Tuning Algorithm Research Articles

A Robust Algorithm for Estimating Total Suspended Solids (TSS) Using Sentinel-2: Case Study in Coastal Waters of Teluk Awur, Jepara, Indonesia

Total suspended solids (TSS) is an important parameter of water quality, so regular monitoring is necessary to prevent further marine pollution due to TSS. Remote sensing is one of the most effective and efficient methods to monitor TSS with cost-effective operations. The Sentinel-2 satellite is freely available to users with high spectral and spatial resolution (10m, 20m, 60m). Dynamic changes in coastal waters and their characteristics cause TSS retrieval algorithms built from available imagery having less optimal results in other water regions. This research aims to develop an empirical TSS algorithm model that specifically applies to the coastal waters of Teluk Awur, Jepara. The algorithm was developed using an empirical method through correlation between spectral values of Sentinel-2 imagery and in situ TSS values. Water sampling was conducted at 110 stations with a depth of 0.5 m on 22 July 2023 simultaneously collocated with Sentinel-2 image recording. Half of the data was used for algorithm tuning and the other half used for validation. The best regression analysis is found in the red band (B4) and the model is linear. The relatively good performance is shown by the coefficient of determination (R²) of 0.45, RMSE (3.40 mg.L-1), and MAPE (10.76%). The resulting algorithmic model was TSS (mg.L-1) =817.213*(B4)-0.959. This study shows that Sentinel-2 MSI images for TSS retrieval in the coastal waters of Teluk Awur could be applicable and the red band (B4) can be used for mapping TSS concentrations in the surrounding study area.

Early identification of potentially low performing community health workers using an ensemble classification model

PurposeCommunity health workers (CHWs) are vital to addressing public health system limitations in developing countries. However, effective identification and support of underperforming CHWs remains a challenge. This study develops a predictive model to proactively identify underperforming CHWs, facilitating targeted interventions for improved CHW programmes.Design/methodology/approachWe developed a predictive model to identify underperforming CHWs in Uttar Pradesh, India. Data from 140,101 CHWs over a 12-month period was used to build, test and validate the model. Classification techniques, ensemble modeling and a model tuning algorithm were employed for accuracy optimization and early identification.FindingsLogistic regression, decision trees and random forests yielded the best performance. While ensemble models offered no significant performance improvements over the base models, the model tuning algorithm effectively increased prediction accuracy by 19 percentage points. This enabled early identification of poor-performing CHWs and high-risk CHW clusters early in the year.Practical implicationsThe developed model has significant potential to improve CHW programmes. It enables targeted support, feedback and resource allocation, leading to enhanced CHW performance, motivation and healthcare outcomes in the communities they serve. The model can provide personalised feedback to help CHWs overcome challenges and dynamic clustering facilitates proactive identification and tailored support for those at risk of underperformance.Originality/valueThis study is the first attempt to use predictive modelling to identify underperforming CHWs, advancing the nascent field of CHW performance analytics. It underscores the effectiveness of digital technologies and data in improving CHW programmes.

Predicting the time to get back to work using statistical models and machine learning approaches

BackgroundWhether machine learning approaches are superior to classical statistical models for survival analyses, especially in the case of lack of proportionality, is unknown.ObjectivesTo compare model performance and predictive accuracy of classic regressions and machine learning approaches using data from the Inspiring Families programme.MethodsThe Inspiring Families programme aims to support members of families with complex issues to return to work. We explored predictors of time to return to work with proportional hazards (Semi-Parametric Cox in Stata) and (Flexible Parametric Parmar-Royston in Stata) against the Survival penalised regression with Elastic Net penalty (scikit-survival), (conditional) Survival Forest algorithm (pySurvival), and (kernel) Survival Support Vector Machine (pySurvival).ResultsAt baseline we obtained data on 61 binary variables from all 3161 participants. No model appeared superior, with a low predictive power (concordance index between 0.51 and 0.61). The median time for finding the first job was about 254 days. The top five contributing variables were ‘family issues and additional barriers’, ‘restriction of hours’, ‘available CV’, ‘self-employment considered’ and ‘education’. The Harrell’s Concordance index was range from 0.60 (Cox model) to 0.71 (Random Survival Forest) suggesting a better fit for the machine learning approaches. However, the comparison for predicting median time on a selected scenario based showed only minor differences.ConclusionImplementing a series of survival models with and without proportional hazards background provides a useful insight as well as better interpretation of the coefficients affected by non-linearities. However, that better fit does not translate to substantially higher predictive power and accuracy from using machine learning approaches. Further tuning of the machine learning algorithms may provide improved results.

Combination of a Rabbit Optimization Algorithm and a Deep-Learning-Based Convolutional Neural Network–Long Short-Term Memory–Attention Model for Arc Sag Prediction of Transmission Lines

Arc droop presents significant challenges in power system management due to its inherent complexity and dynamic nature. To address these challenges in predicting arc sag for transmission lines, this paper proposes an innovative time–series prediction model, AROA-CNN-LSTM-Attention(AROA-CLA). The model aims to enhance arc sag prediction by integrating a convolutional neural network (CNN), a long short-term memory network (LSTM), and an attention mechanism, while also utilizing, for the first time, the adaptive rabbit optimization algorithm (AROA) for CLA parameter tuning. This combination improves both the prediction performance and the generalization capability of the model. By effectively leveraging historical data and exhibiting superior time–series processing capabilities, the AROA-CLA model demonstrates excellent prediction accuracy and stability across different time scales. Experimental results show that, compared to traditional and other modern optimization models, AROA-CLA achieves significant improvements in RMSE, MAE, MedAE, and R2 metrics, particularly in reducing errors, accelerating convergence, and enhancing robustness. These findings confirm the effectiveness and applicability of the AROA-CLA model in arc droop prediction, offering novel approaches for transmission line monitoring and intelligent power system management.

Research on Quadrotor Control Based on Genetic Algorithm and Particle Swarm Optimization for PID Tuning and Fuzzy Control-Based Linear Active Disturbance Rejection Control

The control system of a quadrotor aircraft is characterized by nonlinearity, strong coupling, and underactuation, making it susceptible to external disturbances that can affect flight performance. To address this issue, this paper proposes a novel control system based on inner–outer loop architecture. In this system, the outer loop position control adopts a PID controller optimized by Genetic Algorithm-based Particle Swarm Optimization (GA-PSO), while the inner loop attitude control employs a Linear Active Disturbance Rejection Controller (LADRC) with fuzzy algorithm-based adaptive tuning, forming a dual-loop control structure. Comparisons with traditional dual-loop cascaded PID controllers, conventional PID in the outer loop with LADRC in the inner loop, and conventional PID in the outer loop with fuzzy algorithm-based adaptive tuning in the inner loop demonstrate that the proposed control system can stably track the desired position and attitude angles under certain external disturbances, exhibiting excellent anti-disturbance capability and stability.

Dark energy reconstruction analysis with artificial neural networks: Application on simulated Supernova Ia data from Rubin Observatory

In this paper, we present an analysis of Supernova Ia (SNIa) distance moduli (μ(z)) and dark energy using an Artificial Neural Network (ANN) reconstruction based on LSST simulated three-year SNIa data. The ANNs employed in this study utilize genetic algorithms for hyperparameter tuning and Monte Carlo Dropout for predictions. Our ANN reconstruction architecture is capable of modeling both the distance moduli and their associated statistical errors given redshift values. We compare the performance of the ANN-based reconstruction with two theoretical dark energy models: ΛCDM and Chevallier–Linder–Polarski (CPL). Bayesian analysis is conducted for these theoretical models using the LSST simulations and compared with observations from Pantheon and Pantheon+ SNIa real data. We demonstrate that our model-independent ANN reconstruction is consistent with both theoretical models. Performance metrics and statistical tests reveal that the ANN produces distance modulus estimates that align well with the LSST dataset and exhibit only minor discrepancies with ΛCDM and CPL.

Optimizing Machine Learning-Based Intrusion Detection Systems for Enhanced Security in Cloud Computing Environments.

In today’s cloud computing environments, robust network security is crucial due to the inherently distributed and dynamic nature of cloud systems. Traditional Network Intrusion Detection Systems (NIDS) often face challenges in handling large-scale, rapidly evolving data and sophisticated attack vectors unique to cloud settings. This paper presents an optimized Machine Learning (ML)-based NIDS framework designed specifically for cloud infrastructures, leveraging feature selection, dimensionality reduction, and algorithmic tuning techniques to enhance detection accuracy and reduce false positives. Integrating supervised and unsupervised learning methods, this NIDS system can detect both known and novel attack types efficiently. By utilizing cloud-specific datasets and real-time traffic monitoring, it adapts well to the scalability and elasticity requirements of cloud environments. Additionally, the system incorporates automated optimization techniques, such as hyperparameter tuning and ensemble learning, to further enhance performance. Experimental results show improvements in detection rates, reduced computational overhead, and better scalability, making it a promising solution for modern cloud-based infrastructures.

Modified Arithmetic Optimization Algorithm (MAOA) based torque ripple minimization for a sensorless BLDC motor

ABSTRACT Permanent magnet brushless DC (PM BLDC) motor drives outperform the induction motor drives in terms of performance and improved efficiency. Recent advancements in power electronics technology have improved the application of BLDC drives in a variety of home applications. However, the BLDC motor drives suffer from torque ripple, which causes machine vibration, speed oscillations, and acoustic noise, limiting the application range. In this prelude, an optimization tuning algorithm, namely Modified Arithmetic Optimization Algorithm (MAOA) is suggested in this paper for torque ripple minimization in a sensorless BLDC drive. In this paper, the cuk converter topology with PAM scheme is proposed for the sensorless BLDC drive, and MAOA algorithm is used to improve the gain of the controller. A MATLAB Simulink model is used to validate the results of MAOA tuned BLDC drive.

Tuning similarity-based fuzzy logic programs

We have recently designed a symbolic extension of FASILL (acronym of “Fuzzy Aggregators and Similarity Into a Logic Language”), where some truth degrees, similarity annotations and fuzzy connectives can be left unknown, so that the user can easily see the impact of their possible values at execution time. By extending our previous results in the development of tuning techniques not dealing yet with similarity relations, in this work we automatically tune FASILL programs by appropriately substituting the symbolic constants appearing on their rules and similarity relations with the concrete values that best satisfy the user's preferences. Firstly, we have formally proved two theoretical results with different levels of generality/practicability for tuning programs in a safe and effective way. Regarding efficiency, we have drastically reduced the exponential complexity of the tuning algorithms by splitting the initial set of symbolic constants in disjoint sets and using thresholding techniques. These effects have been evidenced by several experiments and benchmarks developed with the online tool we provide to verify in practice the high performance of the improved system.

Implementation of Skogestad’s Internal Model Control Rule in Tuning Proportional-Integral Controllers for Two-Input and Two-Output Systems Considering Individual Controller Performance Trade-off

Abstract In industrial plants, tuning of decentralized Proportional-Integral-Derivative feedback (PID) controllers in Multiple-Input and Multiple-Output (MIMO) systems is a complex problem, due to input and output interactions, that must be done to ensure individual control objectives are met, while system being sufficiently robust. In this study, a two-input and two-output (TITO) PI controller tuning algorithm was developed considering controller performance prioritization given performance trade-offs, expressed as the novel Individual Controller Performance Trade-off Coefficient (ICPTC), and system robustness, expressed as sensitivity peaks from the generalized Nyquist stability plot. Simplified effective open-loop transfer functions (EOTFs) of the two input-output channels were derived and used along with Skogestad’s Internal Model Control (SIMC) to calculate PI controller gains. Extensive simulations using Wood-Berry (WB) and Vinante-Luyben (VL) distillation column models were made to observe how the sensitivity peaks behave across the simulations, which was then used as the basis of the developed tuning algorithm. A simplified tuning algorithm, which requires less information compared to the main algorithm, was also derived. A mapping algorithm was also created, allowing specific controller gains from other studies to be mapped to an equivalent set of controller gains in the algorithm’s search field. The effectiveness of the three algorithms were tested using Wardle-Wood distillation column (WW) and Xiong and Cai (XC) process models. It was demonstrated using the main algorithm that there is a trade-off between controller performances when ICPTC is varied, at different values of design sensitivity peaks between 1.96 to 4. The usefulness of the simplified tuning and mapping algorithms were also illustrated in the study. This study is potentially useful in tuning TITO PI controllers in industrial plants, where meeting individual control objectives while maintaining robustness is more important than optimizing overall control performance.

Mapping forest tree species and its biodiversity using EnMAP hyperspectral data along with Sentinel-2 temporal data: An approach of tree species classification and diversity indices

Forests play a crucial role in maintaining ecological balance and biodiversity, making the accurate mapping of tree species and assessment of biodiversity indices essential for informed management decisions. This study introduces an innovative methodology that integrates EnMAP (Environmental Mapping and Analysis Program) hyperspectral data with Sentinel-2 multitemporal data to classify tree species in the biodiverse landscapes of Kampinos National Park and its surrounding regions in Poland.We extract essential vegetation indices such as NDVI, NDMI, SAVI, and EVI from Sentinel-2 data to assess forest health and dynamics. The Sentinel-2 data is upscaled from 10 m to 30 m to align with EnMAP’s spatial resolution, followed by precise co-registration of the images using QGIS. Utilizing a rich dataset from the National Forest Inventory, we extract spectral signatures of nine distinct tree species from both data sources. We employ five machine learning algorithms—Support Vector Machines (SVM), Random Forest (RF), CatBoost (CAT), Gradient Boosting Classifier (GBC), and XGBoost (XGB)—to enhance classification accuracy.Through iterative experimentation with data reduction techniques and algorithm tuning, we achieve optimal performance across needle-leaved and broad-leaved species. The resulting tree species maps are validated through quantitative accuracy assessments against mixed-species polygons from the National Forest Inventory and ground truthing in the Kampinos National Park. Achieving an overall accuracy of 85% to 93%, our study demonstrates the efficacy of this integrated approach in tree species mapping. Furthermore, the tree species maps serve as a foundation for deriving key biodiversity indices—species richness, Shannon-Wiener Diversity Index, Simpson’s Diversity Index, and a composite Biodiversity Index—providing insights into spatial biodiversity patterns and informing targeted conservation strategies. This study exemplifies the potential of combining advanced remote sensing techniques with field validation to enhance our understanding of forest ecosystems and guide sustainable management practices.

GA and PSO Techniques Based Optimal Tuning of Power System Stabilizers in a PV Integrated Power Network

This paper involves the employment of Genetic Algorithm (GA) and Particle Swam Optimization (PSO) methods for the optimal tuning of gain and time constant parameters of power system stabilizers in a power network with integrated Photovoltaic (PV) energy conversion systems. To examine the critical modes of the PV integrated system and the impact of the PV integration on various modes of oscillations, eigenvalue analysis is carried out under various PV penetration levels. The investigations indicate that the rotor angle oscillations following a disturbance have less damping as the PV penetration level increases. To enhance the small signal stability, the excitation systems are provided with the signal from power system stabilizers (PSS). The gain and time constant parameters of the PSS are tuned utilizing the GA and PSO methods and compared with the conventional proportional-integral (PI) PSS. The preliminary investigations on the PV integrated standard IEEE power system reveal that the PSO and GA-based PSS are significantly better than the PI-PSS, and further, PSO-PSS is marginally more effective than the GA-PSS in damping the rotor angle oscillations.

Intersensor Calibration of Spaceborne Passive Microwave Radiometers and Algorithm Tuning for Long-Term Sea Ice Trend Analysis Based on AMSR-E Observations

Sea ice monitoring is key to analyzing the Earth’s climate system. Long-term sea ice extent (SIE) has been continuously monitored using various spaceborne passive microwave radiometers (PMRs) since November 1978. As the lifetime of a satellite is usually approximately 5 years, bias caused by differences in PMRs should be eliminated to obtain objective SIE trends. Most sea ice products have been analyzed for long-term trends with a bias adjustment based on the coarse resolution special sensor microwave imager (SSM/I) in operation for the longest period. However, since 2002, Japanese microwave radiometers of the Advanced Microwave Scanning Radiometer (AMSR) series, which have the highest spatial resolution in PMR, have been available. In this study, we developed standardization techniques for processing SIE including calibration of the brightness temperature (TB), tuning the sea ice concentration (SIC) algorithm, and adjusting the SIC threshold to retrieve a consistent SIE trend based on the AMSR for the Earth Observing System (AMSR-E, one of the AMSR that operated from May 2002 to October 2011). Analysis results showed that the root-mean-square error between AMSR-E SICs and those of moderate resolution imaging spectroradiometer (MODIS) was 15%. In this study, SIE was defined as the sum of the areas where the AMSR-E SIC was >15%. When retrieving SIE, we adjusted the SIC threshold for each PMR to be consistent with the SIE calculated based on the 15% SIC threshold for AMSR-E. We then calculated a time-series of the SIE trends over approximately 45 years using the adjusted SIE data. Therefore, we revealed the dramatic decrease in global sea ice extent since 1978. This technique enables retrieval of more accurate long-term sea ice trends for more than half a century in the future.

Nonlinear FOPID controller design for pressure regulation of steam condenser via improved metaheuristic algorithm

Shell and tube heat exchangers are pivotal for efficient heat transfer in various industrial processes. Effective control of these structures is essential for optimizing energy usage and ensuring industrial system reliability. In this regard, this study focuses on adopting a fractional-order proportional-integral-derivative (FOPID) controller for efficient control of shell and tube heat exchanger. The novelty of this work lies in the utilization of an enhanced version of cooperation search algorithm (CSA) for FOPID controller tuning, offering a novel approach to optimization. The enhanced optimizer (en-CSA) integrates a control randomization operator, linear transfer function, and adaptive p-best mutation integrated with original CSA. Through rigorous testing on CEC2020 benchmark functions, en-CSA demonstrates robust performance, surpassing other optimization algorithms. Specifically, en-CSA achieves an average convergence rate improvement of 23% and an enhancement in solution accuracy by 17% compared to standard CSAs. Subsequently, en-CSA is applied to optimize the FOPID controller for steam condenser pressure regulation, a crucial aspect of heat exchanger operation. Nonlinear comparative analysis with contemporary optimization algorithms confirms en-CSA’s superiority, achieving up to 11% faster settling time and up to 55% reduced overshooting. Additionally, en-CSA improves the steady-state error by 8% and enhances the overall stability margin by 12%.

G2PDeep-v2: a web-based deep-learning framework for phenotype prediction and biomarker discovery using multi-omics data.

The G2PDeep-v2 server is a web-based platform powered by deep learning, for phenotype prediction and markers discovery from multi-omics data in any organisms including humans, plants, animals, and viruses. The server provides multiple services for researchers to create deep-learning models through an interactive interface and train these models using an automated hyperparameter tuning algorithm on high-performance computing resources. Users can visualize the results of phenotype and markers predictions and perform Gene Set Enrichment Analysis for the significant markers to provide insights into the molecular mechanisms underlying complex diseases and other biological processes. The G2PDeep-v2 server is publicly available at https://g2pdeep.org/.

Dynamic model of the UC San Diego NHERI six‐degree‐of‐freedom large high‐performance outdoor shake table

AbstractThe UC San Diego large high‐performance outdoor shake table (LHPOST), which was commissioned on October 1, 2004 as a shared‐use experimental facility of the National Science Foundation (NSF) Network for Earthquake Engineering Simulation (NEES) program, was upgraded from its original one degree‐of‐freedom (LHPOST) to a six‐degree‐of‐freedom configuration (LHPOST6) between October 2019 and April 2022. A mechanics‐based numerical model of the LHPOST6 able to capture the dynamics of the upgraded 6‐DOF shake table system under bare table condition is presented in this paper. The model includes: (i) a rigid body kinematic model that relates the platen motion to the motions of the components attached to the platen, (ii) a hydraulic dynamic model that calculates the hydraulic actuator forces based on all fourth‐stage servovalve spool positions, (iii) a hold‐down strut model that determines the pull‐down forces produced by the three hold‐down struts, (iv) Bouc‐Wen models utilized to represent the dissipative forces in the shake table system, and (v) a rigid body dynamic model borrowed from robotic analysis governing the translational and rotational motions of the platen subjected to the forces from the various components attached to the platen. Extensive validation against experimental data shows excellent agreement for tri‐axial and six‐axial earthquake shake table tests. This validated model can be coupled with finite element models of test specimens to study the interaction between the shake table system and the specimens, and it offers potential for enhancing motion tracking performance through off‐line controller tuning or advanced control algorithm development.

SPECTRAL THEORY AND FUNCTIONAL CALCULI IN THE REFLEXIVE BANACH SPACES

The design and assessment of closed loop control systems must include accurate and stable accuracy analysis and simulation. An overview of the significance of closed loop control systems and its uses in several engineering disciplines is given in this paper. The paper then explores the different techniques used for evaluating the accuracy and stability of closed loop control systems, including steady-state error analysis, stability analysis, and simulation techniques. It also discusses the design and tuning of control algorithms to optimize the performance of the system, and identifies the different factors that can affect the accuracy and stability of closed loop control systems, such as sensor noise, model inaccuracies, and environmental disturbances.

Fuzzified input data tuning for agriculture commodities price prediction

<span lang="EN-US">The quality of the input data will typically affect the prediction accuracy. Preprocessing of data is commonly referred to as input data tuning. Tuning the input data is critical for projecting commodity prices. Anomalies or outliers are unavoidable in historical price data. To increase prediction and forecasting accuracy, it is necessary to find and correct outliers before training the prediction model. To correct the anomaly and increase prediction accuracy, the Fuzzified Input Data Tuning and Prediction algorithm proposed in this study. The identified outliers are corrected using the relevant fuzzy set value in this method. With outlier corrected data, we used Long Short-Term Memory and Seasonal Autoregressive Integrated Moving Average to anticipate tomato prices in Karnataka state. The result of the proposed algorithm is compared with the Sliding Window anomalies correction model, and without disposing of the outliers. The suggested algorithm, with 37.89%, performed better than Sliding Window with 40.08% and 43.11% Mean Absolute Percentage Error, respectively, and without outlier correction. The sensitivity analysis shows that the performance of the model is unaffected by the forecasting horizon. Finally, comparitive analysis peformed with previous research work, and the proposed model performed better.</span>

Modeling unsaturated hydraulic conductivity of compacted bentonite using a constrained CatBoost with bootstrap analysis

Accurately determining the hydraulic conductivity of unsaturated bentonite is important for modeling subsurface thermo-hydro-mechanical and chemical processes. This study introduced a new hybrid model that employs a constrained categorial boosting (CatBoost) algorithm, combined with a genetic algorithm for hyperparameter tuning, to estimate the hydraulic conductivity of unsaturated compacted bentonite The performance of the constrained CatBoost model was benchmarked against a diverse set of data-driven baseline regression models, including lasso, elastic net, polynomial, k-nearest neighbors, decision tree, bagging tree, random forest, and CatBoost. The results indicated that the constrained CatBoost model offers a superior balance between model robustness and predictive accuracy in estimating the hydraulic conductivity of compacted bentonite-based materials during the wetting phase. The model effectively captured the U-shape relationship between hydraulic conductivity and suction, a key characteristic of bentonite behavior. Additionally, bootstrapping analyses confirmed the model's reliability under data variability, further validating its applicability in environmental and geotechnical applications.

Axial peak extraction in the measurement of subsurface structures with annular illumination confocal microscopy

Abstract Three-dimensional dark-field confocal microscopy (DFCM) using annular illumination and complementary detection apertures is capable of detecting subsurface defects in ultra-precision optical components. In this study, a DFCM tuning algorithm for large apertures is proposed based on the sinc2 tuning model. This algorithm provides a reliable and theoretically accurate method for extracting the axial position during the measurement of subsurface defects. The rationality and accuracy of this method are verified through simulations and experimental results.