Minimal Optimization Research Articles

Fault characterization enhancement method for rolling bearings based on combination of weighted indicator screening and IMOMEDA

As one of the core components of aeroengine, it is very important to find out the fault of intermediate bearing in time for the safety of aeroengine. Early bearing fault features are easily buried by background noise, which makes it difficult to extract fault features. To solve this problem, a fault feature enhancement method based on weighted index screening and IMOMEDA is proposed in this article. First, employ wavelet packet decomposition to analyze the vibration signal; and the kurtosis, correlation coefficient, and permutation entropy are fused into weighted indexes by entropy weight method to screen the node components with high signal-to-noise ratio for reconstruction; then, envelope autocorrelation analysis is used to optimize the deconvolution cycle parameter T of the multipoint optimal minimum entropy deconvolution adjusted; and then the optimized IMOMEDA is used to filter out the noise components of reconstructed signals to achieve the enhancement of the fault features; and finally, envelope demodulation is performed to identify the fault feature information. After the simulation signal verification, the signal peak factor processed by this method is increased from 7.3 to 9.7, so the fault characteristics are effectively enhanced. The data of different fault types measured by the aeroengine intermediate bearing fault simulation test bench are analyzed. The results show that the method can effectively filter out the strong background noise in the vibration signal of different fault types, enhance the weak fault characteristics related to the bearing fault, and can be used as one of the effective methods for the fault diagnosis of the intermediate bearing of the aeroengine.

Bidirectional Evolutionary Topology Optimization for Stress Minimization Based on the Modified Couple Stress Elasticity

Bidirectional Evolutionary Topology Optimization for Stress Minimization Based on the Modified Couple Stress Elasticity

Speech-Based Techniques for Emotion Detection in Natural Arabic Audio Files

Emotion detection is one of the greatest challenges of Natural Language Processing (NLP). Often referred to as emotion recognition, it is the process of identifying a person’s various feelings or emotions such as: happiness, sadness, or anger. Emotions are a strong feeling regarding a human's situation or relation with others. They are the mental states that affect human behavior and interactions. In this paper, we propose an approach for emotion detection in audio files, focusing on a natural Arabic audio dataset and applying several Machine Learning (ML) classifiers: Sequential Minimal Optimization (SMO), Random Forest (RF), K-Nearest Neighbours (KNN), and Simple Logistic (SL). The classification experiments were conducted using sixteen acoustic feature sets. Many acoustic features were explored including Mel Frequency Cepstral Coefficient (MFCC), Mel spectrogram, spectral contrast, Zero Crossing Rate (ZCR), and Intensity. The experimental results show that SMO and SL classifiers achieved the highest overall accuracy 83.82% when using combinations of all acoustic features (MFCC, Mel spectrogram, Spectral contrast, ZCR and intensity). Additionally, The RF and KNN classifiers yielded Competitive results, with accuracies of 81.71% and 77.34%, respectively. These results suggest that combining multiple acoustic features significantly enhances the performance of emotion detection models, especially for complex emotions in natural Arabic audio datasets

Minimum Wages, Efficiency, and Welfare

Many argue that minimum wages can prevent efficiency losses from monopsony power. We assess this argument in a general equilibrium model of oligopsonistic labor markets with heterogeneous workers and firms. We decompose welfare gains into an efficiency component that captures reductions in monopsony power and a redistributive component that captures the way minimum wages shift resources across people. The minimum wage that maximizes the efficiency component of welfare lies below $8.00 and yields gains worth less than 0.2% of lifetime consumption. When we add back in Utilitarian redistributive motives, the optimal minimum wage is $11 and redistribution accounts for 102.5% of the resulting welfare gains, implying offsetting efficiency losses of −2.5%. The reason a minimum wage struggles to deliver efficiency gains is that with realistic firm productivity dispersion, a minimum wage that eliminates monopsony power at one firm causes severe rationing at another. These results hold under an EITC and progressive labor income taxes calibrated to the U.S. economy.

A multivariate finite horizon production control chart for monitoring the food production process

ABSTRACT Finite horizon production (FHP) processes are prevailing in the food industry. However, monitoring these multivariate FHP processes poses a significant challenge for statistical process control, primarily due to inadequate information about the distribution of multivariate observations. In this paper, a multivariate FHP (MFHP) control chart is proposed to monitor the food production processes with a limited number of reference samples, where the statistic of the proposed chart is derived from the distance from the monitored samples to support vectors of a support vector machine (SVM) classifier. The control limit of the statistic is designed from a conditional perspective, taking into account the variability generated across different reference samples. An enhanced cache-optimized sequential minimal optimization algorithm (ECSMOA) is proposed to speed up the computation of the control limit. Extensive numerical analysis indicates that the proposed chart is more effective and robust in preserving a desired in-control performance and guaranteeing an out-of-control performance. Particularly, the variance of performance measures was reduced by approximately 87.09 % . Finally, an industrial example based on whole wheat bread production processes is given to demonstrate the implementation of the proposed chart.

ConCave-Convex procedure for support vector machines with Huber loss for text classification

The classical support vector machine (SVM) adopts the linear Hinge loss whereas the least squares SVM (LS-SVM) employs the quadratically growing least squares loss function. The robust Ramp loss function is employed in Ramp loss SVM (RSVM) that truncates the Hinge loss function and becomes flat a specified point afterwards, thus, increases robustness to outliers. Recently proposed SVM with pinball loss (pin-SVM) utilizes pinball loss function that maximizes the margin between the class hyperplanes based on quantile distance. Huber loss function is the generalization of linear Hinge loss and quadratic loss. Huber loss solves sensitivity issues of least squares loss to noise and outlier. In this work, we employ the robust Huber loss function for SVM classification for improved generalization performance. The cost function of the proposed approach consists of one convex and one non-convex part, which might sometimes provide local optimum solution instead of a global optimum. We suggest a ConCave-Convex Procedure (CCCP) to resolve this issue. Additionally, the proximal cost is scaled for each class sample based on their class size to reduce the effect of the class imbalance problem. Thus, it can be claimed that the proposed approach incorporates class imbalance learning as well. Extensive experimental analysis establishes efficacy of the proposed method. Furthermore, a sequential minimal optimization (SMO) procedure for high dimensional HSVM is proposed and its performance is tested on two text classification datasets.

Cyclic and Negacyclic Codes With Optimal and Best Known Minimum Distances

Cyclic and Negacyclic Codes With Optimal and Best Known Minimum Distances

Toward Robust Discriminative Projections Learning Against Adversarial Patch Attacks.

As one of the most popular supervised dimensionality reduction methods, linear discriminant analysis (LDA) has been widely studied in machine learning community and applied to many scientific applications. Traditional LDA minimizes the ratio of squared l2 norms, which is vulnerable to the adversarial examples. In recent studies, many l1 -norm-based robust dimensionality reduction methods are proposed to improve the robustness of model. However, due to the difficulty of l1 -norm ratio optimization and weakness on defending a large number of adversarial examples, so far, scarce works have been proposed to utilize sparsity-inducing norms for LDA objective. In this article, we propose a novel robust discriminative projections learning (rDPL) method based on the l1,2 -norm trace-ratio minimization optimization algorithm. Minimizing the l1,2 -norm ratio problem directly is a much more challenging problem than the traditional methods, and there is no existing optimization algorithm to solve such nonsmooth terms ratio problem. We derive a new efficient algorithm to solve this challenging problem and provide a theoretical analysis on the convergence of our algorithm. The proposed algorithm is easy to implement and converges fast in practice. Extensive experiments on both synthetic data and several real benchmark datasets show the effectiveness of the proposed method on defending the adversarial patch attack by comparison with many state-of-the-art robust dimensionality reduction methods.

Effective, but Safe? Physiologically Based Pharmacokinetic (PBPK)-Modeling-Based Dosing Study of Molnupiravir for Risk Assessment in Pediatric Subpopulations.

Despite the end of COVID-19 pandemic, only intravenous remdesivir was approved for treatment of vulnerable pediatric populations. Molnupiravir is effective against viruses beyond SARS-CoV-2 and is orally administrable without CYP-interaction liabilities but has a burden of potential bone or cartilage toxicity, observed at doses exceeding 500 mg/kg/day in rats. Especially, activity of molnupiravir against viruses, such as Ebola, with high fatality rates and no treatment option warrants the exploration of potentially effective but safe doses for pediatric populations, i.e., neonates (0-27 days), infants (1-12 months), and children in early childhood (1-12 years). The bone and cartilage toxicity risk for these populations based on the preclinical results has not been systematically investigated yet. Using physiologically based pharmacokinetic (PBPK) modeling, we developed adult PBPK models for doses ranging from 50 to 1200 mg with minimal parameter optimization because of incorporation of CES1, a carboxylesterase. Therein, CES1 served as the main driver for conversion of molnupiravir to its active metabolite β-d-N4-hydroxycytidine (NHC). By incorporation of the ontogeny of CES1 for pediatric populations, we successfully developed PBPK models for different doses ranging from 10 to 75 mg/kg. For molnupiravir, efficacy is driven by the area under the curve (AUC). To achieve a similar AUC to that seen in adults, a dose of around 28 mg/kg BID was necessary in all three investigated pediatric subpopulations. This dose exceeded the safe dose observed in dogs and was slightly below the toxicity-associated human equivalent dose in rats. In summary, the pediatric PBPK models suggested that an efficacious dose posed a toxicity risk. These data confirmed the contraindication for children <18 years.

WLB-DSCA method for strictly non-circular signals in coprime array

Widely linear beamforming (WLB) performs better than conventional adaptive beamforming, however its performance is restricted by array geometry. Coprime array can improve the beamforming performance compared with uniform linear array given the number of sensors. In this paper, a WLB with difference-sum co-array (WLB-DSCA) is devised for strictly non-circular (SNC) signals in coprime array. We vectorize the augmented covariance matrix of coprime array to produce a DSCA. To efficiently exploit all information of continuous and discontinuous virtual sensors in DSCA, we introduce the sparse representation of DSCA. A norm minimization optimization problem is formulated and then solved to localize the SNC signals in DSCA. We formulate a joint covariance and pseudo covariance matrices optimization problem to determine the powers of SNC signals. The augmented interference-plus-noise covariance matrix (AINCM) is reconstructed. Lastly, the augmented weight vector of the proposed WLB-DSCA is computed. Numerical results validate that the proposed WLB-DSCA is capable of handling SNC signals in coprime array.

Minimum time connection between non-equilibrium steady states: the Brownian gyrator

Abstract We study the problem of minimising the connection time between non-equilibrium steady states of the Brownian gyrator. This is a paradigmatic model in non-equilibrium statistical mechanics, an overdamped Brownian particle trapped in a two-dimensional elliptical potential, with the two degrees of freedom (x, y) coupled to two, in principle different, thermal baths with temperatures Tx and Ty , respectively. Application of Pontryagin’s Maximum Principle reveals that shortest protocols belong to the boundaries of the control set defined by the limiting values of the parameters (k, u) characterising the elliptical potential. We identify two classes of optimal minimum time protocols, i.e. brachistochrones: (i) regular bang–bang protocols, for which (k, u) alternatively take their minimum and maximum values allowed, and (ii) infinitely degenerate singular protocols. We thoroughly investigate the minimum connection time over the brachistochrones in the limit of having infinite capacity for compression. A plethora of striking phenomena emerge: sets of states attained at null connection times, discontinuities in the connection time along adjacent target states, and the fact that, starting from a state in which the oscillators are coupled, uncoupled states are impossible to reach in a finite time.

Novel Energy-Aware 3D UAV Path Planning and Collision Avoidance Using Receding Horizon and Optimization-Based Control

Unmanned Aerial Vehicles (UAVs) have gained significant popularity in recent years thanks to their agility, mobility, and cost-effectiveness. However, UAV navigation presents several challenges, particularly in path planning, which requires determining an optimal route while avoiding obstacles and adhering to various constraints. Another critical challenge is the limited flight time imposed by the onboard battery. This paper introduces a novel approach for energy-efficient three-dimensional online path planning for UAV formations operating in complex environments. We formulate the path planning problem as a minimization optimization problem, and employ Mixed-Integer Linear Programming (MILP) to achieve optimal solutions. The cost function is designed to minimize energy consumption while considering the inter-collision and intra-collision avoidance constraints within a limited detection range. To achieve this, an optimization approach incorporating Receding Horizon Control (RHC) is applied. The entire path is divided into segments or sub-paths, with constraints used to avoid collisions with obstacles and other members of the fleet. The proposed optimization approach enables fast navigation through dense environments and ensures a collision-free path for all UAVs. A path-smoothing strategy is proposed to further reduce energy consumption caused by sharp turns. The results demonstrate the effectiveness and accuracy of the proposed approach in dense environments with high risk of collision. We compared our proposed approach against recent works, and the results illustrate that the proposed approach outperforms others in terms of UAV formation, number of collisions, and partial path generation time.

A Study on Enhancing Crop Yield Prediction with Accuracy through Machine and Deep Learning Models

Accurate crop yield prediction is essential for optimizing agricultural resource allocation and supporting farmers in making informed crop management decisions. This study investigates the effectiveness of various machine learning and deep learning models for predicting crop yields based on key agricultural parameters, including Nitrogen (N), Phosphorous (P), Potassium (K), temperature, humidity, pH, and rainfall. We apply multiple algorithms—Logistic Regression, Multilayer Perceptron, Sequential Minimal Optimization (SMO), J48, Random Forest, REP Tree, and a proposed deep learning model—to evaluate their predictive accuracy in classifying agricultural items. Each model’s performance is assessed using metrics such as Kappa statistic, Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Relative Absolute Error (RAE), Root Relative Squared Error (RRSE), and the time taken to build the model. Findings reveal that while traditional machine learning models like Random Forest and REP Tree show robust performance, the proposed deep learning model demonstrates enhanced accuracy and efficiency, making it highly promising for crop yield prediction applications. This study underscores the potential of advanced learning algorithms to improve agricultural productivity by providing actionable insights for crop planning and resource management.

Machine learning-driven prediction of EBNA1 inhibitors against Epstein–Barr virus in nasopharyngeal carcinoma

Nasopharyngeal carcinoma (NPC), particularly prevalent in regions such as Malaysia, is a significant health concern often linked to Epstein-Barr virus (EBV) infection. The EBV nuclear antigen 1 (EBNA1), crucial for EBV survival and NPC tumorigenicity, has emerged as a potential therapeutic target for EBV-positive NPC. In this study, we utilized quantitative structure-activity relationship (QSAR) models to predict potential inhibitors of EBNA1. These models were developed based on the molecular fingerprints of known EBNA1 inhibitors, using both classification and regression approaches. Our QSAR classification models demonstrated consistently high precision, recall, F1 score, and accuracy scores across the training set. The top-performing models, constructed using logistic regression algorithms, achieved perfect precision scores of 1.000 in the test set evaluation. These models&amp;rsquo; recall, F1 score, and accuracy scores were 0.571, 0.727, and 0.667, respectively. On the other hand, the best-performing model among the regression models was built using the sequential minimal optimization regression algorithm, achieving a correlation coefficient of 0.703. The mean absolute error and root mean square error of this QSAR regression model were 0.173 and 0.217, respectively, whereas the relative absolute error was 0.689. We screened the enamine advanced compound library using this regression model to predict compounds with potential EBNA1 inhibitory effects. This led to the identification of the top 10 compounds with the most promising predicted EBNA1 inhibitory properties.

Safety Constrained Trajectory Optimization for Completion Time Minimization for UAV Communications

Safety Constrained Trajectory Optimization for Completion Time Minimization for UAV Communications

TD3-based trajectory optimization for energy consumption minimization in UAV-assisted MEC system

Unmanned Aerial Vehicle (UAV) assisted Mobile Edge Computing (MEC) systems provide substantial benefits for task offloading and communication services, especially in situations where traditional communication infrastructure is unavailable. Current research emphasizes maintaining communication quality while minimizing total energy consumption and optimizing UAV flight trajectories. However, several issues remain: First, the energy consumption objective function lacks comprehensiveness, neglecting the impact of UAV flight energy consumption; second, an effective Deep Reinforcement Learning (DRL) algorithm has not been employed to address the non-convexity of the objective function; third, there is insufficient discussion regarding the practical significance of the proposed approach. To address these issues, this paper formulates an objective function aimed at minimizing MEC energy consumption by considering task offloading decisions, communication delays, computational energy consumption, and UAV flight energy consumption. We propose a Population Diversity-based Particle Swarm Optimization-Double Delay Deep Deterministic Policy Gradient (PDPSO-TD3) algorithm to find the optimal solution, enhance UAV flight trajectories through optimized offloading decisions, ensure efficient communication, and minimize the total energy consumption of the MEC system. Furthermore, we discuss the practical applicability of PDPSO-TD3 in detail and present the proposed scheme. Experimental results demonstrate that compared to the Deep Deterministic Policy Gradient (DDPG) algorithm, for transmission delay, MEC energy consumption, UAV flight energy consumption, and User Equipments (UEs) access rate metrics. The proposed PDPSO-TD3 algorithm can improvement the performance by about 14.3%, 10.1%, 6.1%, and 3.3%, respectively.

Chance-constrained bi-level optimal scheduling model for distribution network with thermal controllable load aggregators

An increasing amount of distributed renewable energy is being integrated into distribution networks to achieve decarbonization. It is essential to exploit demand-side flexible resources further to enhance system flexibility in response to the intermittency and unpredictability of renewable energy sources. This paper introduces a polytope-based aggregation method for thermostatically controlled loads (TCLs), aggregating numerous individual TCLs into a unified virtual battery via the aggregator (AGG). This approach avoids the dimensionality curse faced by the distribution system operator when directly controlling each TCL, while efficiently utilizing TCL flexibility. Subsequently, a bi-level optimization model is established, where AGGs are treated as independent stakeholders participating in the distribution network scheduling optimization through the local energy market. This model incorporates chance constraints to address the uncertainty of renewable energy sources. Finally, the distributionally robust chance constraint (DRCC) method is used to convert chance constraints into a linear form, and strong duality theory and Karush–Kuhn–Tucker conditions are applied to transform the bi-level model into a single-level model with equilibrium solutions. Case studies on the IEEE 33-bus network demonstrate that the proposed polytope-based aggregation method substantially improves computational efficiency with minimal optimality loss. Additionally, the DRCC method offers superior economic performance compared to robust and deterministic optimization approaches, while maintaining robustness.

Precision medicine in hepatology: harnessing IoT and machine learning for personalized liver disease stage prediction

&lt;span&gt;In this research, we used a dataset from Siksha ‘O’ Anusandhan (S’O’A) University Medical Laboratory containing 6,780 samples collected manually and through internet of things (IoT) sensor sources from 6,780 patients to perform a thorough investigation into liver disease stage prediction. The dataset was carefully cleaned before being sent to the machine learning pipeline. We utilised a range of machine learning models, such as Naïve Bayes (NB), sequential minimal optimisation (SMO), K-STAR, random forest (RF), and multi-class classification (MCC), using Python to predict the stages of liver disease. The results of our simulations demonstrated how well the SMO model performed in comparison to other models. We then expanded our analysis using different machine learning boosting models with SMO as the base model: adaptive boosting (AdaBoost), gradient boost, extreme gradient boosting (XGBoost), CatBoost, and light gradient boosting model (LightGBM). Surprisingly, gradient boost proved to be the most successful, producing an astounding 96% accuracy. A closer look at the data showed that when AdaBoost was combined with the SMO base model, the accuracy results were 94.10%, XGBoost 90%, CatBoost 92%, and LightGBM 94%. These results highlight the effectiveness of proposed model i.e. gradient boosting in improving the prediction of liver disease stage and provide insightful information for improving clinical decision support systems in the field of medical diagnostics.&lt;/span&gt;

Developing a neural network model to predict the optimal minimum flow rate for effective hole cleaning

The object of the study is effective well cleaning during drilling. The subject of the study is the development of a machine learning model based on a neural network for predicting the optimal minimum drilling fluid flow rate. The challenge is the need to improve well cleaning efficiency to prevent stuck pipes and the associated downtime and costs. During the study, a neural network model was developed and tested to predict the minimum flow rate for cleaning wells. The model was trained and tested on data showing its high accuracy and reliability. The mean square error (MSE) reached 0.019169 for LSTM and 0.0828 for GRU, indicating the accuracy of the predictions. Neural network architectures such as Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) were used to efficiently process time series of data and consider long-term dependencies. The results are explained using advanced neural network architectures and machine learning algorithms, which made it possible to achieve good accuracy of predictions. These architectures enable efficient model training on large amounts of data, allowing complex dependencies and influencing factors to be considered. Distinctive features of the results include good accuracy of predictions and the ability to use the model in real-world conditions. The model demonstrates good performance and reliability in predicting the minimum flow rate. The results of the study can be used to optimize the processes of well drilling. Practical applications include using the model to predict the optimal minimum flow rate in various conditions, which will reduce the risks of stuck pipes and increase the efficiency of drilling operations. The model can be integrated into existing monitoring and control systems for drilling processes to improve their performance

Machine learning-based prediction of single clad characteristics and non-destructive characterization of multi-layer deposited FeCoNiCrMo HEA on EN24 via laser cladding

The prediction of the proper metallurgical bonding and bead morphology in a laser cladding is very crucial to get a best profile of multi-clad layer. This work explores the laser cladding performance of FeCoCrNiMo high entropy alloy (HEA) on EN24 by analyzing the bead morphology with various process parameters. Machine learning (ML) technique is applied for two set of data where feasibility of the metallurgical bond is predicted and tested. From second set of data mainly three ML models, Support vector machine (SVM) radial kernels, K-Nearest neighbor (KNN), and multilayer perceptron (MLP) were applied to predict the outcomes. Sequential Minimal Optimization (SMO) algorithm is applied to identify the proper bonding between the substrate and cladded materials, which is classification-based ML model. The KNN model consistently attained the highest predictive accuracy across all response variables. It achieved perfect R² values and exhibited the lowest error metrics for clad width (w), clad height (h), clad depth (d), heat affected zone (HAZ), and Microhardness, establishing it as the most reliable and accurate model among the three applied ML model. To minimize the HAZ, the best conditions are lower laser powers, higher scanning speeds, and lower powder feed rate which is observed by contour plot. This reduces thermal diffusion into the substrate, maintaining material properties. Also, a non-destructive approach is used to characterize the multi-layer cladded before and after the deposition. The cladding process has significantly altered the microstructural and magnetic properties of the EN24 substrate, resulting in more refined grain structure and increased microhardness in the cladded region.