Machine Learning Optimization Research Articles

Explainable machine-learning optimization of h-BN nanosheets with surface defects for enhanced hydrophobicity

Explainable machine-learning optimization of h-BN nanosheets with surface defects for enhanced hydrophobicity

Innovations in animal health: artificial intelligence-enhanced hematocrit analysis for rapid anemia detection in small ruminants

Due to their value as a food source, fiber, and other products globally, there has been a growing focus on the wellbeing and health of small ruminants, particularly in relation to anemia induced by blood-feeding gastrointestinal parasites like Haemonchus contortus. The objective of this study was to assess the packed cell volume (PCV) levels in blood samples from small ruminants, specifically goats, and create an efficient biosensor for more convenient, yet accurate detection of anemia for on-farm use in agricultural environments for animal production optimization. The study encompassed 75 adult male Spanish goats, which underwent PCV testing to ascertain their PCV ranges and their association with anemic conditions. Using artificial intelligence-powered machine learning algorithms, an advanced, easy-to-use sensor was developed for rapidly alerting farmers as to low red blood cell count of their animals in this way to enable timely medical intervention. The developed sensor utilizes a semi-invasive technique that requires only a small blood sample. More precisely, a volume of 30 μL of blood was placed onto Whatman filter paper No. 1, previously soaked with anhydrous glycerol. The blood dispersion pattern on the glycerol-infused paper was then recorded using a smartphone after 180 s. Subsequently, these images were examined in correlation with established PCV values obtained from conventional PCV analysis. Four separate machine learning models (ML) supported models, namely support vector machine (SVM), K-nearest neighbors (KNN), backpropagation neural network (BPNN), and image classification-based Keras model, were created and assessed using the image dataset. The dataset consisted of 1,054 images that were divided into training, testing, and validation sets in a 70:20:10 ratio. The initial findings indicated a detection accuracy of 76.06% after only 10 epochs for recognizing different levels of PCV in relation to anemia, ranging from healthy to severely anemic. This testing accuracy increased markedly, to 95.8% after 100 epochs and other model parameter optimization. Results for SVM had an overall F1 score of 74–100% in identifying the PCV range for blood pattern images representing healthy to severely anemic animals, and BPNN showed 91–100% accuracy in identifying the PCV range for anemia detection. This work demonstrates that AI-driven biosensors can be used for on-site rapid anemia detection. Optimized machine learning models maximize detection accuracy, proving the sensor’s validity and rapidity in assessing anemia levels. This breakthrough will allow farmers, with rapid results, to increase animal wellbeing and agricultural productivity.

Design and Optimization of a Graphene-Enhanced Terahertz Metasurfaces Surface Plasmon Resonance Biosensor for High-Sensitivity Peptide Detection with Machine Learning Optimization Based on XGBoost Regressor

Design and Optimization of a Graphene-Enhanced Terahertz Metasurfaces Surface Plasmon Resonance Biosensor for High-Sensitivity Peptide Detection with Machine Learning Optimization Based on XGBoost Regressor

Graphene-Enabled Multiresonator Metasurfaces for Ultrasensitive Surface Plasmon Resonance Detection of Waterborne Bacteria Across Multiple Frequencies with Machine Learning Optimization

Graphene-Enabled Multiresonator Metasurfaces for Ultrasensitive Surface Plasmon Resonance Detection of Waterborne Bacteria Across Multiple Frequencies with Machine Learning Optimization

Retraction Note: Optical bio sensor based cancer cell detection using optimized machine learning model with quantum computing

Retraction Note: Optical bio sensor based cancer cell detection using optimized machine learning model with quantum computing

Ordered assemblies of peptide nanoparticles with only positive charge

Surface charge patchiness of different charge types can influence the solution behaviours of colloidal particles and globular proteins. Herein, coiled-coil ‘bundlemer’ nanoparticles that display only a single type of surface charge (SC) are computationally designed to compare their solution behaviours to mixed charge-type (MC) counterparts with both positively and negatively charged side chains. Nematic and columnar liquid crystal phases are discovered in low concentrations of SC particles, indicative of particle end-to-end stacking into columns combined with lateral electrostatic repulsion between columns, while MC particles with the same net charge and particle shape produced only amorphous, soluble aggregates. Similarly, porous lattices are formed in mixtures of SC/MC particles of opposite charges while MC/MC mixtures of opposite charges produce only amorphous aggregates. The lattice structure is inferred with a machine learning optimization approach. The differences between SC and MC particle behaviours directly show the importance of surface electrostatic patchiness.

Fast and Accurate Evacuation Planning Algorithm with Bayesian Optimization

In this work, we propose a method for generating an evacuation plan at a high speed to realize safe and swift evacuation in the event of a large-scale disaster such as an earthquake and its accompanying tsunami. Existing conventional methods have several problems. Simulation-based methods that use agents and methods that use existing time expansion networks have high computational costs, which makes it difficult for evacuation routes to be immediately changed according to the effects of disasters such as collapsed buildings and roads. Although heuristics with reduced calculation costs are also being researched, they may result in very long evacuation completion times and cannot generate optimal evacuation plans. We guarantee the optimal solution by reducing the number of maximum flow problem calculations, which constitute the bottleneck for methods using the existing time expansion network, through the use of the Bayesian optimization machine learning method. This reduces the calculation cost of the entire algorithm. The performance of our method is evaluated from the two viewpoints of the evacuation completion time, which indicates the quality of the evacuation plan, and the time required for the generation by the solution of the algorithm in computer experiments under multiple scenarios. In addition, the impact of the number of evacuees and the locations of the sinks are analyzed. We show that our method can quickly generate an optimal evacuation plan.

High‐Gain Triple‐Band T‐Shaped Dielectric Resonator Based Hybrid Two‐Element MIMO Antenna for 5G New Radio, Wi‐Fi 6, V2X, and C‐Band Applications With a Machine Learning Approach

ABSTRACTIn this article, a rectangular dielectric resonator (DR) based multiple input multiple output (MIMO) hybrid antenna with a machine learning (ML) optimization approach for 5G New Radio (NR), WiMAX, WLAN, Wi‐Fi 6, Vehicle to Everything (V2X), and C‐band uplink applications are presented. The proposed antenna provides a triple band. It covers n1, n2, and n39 5G NR at a lower frequency (1.59–2.26 GHz), n48 5G NR at the middle frequency (3.1–3.87 GHz), and n46, n47, n96, WiMAX, WLAN, and C‐band uplink at higher frequency (5.25–6.91 GHz). It achieved more than 20% impedance bandwidth and 20 dB isolation in all frequency bands. The maximum gain of the proposed antenna is 15 dBi. The calculated MIMO parameters are within the accepted range. It is optimized through various ML algorithms, including random forest (RF), K‐nearest neighbor (KNN), artificial neural network (ANN), extreme gradient boosting (XGB) and decision tree (DT). The RF ML algorithm gives 98.09% accuracy compared to other ML algorithms for S parameter prediction.

Scale Production of a Stretchable Fiber Triboelectric Nanogenerator in Customizable Textile for Human Motion Recognition.

Although the fiber-based triboelectric nanogenerator (F-TENG) has been recognized as one of the most promising flexible sensor systems, it is facing a challenge of balancing the performance and the processing scalability. Herein, we develop a hierarchical coaxial F-TENG possessing PU layer, Ag layer, and PA layer from the core to the outer part by an efficient and straightforward two-step braiding method. Owning a small diameter of 1 mm, the F-TENG presents a high linear sensing response, a wide working range of 5 to 150 kPa, and a quick reaction speed of around 200 ms. In addition, it shows high flexibility, cyclic washability, and superior mechanical stability. Furthermore, customizable textiles (e.g., wrist support and socks) that conform perfectly to the human body have been knitted from the F-TENGs as warps or wefts, which are able to monitor human motion signals. Together with an optimized machine learning algorithm, five human motions (stand, slow walk, normal walk, run, and jump) can be analyzed with a precision of up to 99%. In short, this work presents a scalable approach to develop customizable self-powered sensing textiles, offering an excellent wearable digital platform/system for potential motion capture/monitoring, identification, and smart-sports-related applications.

Audio-Based Engine Fault Diagnosis with Wavelet, Markov Blanket, ROCKET, and Optimized Machine Learning Classifiers.

Engine fault diagnosis is a critical task in automotive aftermarket management. Developing appropriate fault-labeled datasets can be challenging due to nonlinearity variations and divergence in feature distribution among different engine kinds or operating scenarios. To solve this task, this study experimentally measures audio emission signals from compression ignition engines in different vehicles, simulating injector failures, intake hose failures, and absence of failures. Based on these faults, a hybrid approach is applied to classify different conditions that help the planning and decision-making of the automobile industry. The proposed hybrid approach combines the wavelet packet transform (WPT), Markov blanket feature selection, random convolutional kernel transform (ROCKET), tree-structured Parzen estimator (TPE) for hyperparameters tuning, and ten machine learning (ML) classifiers, such as ridge regression, quadratic discriminant analysis (QDA), naive Bayes, k-nearest neighbors (k-NN), support vector machine (SVM), multilayer perceptron (MLP), random forest (RF), extra trees (ET), gradient boosting machine (GBM), and LightGBM. The audio data are broken down into sub-time series with various frequencies and resolutions using the WPT. These data are subsequently utilized as input for obtaining an informative feature subset using a Markov blanket-based selection method. This feature subset is then fed into the ROCKET method, which is paired with ML classifiers, and tuned using Optuna using the TPE approach. The generalization performance applying the proposed hybrid approach outperforms other standard ML classifiers.

A novel state of health estimation model for lithium-ion batteries incorporating signal processing and optimized machine learning methods

A novel state of health estimation model for lithium-ion batteries incorporating signal processing and optimized machine learning methods

Model‐Driven Manufacturing of High‐Energy‐Density Batteries: A Review

AbstractThe rapid advancement in energy storage technologies, particularly high‐energy density batteries, is pivotal for diverse applications ranging from portable electronics to electric vehicles and grid storage. This review paper provides a comprehensive analysis of the recent progress in model‐driven manufacturing approaches for high‐energy‐density batteries, highlighting the integration of computational models and simulations with experimental manufacturing processes to optimize performance, reliability, safety, and cost‐effectiveness. We systematically examine various modeling techniques, including electrochemical, thermal, and mechanical models, and their roles in elucidating the complex interplay of materials, design, and manufacturing parameters. The review also discusses the challenges and opportunities in scaling up these model‐driven approaches, addressing key issues such as model validation, parameter sensitivity, and the integration of machine learning and artificial intelligence for predictive modeling, process optimization, and quality assurance. By synthesizing current research findings and industry practices, this paper aims to outline a roadmap for future developments in model‐driven manufacturing of high‐energy density batteries, emphasizing the need for interdisciplinary collaboration and innovation to meet the increasing demands for energy storage solutions.

The potential role of abandoned cropland for food security in China

The widespread abandonment of croplands poses a severe threat to China's food security. However, the existing knowledge regarding the potential for recultivating abandoned croplands is limited. Previous studies have generally overestimated this potential due to inadequate assessments of their suitability for recultivation. In the present study, an optimized machine learning approach was introduced to assess, for the first time, the suitability of abandoned croplands for recultivation in China. In 2022, the total abandoned croplands in China covered 31.2 million hectares, of which 82.54 % was deemed suitable for recultivation. Recultivating abandoned croplands in China could substantially enhance food security, potentially yielding around 162 million tons annually. Moreover, crop switching can further increase the yield rate by up to 24.95 % or energy supply by up to 43.14 %. The present study offers valuable insights to policymakers in determining cropping strategies, establishing strategic grain reserves, and managing international food trade.

Benchmarking Digital Quantum Simulations Above Hundreds of Qubits Using Quantum Critical Dynamics

The real-time simulation of large many-body quantum systems is a formidable task, that may only be achievable with a genuine quantum computational platform. Currently, quantum hardware with a number of qubits sufficient to make classical emulation challenging is available. This condition is necessary for the pursuit of a so-called quantum advantage, but it also makes verifying the results very difficult. In this paper, we flip the perspective and utilize known theoretical results about many-body quantum critical dynamics to qualitatively benchmark digital quantum hardware and various error mitigation techniques. In particular, we benchmark against known universal scaling laws in the Hamiltonian simulation of a time-dependent transverse-field Ising Hamiltonian of up to 133 qubits. Incorporating only basic error mitigation and suppression methods, our study shows reliable control up to a two-qubit gate depth of 28, featuring a maximum of 1396 two-qubit gates, before noise becomes prevalent. These results are transferable to applications such as Hamiltonian simulation, variational algorithms, optimization, or quantum machine learning. We demonstrate this on the example of digitized quantum annealing for optimization and identify an optimal working point in terms of both circuit depth and time step on a 133-site optimization problem. Published by the American Physical Society 2024

Multi-Objective Optimization for Controlling Conflicts in Roadway Surrounding Rock Induced by Floor Stress-Relief Groove

This paper studies the effectiveness of the stress-relief groove on the floor of deep coal roadway and determines the influence of the stress-relief groove parameters on the surrounding rock through qualitative analysis. Based on the displacement conflict problem, evaluation indicators were established, and the optimal solution set was obtained. The innovations of this research include: 1. For geotechnical numerical simulations, novel stress monitoring and plastic zone monitoring techniques have been introduced to accurately reflect the condition of the surrounding rock; 2. The effects of floor relief grooves in deep roadway on surrounding rock have been analyzed, and the advantages and utilities of central and corner relief grooves have been determined; 3. The usability of small datasets has been enhanced by applying SEGA to optimize machine learning models with data augmentation techniques; 4. Multi-objective optimization algorithms have been applied to geotechnical engineering, providing valuable references for decision making. The results demonstrate that multi-objective optimization can significantly enhance the effectiveness of surrounding rock control, resolve conflicts, and achieve more reasonable construction plans. This research provides new theoretical foundations and practical guidance for deep mine roadway-surrounding rock control.

Optimized Machine Learning Algorithms for Predicting the Punching Shear Resistance of Flat Slabs with Transverse Reinforcement

In the calculation of reinforced concrete (RC) flat slabs with transverse reinforcement, punching shear resistance is one of the most critical factors. It is true that design provisions may be implemented, but they often result in significant biases and deviations from expectations. This study aims to present an optimized machine learning (ML) algorithm for estimating the punching shear resistance. Four machine learning (ML) algorithms (SVR, DT, RF, and XGBoost) with Bayesian optimization (BO) are presented in this paper to provide accurate predictions for flat slabs. The adoptability and optimization of the models are achieved through the analysis of a database of 337 test specimens with nine design parameters. Machine learning (ML) techniques are used to estimate punching shear resistance, which is compared with design provisions and equations relating to critical shear crack theory (CSCT). According to this study, Bayesian optimization is still capable of improving the performance of conventional machine learning algorithms, while the XGBoost-based model offers advanced capabilities. Predictions based on BO-XGBoost are in good agreement with actual values (MAE, RMSE, and R2 are 0.09 MN, 0.14 MN, and 0.92, respectively) in test set. Following a detailed explanation using Shapley additive explanation (SHAP), a high-performance ML approach is used to investigate the predictive results. With the proposed optimized algorithms, it is possible to determine the punching shear resistance of flat slabs with transverse reinforcement during the preliminary stages of the construction.

Enhancing pricing strategies in the aftermarket sector with machine learning

PurposeThis research explores the application of machine learning to optimize pricing strategies in the aftermarket sector, particularly focusing on parts with no assigned values and the detection of outliers. The study emphasizes the need to incorporate technical features to improve pricing accuracy and decision-making.Design/methodology/approachThe methodology involves data collection from web scraping and backend sources, followed by data preprocessing, feature engineering and model selection to capture the technical attributes of parts. A Random Forest Regressor model is chosen and trained to predict prices, achieving a 76.14% accuracy rate.FindingsThe model demonstrates accurate price prediction for parts with no assigned values while remaining within an acceptable price range. Additionally, outliers representing extreme pricing scenarios are successfully identified and predicted within the acceptable range.Originality/valueThis research bridges the gap between industry practice and academic research by demonstrating the effectiveness of machine learning for aftermarket pricing optimization. It offers an approach to address the challenges of pricing parts without assigned values and identifying outliers, potentially leading to increased revenue, sharper pricing tactics and a competitive advantage for aftermarket companies.

Terahertz metasurface biosensor for high-sensitivity salinity detection and data encoding with machine learning optimization based on random forest regression

Terahertz metasurface biosensor for high-sensitivity salinity detection and data encoding with machine learning optimization based on random forest regression

Stacking Ensemble Technique Using Optimized Machine Learning Models with Boruta–XGBoost Feature Selection for Landslide Susceptibility Mapping: A Case of Kermanshah Province, Iran

Landslides cause significant human and financial losses in different regions of the world. A high-accuracy landslide susceptibility map (LSM) is required to reduce the adverse effects of landslides. Machine learning (ML) is a robust tool for LSM creation. ML models require large amounts of data to predict landslides accurately. This study has developed a stacking ensemble technique based on ML and optimization to enhance the accuracy of an LSM while considering small datasets. The Boruta–XGBoost feature selection was used to determine the optimal combination of features. Then, an intelligent and accurate analysis was performed to prepare the LSM using a dynamic and hybrid approach based on the Adaptive Fuzzy Inference System (ANFIS), Extreme Learning Machine (ELM), Support Vector Regression (SVR), and new optimization algorithms (Ladybug Beetle Optimization [LBO] and Electric Eel Foraging Optimization [EEFO]). After model optimization, a stacking ensemble learning technique was used to weight the models and combine the model outputs to increase the accuracy and reliability of the LSM. The weight combinations of the models were optimized using LBO and EEFO. The Root Mean Square Error (RMSE) and Area Under the Receiver Operating Characteristic Curve (AUC-ROC) parameters were used to assess the performance of these models. A landslide dataset from Kermanshah province, Iran, and 17 influencing factors were used to evaluate the proposed approach. Landslide inventory was 116 points, and the combined Voronoi and entropy method was applied for non-landslide point sampling. The results showed higher accuracy from the stacking ensemble technique with EEFO and LBO algorithms with AUC-ROC values of 94.81% and 94.84% and RMSE values of 0.3146 and 0.3142, respectively. The proposed approach can help managers and planners prepare accurate and reliable LSMs and, as a result, reduce the human and financial losses associated with landslide events.

Evaluation of Distributed Power and Electric Vehicle Grid-connected Carrying Capacity Based on Genetic Algorithm Optimisation Neural Network

Abstract The integration of new types of loads, such as large electric vehicles (EVs) and distributed energy sources, and the conventional structure and operation of the power distribution network have been significantly transformed. This presents a significant challenge in maintaining the network’s capacity to handle the load. To address this challenge, a carrying capacity assessment method based on a machine learning model optimized by a bionic optimization algorithm is proposed. Firstly, the assessment model’s index system is established, and the distribution network data are collected and preprocessed. Secondly, considering the complexity of the distribution network carrying capacity assessment, a backpropagation (BP) neural network is constructed within the machine learning model. The genetic algorithm, inspired by biological optimization, is used to fine-tune the machine learning model’s parameters. Subsequently, the model’s accuracy and generalization capability are evaluated, and the optimized machine learning model is used to assess the carrying capacity of EVs and distributed power sources. The results of the carrying capacity assessment can provide an effective basis for subsequent power distribution network planning. This method combines the benefits of machine learning with bionic optimization algorithms to tackle the challenges associated with incorporating new load types into the power distribution network. The model’s ability to accurately assess the carrying capacity can support effective planning and management of the evolving distribution network.