RESUMEN

Mine water surge is one of the main safety risks in coal mines. This research offers a novel mine water source identification model (BO-CatBoost) to successfully avoid and control mine sudden water catastrophes by properly identifying the sources of mine water. First, the classification model is trained and built using the Categorical Boosting (CatBoost) algorithm. The Gaussian process Bayesian optimization (BO) algorithm is used to optimize parameters, and the optimal parameter combination is integrated into the CatBoost algorithm to build the BO-CatBoost mine water source identification model, which further improves the accuracy of mine water source identification. The model was also applied to the Pingdingshan mine to verify the practicality of the model. Then, 29 groups of unknown water sources in Pingdingshan were selected as validation samples for the model and compared with the conventional CatBoost, Light Gradient Boosting Machine (LightGBM), and Extreme Gradient Boosting (Xgboost) models. The comparison results demonstrate that the accuracy of LightGBM, Xgboost, CatBoost, and BO-CatBoost models can reach 69%, 79.3%, 79.3%, and 100% respectively, and the RMSE is 0.947, 0.643, 0.719, and 0.0 respectively. The comprehensive analysis shows that, when it comes to mine water source detection, the BO-CatBoost model performs noticeably better than other models in terms of discriminative accuracy and generalization capacity. Lastly, the multi-output prediction and decision-making process of the BO-CatBoost water source identification model is visualized by the interpretability analysis performed with the SHAP approach. The research demonstrates that the BO-CatBoost model can more precisely and impartially identify mine water sources, offering fresh concepts for mine water source detection.

Asunto(s)

RESUMEN

This study investigates the prediction of ground loss rate during soft-soil shield tunneling using Peck's back analysis method and XGBoost model. Bayesian optimization is employed to determine optimal hyperparameters, ensuring comprehensive and efficient model tuning. The XGBoost model is compared with Random Forest (RF) and Support Vector Machine (SVM) models to benchmark its performance. The results demonstrate the superior accuracy and robustness of the XGBoost model. Also, the results show that the soil properties and the grouting factors of the excavation face affect the duration of the instantaneous settlement of the ground surface. There is a specific correlation between the depth-to-diameter ratio, the coefficient of variation in the advancing speed of the shield machine, the maximum surface subsidence, and the ground loss rate. The prediction model of the ground loss rate based on the combined approach of Peck back analysis and eXtreme Gradient Boosting and Bayesian optimization has high reliability in soft-soil layers, and this method can provide a specific reference for predicting construction risk in related projects.

RESUMEN

Hydrogel-based sorbents show promise in the removal of toxic metals from water. However, optimizing their performance through conventional trial-and-error methods is both costly and challenging due to the inherent high-dimensional parameter space associated with complex condition combinations. In this study, machine learning (ML) was employed to uncover the relationship between the fabrication condition of hydrogel sorbent and their efficiency in removing toxic metals. The developed XGBoost models demonstrated exceptional accuracy in predicting hydrogel adsorption coefficients (Kd) based on synthesis materials and fabrication conditions. Key factors such as reaction temperature (50-70 °C), time (5-72 h), initiator ((NH4)2S2O8: 2.3-10.3 mol%), and crosslinker (Methylene-Bis-Acrylamide: 1.5-4.3 mol%) significantly influenced Kd. Subsequently, ten hydrogels were fabricated utilizing these optimized feature combinations based on Bayesian optimization, exhibiting superior toxic metal adsorption capabilities that surpassed existing limits (logKd (Cu): increased from 2.70 to 3.06; logKd (Pb): increased from 2.76 to 3.37). Within these determined combinations, the error range (0.025-0.172) between model predictions and experimental validations for logKd (Pb) indicated negligible disparity. Our research outcomes not only offer valuable insights but also provide practical guidance, highlighting the potential for custom-tailored hydrogel designs to combat specific contaminants, courtesy of ML-based Bayesian optimization.

Asunto(s)

RESUMEN

Accurately detecting voltage faults is essential for ensuring the safe and stable operation of energy storage power station systems. To swiftly identify operational faults in energy storage batteries, this study introduces a voltage anomaly prediction method based on a Bayesian optimized (BO)-Informer neural network. Firstly, the temporal characteristics and actual data collected by the battery management system (BMS) are considered to establish a long-term operational dataset for the energy storage station. The Pearson correlation coefficient (PCC) is used to quantify the correlations between these data. Secondly, an Informer neural network with BO hyperparameters is used to build the voltage prediction model. The performance of the proposed model is assessed by comparing it with several state-of-the-art models. With a 1 min sampling interval and one-step prediction, trained on 70% of the available data, the proposed model reduces the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) of the predictions to 9.18 mV, 0.0831 mV, and 6.708 mV, respectively. Furthermore, the influence of different sampling intervals and training set ratios on prediction results is analyzed using actual grid operation data, leading to a dataset that balances efficiency and accuracy. The proposed BO-based method achieves more precise voltage abnormity prediction than the existing methods.

RESUMEN

Establishing a highly reliable and accurate water quality prediction model is critical for effective water environment management. However, enhancing the performance of these predictive models continues to pose challenges, especially in the plain watershed with complex hydraulic conditions. This study aims to evaluate the efficacy of three traditional machine learning models versus three deep learning models in predicting the water quality of plain river networks and to develop a novel hybrid deep learning model to further improve prediction accuracy. The performance of the proposed model was assessed under various input feature sets and data temporal frequencies. The findings indicated that deep learning models outperformed traditional machine learning models in handling complex time series data. Long Short-Term Memory (LSTM) models improved the R2 by approximately 29% and lowered the Root Mean Square Error (RMSE) by about 48.6% on average. The hybrid Bayes-LSTM-GRU (Gated Recurrent Unit) model significantly enhanced prediction accuracy, reducing the average RMSE by 18.1% compared to the single LSTM model. Models trained on feature-selected datasets exhibited superior performance compared to those trained on original datasets. Higher temporal frequencies of input data generally provide more useful information. However, in datasets with numerous abrupt changes, increasing the temporal interval proves beneficial. Overall, the proposed hybrid deep learning model demonstrates an efficient and cost-effective method for improving water quality prediction performance, showing significant potential for application in managing water quality in plain watershed.

RESUMEN

Neural Architecture Search (NAS) outperforms handcrafted Neural Network (NN) design. However, current NAS methods generally use hard-coded search spaces, and predefined hierarchical architectures. As a consequence, adapting them to a new problem can be cumbersome, and it is hard to know which of the NAS algorithm or the predefined hierarchical structure impacts performance the most. To improve flexibility, and be less reliant on expert knowledge, this paper proposes a NAS methodology in which the search space is easily customizable, and allows for full network search. NAS is performed with Gaussian Process (GP)-based Bayesian Optimization (BO) in a continuous architecture embedding space. This embedding is built upon a Wasserstein Autoencoder, regularized by both a Maximum Mean Discrepancy (MMD) penalization and a Fully Input Convex Neural Network (FICNN) latent predictor, trained to infer the parameter count of architectures. This paper first assesses the embedding's suitability for optimization by solving 2 computationally inexpensive problems: minimizing the number of parameters, and maximizing a zero-shot accuracy proxy. Then, two variants of complexity-aware NAS are performed on CIFAR-10 and STL-10, based on two different search spaces, providing competitive NN architectures with limited model sizes.

RESUMEN

Manual identification of tomato leaf diseases is a time-consuming and laborious process that may lead to inaccurate results without professional assistance. Therefore, an automated, early, and precise leaf disease recognition system is essential for farmers to ensure the quality and quantity of tomato production by providing timely interventions to mitigate disease spread. In this study, we have proposed seven robust Bayesian optimized deep hybrid learning models leveraging the synergy between deep learning and machine learning for the automated classification of ten types of tomato leaves (nine diseased and one healthy). We customized the popular Convolutional Neural Network (CNN) algorithm for automatic feature extraction due to its ability to capture spatial hierarchies of features directly from raw data and classical machine learning techniques [Random Forest (RF), XGBoost, GaussianNB (GNB), Support Vector Machines (SVM), Multinomial Logistic Regression (MLR), K-Nearest Neighbor (KNN)], and stacking for classifications. Additionally, the study incorported a Boruta feature filtering layer to capture the statistically significant features. The standard, research-oriented PlantVillage dataset was used for the performance testing, which facilitates benchmarking against prior research and enables meaningful comparisons of classification performance across different approaches. We utilized a variety of statistical classification metrics to demonstrate the robustness of our models. Using the CNN-Stacking model, this study achieved the highest classification performance among the seven hybrid models. On an unseen dataset, this model achieved average precision, recall, f1-score, mcc, and accuracy values of 98.527%, 98.533%, 98.527%, 98.525%, and 98.268%, respectively. Our study requires only 0.174 s of testing time to correctly identify noisy, blurry, and transformed images. This indicates our approach's time efficiency and generalizability in images captured under challenging lighting conditions and with complex backgrounds. Based on the comparative analysis, our approach is superior and computationally inexpensive compared to the existing studies. This work will aid in developing a smartphone app to offer farmers a real-time disease diagnosis tool and management strategies.

Asunto(s)

RESUMEN

We present a full space inverse materials design (FSIMD) approach that fully automates the materials design for target physical properties without the need to provide the atomic composition, chemical stoichiometry, and crystal structure in advance. Here, we used density functional theory reference data to train a universal machine learning potential (UPot) and transfer learning to train a universal bulk modulus model (UBmod). Both UPot and UBmod were able to cover materials systems composed of any element among 42 elements. Interfaced with optimization algorithm and enhanced sampling, the FSIMD approach is applied to find the materials with the largest cohesive energy and the largest bulk modulus, respectively. NaCl-type ZrC was found to be the material with the largest cohesive energy. For bulk modulus, diamond was identified to have the largest value. The FSIMD approach is also applied to design materials with other multi-objective properties with accuracy limited principally by the amount, reliability, and diversity of the training data. The FSIMD approach provides a new way for inverse materials design with other functional properties for practical applications.

RESUMEN

Concentrated solar power (CSP) is one of the few sustainable energy technologies that offers day-to-night energy storage. Recent development of the supercritical carbon dioxide (sCO2) Brayton cycle has made CSP a potentially cost-competitive energy source. However, as CSP plants are most efficient in desert regions, where there is high solar irradiance and low land cost, careful design of a dry cooling system is crucial to make CSP practical. In this work, we present a machine learning system to optimize the factory design and configuration of a dry cooling system for an sCO2 Brayton cycle CSP plant. For this, we develop a physics-based simulation of the cooling properties of an air-cooled heat exchanger. The simulator is able to construct a dry cooling system satisfying a wide variety of power cycle requirements (e.g., 10-100 MW) for any surface air temperature. Using this simulator, we leverage recent results in high-dimensional Bayesian optimization to optimize dry cooler designs that minimize lifetime cost for a given location, reducing this cost by 67% compared to recently proposed designs. Our simulation and optimization framework can increase the development pace of economically-viable sustainable energy generation systems.

RESUMEN

Locally resonant metamaterials (LRMs) have recently emerged in the search for lightweight noise and vibration solutions. These materials have the ability to create stop bands, which arise from the sub-wavelength addition of identical resonators to a host structure and result in strong vibration attenuation. However, their manufacturing inevitably introduces variability such that the system as-manufactured often deviates significantly from the original as-designed. This can reduce attenuation performance, but may also broaden the attenuation band. This work focuses on the impact of variability within tolerance ranges in resonator properties on the vibration attenuation in metamaterial beams. Following a qualitative pre-study, two non-intrusive uncertainty propagation approaches are applied to find the upper and lower bounds of three performance metrics, by evaluating deterministic metamaterial models with uncertain parameters defined as interval variables. A global search approach is used and compared with a machine learning (ML)-based uncertainty propagation approach which significantly reduces the required number of simulations. Variability in resonator stiffnesses and masses is found to have the highest impact. Variability in the resonator positions only has a comparable impact for less deep sub-wavelength designs. The broadening potential of varying resonator properties is exploited in broadband optimization and the robustness of the optimized metamaterial is assessed.This article is part of the theme issue 'Current developments in elastic and acoustic metamaterials science (Part 2)'.

RESUMEN

The prevalence of brain tumor disorders is currently a global issue. In general, radiography, which includes a large number of images, is an efficient method for diagnosing these life-threatening disorders. The biggest issue in this area is that it takes a radiologist a long time and is physically strenuous to look at all the images. As a result, research into developing systems based on machine learning to assist radiologists in diagnosis continues to rise daily. Convolutional neural networks (CNNs), one type of deep learning approach, have been pivotal in achieving state-of-the-art results in several medical imaging applications, including the identification of brain tumors. CNN hyperparameters are typically set manually for segmentation and classification, which might take a while and increase the chance of using suboptimal hyperparameters for both tasks. Bayesian optimization is a useful method for updating the deep CNN's optimal hyperparameters. The CNN network, however, can be considered a "black box" model because of how difficult it is to comprehend the information it stores because of its complexity. Therefore, this problem can be solved by using Explainable Artificial Intelligence (XAI) tools, which provide doctors with a realistic explanation of CNN's assessments. Implementation of deep learning-based systems in real-time diagnosis is still rare. One of the causes could be that these methods don't quantify the Uncertainty in the predictions, which could undermine trust in the AI-based diagnosis of diseases. To be used in real-time medical diagnosis, CNN-based models must be realistic and appealing, and uncertainty needs to be evaluated. So, a novel three-phase strategy is proposed for segmenting and classifying brain tumors. Segmentation of brain tumors using the DeeplabV3+ model is first performed with tuning of hyperparameters using Bayesian optimization. For classification, features from state-of-the-art deep learning models Darknet53 and mobilenetv2 are extracted and fed to SVM for classification, and hyperparameters of SVM are also optimized using a Bayesian approach. The second step is to understand whatever portion of the images CNN uses for feature extraction using XAI algorithms. Using confusion entropy, the Uncertainty of the Bayesian optimized classifier is finally quantified. Based on a Bayesian-optimized deep learning framework, the experimental findings demonstrate that the proposed method outperforms earlier techniques, achieving a 97 % classification accuracy and a 0.98 global accuracy.

Asunto(s)

RESUMEN

In this paper, we propose a Bayesian Optimization (BO)-based strategy using the Gaussian Process (GP) for feature detection of a known but non-cooperative space object by a chaser with a monocular camera and a single-beam LIDAR in a close-proximity operation. Specifically, the objective of the proposed Space Object Chaser-Resident Assessment Feature Tracking (SOCRAFT) algorithm is to determine the camera directional angles so that the maximum number of features within the camera range is detected while the chaser moves in a predefined orbit around the target. For the chaser-object spatial incentive, rewards are assigned to the chaser states from a combined model with two components: feature detection score and sinusoidal reward. To calculate the sinusoidal reward, estimated feature locations are required, which are predicted by Gaussian Process models. Another Gaussian Process model provides the reward distribution, which is then used by the Bayesian Optimization to determine the camera directional angles. Simulations are conducted in both 2D and 3D domains. The results demonstrate that SOCRAFT can generally detect the maximum number of features within the limited camera range and field of view.

RESUMEN

This paper proposes a model-based optimization method for the production of automotive seals in an extrusion process. The high production throughput, coupled with quality constraints and the inherent uncertainty of the process, encourages the search for operating conditions that minimize nonconformities. The main uncertainties arise from the process variability and from the raw material itself. The proposed method, which is based on Bayesian optimization, takes these factors into account and obtains a robust set of process parameters. Due to the high computational cost and complexity of performing detailed simulations, a reduced order model is used to address the optimization. The proposal has been evaluated in a virtual environment, where it has been verified that it is able to minimize the impact of process uncertainties. In particular, it would significantly improve the quality of the product without incurring additional costs, achieving a 50% tighter dimensional tolerance compared to a solution obtained by a deterministic optimization algorithm.

RESUMEN

Hyperparameter optimization (HPO) has been well-developed and evolved into a well-established research topic over the decades. With the success and wide application of deep learning, HPO has garnered increased attention, particularly within the realm of machine learning model training and inference. The primary objective is to mitigate the challenges associated with manual hyperparameter tuning, which can be ad-hoc, reliant on human expertise, and consequently hinders reproducibility while inflating deployment costs. Recognizing the growing significance of HPO, this paper surveyed classical HPO methods, approaches for accelerating the optimization process, HPO in an online setting (dynamic algorithm configuration, DAC), and when there is more than one objective to optimize (multi-objective HPO). Acceleration strategies were categorized into multi-fidelity, bandit-based, and early stopping; DAC algorithms encompassed gradient-based, population-based, and reinforcement learning-based methods; multi-objective HPO can be approached via scalarization, metaheuristics, and model-based algorithms tailored for multi-objective situation. A tabulated overview of popular frameworks and tools for HPO was provided, catering to the interests of practitioners.

RESUMEN

Efforts to enhance the accuracy of protein sequence classification are of utmost importance in driving forward biological analyses and facilitating significant medical advancements. This study presents a cutting-edge model called ProtICNN-BiLSTM, which combines attention-based Improved Convolutional Neural Networks (ICNN) and Bidirectional Long Short-Term Memory (BiLSTM) units seamlessly. Our main goal is to improve the accuracy of protein sequence classification by carefully optimizing performance through Bayesian Optimisation. ProtICNN-BiLSTM combines the power of CNN and BiLSTM architectures to effectively capture local and global protein sequence dependencies. In the proposed model, the ICNN component uses convolutional operations to identify local patterns. Captures long-range associations by analyzing sequence data forward and backwards. In advanced biological studies, Bayesian Optimisation optimizes model hyperparameters for efficiency and robustness. The model was extensively confirmed with PDB-14,189 and other protein data. We found that ProtICNN-BiLSTM outperforms traditional categorization models. Bayesian Optimization's fine-tuning and seamless integration of local and global sequence information make it effective. The precision of ProtICNN-BiLSTM improves comparative protein sequence categorization. The study improves computational bioinformatics for complex biological analysis. Good results from the ProtICNN-BiLSTM model improve protein sequence categorization. This powerful tool could improve medical and biological research. The breakthrough protein sequence classification model is ProtICNN-BiLSTM. Bayesian optimization, ICNN, and BiLSTM analyze biological data accurately.

Asunto(s)

RESUMEN

Human-in-the-loop (HIL) optimization is a control paradigm used for tuning the control parameters of human-interacting devices while accounting for variability among individuals. A limitation of state-of-the-art HIL optimization algorithms such as Bayesian Optimization (BO) is that they assume that the relationship between control parameters and user response does not change over time. BO can be modified to account for the dynamics of the user response by implementing time into the kernel function, a method known as Dynamic Bayesian Optimization (DBO). However, it is unknown if DBO outperforms BO when the human response is characterized by models of human motor learning. In this work, we simulated runs of HIL optimization using BO and DBO towards establishing if DBO is a suitable paradigm for HIL optimization in the presence of motor learning. Simulations were conducted assuming either purely time-dependent participant responses, or assuming that responses would arise from state-space models of motor learning capable of describing both adaptation and use-dependent learning behavior. Statistical comparisons indicated that DBO was never inferior to BO, and, after a certain number of iterations, generally outperformed BO in convergence to optimal inputs and outputs. The number of iterations beyond which DBO was superior to BO occurred earlier when the input-output relationship of the simulated responses was more dynamic. Our results suggest that DBO may improve the performance of HIL optimization over BO when a sufficient number of iterations can be evaluated to accurately distinguish between unstructured variability (noise) and learning.

RESUMEN

This study advances the field of infectious disease forecasting by introducing a novel approach to micro-level contact modeling, leveraging human movement patterns to generate realistic temporal-dynamic networks. Through the incorporation of human mobility models and parameter tuning, this research presents an innovative method for simulating micro-level encounters that closely mirror infection dynamics within confined spaces. Central to our methodology is the application of Bayesian optimization for parameter selection, which refines our models to emulate both the properties of real-world infection curves and the characteristics of network properties. Typically, large-scale epidemiological simulations overlook the specifics of human mobility within confined spaces or rely on overly simplistic models. By focusing on the distinct aspects of infection propagation within specific locations, our approach strengthens the realism of such pandemic simulations. The resulting models shed light on the role of spatial encounters in disease spread and improve the capability to forecast and respond to infectious disease outbreaks. This work not only contributes to the scientific understanding of micro-level transmission patterns but also offers a new perspective on temporal network generation for epidemiological modeling.

RESUMEN

Current research practice for optimizing bioink involves exhaustive experimentation with multi-material composition for determining the printability, shape fidelity and biocompatibility. Predicting bioink properties can be beneficial to the research community but is a challenging task due to the non-Newtonian behavior in complex composition. Existing models such as Cross model become inadequate for predicting the viscosity for heterogeneous composition of bioinks. In this paper, we utilize a machine learning framework to accurately predict the viscosity of heterogeneous bioink compositions, aiming to enhance extrusion-based bioprinting techniques. Utilizing Bayesian optimization (BO), our strategy leverages a limited dataset to inform our model. This is a technique especially useful of the typically sparse data in this domain. Moreover, we have also developed a mask technique that can handle complex constraints, informed by domain expertise, to define the feasible parameter space for the components of the bioink and their interactions. Our proposed method is focused on predicting the intrinsic factor (e.g. viscosity) of the bioink precursor which is tied to the extrinsic property (e.g. cell viability) through the mask function. Through the optimization of the hyperparameter, we strike a balance between exploration of new possibilities and exploitation of known data, a balance crucial for refining our acquisition function. This function then guides the selection of subsequent sampling points within the defined viable space and the process continues until convergence is achieved, indicating that the model has sufficiently explored the parameter space and identified the optimal or near-optimal solutions. Employing this AI-guided BO framework, we have developed, tested, and validated a surrogate model for determining the viscosity of heterogeneous bioink compositions. This data-driven approach significantly reduces the experimental workload required to identify bioink compositions conducive to functional tissue growth. It not only streamlines the process of finding the optimal bioink compositions from a vast array of heterogeneous options but also offers a promising avenue for accelerating advancements in tissue engineering by minimizing the need for extensive experimental trials.

Asunto(s)

RESUMEN

In case of future viral threats, including the proposed Disease X that has been discussed since the emergence of the COVID-19 pandemic in March 2020, our research has focused on the development of antiviral strategies using fragrance compounds with known antiviral activity. Despite the recognized antiviral properties of mixtures of certain fragrance compounds, there has been a lack of a systematic approach to optimize these mixtures. Confronted with the significant combinatorial challenge and the complexity of the compound formulation space, we employed Bayesian optimization, guided by Gaussian Process Regression (GPR), to systematically explore and identify formulations with demonstrable antiviral efficacy. This approach required the transformation of the characteristics of formulations into quantifiable feature values using molecular descriptors, subsequently modeling these data to predict and propose formulations with likely antiviral efficacy enhancements. The predicted formulations underwent experimental testing, resulting in the identification of combinations capable of inactivating 99.99% of viruses, including a notably efficacious formulation of five distinct fragrance types. This model demonstrates high predictive accuracy (coefficient determination Rcv2 > 0.7) and suggests a new frontier in antiviral strategy development. Our findings indicate the powerful potential of computational modeling to surpass human analytical capabilities in the pursuit of complex, fragrance-based antiviral formulations.

RESUMEN

Urban environments, characterized by high population density and intricate infrastructures, are susceptible to a range of emergencies such as fires and traffic accidents. Optimal placement and distribution of fire stations and ambulance centers are thus imperative for safeguarding both life and property. An investigation into the distribution inefficiencies of emergency service facilities in selected districts of Chengdu reveals that imbalanced distribution of these facilities results in suboptimal response times during critical incidents. To address this challenge, a two-stage clustering method, incorporating X-means and K-means algorithms, is employed to identify optimal number and locations for Unmanned Aerial Vehicle (UAV) fire stations and drone ambulance centers. A Mixed-Integer Linear Programming (MILP) model is subsequently constructed and solved using the Gurobi optimization platform. Bayesian optimization-a machine learning technique-is exploited to elucidate the interplay between response speed and service capacity of these UAV-based emergency service stations under an optimized layout. Results affirm that integration of MILP and machine learning provides a robust framework for solving complex problems related to the siting and allocation of emergency service facilities. The proposed hybrid algorithm demonstrates substantial potential for enhancing emergency preparedness and response in urban settings.