Improve Model Accuracy Research Articles

FDP-FL: differentially private federated learning with flexible privacy budget allocation

Abstract Federated learning (FL) as a privacy-preserving technology enables multiple clients to collaboratively train models on decentralized data. However, transmitting model parameters between local clients and the central server can potentially result in information leakage. Differentially private federated learning (DPFL) has emerged as a promising solution to enhance privacy. Nevertheless, existing DPFL schemes suffer from two issues: (i) most schemes that aim to achieve desired model accuracy may incur a high privacy budget. (ii) several schemes that consider the trade-off between privacy and accuracy by utilizing linear clipping bound may distort numerous model parameters. In this paper, we first propose FDP-FL, a flexible differential privacy approach for FL. FDP-FL introduces a novel series sum privacy budget allocation instead of uniform allocation and enables adaptive and nonlinear noise scale decay. In this way, a tight bound for cumulative privacy loss can be achieved while optimizing model accuracy. Then in order to mitigate gradient leakages caused by honest-but-curious clients and server, we further design client-level FDP-FL and record-level FDP-FL, respectively. Experimental results demonstrate that our FDP-FL improves model accuracy by $\sim $13.3% compared with the basic DP-FL under a fixed privacy budget and outperforms existing trade-off schemes with the same hyperparameter setting.

A novel hybrid genetic algorithm and Nelder-Mead approach and it’s application for parameter estimation

Background Traditional optimization methods often struggle to balance global exploration and local refinement, particularly in complex real-world problems. To address this challenge, we introduce a novel hybrid optimization strategy that integrates the Nelder-Mead (NM) technique and the Genetic Algorithm (GA), named the Genetic and Nelder-Mead Algorithm (GANMA). This hybrid approach aims to enhance performance across various benchmark functions and parameter estimation tasks. Methods GANMA combines the global search capabilities of GA with the local refinement strength of NM. It is first tested on 15 benchmark functions commonly used to evaluate optimization strategies. The effectiveness of GANMA is also demonstrated through its application to parameter estimation problems, showcasing its practical utility in real-world scenarios. Results GANMA outperforms traditional optimization methods in terms of robustness, convergence speed, and solution quality. The hybrid algorithm excels across different function landscapes, including those with high dimensionality and multimodality, which are often encountered in real-world optimization issues. Additionally, GANMA improves model accuracy and interpretability in parameter estimation tasks, enhancing both model fitting and prediction. Conclusions GANMA proves to be a flexible and powerful optimization method suitable for both benchmark optimization and real-world parameter estimation challenges. Its capability to efficiently explore parameter spaces and refine solutions makes it a promising tool for scientific, engineering, and economic applications. GANMA offers a valuable solution for improving model performance and effectively handling complex optimization problems.

Initial evaluation of a personalized advantage index to determine which individuals may benefit from mindfulness-based cognitive therapy for suicide prevention

ObjectiveDevelop and evaluate a treatment matching algorithm to predict differential treatment response to Mindfulness-Based Cognitive Therapy for suicide prevention (MBCT-S) versus enhanced treatment-as-usual (eTAU). MethodsAnalyses used data from Veterans at high-risk for suicide assigned to either MBCT-S (n = 71) or eTAU (n = 69) in a randomized clinical trial. Potential predictors (n = 55) included available demographic, clinical, and neurocognitive variables. Random forest models were used to predict risk of suicidal event (suicidal behaviors, or ideation resulting in hospitalization or emergency department visit) within 12 months following randomization, characterize the prediction, and develop a Personalized Advantage Index (PAI). ResultsA slightly better prediction model emerged for MBCT-S (AUC = 0.70) than eTAU (AUC = 0.63). Important outcome predictors for participants in the MBCT-S arm included PTSD diagnosis, decisional efficiency on a neurocognitive task (Go/No-Go), prior-year mental health residential treatment, and non-suicidal self-injury. Significant predictors for participants in the eTAU arm included past-year acute psychiatric hospitalizations, past-year outpatient psychotherapy visits, past-year suicidal ideation severity, and attentional control (indexed by Stroop task). A moderation analysis showed that fewer suicidal events occurred among those randomized to their PAI-indicated optimal treatment. ConclusionsPAI-guided treatment assignment may enhance suicide prevention outcomes. However, prior to real-world application, additional research is required to improve model accuracy and evaluate model generalization.

Modeling the Optimal Distance Between Pipes in a Solar Water Heating Collector

This study proposes a mathematical model based on normal distribution to determine the optimal distance between pipes in a solar water heating collector. The model takes into account key system parameters such as material thermal conductivity, heat losses, and solar radiation intensity. Experimental data collected for model validation confirm its accuracy and adequacy. The main results show that the maximum efficiency (η) of the solar water heating collector is achieved at a pipe spacing of approximately 0.0469 m. The analytical method demonstrates a smooth decrease in efficiency when deviating from the optimal distance, whereas the experimental data indicate a high sensitivity of the system to changes in this parameter. Thus, the proposed model is a useful tool for designers, allowing for precise prediction of optimal system parameters and increased efficiency. Further research and experiments are planned to improve model accuracy and expand its applicability.

Deep learning-based sow posture classifier using colour and depth images

Assessing sow posture is essential for understanding their physiological condition and helping farmers improve herd productivity. Deep learning-based techniques have proven effective for image interpretation, offering a better alternative to traditional image processing methods. However, distinguishing transitional postures such as sitting and kneeling is challenging with only conventional top-view RGB images. This study aimed to develop and compare different deep learning-based sow posture classifiers using different architectures and image types. Using Kinect v.2 cameras, RGB and depth images were collected from 9 sows housed individually in farrowing crates. A total of 26,362 images were manually labelled by posture: “standing”, “kneeling”, “sitting”, “ventral recumbency” and “lateral recumbency”. Different deep learning algorithms were developed to detect sow postures from three types of images: colour (RGB), depth (depth image transformed into greyscale), and fused (colour-depth composite images). Results indicated that the ResNet-18 model presented the best results and that including depth information improved the performance of all models tested. Depth and fused models achieved higher accuracies than the models using only RGB images. The best model used only depth images as input and presented an accuracy of 98.3 %. The mean precision and recall values were 97.04 % and 97.32 %, respectively (F1-score = 97.2 %). The study shows improved posture classification using depth images. Future research can improve model accuracy and speed by expanding the database, exploring fused methods and computational models, considering different breeds of sows, and incorporating more postures. These models can be integrated into computer vision systems to automatically characterise sow behavior.

Optimization of machine learning model training procedure on multi-gpu systems to enhance cyber security in telecommunication networks

This paper analyzes the optimization features of machine learning (ML) model training procedures using multi-GPU systems to enhance cyber security in telecommunication networks. A key aspect of the study is the use of data parallelism, which allows the distribution of the training load across multiple GPUs, significantly reducing training time and improving model accuracy-critical factors for rapid threat detection in cyberspace. A novel approach for optimizing data batch size using Mutual Information (MI) is proposed, which harmonizes the utilization of computational resources with the information content of the training data. MI helps to determine the optimal data batch size that minimizes training errors and improves model accuracy without a significant increase in training time. Experimental results demonstrate the substantial advantages of multi-GPU configurations compared to single-GPU setups, providing faster training and improved model accuracy. It was particularly emphasized that MI-guided batch size tuning significantly outperforms traditional manual tuning methods, ensuring higher validation accuracy and reducing training time. The study showed that the MI-based approach is an effective tool for addressing the problem of optimizing ML model training processes in real-world scenarios where cyber security is critical. The proposed methods allow ML models to train faster and more accurately identify potential threats, making them particularly relevant for telecommunication networks where a rapid response to new threats in real time is required. The implementation of modern computational technologies such as multi-GPU systems and MI-optimized training enhances the efficiency and accuracy of machine learning models. This, in turn, improves cyber security measures and ensures a more reliable defence of telecommunication networks against malicious attacks. It is noted that the proposed approaches can be adapted not only for cyber security but also for other areas where high model accuracy and fast training are important. Future research prospects include the development of new machine learning methods, particularly deep neural networks, the exploration of alternative computational architectures such as quantum computing or distributed systems, and their integration into real-time systems. Special attention should be paid to the ethical aspects of implementing automated cyber security systems, particularly in preventing bias in algorithms and ensuring fairness in their application.

A hybrid BOA-SVR approach for predicting aerobic organic and nitrogen removal in a gas-liquid-solid circulating fluidized bed bioreactor

This study introduces the hybrid of the Bayesian optimization algorithm and support vector regression (BOA-SVR) models to predict the removal of aerobic organic (total chemical oxygen demand, COD) and nitrogen compounds such as total Kjeldahl Nitrogen (TKN), ammonium nitrogen (NH4-N), and nitrate nitrogen (NO3-N) from municipal wastewater in a gas-liquid-solid circulating fluidized bed (GLSCFB) bioreactor. GLSCFB bioreactors treat wastewater by removing nutrients biologically. The downer of a GLSCFB bioreactor provided experimental data on TKN, NH4-N, NO3-N, and TCOD removal. The hybrid optimal intelligence algorithm (BOA-SVR) has improved model accuracy across multiple domains by combining BOA and SVR. The coefficient of determination (R2), residual, mean absolute error (MAE), root mean square error (RMSE), and fractional bias (FB) were used to analyze BOA-SVR model performance. The models match experimental data from four operational stages well, with R2 or adj R2 values above 0.99 for all responses. The model's accuracy was confirmed by relative deviations and residual plots showing dispersion around the zero-reference line. The BOA-SVR model consistently predicted dependent variables with low RMSE and MAE values (≤ 2.24 and 2.21, respectively) and near-zero FB. Computing efficiency was shown by optimizing TCOD, TKN, NH4-N, and NO3-N models in 70.61, 72.89, 74.37, and 54.07 s. A rigorous test on unseen data with different noise levels confirmed the model's stability. Furthermore, BOA-SVR performs better than traditional multiple linear regression (MLR). Overall, the BOA-SVR model predicts biological nutrient removal in municipal wastewater utilizing a GLSCFB bioreactor quickly, correctly, and efficiently, reducing experimental stress and resource use.

A Deep Learning Architectures for Kidney Disease Classification

Deep learning has become an extremely powerful tool for complex tasks such as image classification and segmentation. The medical industry often lacks high-quality, balanced datasets, which can be a challenge for deep learning algorithms that need sufficiently large amounts of data to train and increase their performance. This is especially important in the context of kidney issues such as for stones, cysts and tumors. We used deep learning models for this study to classify or detect several types of kidney diseases. We use different classification models, such as VGG-19, (CNNs) Convolutional Neural Networks, ResNet- 101, VGG-16, ResNet-50, and DenseNet-169, which can be enhanced through techniques such as classification, segmentation, and transfer learning. These algorithms can help improve model accuracy by allowing them to learn from multiple datasets. This technique has the potential to revolutionize the diagnosis and treatment of kidney problems as it enables more accurate and effective classification of CT-scan images. This may ultimately lead to better patient outcomes and improved overall health outcomes. INDEX TERMS Kidney disease, deep learning, image classification, convolutional neural networks (CNNs), segmentation, transfer learning, CT-scan images.

CSRM‐1.0: A China Seismological Reference Model

AbstractHigh‐resolution seismic model is crucial for advancing our understandings on geological processes and enhancing seismic hazard mitigation programs. We construct a high‐resolution China Seismological Reference Model (CSRM‐1.0) in the top 100 km of the crust and uppermost mantle in continental China following a top‐down construction process. The employed seismic constraints include P‐wave polarization angle from tele‐seismic event, short‐period Rayleigh wave ellipticity from ambient noise, long‐period Rayleigh wave ellipticity from earthquake data, receiver function, empirical Green's function from ambient noise, Rayleigh wave phase/group velocity dispersion curves from regional earthquakes, and Pn‐wave travel time extracted from seismic data of 4,435 stations. CSRM‐1.0 has a spatial crustal resolution of ∼60 km beneath the north‐south seismic belt and trans‐North China orogen regions and ∼120 km beneath the rest of continental China, and a spatial mantle resolution of ∼300 km. CSRM‐1.0 exhibits prominent velocity heterogeneities in the crust and uppermost mantle and an eastward thinning of the crust, geographically correlating with geological settings. CSRM‐1.0 improvements include accurate estimation of shallow seismic structure, increased spatial resolution and improved model accuracy. Crustal composition inferred from CSRM‐1.0 exhibits a general transition from a felsic upper crust to a mafic lower crust. Mafic rocks in the lower crust are found predominantly along inter‐block boundaries and sporadically within the interiors of blocks, likely resulted from preferential inter‐block intrusions of magmas related to various oceanic plate subductions and the Emeishan mantle plume. This study contributes seismic constraints and CSRM‐1.0 to the CSRM product center (http://chinageorefmodel.org) as a backbone open‐access geophysical cyberinfrastructure.

Improving Discharge Predictions in Ungauged Basins: Harnessing the Power of Disaggregated Data Modeling and Machine Learning

AbstractCurrent machine learning methods for discharge prediction often employ aggregated basin‐wide hydrometeorological data (lumped modeling) for parametric and non‐parametric training. This approach may overlook the spatial heterogeneity of river systems and their impact on discharge patterns. We hypothesize that integrating spatiotemporal hydrologic knowledge into the data modeling process (distributed/disaggregated modeling) can improve the performance of discharge prediction models. To test this hypothesis, we designed experiments comparing the performance of identical Long Short‐Term Memory Recurrent Neural Network (LSTM‐RNN) models forced with either lumped or distributed features. We gather meteorological forcing and static attributes for the Mackenzie basin in Canada‐ a large and unique basin. Importantly, discharge performance is assessed out‐of‐sample with k‐fold replication across gauges. Training LSTMs with disaggregated data significantly improved model accuracy. Specifically, there was a 9.6% increase in the mean Nash‐Sutcliffe Efficiency and a 4.6% increase in the mean Kling‐Gupta Efficiency, indicating a better agreement between predicted and actual observations in terms of mean, variability, and correlation. These experiments and results demonstrate the importance of integrating topologically guided geomorphologic and hydrologic information (distributed modeling) in data‐driven discharge predictions.

Hyper parameter Optimization in CNNs for EEG Analysis

Electroencephalography (EEG) is a crucial tool for assessing brain activity and diagnosing neurological disorders. The application of Convolutional Neural Networks (CNNs) in EEG analysis has shown promising results due to their ability to automatically learn and extract relevant features from complex, high-dimensional data. However, the effectiveness of CNNs is heavily influenced by hyper-parameters, which govern the network's architecture and training process. This paper focuses on hyper-parameter optimization (HPO) as a means to enhance the performance of CNNs in EEG analysis. We explore various strategies for HPO, including traditional methods such as grid search and random search, as well as advanced techniques like Bayesian optimization and evolutionary algorithms. Each method's strengths and limitations are discussed in the context of EEG applications, emphasizing their role in improving model accuracy and generalization. Additionally, we analyze the impact of different hyper-parameter configurations on CNN performance using case studies and comparative experiments. The findings indicate that automated HPO techniques can significantly enhance model robustness and efficiency, leading to more accurate interpretations of EEG signals. By optimizing hyper-parameters, researchers can leverage CNNs more effectively, ultimately advancing the field of EEG analysis and improving clinical outcomes. This paper contributes to the understanding of how systematic hyper-parameter optimization can play a pivotal role in maximizing the potential of CNNs for interpreting complex brain data.

Detection and Classification of Banana Leaf Diseases: Systematic Literature Review

Bananas, a staple fruit globally, are essential for sustenance, employment, and income. However, diseases like Sigatoka, Bacterial Wilt, Bunchy Top, and Fusarium Wilt pose a threat to their cultivation, affecting both small-scale and large-scale production. This survey investigates methods for the early identification and classification of these banana leaf diseases using deep learning and machine learning techniques. A systematic review of 15 studies revealed that the majority of research concentrates on binary classification, which distinguishes healthy from diseased leaves. Common preprocessing steps include image resizing, color space conversion, and background removal to improve model accuracy. We utilize techniques such as ensemble approaches, support vector machines (SVM), random forests, K-means clustering, and convolutional neural networks (CNNs), with CNNs demonstrating superior performance, achieving accuracy rates ranging from 85% to 98.97%. CNNs excel in hierarchical feature extraction but require significant computational power. Traditional machine learning methods offer simplicity and resistance to overfitting but need careful parameter tuning. Advanced deep learning architectures, such as DenseNet and Inception V3, achieve high accuracy but with greater computational demands. Lightweight models like SqueezeNet balance performance and size, but ensemble methods, while improving generalization, add complexity. The choice of method depends on dataset characteristics, available computational resources, and desired trade-offs between performance and complexity. This study provides an overview of current research in banana leaf disease classification, discussing the strengths and limitations of various approaches and suggesting directions for future research to improve detection accuracy and robustness.

Prediction of Glass Transition Temperature of Polymers Using Simple Machine Learning.

Polymer materials have garnered significant attention due to their exceptional mechanical properties and diverse industrial applications. Understanding the glass transition temperature (Tg) of polymers is critical to prevent operational failures at specific temperatures. Traditional methods for measuring Tg, such as differential scanning calorimetry (DSC) and dynamic mechanical analysis, while accurate, are often time-consuming, costly, and susceptible to inaccuracies due to random and uncertain factors. To address these limitations, the aim of the present study is to investigate the potential of Simplified Molecular Input Line Entry System (SMILES) as descriptors in simple machine learning models to predict Tg efficiently and reliably. Five models were utilized: k-nearest neighbors (KNNs), support vector regression (SVR), extreme gradient boosting (XGBoost), artificial neural network (ANN), and recurrent neural network (RNN). SMILES descriptors were converted into numerical data using either One Hot Encoding (OHE) or Natural Language Processing (NLP). The study found that SMILES inputs with fewer than 200 characters were inadequate for accurately describing compound structures, while inputs exceeding 200 characters diminished model performance due to the curse of dimensionality. The ANN model achieved the highest R2 value of 0.79; however, the XGB model, with an R2 value of 0.774, exhibited the highest stability and shorter training times compared to other models, making it the preferred choice for Tg prediction. The efficiency of the OHE method over NLP was demonstrated by faster training times across the KNN, SVR, XGB, and ANN models. Validation of new polymer data showed the XGB model's robustness, with an average prediction deviation of 9.76 from actual Tg values. These findings underscore the importance of optimizing SMILES conversion methods and model parameters to enhance prediction reliability. Future research should focus on improving model accuracy and generalizability by incorporating additional features and advanced techniques. This study contributes to the development of efficient and reliable predictive models for polymer properties, facilitating the design and application of new polymer materials.

Numerical simulation study on the impact of convective heat transfer on lithium battery air cooling thermal model

To enhance the accuracy of lithium battery thermal models, this study investigates the impact of temperature-dependent convective heat transfer coefficients on the battery’s air cooling and heat dissipation model, based on the sweeping in-line robs bundle method proposed by Zukauskas. By calculating and fitting the relationship between the convective heat transfer coefficient and temperature at flow rates of 0.05 m/s, 0.15 m/s, 0.25 m/s, and 0.35 m/s, it was found that the relationship is complex. An electrochemical-thermal coupling model was established using the operational characteristics of lithium batteries, and a thermal runaway reaction kinetics model was created using isothermal thermal runaway experiments and least squares optimization. The temperature-dependent convective heat transfer coefficient was then integrated into both models. Numerical simulations revealed that during normal discharge, the maximum temperature difference in the battery when the convective heat transfer coefficient is a function of temperature is less than 1 % compared to when it is constant. However, in the high-temperature thermal runaway model, the impact of temperature-dependent convective heat transfer coefficients on the thermal runaway critical parameters is minimal at flow rates of 0.05 m/s and 0.15 m/s. When the flow rate increases to 0.25 m/s and 0.35 m/s, the impact on the trigger time of thermal runaway is 17.34 % and 18.07 %, respectively. Experimental validation and research results indicate that the temperature effect on the convective heat transfer coefficient should be considered in high-temperature thermal runaway and thermal management models to calculate the convective heat transfer more accurately within the battery pack, improving model accuracy and reducing the risks of thermal runaway.

A Novel Dataset Replenishment Strategy Integrating Time-Series InSAR for Refined Landslide Susceptibility Mapping in Karst Regions

The accuracy of landslide susceptibility mapping is influenced by the quality of sample data, factor systems, and assessment methods. This study aims to enhance the representativeness and overall quality of the sample dataset through an effective sample expansion strategy, achieving greater precision and reliability in the landslide susceptibility model. An integrated interpretative framework for landslide susceptibility assessment is developed using the XGBoost-SHAP-PDP algorithm to deeply investigate the key contributing factors of landslides in karst areas. Firstly, 17 conditioning factors (e.g., surface deformation rate, land surface temperature, slope, lithology, and NDVI) were introduced based on field surveys, satellite imagery, and literature reviews, to construct a landslide susceptibility conditioning factor system in line with karst geomorphology characteristics. Secondly, a sample expansion strategy combining the frequency ratio (FR) with SBAS-InSAR interpretation results was proposed to optimize the landslide susceptibility assessment dataset. The XGBoost algorithm was then utilized to build the assessment model. Finally, the SHAP and PDP algorithms were applied to interpret the model, examining the primary contributing factors and their influence on landslides in karst areas from both global and single-factor perspectives. Results showed a significant improvement in model accuracy after sample expansion, with AUC values of 0.9579 and 0.9790 for the training and testing sets, respectively. The top three important factors were distance from mining sites, lithology, and NDVI, while land surface temperature, soil erosion modulus, and surface deformation rate also significantly contributed to landslide susceptibility. In summary, this paper provides an in-depth discussion of the effectiveness of LSM in predicting landslide occurrence in complex terrain environments. The reliability and accuracy of the landslide susceptibility assessment model were significantly improved by optimizing the sample dataset within the karst landscape region. In addition, the research results not only provide an essential reference for landslide prevention and control in the karst region of Southwest China and regional central engineering construction planning but also provide a scientific basis for the prevention and control of geologic hazards globally, showing a wide range of application prospects and practical significance.

Rapid prediction and visualization of safe moisture content in alfalfa seeds based on multispectral imaging technology

Moisture significantly impacts seed sales, storage, and processing. Traditional moisture testing methods are often slow, labor-intensive, and inadequate for the rapid detection demands of modern agriculture, particularly for non-destructive testing of individual seeds. This study applied multispectral imaging to obtain morphological and spectral data from alfalfa seeds at six moisture levels (4 %, 8 %, 12 %, 16 %, 25 %, and 41 %). By integrating algorithms such as Support Vector Machines (SVM), Random Forests (RF), Linear Discriminant Analysis (LDA), Back Propagation Neural Network (BPNN), and normalized typical discriminant analysis (nCDA) algorithms, classification models were developed to distinguish between safe and unsafe moisture levels. The Results indicated that spectral data alone significantly improved model accuracy and prediction. nCDA visualizations effectively illustrated spatial moisture distribution, highlighting stark color differences between seeds in the safe moisture range (4 %, 8 %, 12 %) and those in the unsafe range (16 %, 25 %, 41 %). BPNN exhibited high model precision, achieving a recognition accuracy rate of 90.1 % for safe and unsafe moisture content. Key wavelengths identified by the Permutation method included 970, 880, 570, and 490 nm. Pearson correlation analysis showed a significant positive correlation between germination indicators and spectral data, which strengthened with longer seed storage. These findings confirm the potential of multispectral imaging for assessing the safe moisture content of alfalfa seeds, supporting the development of detection systems for evaluating moisture content in individual seeds. This advancement enables the rapid removal of high-moisture seeds, preventing deterioration during storage.

A three-stage wavelength selection algorithm for near-infrared spectroscopy calibration

The near-infrared spectral data is highly high dimensional and contains redundant information, it is necessary to identify the most representative characteristic wavelengths before modeling to improve model accuracy and reliability. At present, there are many methods for selecting the characteristic wavelengths of NIR spectroscopy, but the collinearity among wavelengths is still a main issue that leads to poor model effects. Therefore, this study proposes a three-stage wavelength selection algorithm (Stage III) to reduce redundancy in NIR spectral data and collinearity between wavelength variables, resulting in a simpler and more accurate predictive model. The research uses a public NIR data set of corn samples as its subject. Initially, the wavelengths with the higher correlation coefficients are chosen after calculating the relationship coefficients between every wavelength vector and the concentration vector. On this basis, the correlation coefficients between the vectors of each wavelength point are calculated, and those wavelength points with smaller correlation coefficients with other wavelength points are selected. Ultimately, the stepwise regression analysis selects the wavelengths that provide substantial value to the model as the variables for modeling, leading to the development of a multiple linear regression model. The results show that the model using the three-stage wavelength selection algorithm outperforms those using the full spectrum, Stages I and Stage II, and the coefficient of determination of the test set of the Stage III-MLR model achieved an accuracy of 0.9360. Instead of the successive projections algorithm (SPA), uninformative variable elimination (UVE), and competitive adaptive reweighted sampling (CARS), Stage III is better in the model prediction accuracy. Therefore, the three-stage wavelength selection algorithm is an effective wavelength selection algorithm that can effectively model NIR spectroscopy, reduce the collinearity between the wavelength variables, simplify the complexity of the model, and improve the prediction precision of the model.

A multi-view ensemble machine learning approach for 3D modeling using geological and geophysical data

Geophysical data are often integrated into geological data for 3D modeling of underground spaces. However, the existing single-view approach means it is difficult to adequately fuse the valid information between the two types of data, and the complexity of lithological decoding and classification is high. To address this issue, a multi-view ensemble machine learning (ML) framework is proposed. Initially, the original dataset of lithology prediction is constructed by aligning geological and geophysical data with different spatial scales. Next, the dataset is divided into three datasets of structural strength, density, and moisture content according to the lithology properties of the geophysical data. The proposed framework is then used to capture the lithologic characteristics under different views to achieve the prediction of lithologic labels. In this process, a self-attentive mechanism is used to adaptively fuse the valid information under each view. To validate the proposed framework, it is applied to a project in Jiaxing, Zhejiang Province, China. Compared with existing ML methods, the proposed multi-view ensemble ML framework improves modeling accuracy and constructs models with low uncertainty. The framework can be extended to other multi-source data fusion tasks across geoscience domains.

Mengejar Kinerja Maksimal: Teknik Pengoptimalan Terkini dalam Pembelajaran Mesin

In the era of data revolution and artificial intelligence, machine learning model optimization has become one of the most dynamic and crucial research areas. This article reviews the latest techniques in machine learning model optimization with a focus on pursuing maximum performance. We discuss various methods applied to improve model accuracy and efficiency, ranging from hyperparameter tuning techniques, advanced optimization algorithms such as Bayesian optimization, to innovative approaches such as meta-learning and transfer learning. These optimization techniques not only aim to improve model performance but also to overcome challenges related to big data, model complexity, and computational limitations. We investigate how these methods can be integrated in machine learning pipelines to achieve better results with more efficient resources. Through a review of recent literature and case studies of applications in various domains, this article provides in-depth insights into the trends and developments in model optimization, as well as practical recommendations for researchers and practitioners in pursuing maximum performance from their machine learning systems. A better understanding of these cutting-edge techniques is expected to facilitate the achievement of better and more innovative results in future machine learning applications.

Residual fatigue life prediction based on a novel improved Manson-Halford model considering loading interaction effect

The classical nonlinear fatigue cumulative damage model Manson-Halford is widely used in fatigue life analysis and prediction, but this model lacks consideration for the effects of load interaction. At present, some studies have proposed new correction models to overcome the shortcomings of classical models. However, the problem with these models is that the parameters are difficult to determine, resulting in a cumbersome application process or the correction process is based only on a single parameter. Insufficient correction leads to large fluctuations in life prediction errors. To overcome the above problems, this article proposes a new correction method and establishes a new improved model. Unlike existing models, the newly improved model is based solely on S-N curve parameters and does not require additional material parameters. It fully considers the relationship between adjacent loads and the difference in fatigue life under different stress states, and dynamically modifies the classical model based on larger influence weights. By conducting multi-level fatigue tests on 300M steel, a new improved model was used to accurately predict its remaining fatigue life. Compared with the classical model, the prediction error was reduced by 11.75 %. Utilized fatigue test data from various other materials to predict the fatigue life of the improved model under different levels of stress loading. The results indicate that in the vast majority of cases, the improved model has the highest prediction accuracy among all compared models, with a minimum relative prediction error of only 3.79 % and small fluctuations in prediction error. Compared with the classical model, the maximum reduction in relative prediction error after model improvement reached 28.73 %, indicating the effectiveness and accuracy of the new improved model.