only lately begun to be advocated as a strategy for reducing climate change in order to meet low-carbon energy transition goals. To achieve flexible operation across a wide operating range when it participates in peak regulation in the power systems, the pressurised water reactor (PWR) NE systems must overcome the nonlinearity problem induced by the substantial variation. In light of this viewpoint, the objective of this work is to evaluate the reactor core (main component) of the NE system via different recent optimization techniques. The PWR, which is the most common form, is the reactor under investigation. For controlling the movement of control rods that correspond with reactivity for power regulation the PWR, PID controller is employed. This study presents a dynamic model of the PWR, which includes the reactor core, the upper and lower plenums, and the piping that connects the reactor core to the steam alternator is analyzed and investigated. The PWR dynamic model is controlled by a PID controller optimized by the gold rush optimizer (GRO) built on the integration of the time-weighted square error performance indicator. Additionally, to exhibit the efficacy of the presented GRO, the dragonfly approach, Arithmetic algorithm, and planet optimization algorithm are used to adjust the PID controller parameters. Furthermore, a comparison among the optimized PID gains with the applied algorithms shows great accuracy, efficacy, and effectiveness of the proposed GRO. MATLAB\ Simulink program is used to model and simulate the system components and the applied algorithms. The simulation findings demonstrate that the suggested optimized PID control strategy has superior efficiency and resilience in terms of less overshoot and settling time.

show abstract

Section: Plos Onementioning

confidence: 99%

“…! A 2 is the vector constant computed by Eq (33). In this equation, the parameter l 2 is utilized instead of the parameter l 1 to raise the exploitation capability of the mining technique.…”

Section: Plos Onementioning

confidence: 99%

Optimal controller design for reactor core power stabilization in a pressurized water reactor: Applications of gold rush algorithm

Abdelfattah,

Esmail,

kotb

et al. 2024

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Swarm algorithms demonstrate practical utility across a wide range of real-world challenges, spanning diverse domains. Successful examples encompass medical applications [75], the detection of credit card fraud [76] and global optimization problems [77,78]. Furthermore, swarm metaheuristics find successful applications in cloud computing [79], plant classification [80], energy production forecasts [81], economy [82], improving audit opinion forecasting [83], software testing [84], feature selection [85], security and intrusion detection [86] and improving wireless sensor network performance [87].…”

Section: Metaheuristic Optimizationmentioning

confidence: 99%

Respiratory Condition Detection Using Audio Analysis and Convolutional Neural Networks Optimized by Modified Metaheuristics

Bacanin,

Jovanovic,

Stoean

et al. 2024

Axioms

Self Cite

View full text Add to dashboard Cite

Respiratory conditions have been a focal point in recent medical studies. Early detection and timely treatment are crucial factors in improving patient outcomes for any medical condition. Traditionally, doctors diagnose respiratory conditions through an investigation process that involves listening to the patient’s lungs. This study explores the potential of combining audio analysis with convolutional neural networks to detect respiratory conditions in patients. Given the significant impact of proper hyperparameter selection on network performance, contemporary optimizers are employed to enhance efficiency. Moreover, a modified algorithm is introduced that is tailored to the specific demands of this study. The proposed approach is validated using a real-world medical dataset and has demonstrated promising results. Two experiments are conducted: the first tasked models with respiratory condition detection when observing mel spectrograms of patients’ breathing patterns, while the second experiment considered the same data format for multiclass classification. Contemporary optimizers are employed to optimize the architecture selection and training parameters of models in both cases. Under identical test conditions, the best models are optimized by the introduced modified metaheuristic, with an accuracy of 0.93 demonstrated for condition detection, and a slightly reduced accuracy of 0.75 for specific condition identification.

show abstract

“…Population-based algorithms have lately become a usual choice for addressing different real-world problems. These algorithms are useful for many fields, such as prediction of COVID-19 cases (Zivkovic et al 2021a, b), organizing on demand computational services (Bacanin et al 2019;Bezdan et al 2020a, b;Zivkovic et al 2021c), optimizing wireless sensors and IoT (Zivkovic et al 2020(Zivkovic et al , 2021d, feature selection (Bezdan et al 2021;Bacanin et al 2023a), processing and classifying medical images (Bezdan et al 2020c;Zivkovic et al 2022), addressing global optimization problems (Strumberger et al 2019;Preuss et al 2011), identifying credit card fraud (Jovanovic et al 2022b;Petrovic et al 2022), monitoring and forecasting air pollution (Bacanin et al 2022a;Jovanovic et al 2023a), detecting network and computer system intrusions (Bacanin et al 2022b;Stankovic et al 2022), predicting power generation and energy load (Bacanin et al 2023b;Stoean et al 2023), and optimizing different ML models (Salb et al 2022;Milosevic et al 2021;Gajic et al 2021;Bacanin et al 2022c, d;Jovanovic et al 2022aJovanovic et al , 2023bBukumira et al 2022).…”

Section: Metaheuristics Optimizationmentioning

confidence: 99%

Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting

Pavlov-Kagadejev,

Jovanovic,

Bacanin

et al. 2024

Artif Intell Rev

Self Cite

View full text Add to dashboard Cite

Power supply from renewable energy is an important part of modern power grids. Robust methods for predicting production are required to balance production and demand to avoid losses. This study proposed an approach that incorporates signal decomposition techniques with Long Short-Term Memory (LSTM) neural networks tuned via a modified metaheuristic algorithm used for wind power generation forecasting. LSTM networks perform notably well when addressing time-series prediction, and further hyperparameter tuning by a modified version of the reptile search algorithm (RSA) can help improve performance. The modified RSA was first evaluated against standard CEC2019 benchmark instances before being applied to the practical challenge. The proposed tuned LSTM model has been tested against two wind production datasets with hourly resolutions. The predictions were executed without and with decomposition for one, two, and three steps ahead. Simulation outcomes have been compared to LSTM networks tuned by other cutting-edge metaheuristics. It was observed that the introduced methodology notably exceed other contenders, as was later confirmed by the statistical analysis. Finally, this study also provides interpretations of the best-performing models on both observed datasets, accompanied by the analysis of the importance and impact each feature has on the predictions.

show abstract

Tuning XGBoost by Planet Optimization Algorithm: An Application for Diabetes Classification

Cited by 17 publications

References 36 publications

Optimal controller design for reactor core power stabilization in a pressurized water reactor: Applications of gold rush algorithm

Optimal controller design for reactor core power stabilization in a pressurized water reactor: Applications of gold rush algorithm

Respiratory Condition Detection Using Audio Analysis and Convolutional Neural Networks Optimized by Modified Metaheuristics

Optimizing long-short-term memory models via metaheuristics for decomposition aided wind energy generation forecasting

Contact Info

Product

Resources

About